aboutgitcodebugslistschat
path: root/netlink.c
blob: bf79dd498acd1a35d4156f31c4be3402902000e0 (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
// SPDX-License-Identifier: GPL-2.0-or-later

/* PASST - Plug A Simple Socket Transport
 *  for qemu/UNIX domain socket mode
 *
 * PASTA - Pack A Subtle Tap Abstraction
 *  for network namespace/tap device mode
 *
 * netlink.c - rtnetlink routines: interfaces, addresses, routes
 *
 * Copyright (c) 2020-2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 */

#include <sched.h>
#include <string.h>
#include <stddef.h>
#include <errno.h>
#include <sys/types.h>
#include <limits.h>
#include <unistd.h>
#include <signal.h>
#include <stdlib.h>
#include <stdbool.h>
#include <stdint.h>
#include <arpa/inet.h>
#include <netinet/in.h>
#include <netinet/if_ether.h>

#include <linux/netlink.h>
#include <linux/rtnetlink.h>

#include "util.h"
#include "passt.h"
#include "log.h"
#include "netlink.h"

/* Netlink expects a buffer of at least 8kiB or the system page size,
 * whichever is larger.  32kiB is recommended for more efficient.
 * Since the largest page size on any remotely common Linux setup is
 * 64kiB (ppc64), that should cover it.
 *
 * https://www.kernel.org/doc/html/next/userspace-api/netlink/intro.html#buffer-sizing
 */
#define NLBUFSIZ 65536

/* Socket in init, in target namespace, sequence (just needs to be monotonic) */
int nl_sock	= -1;
int nl_sock_ns	= -1;
static int nl_seq = 1;

/**
 * nl_sock_init_do() - Set up netlink sockets in init or target namespace
 * @arg:	Execution context, if running from namespace, NULL otherwise
 *
 * Return: 0
 */
static int nl_sock_init_do(void *arg)
{
	struct sockaddr_nl addr = { .nl_family = AF_NETLINK, };
	int *s = arg ? &nl_sock_ns : &nl_sock;
#ifdef NETLINK_GET_STRICT_CHK
	int y = 1;
#endif

	if (arg)
		ns_enter((struct ctx *)arg);

	*s = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE);
	if (*s < 0 || bind(*s, (struct sockaddr *)&addr, sizeof(addr))) {
		*s = -1;
		return 0;
	}

#ifdef NETLINK_GET_STRICT_CHK
	if (setsockopt(*s, SOL_NETLINK, NETLINK_GET_STRICT_CHK, &y, sizeof(y)))
		debug("netlink: cannot set NETLINK_GET_STRICT_CHK on %i", *s);
#endif
	return 0;
}

/**
 * nl_sock_init() - Call nl_sock_init_do(), won't return on failure
 * @c:		Execution context
 * @ns:		Get socket in namespace, not in init
 */
void nl_sock_init(const struct ctx *c, bool ns)
{
	if (ns) {
		NS_CALL(nl_sock_init_do, c);
		if (nl_sock_ns == -1)
			goto fail;
	} else {
		nl_sock_init_do(NULL);
	}

	if (nl_sock == -1)
		goto fail;

	return;

fail:
	die("Failed to get netlink socket");
}

/**
 * nl_send() - Prepare and send netlink request
 * @s:		Netlink socket
 * @req:	Request (will fill netlink header)
 * @type:	Request type
 * @flags:	Extra request flags (NLM_F_REQUEST and NLM_F_ACK assumed)
 * @len:	Request length
 *
 * Return: sequence number of request on success, terminates on error
 */
static uint32_t nl_send(int s, void *req, uint16_t type,
		       uint16_t flags, ssize_t len)
{
	struct nlmsghdr *nh;
	ssize_t n;

	nh = (struct nlmsghdr *)req;
	nh->nlmsg_type = type;
	nh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags;
	nh->nlmsg_len = len;
	nh->nlmsg_seq = nl_seq++;
	nh->nlmsg_pid = 0;

	n = send(s, req, len, 0);
	if (n < 0)
		die("netlink: Failed to send(): %s", strerror(errno));
	else if (n < len)
		die("netlink: Short send (%zd of %zd bytes)", n, len);

	return nh->nlmsg_seq;
}

/**
 * nl_status() - Check status given by a netlink response
 * @nh:		Netlink response header
 * @n:		Remaining space in response buffer from @nh
 * @seq:	Request sequence number we expect a response to
 *
 * Return: 0 if @nh indicated successful completion,
 *         < 0, negative error code if @nh indicated failure
 *         > 0 @n if there are more responses to request @seq
 *     terminates if sequence numbers are out of sync
 */
static int nl_status(const struct nlmsghdr *nh, ssize_t n, uint32_t seq)
{
	ASSERT(NLMSG_OK(nh, n));

