summaryrefslogtreecommitdiffstats
path: root/sys/net/if_tun.c
blob: b2070ef1cc45b8bb328de62704253ba958d91e0e (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
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
/*	$NetBSD: if_tun.c,v 1.14 1994/06/29 06:36:25 cgd 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 it's
 * roots in a similar driver written by Phil Cockcroft (formerly) at
 * UCL. This driver is based much more on read/write/poll mode of
 * operation though.
 *
 * $FreeBSD$
 */

#include "opt_atalk.h"
#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_ipx.h"

#include <sys/param.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/systm.h>
#include <sys/jail.h>
#include <sys/mbuf.h>
#include <sys/module.h>
#include <sys/socket.h>
#include <sys/fcntl.h>
#include <sys/filio.h>
#include <sys/sockio.h>
#include <sys/ttycom.h>
#include <sys/poll.h>
#include <sys/selinfo.h>
#include <sys/signalvar.h>
#include <sys/filedesc.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/conf.h>
#include <sys/uio.h>
#include <sys/malloc.h>
#include <sys/random.h>

#include <net/if.h>
#include <net/if_clone.h>
#include <net/if_types.h>
#include <net/netisr.h>
#include <net/route.h>
#include <net/vnet.h>
#ifdef INET
#include <netinet/in.h>
#endif
#include <net/bpf.h>
#include <net/if_tun.h>

#include <sys/queue.h>
#include <sys/condvar.h>

#include <security/mac/mac_framework.h>

/*
 * tun_list is protected by global tunmtx.  Other mutable fields are
 * protected by tun->tun_mtx, or by their owning subsystem.  tun_dev is
 * static for the duration of a tunnel interface.
 */
struct tun_softc {
	TAILQ_ENTRY(tun_softc)	tun_list;
	struct cdev *tun_dev;
	u_short	tun_flags;		/* misc flags */
#define	TUN_OPEN	0x0001
#define	TUN_INITED	0x0002
#define	TUN_RCOLL	0x0004
#define	TUN_IASET	0x0008
#define	TUN_DSTADDR	0x0010
#define	TUN_LMODE	0x0020
#define	TUN_RWAIT	0x0040
#define	TUN_ASYNC	0x0080
#define	TUN_IFHEAD	0x0100

#define TUN_READY       (TUN_OPEN | TUN_INITED)

	/*
	 * XXXRW: tun_pid is used to exclusively lock /dev/tun.  Is this
	 * actually needed?  Can we just return EBUSY if already open?
	 * Problem is that this involved inherent races when a tun device
	 * is handed off from one process to another, as opposed to just
	 * being slightly stale informationally.
	 */
	pid_t	tun_pid;		/* owning pid */
	struct	ifnet *tun_ifp;		/* the interface */
	struct  sigio *tun_sigio;	/* information for async I/O */
	struct	selinfo	tun_rsel;	/* read select */
	struct mtx	tun_mtx;	/* protect mutable softc fields */
	struct cv	tun_cv;		/* protect against ref'd dev destroy */
};
#define TUN2IFP(sc)	((sc)->tun_ifp)

#define TUNDEBUG	if (tundebug) if_printf
#define	TUNNAME		"tun"

/*
 * All mutable global variables in if_tun are locked using tunmtx, with
 * the exception of tundebug, which is used unlocked, and tunclones,
 * which is static after setup.
 */
static struct mtx tunmtx;
static MALLOC_DEFINE(M_TUN, TUNNAME, "Tunnel Interface");
static int tundebug = 0;
static int tundclone = 1;
static struct clonedevs *tunclones;
static TAILQ_HEAD(,tun_softc)	tunhead = TAILQ_HEAD_INITIALIZER(tunhead);
SYSCTL_INT(_debug, OID_AUTO, if_tun_debug, CTLFLAG_RW, &tundebug, 0, "");

SYSCTL_DECL(_net_link);
static SYSCTL_NODE(_net_link, OID_AUTO, tun, CTLFLAG_RW, 0,
    "IP tunnel software network interface.");
SYSCTL_INT(_net_link_tun, OID_AUTO, devfs_cloning, CTLFLAG_RW, &tundclone, 0,
    "Enable legacy devfs interface creation.");

