aboutsummaryrefslogtreecommitdiff
path: root/sys/compat/linux/linux.c
blob: 2e6e52f7490c206be3e924c29d6273bbc3dfe6c3 (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
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
/*-
 * Copyright (c) 2015 Dmitry Chagin <dchagin@FreeBSD.org>
 *
 * 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.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include "opt_inet6.h"

#include <sys/param.h>
#include <sys/conf.h>
#include <sys/ctype.h>
#include <sys/file.h>
#include <sys/filedesc.h>
#include <sys/jail.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/poll.h>
#include <sys/proc.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>

#include <net/if.h>
#include <net/if_var.h>
#include <net/if_dl.h>
#include <net/if_types.h>
#include <netlink/netlink.h>

#include <sys/un.h>
#include <netinet/in.h>

#include <compat/linux/linux.h>
#include <compat/linux/linux_common.h>
#include <compat/linux/linux_mib.h>
#include <compat/linux/linux_util.h>

CTASSERT(LINUX_IFNAMSIZ == IFNAMSIZ);

static bool use_real_ifnames = false;
SYSCTL_BOOL(_compat_linux, OID_AUTO, use_real_ifnames, CTLFLAG_RWTUN,
    &use_real_ifnames, 0,
    "Use FreeBSD interface names instead of generating ethN aliases");

static int bsd_to_linux_sigtbl[LINUX_SIGTBLSZ] = {
	LINUX_SIGHUP,	/* SIGHUP */
	LINUX_SIGINT,	/* SIGINT */
	LINUX_SIGQUIT,	/* SIGQUIT */
	LINUX_SIGILL,	/* SIGILL */
	LINUX_SIGTRAP,	/* SIGTRAP */
	LINUX_SIGABRT,	/* SIGABRT */
	0,		/* SIGEMT */
	LINUX_SIGFPE,	/* SIGFPE */
	LINUX_SIGKILL,	/* SIGKILL */
	LINUX_SIGBUS,	/* SIGBUS */
	LINUX_SIGSEGV,	/* SIGSEGV */
	LINUX_SIGSYS,	/* SIGSYS */
	LINUX_SIGPIPE,	/* SIGPIPE */
	LINUX_SIGALRM,	/* SIGALRM */
	LINUX_SIGTERM,	/* SIGTERM */
	LINUX_SIGURG,	/* SIGURG */
	LINUX_SIGSTOP,	/* SIGSTOP */
	LINUX_SIGTSTP,	/* SIGTSTP */
	LINUX_SIGCONT,	/* SIGCONT */
	LINUX_SIGCHLD,	/* SIGCHLD */
	LINUX_SIGTTIN,	/* SIGTTIN */
	LINUX_SIGTTOU,	/* SIGTTOU */
	LINUX_SIGIO,	/* SIGIO */
	LINUX_SIGXCPU,	/* SIGXCPU */
	LINUX_SIGXFSZ,	/* SIGXFSZ */
	LINUX_SIGVTALRM,/* SIGVTALRM */
	LINUX_SIGPROF,	/* SIGPROF */
	LINUX_SIGWINCH,	/* SIGWINCH */
	0,		/* SIGINFO */
	LINUX_SIGUSR1,	/* SIGUSR1 */
	LINUX_SIGUSR2	/* SIGUSR2 */
};

#define	LINUX_SIGPWREMU	(SIGRTMIN + (LINUX_SIGRTMAX - LINUX_SIGRTMIN) + 1)