	if (nh->nlmsg_seq != seq)
		die("netlink: Unexpected sequence number (%u != %u)",
		    nh->nlmsg_seq, seq);

	if (nh->nlmsg_type == NLMSG_DONE) {
		return 0;
	}
	if (nh->nlmsg_type == NLMSG_ERROR) {
		struct nlmsgerr *errmsg = (struct nlmsgerr *)NLMSG_DATA(nh);
		return errmsg->error;
	}

	return n;
}

/**
 * nl_next() - Get next netlink response message, recv()ing if necessary
 * @s:		Netlink socket
 * @buf:	Buffer for responses (at least NLBUFSIZ long)
 * @nh:		Previous message, or NULL if there are none
 * @n:		Variable with remaining unread bytes in buffer (updated)
 *
 * Return: pointer to next unread netlink response message (may block)
 */
static struct nlmsghdr *nl_next(int s, char *buf, struct nlmsghdr *nh, ssize_t *n)
{
	if (nh) {
		nh = NLMSG_NEXT(nh, *n);
		if (NLMSG_OK(nh, *n))
			return nh;
	}

	*n = recv(s, buf, NLBUFSIZ, 0);
	if (*n < 0)
		die("netlink: Failed to recv(): %s", strerror(errno));

	nh = (struct nlmsghdr *)buf;
	if (!NLMSG_OK(nh, *n))
		die("netlink: Response datagram with no message");

	return nh;
}

/**
 * nl_foreach - 'for' type macro to step through netlink response messages
 * nl_foreach_oftype - as above, but only messages of expected type
 * @nh:		Steps through each response header (struct nlmsghdr *)
 * @status:	When loop exits indicates if there was an error (ssize_t)
 * @s:		Netlink socket
 * @buf:	Buffer for responses (at least NLBUFSIZ long)
 * @seq:	Sequence number of request we're getting responses for
 * @type:	Type of netlink message to process
 */
#define nl_foreach(nh, status, s, buf, seq)				\
	for ((nh) = nl_next((s), (buf), NULL, &(status));		\
	     ((status) = nl_status((nh), (status), (seq))) > 0;		\
	     (nh) = nl_next((s), (buf), (nh), &(status)))

#define nl_foreach_oftype(nh, status, s, buf, seq, type)		\
	nl_foreach((nh), (status), (s), (buf), (seq))			\
		if ((nh)->nlmsg_type != (type)) {			\
			warn("netlink: Unexpected message type");	\
		} else

/**
 * nl_do() - Send netlink "do" request, and wait for acknowledgement
 * @s:		Netlink socket
 * @req:	Request (will fill netlink header)
 * @type:	Request type
 * @flags:	Extra request flags (NLM_F_REQUEST and NLM_F_ACK assumed)
 * @len:	Request length
 *
 * Return: 0 on success, negative error code on error
 */
static int nl_do(int s, void *req, uint16_t type, uint16_t flags, ssize_t len)
{
	struct nlmsghdr *nh;
	char buf[NLBUFSIZ];
	ssize_t status;
	uint32_t seq;

	seq = nl_send(s, req, type, flags, len);
	nl_foreach(nh, status, s, buf, seq)
		warn("netlink: Unexpected response message");

	return status;
}

/**
 * nl_get_ext_if() - Get interface index supporting IP version being probed
 * @s:	Netlink socket
 * @af:	Address family (AF_INET or AF_INET6) to look for connectivity
 *      for.
 *
 * Return: interface index, 0 if not found
 */
unsigned int nl_get_ext_if(int s, sa_family_t af)
{
	struct { struct nlmsghdr nlh; struct rtmsg rtm; } req = {
		.rtm.rtm_table	 = RT_TABLE_MAIN,
		.rtm.rtm_scope	 = RT_SCOPE_UNIVERSE,
		.rtm.rtm_type	 = RTN_UNICAST,
		.rtm.rtm_family	 = af,
	};
	unsigned int ifi = 0;
	struct nlmsghdr *nh;
	struct rtattr *rta;
	char buf[NLBUFSIZ];
	ssize_t status;
	uint32_t seq;
	size_t na;