TUNABLE_INT("net.link.tun.devfs_cloning", &tundclone);

static void	tunclone(void *arg, struct ucred *cred, char *name,
		    int namelen, struct cdev **dev);
static void	tuncreate(const char *name, struct cdev *dev);
static int	tunifioctl(struct ifnet *, u_long, caddr_t);
static void	tuninit(struct ifnet *);
static int	tunmodevent(module_t, int, void *);
static int	tunoutput(struct ifnet *, struct mbuf *, struct sockaddr *,
		    struct route *ro);
static void	tunstart(struct ifnet *);

static int	tun_clone_create(struct if_clone *, int, caddr_t);
static void	tun_clone_destroy(struct ifnet *);

IFC_SIMPLE_DECLARE(tun, 0);

static d_open_t		tunopen;
static d_close_t	tunclose;
static d_read_t		tunread;
static d_write_t	tunwrite;
static d_ioctl_t	tunioctl;
static d_poll_t		tunpoll;
static d_kqfilter_t	tunkqfilter;

static int		tunkqread(struct knote *, long);
static int		tunkqwrite(struct knote *, long);
static void		tunkqdetach(struct knote *);

static struct filterops tun_read_filterops = {
	.f_isfd =	1,
	.f_attach =	NULL,
	.f_detach =	tunkqdetach,
	.f_event =	tunkqread,
};

static struct filterops tun_write_filterops = {
	.f_isfd =	1,
	.f_attach =	NULL,
	.f_detach =	tunkqdetach,
	.f_event =	tunkqwrite,
};

static struct cdevsw tun_cdevsw = {
	.d_version =	D_VERSION,
	.d_flags =	D_NEEDMINOR,
	.d_open =	tunopen,
	.d_close =	tunclose,
	.d_read =	tunread,
	.d_write =	tunwrite,
	.d_ioctl =	tunioctl,
	.d_poll =	tunpoll,
	.d_kqfilter =	tunkqfilter,
	.d_name =	TUNNAME,
};

static int
tun_clone_create(struct if_clone *ifc, int unit, caddr_t params)
{
	struct cdev *dev;
	int i;

	/* find any existing device, or allocate new unit number */
	i = clone_create(&tunclones, &tun_cdevsw, &unit, &dev, 0);
	if (i) {
		/* No preexisting struct cdev *, create one */
		dev = make_dev(&tun_cdevsw, unit,
		    UID_UUCP, GID_DIALER, 0600, "%s%d", ifc->ifc_name, unit);
	}
	tuncreate(ifc->ifc_name, dev);

	return (0);
}

static void
tunclone(void *arg, struct ucred *cred, char *name, int namelen,
    struct cdev **dev)
{
	char devname[SPECNAMELEN + 1];
	int u, i, append_unit;

	if (*dev != NULL)
		return;

	/*
	 * If tun cloning is enabled, only the superuser can create an
	 * interface.
	 */
	if (!tundclone || priv_check_cred(cred, PRIV_NET_IFCREATE, 0) != 0)
		return;

	if (strcmp(name, TUNNAME) == 0) {
		u = -1;
	} else if (dev_stdclone(name, NULL, TUNNAME, &u) != 1)
		return;	/* Don't recognise the name */
	if (u != -1 && u > IF_MAXUNIT)
		return;	/* Unit number too high */

	if (u == -1)
		append_unit = 1;
	else
		append_unit = 0;

	CURVNET_SET(CRED_TO_VNET(cred));
	/* find any existing device, or allocate new unit number */
	i = clone_create(&tunclones, &tun_cdevsw, &u, dev, 0);
	if (i) {
		if (append_unit) {
			namelen = snprintf(devname, sizeof(devname), "%s%d",
			    name, u);
			name = devname;
		}
		/* No preexisting struct cdev *, create one */
		*dev = make_dev_credf(MAKEDEV_REF, &tun_cdevsw, u, cred,
		    UID_UUCP, GID_DIALER, 0600, "%s", name);
	}

	if_clone_create(name, namelen, NULL);
	CURVNET_RESTORE();
}

static void
tun_destroy(struct tun_softc *tp)
{
	struct cdev *dev;

	mtx_lock(&tp->tun_mtx);
	if ((tp->tun_flags & TUN_OPEN) != 0)
		cv_wait_unlock(&tp->tun_cv, &tp->tun_mtx);
	else
		mtx_unlock(&tp->tun_mtx);