static int linux_to_bsd_sigtbl[LINUX_SIGTBLSZ] = {
	SIGHUP,		/* LINUX_SIGHUP */
	SIGINT,		/* LINUX_SIGINT */
	SIGQUIT,	/* LINUX_SIGQUIT */
	SIGILL,		/* LINUX_SIGILL */
	SIGTRAP,	/* LINUX_SIGTRAP */
	SIGABRT,	/* LINUX_SIGABRT */
	SIGBUS,		/* LINUX_SIGBUS */
	SIGFPE,		/* LINUX_SIGFPE */
	SIGKILL,	/* LINUX_SIGKILL */
	SIGUSR1,	/* LINUX_SIGUSR1 */
	SIGSEGV,	/* LINUX_SIGSEGV */
	SIGUSR2,	/* LINUX_SIGUSR2 */
	SIGPIPE,	/* LINUX_SIGPIPE */
	SIGALRM,	/* LINUX_SIGALRM */
	SIGTERM,	/* LINUX_SIGTERM */
	SIGBUS,		/* LINUX_SIGSTKFLT */
	SIGCHLD,	/* LINUX_SIGCHLD */
	SIGCONT,	/* LINUX_SIGCONT */
	SIGSTOP,	/* LINUX_SIGSTOP */
	SIGTSTP,	/* LINUX_SIGTSTP */
	SIGTTIN,	/* LINUX_SIGTTIN */
	SIGTTOU,	/* LINUX_SIGTTOU */
	SIGURG,		/* LINUX_SIGURG */
	SIGXCPU,	/* LINUX_SIGXCPU */
	SIGXFSZ,	/* LINUX_SIGXFSZ */
	SIGVTALRM,	/* LINUX_SIGVTALARM */
	SIGPROF,	/* LINUX_SIGPROF */
	SIGWINCH,	/* LINUX_SIGWINCH */
	SIGIO,		/* LINUX_SIGIO */
	/*
	 * FreeBSD does not have SIGPWR signal, map Linux SIGPWR signal
	 * to the first unused FreeBSD signal number. Since Linux supports
	 * signals from 1 to 64 we are ok here as our SIGRTMIN = 65.
	 */
	LINUX_SIGPWREMU,/* LINUX_SIGPWR */
	SIGSYS		/* LINUX_SIGSYS */
};

static struct cdev *dev_shm_cdev;
static struct cdevsw dev_shm_cdevsw = {
     .d_version = D_VERSION,
     .d_name    = "dev_shm",
};

/*
 * Map Linux RT signals to the FreeBSD RT signals.
 */
static inline int
linux_to_bsd_rt_signal(int sig)
{

	return (SIGRTMIN + sig - LINUX_SIGRTMIN);
}

static inline int
bsd_to_linux_rt_signal(int sig)
{

	return (sig - SIGRTMIN + LINUX_SIGRTMIN);
}

int
linux_to_bsd_signal(int sig)
{

	KASSERT(sig > 0 && sig <= LINUX_SIGRTMAX, ("invalid Linux signal %d\n", sig));

	if (sig < LINUX_SIGRTMIN)
		return (linux_to_bsd_sigtbl[_SIG_IDX(sig)]);

	return (linux_to_bsd_rt_signal(sig));
}

int
bsd_to_linux_signal(int sig)
{

	if (sig <= LINUX_SIGTBLSZ)
		return (bsd_to_linux_sigtbl[_SIG_IDX(sig)]);
	if (sig == LINUX_SIGPWREMU)
		return (LINUX_SIGPWR);

	return (bsd_to_linux_rt_signal(sig));
}

int
linux_to_bsd_sigaltstack(int lsa)
{
	int bsa = 0;

	if (lsa & LINUX_SS_DISABLE)
		bsa |= SS_DISABLE;
	/*
	 * Linux ignores SS_ONSTACK flag for ss
	 * parameter while FreeBSD prohibits it.
	 */
	return (bsa);
}

int
bsd_to_linux_sigaltstack(int bsa)
{
	int lsa = 0;

	if (bsa & SS_DISABLE)
		lsa |= LINUX_SS_DISABLE;
	if (bsa & SS_ONSTACK)
		lsa |= LINUX_SS_ONSTACK;
	return (lsa);
}

void
linux_to_bsd_sigset(l_sigset_t *lss, sigset_t *bss)
{
	int b, l;

	SIGEMPTYSET(*bss);
	for (l = 1; l <= LINUX_SIGRTMAX; l++) {
		if (LINUX_SIGISMEMBER(*lss, l)) {
			b = linux_to_bsd_signal(l);
			if (b)
				SIGADDSET(*bss, b);
		}
	}
}

void
bsd_to_linux_sigset(sigset_t *bss, l_sigset_t *lss)
{
	int b, l;