	seq = nl_send(s, &req, RTM_GETROUTE, NLM_F_DUMP, sizeof(req));
	nl_foreach_oftype(nh, status, s, buf, seq, RTM_NEWROUTE) {
		struct rtmsg *rtm = (struct rtmsg *)NLMSG_DATA(nh);

		if (ifi || rtm->rtm_dst_len || rtm->rtm_family != af)
			continue;

		for (rta = RTM_RTA(rtm), na = RTM_PAYLOAD(nh); RTA_OK(rta, na);
		     rta = RTA_NEXT(rta, na)) {
			if (rta->rta_type != RTA_OIF)
				continue;

			ifi = *(unsigned int *)RTA_DATA(rta);
		}
	}
	if (status < 0)
		warn("netlink: RTM_GETROUTE failed: %s", strerror(-status));

	return ifi;
}

/**
 * nl_route_get_def() - Get default route for given interface and address family
 * @s:		Netlink socket
 * @ifi:	Interface index
 * @af:		Address family
 * @gw:		Default gateway to fill on NL_GET
 *
 * Return: 0 on success, negative error code on failure
 */
int nl_route_get_def(int s, unsigned int ifi, sa_family_t af, void *gw)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct rtmsg rtm;
		struct rtattr rta;
		unsigned int ifi;
	} req = {
		.rtm.rtm_family	  = af,
		.rtm.rtm_table	  = RT_TABLE_MAIN,
		.rtm.rtm_scope	  = RT_SCOPE_UNIVERSE,
		.rtm.rtm_type	  = RTN_UNICAST,

		.rta.rta_type	  = RTA_OIF,
		.rta.rta_len	  = RTA_LENGTH(sizeof(unsigned int)),
		.ifi		  = ifi,
	};
	struct nlmsghdr *nh;
	bool found = false;
	char buf[NLBUFSIZ];
	ssize_t status;
	uint32_t seq;

	seq = nl_send(s, &req, RTM_GETROUTE, NLM_F_DUMP, sizeof(req));
	nl_foreach_oftype(nh, status, s, buf, seq, RTM_NEWROUTE) {
		struct rtmsg *rtm = (struct rtmsg *)NLMSG_DATA(nh);
		struct rtattr *rta;
		size_t na;

		if (found || rtm->rtm_dst_len)
			continue;

		for (rta = RTM_RTA(rtm), na = RTM_PAYLOAD(nh); RTA_OK(rta, na);
		     rta = RTA_NEXT(rta, na)) {
			if (rta->rta_type != RTA_GATEWAY)
				continue;

			memcpy(gw, RTA_DATA(rta), RTA_PAYLOAD(rta));
			found = true;
		}
	}
	return status;
}

/**
 * nl_route_set_def() - Set default route for given interface and address family
 * @s:		Netlink socket
 * @ifi:	Interface index in target namespace
 * @af:		Address family
 * @gw:		Default gateway to set
 *
 * Return: 0 on success, negative error code on failure
 */
int nl_route_set_def(int s, unsigned int ifi, sa_family_t af, const void *gw)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct rtmsg rtm;
		struct rtattr rta;
		unsigned int ifi;
		union {
			struct {
				struct rtattr rta_dst;
				struct in6_addr d;
				struct rtattr rta_gw;
				struct in6_addr a;
			} r6;
			struct {
				struct rtattr rta_dst;
				struct in_addr d;
				struct rtattr rta_gw;
				struct in_addr a;
			} r4;
		} set;
	} req = {
		.rtm.rtm_family	  = af,
		.rtm.rtm_table	  = RT_TABLE_MAIN,
		.rtm.rtm_scope	  = RT_SCOPE_UNIVERSE,
		.rtm.rtm_type	  = RTN_UNICAST,
		.rtm.rtm_protocol = RTPROT_BOOT,

		.rta.rta_type	  = RTA_OIF,
		.rta.rta_len	  = RTA_LENGTH(sizeof(unsigned int)),
		.ifi		  = ifi,
	};
	ssize_t len;

	if (af == AF_INET6) {
		size_t rta_len = RTA_LENGTH(sizeof(req.set.r6.d));

		len = offsetof(struct req_t, set.r6) + sizeof(req.set.r6);

		req.set.r6.rta_dst.rta_type = RTA_DST;
		req.set.r6.rta_dst.rta_len = rta_len;

		memcpy(&req.set.r6.a, gw, sizeof(req.set.r6.a));
		req.set.r6.rta_gw.rta_type = RTA_GATEWAY;
		req.set.r6.rta_gw.rta_len = rta_len;
	} else {
		size_t rta_len = RTA_LENGTH(sizeof(req.set.r4.d));