	CURVNET_SET(TUN2IFP(tp)->if_vnet);
	dev = tp->tun_dev;
	bpfdetach(TUN2IFP(tp));
	if_detach(TUN2IFP(tp));
	if_free(TUN2IFP(tp));
	destroy_dev(dev);
	seldrain(&tp->tun_rsel);
	knlist_destroy(&tp->tun_rsel.si_note);
	mtx_destroy(&tp->tun_mtx);
	cv_destroy(&tp->tun_cv);
	free(tp, M_TUN);
	CURVNET_RESTORE();
}

static void
tun_clone_destroy(struct ifnet *ifp)
{
	struct tun_softc *tp = ifp->if_softc;

	mtx_lock(&tunmtx);
	TAILQ_REMOVE(&tunhead, tp, tun_list);
	mtx_unlock(&tunmtx);
	tun_destroy(tp);
}

static int
tunmodevent(module_t mod, int type, void *data)
{
	static eventhandler_tag tag;
	struct tun_softc *tp;

	switch (type) {
	case MOD_LOAD:
		mtx_init(&tunmtx, "tunmtx", NULL, MTX_DEF);
		clone_setup(&tunclones);
		tag = EVENTHANDLER_REGISTER(dev_clone, tunclone, 0, 1000);
		if (tag == NULL)
			return (ENOMEM);
		if_clone_attach(&tun_cloner);
		break;
	case MOD_UNLOAD:
		if_clone_detach(&tun_cloner);
		EVENTHANDLER_DEREGISTER(dev_clone, tag);
		drain_dev_clone_events();

		mtx_lock(&tunmtx);
		while ((tp = TAILQ_FIRST(&tunhead)) != NULL) {
			TAILQ_REMOVE(&tunhead, tp, tun_list);
			mtx_unlock(&tunmtx);
			tun_destroy(tp);
			mtx_lock(&tunmtx);
		}
		mtx_unlock(&tunmtx);
		clone_cleanup(&tunclones);
		mtx_destroy(&tunmtx);
		break;
	default:
		return EOPNOTSUPP;
	}
	return 0;
}

static moduledata_t tun_mod = {
	"if_tun",
	tunmodevent,
	NULL
};

DECLARE_MODULE(if_tun, tun_mod, SI_SUB_PSEUDO, SI_ORDER_ANY);

static void
tunstart(struct ifnet *ifp)
{
	struct tun_softc *tp = ifp->if_softc;
	struct mbuf *m;

	TUNDEBUG(ifp,"%s starting\n", ifp->if_xname);
	if (ALTQ_IS_ENABLED(&ifp->if_snd)) {
		IFQ_LOCK(&ifp->if_snd);
		IFQ_POLL_NOLOCK(&ifp->if_snd, m);
		if (m == NULL) {
			IFQ_UNLOCK(&ifp->if_snd);
			return;
		}
		IFQ_UNLOCK(&ifp->if_snd);
	}

	mtx_lock(&tp->tun_mtx);
	if (tp->tun_flags & TUN_RWAIT) {
		tp->tun_flags &= ~TUN_RWAIT;
		wakeup(tp);
	}
	selwakeuppri(&tp->tun_rsel, PZERO + 1);
	KNOTE_LOCKED(&tp->tun_rsel.si_note, 0);
	if (tp->tun_flags & TUN_ASYNC && tp->tun_sigio) {
		mtx_unlock(&tp->tun_mtx);
		pgsigio(&tp->tun_sigio, SIGIO, 0);
	} else
		mtx_unlock(&tp->tun_mtx);
}

/* XXX: should return an error code so it can fail. */
static void
tuncreate(const char *name, struct cdev *dev)
{
	struct tun_softc *sc;
	struct ifnet *ifp;

	dev->si_flags &= ~SI_CHEAPCLONE;

	sc = malloc(sizeof(*sc), M_TUN, M_WAITOK | M_ZERO);
	mtx_init(&sc->tun_mtx, "tun_mtx", NULL, MTX_DEF);
	cv_init(&sc->tun_cv, "tun_condvar");
	sc->tun_flags = TUN_INITED;
	sc->tun_dev = dev;
	mtx_lock(&tunmtx);
	TAILQ_INSERT_TAIL(&tunhead, sc, tun_list);
	mtx_unlock(&tunmtx);