	LINUX_SIGEMPTYSET(*lss);
	for (b = 1; b <= SIGRTMAX; b++) {
		if (SIGISMEMBER(*bss, b)) {
			l = bsd_to_linux_signal(b);
			if (l)
				LINUX_SIGADDSET(*lss, l);
		}
	}
}

/*
 * Translate a FreeBSD interface name to a Linux interface name
 * by interface name, and return the number of bytes copied to lxname.
 */
int
ifname_bsd_to_linux_name(const char *bsdname, char *lxname, size_t len)
{
	struct epoch_tracker et;
	struct ifnet *ifp;
	int ret;

	ret = 0;
	CURVNET_SET(TD_TO_VNET(curthread));
	NET_EPOCH_ENTER(et);
	ifp = ifunit(bsdname);
	if (ifp != NULL)
		ret = ifname_bsd_to_linux_ifp(ifp, lxname, len);
	NET_EPOCH_EXIT(et);
	CURVNET_RESTORE();
	return (ret);
}

/*
 * Translate a FreeBSD interface name to a Linux interface name
 * by interface index, and return the number of bytes copied to lxname.
 */
int
ifname_bsd_to_linux_idx(u_int idx, char *lxname, size_t len)
{
	struct epoch_tracker et;
	struct ifnet *ifp;
	int ret;

	ret = 0;
	CURVNET_SET(TD_TO_VNET(curthread));
	NET_EPOCH_ENTER(et);
	ifp = ifnet_byindex(idx);
	if (ifp != NULL)
		ret = ifname_bsd_to_linux_ifp(ifp, lxname, len);
	NET_EPOCH_EXIT(et);
	CURVNET_RESTORE();
	return (ret);
}

/*
 * Translate a FreeBSD interface name to a Linux interface name,
 * and return the number of bytes copied to lxname, 0 if interface
 * not found, -1 on error.
 */
struct ifname_bsd_to_linux_ifp_cb_s {
	struct ifnet	*ifp;
	int		ethno;
	char		*lxname;
	size_t		len;
};

static int
ifname_bsd_to_linux_ifp_cb(if_t ifp, void *arg)
{
	struct ifname_bsd_to_linux_ifp_cb_s *cbs = arg;

	if (ifp == cbs->ifp)
		return (snprintf(cbs->lxname, cbs->len, "eth%d", cbs->ethno));
	if (IFP_IS_ETH(ifp))
		cbs->ethno++;
	return (0);
}

int
ifname_bsd_to_linux_ifp(struct ifnet *ifp, char *lxname, size_t len)
{
	struct ifname_bsd_to_linux_ifp_cb_s arg = {
		.ifp = ifp,
		.ethno = 0,
		.lxname = lxname,
		.len = len,
	};

	NET_EPOCH_ASSERT();

	/*
	 * Linux loopback interface name is lo (not lo0),
	 * we translate lo to lo0, loX to loX.
	 */
	if (IFP_IS_LOOP(ifp) && strncmp(ifp->if_xname, "lo0", IFNAMSIZ) == 0)
		return (strlcpy(lxname, "lo", len));

	/* Short-circuit non ethernet interfaces. */
	if (!IFP_IS_ETH(ifp) || linux_use_real_ifname(ifp))
		return (strlcpy(lxname, if_name(ifp), len));

 	/* Determine the (relative) unit number for ethernet interfaces. */
	return (if_foreach(ifname_bsd_to_linux_ifp_cb, &arg));
}

/*
 * Translate a Linux interface name to a FreeBSD interface name,
 * and return the associated ifnet structure
 * bsdname and lxname need to be least IFNAMSIZ bytes long, but
 * can point to the same buffer.
 */
struct ifname_linux_to_ifp_cb_s {
	bool		is_lo;
	bool		is_eth;
	int		ethno;
	int		unit;
	const char	*lxname;
	if_t		ifp;
};

static int
ifname_linux_to_ifp_cb(if_t ifp, void *arg)
{
	struct ifname_linux_to_ifp_cb_s *cbs = arg;

	NET_EPOCH_ASSERT();