		len = offsetof(struct req_t, set.r4) + sizeof(req.set.r4);

		req.set.r4.rta_dst.rta_type = RTA_DST;
		req.set.r4.rta_dst.rta_len = rta_len;

		memcpy(&req.set.r4.a, gw, sizeof(req.set.r4.a));
		req.set.r4.rta_gw.rta_type = RTA_GATEWAY;
		req.set.r4.rta_gw.rta_len = rta_len;
	}

	return nl_do(s, &req, RTM_NEWROUTE, NLM_F_CREATE | NLM_F_EXCL, len);
}

/**
 * nl_route_dup() - Copy routes for given interface and address family
 * @s_src:	Netlink socket in source namespace
 * @ifi_src:	Source interface index
 * @s_dst:	Netlink socket in destination namespace
 * @ifi_dst:	Interface index in destination namespace
 * @af:		Address family
 *
 * Return: 0 on success, negative error code on failure
 */
int nl_route_dup(int s_src, unsigned int ifi_src,
		 int s_dst, unsigned int ifi_dst, sa_family_t af)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct rtmsg rtm;
		struct rtattr rta;
		unsigned int ifi;
	} req = {
		.rtm.rtm_family	  = af,
		.rtm.rtm_table	  = RT_TABLE_MAIN,
		.rtm.rtm_scope	  = RT_SCOPE_UNIVERSE,
		.rtm.rtm_type	  = RTN_UNICAST,

		.rta.rta_type	  = RTA_OIF,
		.rta.rta_len	  = RTA_LENGTH(sizeof(unsigned int)),
		.ifi		  = ifi_src,
	};
	ssize_t nlmsgs_size, status;
	unsigned dup_routes = 0;
	struct nlmsghdr *nh;
	char buf[NLBUFSIZ];
	uint32_t seq;
	unsigned i;

	seq = nl_send(s_src, &req, RTM_GETROUTE, NLM_F_DUMP, sizeof(req));

	/* nl_foreach() will step through multiple response datagrams,
	 * which we don't want here because we need to have all the
	 * routes in the buffer at once.
	 */
	nh = nl_next(s_src, buf, NULL, &nlmsgs_size);
	for (status = nlmsgs_size;
	     NLMSG_OK(nh, status) && (status = nl_status(nh, status, seq)) > 0;
	     nh = NLMSG_NEXT(nh, status)) {
		struct rtmsg *rtm = (struct rtmsg *)NLMSG_DATA(nh);
		struct rtattr *rta;
		size_t na;

		if (nh->nlmsg_type != RTM_NEWROUTE)
			continue;

		dup_routes++;

		for (rta = RTM_RTA(rtm), na = RTM_PAYLOAD(nh); RTA_OK(rta, na);
		     rta = RTA_NEXT(rta, na)) {
			if (rta->rta_type == RTA_OIF) {
				/* The host obviously list's the host interface
				 * id here, we need to change it to the
				 * namespace's interface id
				 */
				*(unsigned int *)RTA_DATA(rta) = ifi_dst;
			} else if (rta->rta_type == RTA_PREFSRC) {
				/* Host routes might include a preferred source
				 * address, which must be one of the host's
				 * addresses.  However, with -a pasta will use a
				 * different namespace address, making such a
				 * route invalid in the namespace.  Strip off
				 * RTA_PREFSRC attributes to avoid that. */
				rta->rta_type = RTA_UNSPEC;
			}
		}
	}

	if (!NLMSG_OK(nh, status) || status > 0) {
		/* Process any remaining datagrams in a different
		 * buffer so we don't overwrite the first one.
		 */
		char tail[NLBUFSIZ];
		unsigned extra = 0;

		nl_foreach_oftype(nh, status, s_src, tail, seq, RTM_NEWROUTE)
			extra++;

		if (extra) {
			err("netlink: Too many routes to duplicate");
			return -E2BIG;
		}
	}
	if (status < 0)
		return status;