	ifp = sc->tun_ifp = if_alloc(IFT_PPP);
	if (ifp == NULL)
		panic("%s%d: failed to if_alloc() interface.\n",
		    name, dev2unit(dev));
	if_initname(ifp, name, dev2unit(dev));
	ifp->if_mtu = TUNMTU;
	ifp->if_ioctl = tunifioctl;
	ifp->if_output = tunoutput;
	ifp->if_start = tunstart;
	ifp->if_flags = IFF_POINTOPOINT | IFF_MULTICAST;
	ifp->if_softc = sc;
	IFQ_SET_MAXLEN(&ifp->if_snd, ifqmaxlen);
	ifp->if_snd.ifq_drv_maxlen = 0;
	IFQ_SET_READY(&ifp->if_snd);
	knlist_init_mtx(&sc->tun_rsel.si_note, &sc->tun_mtx);
	ifp->if_capabilities |= IFCAP_LINKSTATE;
	ifp->if_capenable |= IFCAP_LINKSTATE;

	if_attach(ifp);
	bpfattach(ifp, DLT_NULL, sizeof(u_int32_t));
	dev->si_drv1 = sc;
	TUNDEBUG(ifp, "interface %s is created, minor = %#x\n",
	    ifp->if_xname, dev2unit(dev));
}

static int
tunopen(struct cdev *dev, int flag, int mode, struct thread *td)
{
	struct ifnet	*ifp;
	struct tun_softc *tp;

	/*
	 * XXXRW: Non-atomic test and set of dev->si_drv1 requires
	 * synchronization.
	 */
	tp = dev->si_drv1;
	if (!tp) {
		tuncreate(TUNNAME, dev);
		tp = dev->si_drv1;
	}

	/*
	 * XXXRW: This use of tun_pid is subject to error due to the
	 * fact that a reference to the tunnel can live beyond the
	 * death of the process that created it.  Can we replace this
	 * with a simple busy flag?
	 */
	mtx_lock(&tp->tun_mtx);
	if (tp->tun_pid != 0 && tp->tun_pid != td->td_proc->p_pid) {
		mtx_unlock(&tp->tun_mtx);
		return (EBUSY);
	}
	tp->tun_pid = td->td_proc->p_pid;

	tp->tun_flags |= TUN_OPEN;
	ifp = TUN2IFP(tp);
	if_link_state_change(ifp, LINK_STATE_UP);
	TUNDEBUG(ifp, "open\n");
	mtx_unlock(&tp->tun_mtx);

	return (0);
}

/*
 * tunclose - close the device - mark i/f down & delete
 * routing info
 */
static	int
tunclose(struct cdev *dev, int foo, int bar, struct thread *td)
{
	struct tun_softc *tp;
	struct ifnet *ifp;

	tp = dev->si_drv1;
	ifp = TUN2IFP(tp);

	mtx_lock(&tp->tun_mtx);
	tp->tun_flags &= ~TUN_OPEN;
	tp->tun_pid = 0;

	/*
	 * junk all pending output
	 */
	CURVNET_SET(ifp->if_vnet);
	IFQ_PURGE(&ifp->if_snd);

	if (ifp->if_flags & IFF_UP) {
		mtx_unlock(&tp->tun_mtx);
		if_down(ifp);
		mtx_lock(&tp->tun_mtx);
	}

	/* Delete all addresses and routes which reference this interface. */
	if (ifp->if_drv_flags & IFF_DRV_RUNNING) {
		struct ifaddr *ifa;

		ifp->if_drv_flags &= ~IFF_DRV_RUNNING;
		mtx_unlock(&tp->tun_mtx);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			/* deal w/IPv4 PtP destination; unlocked read */
			if (ifa->ifa_addr->sa_family == AF_INET) {
				rtinit(ifa, (int)RTM_DELETE,
				    tp->tun_flags & TUN_DSTADDR ? RTF_HOST : 0);
			} else {
				rtinit(ifa, (int)RTM_DELETE, 0);
			}
		}
		if_purgeaddrs(ifp);
		mtx_lock(&tp->tun_mtx);
	}
	if_link_state_change(ifp, LINK_STATE_DOWN);
	CURVNET_RESTORE();

	funsetown(&tp->tun_sigio);
	selwakeuppri(&tp->tun_rsel, PZERO + 1);
	KNOTE_LOCKED(&tp->tun_rsel.si_note, 0);
	TUNDEBUG (ifp, "closed\n");

	cv_broadcast(&tp->tun_cv);
	mtx_unlock(&tp->tun_mtx);
	return (0);
}

static void
tuninit(struct ifnet *ifp)
{
	struct tun_softc *tp = ifp->if_softc;
#ifdef INET
	struct ifaddr *ifa;
#endif

	TUNDEBUG(ifp, "tuninit\n");

	mtx_lock(&tp->tun_mtx);
	ifp->if_flags |= IFF_UP;
	ifp->if_drv_flags |= IFF_DRV_RUNNING;
	getmicrotime(&ifp->if_lastchange);