	/*
	 * Allow Linux programs to use FreeBSD names. Don't presume
	 * we never have an interface named "eth", so don't make
	 * the test optional based on is_eth.
	 */
	if (strncmp(if_name(ifp), cbs->lxname, LINUX_IFNAMSIZ) == 0)
		goto out;
	if (cbs->is_eth && IFP_IS_ETH(ifp) && cbs->unit == cbs->ethno)
		goto out;
	if (cbs->is_lo && IFP_IS_LOOP(ifp))
		goto out;
	if (IFP_IS_ETH(ifp))
		cbs->ethno++;
	return (0);

out:
	cbs->ifp = ifp;
	return (1);
}

struct ifnet *
ifname_linux_to_ifp(struct thread *td, const char *lxname)
{
	struct ifname_linux_to_ifp_cb_s arg = {
		.ethno = 0,
		.lxname = lxname,
		.ifp = NULL,
	};
	int len;
	char *ep;

	NET_EPOCH_ASSERT();

	for (len = 0; len < LINUX_IFNAMSIZ; ++len)
		if (!isalpha(lxname[len]) || lxname[len] == '\0')
			break;
	if (len == 0 || len == LINUX_IFNAMSIZ)
		return (NULL);
	/*
	 * Linux loopback interface name is lo (not lo0),
	 * we translate lo to lo0, loX to loX.
	 */
	arg.is_lo = (len == 2 && strncmp(lxname, "lo", LINUX_IFNAMSIZ) == 0);
	arg.unit = (int)strtoul(lxname + len, &ep, 10);
	if ((ep == NULL || ep == lxname + len || ep >= lxname + LINUX_IFNAMSIZ) &&
	    arg.is_lo == 0)
		return (NULL);
	arg.is_eth = (len == 3 && strncmp(lxname, "eth", len) == 0);

	if_foreach(ifname_linux_to_ifp_cb, &arg);
	return (arg.ifp);
}

int
ifname_linux_to_bsd(struct thread *td, const char *lxname, char *bsdname)
{
	struct epoch_tracker et;
	struct ifnet *ifp;

	CURVNET_SET(TD_TO_VNET(td));
	NET_EPOCH_ENTER(et);
	ifp = ifname_linux_to_ifp(td, lxname);
	if (ifp != NULL && bsdname != NULL)
		strlcpy(bsdname, if_name(ifp), IFNAMSIZ);
	NET_EPOCH_EXIT(et);
	CURVNET_RESTORE();
	return (ifp != NULL ? 0 : EINVAL);
}

unsigned short
linux_ifflags(struct ifnet *ifp)
{
	unsigned short fl, flags;

	fl = (if_getflags(ifp) | if_getdrvflags(ifp)) & 0xffff;
	flags = 0;
	if (fl & IFF_UP)
		flags |= LINUX_IFF_UP;
	if (fl & IFF_BROADCAST)
		flags |= LINUX_IFF_BROADCAST;
	if (fl & IFF_DEBUG)
		flags |= LINUX_IFF_DEBUG;
	if (fl & IFF_LOOPBACK)
		flags |= LINUX_IFF_LOOPBACK;
	if (fl & IFF_POINTOPOINT)
		flags |= LINUX_IFF_POINTOPOINT;
	if (fl & IFF_DRV_RUNNING)
		flags |= LINUX_IFF_RUNNING;
	if (fl & IFF_NOARP)
		flags |= LINUX_IFF_NOARP;
	if (fl & IFF_PROMISC)
		flags |= LINUX_IFF_PROMISC;
	if (fl & IFF_ALLMULTI)
		flags |= LINUX_IFF_ALLMULTI;
	if (fl & IFF_MULTICAST)
		flags |= LINUX_IFF_MULTICAST;
	return (flags);
}

static u_int
linux_ifhwaddr_cb(void *arg, struct ifaddr *ifa, u_int count)
{
	struct sockaddr_dl *sdl = (struct sockaddr_dl *)ifa->ifa_addr;
	struct l_sockaddr *lsa = arg;

	if (count > 0)
		return (0);
	if (sdl->sdl_type != IFT_ETHER)
		return (0);
	bzero(lsa, sizeof(*lsa));
	lsa->sa_family = LINUX_ARPHRD_ETHER;
	bcopy(LLADDR(sdl), lsa->sa_data, LINUX_IFHWADDRLEN);
	return (1);
}