	/* Routes might have dependencies between each other, and the kernel
	 * processes RTM_NEWROUTE messages sequentially. For n routes, we might
	 * need to send the requests up to n times to get all of them inserted.
	 * Routes that have been already inserted will return -EEXIST, but we
	 * can safely ignore that and repeat the requests. This avoids the need
	 * to calculate dependencies: let the kernel do that.
	 */
	for (i = 0; i < dup_routes; i++) {
		for (nh = (struct nlmsghdr *)buf, status = nlmsgs_size;
		     NLMSG_OK(nh, status);
		     nh = NLMSG_NEXT(nh, status)) {
			uint16_t flags = nh->nlmsg_flags;
			int rc;

			if (nh->nlmsg_type != RTM_NEWROUTE)
				continue;

			rc = nl_do(s_dst, nh, RTM_NEWROUTE,
				   (flags & ~NLM_F_DUMP_FILTERED) | NLM_F_CREATE,
				   nh->nlmsg_len);
			if (rc < 0 && rc != -ENETUNREACH && rc != -EEXIST)
				return rc;
		}
	}

	return 0;
}

/**
 * nl_addr_get() - Get most specific global address, given interface and family
 * @s:		Netlink socket
 * @ifi:	Interface index in outer network namespace
 * @af:		Address family
 * @addr:	Global address to fill
 * @prefix_len:	Mask or prefix length, to fill (for IPv4)
 * @addr_l:	Link-scoped address to fill (for IPv6)
 *
 * Return: 9 on success, negative error code on failure
 */
int nl_addr_get(int s, unsigned int ifi, sa_family_t af,
		void *addr, int *prefix_len, void *addr_l)
{
	uint8_t prefix_max = 0, prefix_max_ll = 0;
	struct req_t {
		struct nlmsghdr nlh;
		struct ifaddrmsg ifa;
	} req = {
		.ifa.ifa_family    = af,
		.ifa.ifa_index     = ifi,
	};
	struct nlmsghdr *nh;
	char buf[NLBUFSIZ];
	ssize_t status;
	uint32_t seq;

	seq = nl_send(s, &req, RTM_GETADDR, NLM_F_DUMP, sizeof(req));
	nl_foreach_oftype(nh, status, s, buf, seq, RTM_NEWADDR) {
		struct ifaddrmsg *ifa = (struct ifaddrmsg *)NLMSG_DATA(nh);
		struct rtattr *rta;
		size_t na;

		if (ifa->ifa_index != ifi)
			continue;

		for (rta = IFA_RTA(ifa), na = IFA_PAYLOAD(nh); RTA_OK(rta, na);
		     rta = RTA_NEXT(rta, na)) {
			if (rta->rta_type != IFA_ADDRESS)
				continue;

			if (af == AF_INET && ifa->ifa_prefixlen > prefix_max) {
				memcpy(addr, RTA_DATA(rta), RTA_PAYLOAD(rta));

				prefix_max = *prefix_len = ifa->ifa_prefixlen;
			} else if (af == AF_INET6 && addr &&
				   ifa->ifa_scope == RT_SCOPE_UNIVERSE &&
				   ifa->ifa_prefixlen > prefix_max) {
				memcpy(addr, RTA_DATA(rta), RTA_PAYLOAD(rta));

				prefix_max = ifa->ifa_prefixlen;
			}

			if (addr_l &&
			    af == AF_INET6 && ifa->ifa_scope == RT_SCOPE_LINK &&
			    ifa->ifa_prefixlen > prefix_max_ll) {
				memcpy(addr_l, RTA_DATA(rta), RTA_PAYLOAD(rta));

				prefix_max_ll = ifa->ifa_prefixlen;
			}
		}
	}
	return status;
}

/**
 * nl_add_set() - Set IP addresses for given interface and address family
 * @s:		Netlink socket
 * @ifi:	Interface index
 * @af:		Address family
 * @addr:	Global address to set
 * @prefix_len:	Mask or prefix length to set
 *
 * Return: 0 on success, negative error code on failure
 */
int nl_addr_set(int s, unsigned int ifi, sa_family_t af,
		const void *addr, int prefix_len)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct ifaddrmsg ifa;
		union {
			struct {
				struct rtattr rta_l;
				struct in_addr l;
				struct rtattr rta_a;
				struct in_addr a;
			} a4;
			struct {
				struct rtattr rta_l;
				struct in6_addr l;
				struct rtattr rta_a;
				struct in6_addr a;
			} a6;
		} set;
	} req = {
		.ifa.ifa_family    = af,
		.ifa.ifa_index     = ifi,
		.ifa.ifa_prefixlen = prefix_len,
		.ifa.ifa_scope	   = RT_SCOPE_UNIVERSE,
	};
	ssize_t len;

	if (af == AF_INET6) {
		size_t rta_len = RTA_LENGTH(sizeof(req.set.a6.l));