#ifdef INET
	if_addr_rlock(ifp);
	TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
		if (ifa->ifa_addr->sa_family == AF_INET) {
			struct sockaddr_in *si;

			si = (struct sockaddr_in *)ifa->ifa_addr;
			if (si->sin_addr.s_addr)
				tp->tun_flags |= TUN_IASET;

			si = (struct sockaddr_in *)ifa->ifa_dstaddr;
			if (si && si->sin_addr.s_addr)
				tp->tun_flags |= TUN_DSTADDR;
		}
	}
	if_addr_runlock(ifp);
#endif
	mtx_unlock(&tp->tun_mtx);
}

/*
 * Process an ioctl request.
 */
static int
tunifioctl(struct ifnet *ifp, u_long cmd, caddr_t data)
{
	struct ifreq *ifr = (struct ifreq *)data;
	struct tun_softc *tp = ifp->if_softc;
	struct ifstat *ifs;
	int		error = 0;

	switch(cmd) {
	case SIOCGIFSTATUS:
		ifs = (struct ifstat *)data;
		mtx_lock(&tp->tun_mtx);
		if (tp->tun_pid)
			sprintf(ifs->ascii + strlen(ifs->ascii),
			    "\tOpened by PID %d\n", tp->tun_pid);
		mtx_unlock(&tp->tun_mtx);
		break;
	case SIOCSIFADDR:
		tuninit(ifp);
		TUNDEBUG(ifp, "address set\n");
		break;
	case SIOCSIFDSTADDR:
		tuninit(ifp);
		TUNDEBUG(ifp, "destination address set\n");
		break;
	case SIOCSIFMTU:
		ifp->if_mtu = ifr->ifr_mtu;
		TUNDEBUG(ifp, "mtu set\n");
		break;
	case SIOCSIFFLAGS:
	case SIOCADDMULTI:
	case SIOCDELMULTI:
		break;
	default:
		error = EINVAL;
	}
	return (error);
}

/*
 * tunoutput - queue packets from higher level ready to put out.
 */
static int
tunoutput(struct ifnet *ifp, struct mbuf *m0, struct sockaddr *dst,
    struct route *ro)
{
	struct tun_softc *tp = ifp->if_softc;
	u_short cached_tun_flags;
	int error;
	u_int32_t af;

	TUNDEBUG (ifp, "tunoutput\n");

#ifdef MAC
	error = mac_ifnet_check_transmit(ifp, m0);
	if (error) {
		m_freem(m0);
		return (error);
	}
#endif

	/* Could be unlocked read? */
	mtx_lock(&tp->tun_mtx);
	cached_tun_flags = tp->tun_flags;
	mtx_unlock(&tp->tun_mtx);
	if ((cached_tun_flags & TUN_READY) != TUN_READY) {
		TUNDEBUG (ifp, "not ready 0%o\n", tp->tun_flags);
		m_freem (m0);
		return (EHOSTDOWN);
	}

	if ((ifp->if_flags & IFF_UP) != IFF_UP) {
		m_freem (m0);
		return (EHOSTDOWN);
	}

	/* BPF writes need to be handled specially. */
	if (dst->sa_family == AF_UNSPEC) {
		bcopy(dst->sa_data, &af, sizeof(af));
		dst->sa_family = af; 
	}

	if (bpf_peers_present(ifp->if_bpf)) {
		af = dst->sa_family;
		bpf_mtap2(ifp->if_bpf, &af, sizeof(af), m0);
	}

	/* prepend sockaddr? this may abort if the mbuf allocation fails */
	if (cached_tun_flags & TUN_LMODE) {
		/* allocate space for sockaddr */
		M_PREPEND(m0, dst->sa_len, M_DONTWAIT);

		/* if allocation failed drop packet */
		if (m0 == NULL) {
			ifp->if_iqdrops++;
			ifp->if_oerrors++;
			return (ENOBUFS);
		} else {
			bcopy(dst, m0->m_data, dst->sa_len);
		}
	}

	if (cached_tun_flags & TUN_IFHEAD) {
		/* Prepend the address family */
		M_PREPEND(m0, 4, M_DONTWAIT);