int
linux_ifhwaddr(struct ifnet *ifp, struct l_sockaddr *lsa)
{

	if (IFP_IS_LOOP(ifp)) {
		bzero(lsa, sizeof(*lsa));
		lsa->sa_family = LINUX_ARPHRD_LOOPBACK;
		return (0);
	}
	if (!IFP_IS_ETH(ifp))
		return (ENOENT);
	if (if_foreach_addr_type(ifp, AF_LINK, linux_ifhwaddr_cb, lsa) > 0)
		return (0);
	return (ENOENT);
}

int
linux_to_bsd_domain(int domain)
{

	switch (domain) {
	case LINUX_AF_UNSPEC:
		return (AF_UNSPEC);
	case LINUX_AF_UNIX:
		return (AF_LOCAL);
	case LINUX_AF_INET:
		return (AF_INET);
	case LINUX_AF_INET6:
		return (AF_INET6);
	case LINUX_AF_AX25:
		return (AF_CCITT);
	case LINUX_AF_IPX:
		return (AF_IPX);
	case LINUX_AF_APPLETALK:
		return (AF_APPLETALK);
	case LINUX_AF_NETLINK:
		return (AF_NETLINK);
	}
	return (-1);
}

int
bsd_to_linux_domain(int domain)
{

	switch (domain) {
	case AF_UNSPEC:
		return (LINUX_AF_UNSPEC);
	case AF_LOCAL:
		return (LINUX_AF_UNIX);
	case AF_INET:
		return (LINUX_AF_INET);
	case AF_INET6:
		return (LINUX_AF_INET6);
	case AF_CCITT:
		return (LINUX_AF_AX25);
	case AF_IPX:
		return (LINUX_AF_IPX);
	case AF_APPLETALK:
		return (LINUX_AF_APPLETALK);
	case AF_NETLINK:
		return (LINUX_AF_NETLINK);
	}
	return (-1);
}

/*
 * Based on the fact that:
 * 1. Native and Linux storage of struct sockaddr
 * and struct sockaddr_in6 are equal.
 * 2. On Linux sa_family is the first member of all struct sockaddr.
 */
int
bsd_to_linux_sockaddr(const struct sockaddr *sa, struct l_sockaddr **lsa,
    socklen_t len)
{
	struct l_sockaddr *kosa;
	int bdom;

	*lsa = NULL;
	if (len < 2 || len > UCHAR_MAX)
		return (EINVAL);
	bdom = bsd_to_linux_domain(sa->sa_family);
	if (bdom == -1)
		return (EAFNOSUPPORT);

	kosa = malloc(len, M_LINUX, M_WAITOK);
	bcopy(sa, kosa, len);
	kosa->sa_family = bdom;
	*lsa = kosa;
	return (0);
}

int
linux_to_bsd_sockaddr(const struct l_sockaddr *osa, struct sockaddr **sap,
    socklen_t *len)
{
	struct sockaddr *sa;
	struct l_sockaddr *kosa;
#ifdef INET6
	struct sockaddr_in6 *sin6;
	bool  oldv6size;
#endif
	char *name;
	int salen, bdom, error, hdrlen, namelen;

	if (*len < 2 || *len > UCHAR_MAX)
		return (EINVAL);

	salen = *len;

#ifdef INET6
	oldv6size = false;
	/*
	 * Check for old (pre-RFC2553) sockaddr_in6. We may accept it
	 * if it's a v4-mapped address, so reserve the proper space
	 * for it.
	 */
	if (salen == sizeof(struct sockaddr_in6) - sizeof(uint32_t)) {
		salen += sizeof(uint32_t);
		oldv6size = true;
	}
#endif

	kosa = malloc(salen, M_SONAME, M_WAITOK);

	if ((error = copyin(osa, kosa, *len)))
		goto out;

	bdom = linux_to_bsd_domain(kosa->sa_family);
	if (bdom == -1) {
		error = EAFNOSUPPORT;
		goto out;
	}

#ifdef INET6
	/*
	 * Older Linux IPv6 code uses obsolete RFC2133 struct sockaddr_in6,
	 * which lacks the scope id compared with RFC2553 one. If we detect
	 * the situation, reject the address and write a message to system log.
	 *
	 * Still accept addresses for which the scope id is not used.
	 */
	if (oldv6size) {
		if (bdom == AF_INET6) {
			sin6 = (struct sockaddr_in6 *)kosa;
			if (IN6_IS_ADDR_V4MAPPED(&sin6->sin6_addr) ||
			    (!IN6_IS_ADDR_LINKLOCAL(&sin6->sin6_addr) &&
			     !IN6_IS_ADDR_SITELOCAL(&sin6->sin6_addr) &&
			     !IN6_IS_ADDR_V4COMPAT(&sin6->sin6_addr) &&
			     !IN6_IS_ADDR_UNSPECIFIED(&sin6->sin6_addr) &&
			     !IN6_IS_ADDR_MULTICAST(&sin6->sin6_addr))) {
				sin6->sin6_scope_id = 0;
			} else {
				linux_msg(curthread,
				    "obsolete pre-RFC2553 sockaddr_in6 rejected");
				error = EINVAL;
				goto out;
			}
		} else
			salen -= sizeof(uint32_t);
	}
#endif
	if (bdom == AF_INET) {
		if (salen < sizeof(struct sockaddr_in)) {
			error = EINVAL;
			goto out;
		}
		salen = sizeof(struct sockaddr_in);
	}

	if (bdom == AF_LOCAL && salen > sizeof(struct sockaddr_un)) {
		hdrlen = offsetof(struct sockaddr_un, sun_path);
		name = ((struct sockaddr_un *)kosa)->sun_path;
		if (*name == '\0') {
			/*
			 * Linux abstract namespace starts with a NULL byte.
			 * XXX We do not support abstract namespace yet.
			 */
			namelen = strnlen(name + 1, salen - hdrlen - 1) + 1;
		} else
			namelen = strnlen(name, salen - hdrlen);
		salen = hdrlen + namelen;
		if (salen > sizeof(struct sockaddr_un)) {
			error = ENAMETOOLONG;
			goto out;
		}
	}

	if (bdom == AF_NETLINK) {
		if (salen < sizeof(struct sockaddr_nl)) {
			error = EINVAL;
			goto out;
		}
		salen = sizeof(struct sockaddr_nl);
	}

	sa = (struct sockaddr *)kosa;
	sa->sa_family = bdom;
	sa->sa_len = salen;

	*sap = sa;
	*len = salen;
	return (0);

out:
	free(kosa, M_SONAME);
	return (error);
}

void
linux_dev_shm_create(void)
{
	int error;

	error = make_dev_p(MAKEDEV_CHECKNAME | MAKEDEV_WAITOK, &dev_shm_cdev,
	    &dev_shm_cdevsw, NULL, UID_ROOT, GID_WHEEL, 0, "shm/.mountpoint");
	if (error != 0) {
		printf("%s: failed to create device node, error %d\n",
		    __func__, error);
	}
}

void
linux_dev_shm_destroy(void)
{

	destroy_dev(dev_shm_cdev);
}

int
bsd_to_linux_bits_(int value, struct bsd_to_linux_bitmap *bitmap,
    size_t mapcnt, int no_value)
{
	int bsd_mask, bsd_value, linux_mask, linux_value;
	int linux_ret;
	size_t i;
	bool applied;

	applied = false;
	linux_ret = 0;
	for (i = 0; i < mapcnt; ++i) {
		bsd_mask = bitmap[i].bsd_mask;
		bsd_value = bitmap[i].bsd_value;
		if (bsd_mask == 0)
			bsd_mask = bsd_value;

		linux_mask = bitmap[i].linux_mask;
		linux_value = bitmap[i].linux_value;
		if (linux_mask == 0)
			linux_mask = linux_value;