		/* if allocation failed drop packet */
		if (m0 == NULL) {
			ifp->if_iqdrops++;
			ifp->if_oerrors++;
			return (ENOBUFS);
		} else
			*(u_int32_t *)m0->m_data = htonl(dst->sa_family);
	} else {
#ifdef INET
		if (dst->sa_family != AF_INET)
#endif
		{
			m_freem(m0);
			return (EAFNOSUPPORT);
		}
	}

	error = (ifp->if_transmit)(ifp, m0);
	if (error)
		return (ENOBUFS);
	ifp->if_opackets++;
	return (0);
}

/*
 * the cdevsw interface is now pretty minimal.
 */
static	int
tunioctl(struct cdev *dev, u_long cmd, caddr_t data, int flag,
    struct thread *td)
{
	int		error;
	struct tun_softc *tp = dev->si_drv1;
	struct tuninfo *tunp;

	switch (cmd) {
	case TUNSIFINFO:
		tunp = (struct tuninfo *)data;
		if (tunp->mtu < IF_MINMTU)
			return (EINVAL);
		if (TUN2IFP(tp)->if_mtu != tunp->mtu) {
			error = priv_check(td, PRIV_NET_SETIFMTU);
			if (error)
				return (error);
		}
		mtx_lock(&tp->tun_mtx);
		TUN2IFP(tp)->if_mtu = tunp->mtu;
		TUN2IFP(tp)->if_type = tunp->type;
		TUN2IFP(tp)->if_baudrate = tunp->baudrate;
		mtx_unlock(&tp->tun_mtx);
		break;
	case TUNGIFINFO:
		tunp = (struct tuninfo *)data;
		mtx_lock(&tp->tun_mtx);
		tunp->mtu = TUN2IFP(tp)->if_mtu;
		tunp->type = TUN2IFP(tp)->if_type;
		tunp->baudrate = TUN2IFP(tp)->if_baudrate;
		mtx_unlock(&tp->tun_mtx);
		break;
	case TUNSDEBUG:
		tundebug = *(int *)data;
		break;
	case TUNGDEBUG:
		*(int *)data = tundebug;
		break;
	case TUNSLMODE:
		mtx_lock(&tp->tun_mtx);
		if (*(int *)data) {
			tp->tun_flags |= TUN_LMODE;
			tp->tun_flags &= ~TUN_IFHEAD;
		} else
			tp->tun_flags &= ~TUN_LMODE;
		mtx_unlock(&tp->tun_mtx);
		break;
	case TUNSIFHEAD:
		mtx_lock(&tp->tun_mtx);
		if (*(int *)data) {
			tp->tun_flags |= TUN_IFHEAD;
			tp->tun_flags &= ~TUN_LMODE;
		} else
			tp->tun_flags &= ~TUN_IFHEAD;
		mtx_unlock(&tp->tun_mtx);
		break;
	case TUNGIFHEAD:
		mtx_lock(&tp->tun_mtx);
		*(int *)data = (tp->tun_flags & TUN_IFHEAD) ? 1 : 0;
		mtx_unlock(&tp->tun_mtx);
		break;
	case TUNSIFMODE:
		/* deny this if UP */
		if (TUN2IFP(tp)->if_flags & IFF_UP)
			return(EBUSY);

		switch (*(int *)data & ~IFF_MULTICAST) {
		case IFF_POINTOPOINT:
		case IFF_BROADCAST:
			mtx_lock(&tp->tun_mtx);
			TUN2IFP(tp)->if_flags &=
			    ~(IFF_BROADCAST|IFF_POINTOPOINT|IFF_MULTICAST);
			TUN2IFP(tp)->if_flags |= *(int *)data;
			mtx_unlock(&tp->tun_mtx);
			break;
		default:
			return(EINVAL);
		}
		break;
	case TUNSIFPID:
		mtx_lock(&tp->tun_mtx);
		tp->tun_pid = curthread->td_proc->p_pid;
		mtx_unlock(&tp->tun_mtx);
		break;
	case FIONBIO:
		break;
	case FIOASYNC:
		mtx_lock(&tp->tun_mtx);
		if (*(int *)data)
			tp->tun_flags |= TUN_ASYNC;
		else
			tp->tun_flags &= ~TUN_ASYNC;
		mtx_unlock(&tp->tun_mtx);
		break;
	case FIONREAD:
		if (!IFQ_IS_EMPTY(&TUN2IFP(tp)->if_snd)) {
			struct mbuf *mb;
			IFQ_LOCK(&TUN2IFP(tp)->if_snd);
			IFQ_POLL_NOLOCK(&TUN2IFP(tp)->if_snd, mb);
			for (*(int *)data = 0; mb != NULL; mb = mb->m_next)
				*(int *)data += mb->m_len;
			IFQ_UNLOCK(&TUN2IFP(tp)->if_snd);
		} else
			*(int *)data = 0;
		break;
	case FIOSETOWN:
		return (fsetown(*(int *)data, &tp->tun_sigio));

	case FIOGETOWN:
		*(int *)data = fgetown(&tp->tun_sigio);
		return (0);