		/*
		 * If a mask larger than just the value is set, we explicitly
		 * want to make sure that only this bit we mapped within that
		 * mask is set.
		 */
		if ((value & bsd_mask) == bsd_value) {
			linux_ret = (linux_ret & ~linux_mask) | linux_value;
			applied = true;
		}
	}

	if (!applied)
		return (no_value);
	return (linux_ret);
}

int
linux_to_bsd_bits_(int value, struct bsd_to_linux_bitmap *bitmap,
    size_t mapcnt, int no_value)
{
	int bsd_mask, bsd_value, linux_mask, linux_value;
	int bsd_ret;
	size_t i;
	bool applied;

	applied = false;
	bsd_ret = 0;
	for (i = 0; i < mapcnt; ++i) {
		bsd_mask = bitmap[i].bsd_mask;
		bsd_value = bitmap[i].bsd_value;
		if (bsd_mask == 0)
			bsd_mask = bsd_value;

		linux_mask = bitmap[i].linux_mask;
		linux_value = bitmap[i].linux_value;
		if (linux_mask == 0)
			linux_mask = linux_value;

		/*
		 * If a mask larger than just the value is set, we explicitly
		 * want to make sure that only this bit we mapped within that
		 * mask is set.
		 */
		if ((value & linux_mask) == linux_value) {
			bsd_ret = (bsd_ret & ~bsd_mask) | bsd_value;
			applied = true;
		}
	}

	if (!applied)
		return (no_value);
	return (bsd_ret);
}

void
linux_to_bsd_poll_events(struct thread *td, int fd, short lev,
    short *bev)
{
	struct file *fp;
	int error;
	short bits = 0;

	if (lev & LINUX_POLLIN)
		bits |= POLLIN;
	if (lev & LINUX_POLLPRI)
		bits |=	POLLPRI;
	if (lev & LINUX_POLLOUT)
		bits |= POLLOUT;
	if (lev & LINUX_POLLERR)
		bits |= POLLERR;
	if (lev & LINUX_POLLHUP)
		bits |= POLLHUP;
	if (lev & LINUX_POLLNVAL)
		bits |= POLLNVAL;
	if (lev & LINUX_POLLRDNORM)
		bits |= POLLRDNORM;
	if (lev & LINUX_POLLRDBAND)
		bits |= POLLRDBAND;
	if (lev & LINUX_POLLWRBAND)
		bits |= POLLWRBAND;
	if (lev & LINUX_POLLWRNORM)
		bits |= POLLWRNORM;

	if (lev & LINUX_POLLRDHUP) {
		/*
		 * It seems that the Linux silencly ignores POLLRDHUP
		 * on non-socket file descriptors unlike FreeBSD, where
		 * events bits is more strictly checked (POLLSTANDARD).
		 */
		error = fget_unlocked(td, fd, &cap_no_rights, &fp);
		if (error == 0) {
			/*
			 * XXX. On FreeBSD POLLRDHUP applies only to
			 * stream sockets.
			 */
			if (fp->f_type == DTYPE_SOCKET)
				bits |= POLLRDHUP;
			fdrop(fp, td);
		}
	}

	if (lev & LINUX_POLLMSG)
		LINUX_RATELIMIT_MSG_OPT1("unsupported POLLMSG, events(%d)", lev);
	if (lev & LINUX_POLLREMOVE)
		LINUX_RATELIMIT_MSG_OPT1("unsupported POLLREMOVE, events(%d)", lev);

	*bev = bits;
}

void
bsd_to_linux_poll_events(short bev, short *lev)
{
	short bits = 0;

	if (bev & POLLIN)
		bits |= LINUX_POLLIN;
	if (bev & POLLPRI)
		bits |=	LINUX_POLLPRI;
	if (bev & (POLLOUT | POLLWRNORM))
		/*
		 * POLLWRNORM is equal to POLLOUT on FreeBSD,
		 * but not on Linux
		 */
		bits |= LINUX_POLLOUT;
	if (bev & POLLERR)
		bits |= LINUX_POLLERR;
	if (bev & POLLHUP)
		bits |= LINUX_POLLHUP;
	if (bev & POLLNVAL)
		bits |= LINUX_POLLNVAL;
	if (bev & POLLRDNORM)
		bits |= LINUX_POLLRDNORM;
	if (bev & POLLRDBAND)
		bits |= LINUX_POLLRDBAND;
	if (bev & POLLWRBAND)
		bits |= LINUX_POLLWRBAND;
	if (bev & POLLRDHUP)
		bits |= LINUX_POLLRDHUP;

	*lev = bits;
}

bool
linux_use_real_ifname(const struct ifnet *ifp)
{

	return (use_real_ifnames);
}