	/* This is deprecated, FIOSETOWN should be used instead. */
	case TIOCSPGRP:
		return (fsetown(-(*(int *)data), &tp->tun_sigio));

	/* This is deprecated, FIOGETOWN should be used instead. */
	case TIOCGPGRP:
		*(int *)data = -fgetown(&tp->tun_sigio);
		return (0);

	default:
		return (ENOTTY);
	}
	return (0);
}

/*
 * The cdevsw read interface - reads a packet at a time, or at
 * least as much of a packet as can be read.
 */
static	int
tunread(struct cdev *dev, struct uio *uio, int flag)
{
	struct tun_softc *tp = dev->si_drv1;
	struct ifnet	*ifp = TUN2IFP(tp);
	struct mbuf	*m;
	int		error=0, len;

	TUNDEBUG (ifp, "read\n");
	mtx_lock(&tp->tun_mtx);
	if ((tp->tun_flags & TUN_READY) != TUN_READY) {
		mtx_unlock(&tp->tun_mtx);
		TUNDEBUG (ifp, "not ready 0%o\n", tp->tun_flags);
		return (EHOSTDOWN);
	}

	tp->tun_flags &= ~TUN_RWAIT;

	do {
		IFQ_DEQUEUE(&ifp->if_snd, m);
		if (m == NULL) {
			if (flag & O_NONBLOCK) {
				mtx_unlock(&tp->tun_mtx);
				return (EWOULDBLOCK);
			}
			tp->tun_flags |= TUN_RWAIT;
			error = mtx_sleep(tp, &tp->tun_mtx, PCATCH | (PZERO + 1),
			    "tunread", 0);
			if (error != 0) {
				mtx_unlock(&tp->tun_mtx);
				return (error);
			}
		}
	} while (m == NULL);
	mtx_unlock(&tp->tun_mtx);

	while (m && uio->uio_resid > 0 && error == 0) {
		len = min(uio->uio_resid, m->m_len);
		if (len != 0)
			error = uiomove(mtod(m, void *), len, uio);
		m = m_free(m);
	}

	if (m) {
		TUNDEBUG(ifp, "Dropping mbuf\n");
		m_freem(m);
	}
	return (error);
}

/*
 * the cdevsw write interface - an atomic write is a packet - or else!
 */
static	int
tunwrite(struct cdev *dev, struct uio *uio, int flag)
{
	struct tun_softc *tp = dev->si_drv1;
	struct ifnet	*ifp = TUN2IFP(tp);
	struct mbuf	*m;
	uint32_t	family;
	int 		isr;

	TUNDEBUG(ifp, "tunwrite\n");

	if ((ifp->if_flags & IFF_UP) != IFF_UP)
		/* ignore silently */
		return (0);

	if (uio->uio_resid == 0)
		return (0);

	if (uio->uio_resid < 0 || uio->uio_resid > TUNMRU) {
		TUNDEBUG(ifp, "len=%zd!\n", uio->uio_resid);
		return (EIO);
	}

	if ((m = m_uiotombuf(uio, M_DONTWAIT, 0, 0, M_PKTHDR)) == NULL) {
		ifp->if_ierrors++;
		return (ENOBUFS);
	}

	m->m_pkthdr.rcvif = ifp;
#ifdef MAC
	mac_ifnet_create_mbuf(ifp, m);
#endif

	/* Could be unlocked read? */
	mtx_lock(&tp->tun_mtx);
	if (tp->tun_flags & TUN_IFHEAD) {
		mtx_unlock(&tp->tun_mtx);
		if (m->m_len < sizeof(family) &&
		    (m = m_pullup(m, sizeof(family))) == NULL)
			return (ENOBUFS);
		family = ntohl(*mtod(m, u_int32_t *));
		m_adj(m, sizeof(family));
	} else {
		mtx_unlock(&tp->tun_mtx);
		family = AF_INET;
	}

	BPF_MTAP2(ifp, &family, sizeof(family), m);

	switch (family) {
#ifdef INET
	case AF_INET:
		isr = NETISR_IP;
		break;
#endif
#ifdef INET6
	case AF_INET6:
		isr = NETISR_IPV6;
		break;
#endif
#ifdef IPX
	case AF_IPX:
		isr = NETISR_IPX;
		break;
#endif
#ifdef NETATALK
	case AF_APPLETALK:
		isr = NETISR_ATALK2;
		break;
#endif
	default:
		m_freem(m);
		return (EAFNOSUPPORT);
	}
	/* First chunk of an mbuf contains good junk */
	if (harvest.point_to_point)
		random_harvest(m, 16, 3, 0, RANDOM_NET);
	ifp->if_ibytes += m->m_pkthdr.len;
	ifp->if_ipackets++;
	CURVNET_SET(ifp->if_vnet);
	M_SETFIB(m, ifp->if_fib);
	netisr_dispatch(isr, m);
	CURVNET_RESTORE();
	return (0);
}

/*
 * tunpoll - the poll 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.
 */
static	int
tunpoll(struct cdev *dev, int events, struct thread *td)
{
	struct tun_softc *tp = dev->si_drv1;
	struct ifnet	*ifp = TUN2IFP(tp);
	int		revents = 0;
	struct mbuf	*m;

	TUNDEBUG(ifp, "tunpoll\n");

	if (events & (POLLIN | POLLRDNORM)) {
		IFQ_LOCK(&ifp->if_snd);
		IFQ_POLL_NOLOCK(&ifp->if_snd, m);
		if (m != NULL) {
			TUNDEBUG(ifp, "tunpoll q=%d\n", ifp->if_snd.ifq_len);
			revents |= events & (POLLIN | POLLRDNORM);
		} else {
			TUNDEBUG(ifp, "tunpoll waiting\n");
			selrecord(td, &tp->tun_rsel);
		}
		IFQ_UNLOCK(&ifp->if_snd);
	}
	if (events & (POLLOUT | POLLWRNORM))
		revents |= events & (POLLOUT | POLLWRNORM);

	return (revents);
}

/*
 * tunkqfilter - support for the kevent() system call.
 */
static int
tunkqfilter(struct cdev *dev, struct knote *kn)
{
	struct tun_softc	*tp = dev->si_drv1;
	struct ifnet	*ifp = TUN2IFP(tp);

	switch(kn->kn_filter) {
	case EVFILT_READ:
		TUNDEBUG(ifp, "%s kqfilter: EVFILT_READ, minor = %#x\n",
		    ifp->if_xname, dev2unit(dev));
		kn->kn_fop = &tun_read_filterops;
		break;

	case EVFILT_WRITE:
		TUNDEBUG(ifp, "%s kqfilter: EVFILT_WRITE, minor = %#x\n",
		    ifp->if_xname, dev2unit(dev));
		kn->kn_fop = &tun_write_filterops;
		break;

	default:
		TUNDEBUG(ifp, "%s kqfilter: invalid filter, minor = %#x\n",
		    ifp->if_xname, dev2unit(dev));
		return(EINVAL);
	}

	kn->kn_hook = tp;
	knlist_add(&tp->tun_rsel.si_note, kn, 0);

	return (0);
}

/*
 * Return true of there is data in the interface queue.
 */
static int
tunkqread(struct knote *kn, long hint)
{
	int			ret;
	struct tun_softc	*tp = kn->kn_hook;
	struct cdev		*dev = tp->tun_dev;
	struct ifnet	*ifp = TUN2IFP(tp);

	if ((kn->kn_data = ifp->if_snd.ifq_len) > 0) {
		TUNDEBUG(ifp,
		    "%s have data in the queue.  Len = %d, minor = %#x\n",
		    ifp->if_xname, ifp->if_snd.ifq_len, dev2unit(dev));
		ret = 1;
	} else {
		TUNDEBUG(ifp,
		    "%s waiting for data, minor = %#x\n", ifp->if_xname,
		    dev2unit(dev));
		ret = 0;
	}

	return (ret);
}

/*
 * Always can write, always return MTU in kn->data.
 */
static int
tunkqwrite(struct knote *kn, long hint)
{
	struct tun_softc	*tp = kn->kn_hook;
	struct ifnet	*ifp = TUN2IFP(tp);

	kn->kn_data = ifp->if_mtu;

	return (1);
}

static void
tunkqdetach(struct knote *kn)
{
	struct tun_softc	*tp = kn->kn_hook;

	knlist_remove(&tp->tun_rsel.si_note, kn, 0);
}
OpenPOWER on IntegriCloud