		/* By default, strictly speaking, it's duplicated */
		req.ifa.ifa_flags = IFA_F_NODAD;

		len = offsetof(struct req_t, set.a6) + sizeof(req.set.a6);

		memcpy(&req.set.a6.l, addr, sizeof(req.set.a6.l));
		req.set.a6.rta_l.rta_len = rta_len;
		req.set.a4.rta_l.rta_type = IFA_LOCAL;
		memcpy(&req.set.a6.a, addr, sizeof(req.set.a6.a));
		req.set.a6.rta_a.rta_len = rta_len;
		req.set.a6.rta_a.rta_type = IFA_ADDRESS;
	} else {
		size_t rta_len = RTA_LENGTH(sizeof(req.set.a4.l));

		len = offsetof(struct req_t, set.a4) + sizeof(req.set.a4);

		memcpy(&req.set.a4.l, addr, sizeof(req.set.a4.l));
		req.set.a4.rta_l.rta_len = rta_len;
		req.set.a4.rta_l.rta_type = IFA_LOCAL;
		memcpy(&req.set.a4.a, addr, sizeof(req.set.a4.a));
		req.set.a4.rta_a.rta_len = rta_len;
		req.set.a4.rta_a.rta_type = IFA_ADDRESS;
	}

	return nl_do(s, &req, RTM_NEWADDR, NLM_F_CREATE | NLM_F_EXCL, len);
}

/**
 * nl_addr_dup() - Copy IP addresses for given interface and address family
 * @s_src:	Netlink socket in source network namespace
 * @ifi_src:	Interface index in source network namespace
 * @s_dst:	Netlink socket in destination network namespace
 * @ifi_dst:	Interface index in destination namespace
 * @af:		Address family
 *
 * Return: 0 on success, negative error code on failure
 */
int nl_addr_dup(int s_src, unsigned int ifi_src,
		int s_dst, unsigned int ifi_dst, sa_family_t af)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct ifaddrmsg ifa;
	} req = {
		.ifa.ifa_family    = af,
		.ifa.ifa_index     = ifi_src,
		.ifa.ifa_prefixlen = 0,
	};
	char buf[NLBUFSIZ];
	struct nlmsghdr *nh;
	ssize_t status;
	uint32_t seq;
	int rc = 0;

	seq = nl_send(s_src, &req, RTM_GETADDR, NLM_F_DUMP, sizeof(req));
	nl_foreach_oftype(nh, status, s_src, buf, seq, RTM_NEWADDR) {
		struct ifaddrmsg *ifa;
		struct rtattr *rta;
		size_t na;

		ifa = (struct ifaddrmsg *)NLMSG_DATA(nh);

		if (rc < 0 || ifa->ifa_scope == RT_SCOPE_LINK ||
		    ifa->ifa_index != ifi_src)
			continue;

		ifa->ifa_index = ifi_dst;

		for (rta = IFA_RTA(ifa), na = IFA_PAYLOAD(nh); RTA_OK(rta, na);
		     rta = RTA_NEXT(rta, na)) {
			/* Strip label and expiry (cacheinfo) information */
			if (rta->rta_type == IFA_LABEL ||
			    rta->rta_type == IFA_CACHEINFO)
				rta->rta_type = IFA_UNSPEC;
		}

		rc = nl_do(s_dst, nh, RTM_NEWADDR,
			   (nh->nlmsg_flags & ~NLM_F_DUMP_FILTERED) | NLM_F_CREATE,
			   nh->nlmsg_len);
	}
	if (status < 0)
		return status;

	return rc;
}

/**
 * nl_link_get_mac() - Get link MAC address
 * @s:		Netlink socket
 * @ifi:	Interface index
 * @mac:	Fill with current MAC address
 *
 * Return: 0 on success, negative error code on failure
 */
int nl_link_get_mac(int s, unsigned int ifi, void *mac)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct ifinfomsg ifm;
	} req = {
		.ifm.ifi_family	  = AF_UNSPEC,
		.ifm.ifi_index	  = ifi,
	};
	struct nlmsghdr *nh;
	char buf[NLBUFSIZ];
	ssize_t status;
	uint32_t seq;

	seq = nl_send(s, &req, RTM_GETLINK, 0, sizeof(req));
	nl_foreach_oftype(nh, status, s, buf, seq, RTM_NEWLINK) {
		struct ifinfomsg *ifm = (struct ifinfomsg *)NLMSG_DATA(nh);
		struct rtattr *rta;
		size_t na;

		for (rta = IFLA_RTA(ifm), na = RTM_PAYLOAD(nh);
		     RTA_OK(rta, na);
		     rta = RTA_NEXT(rta, na)) {
			if (rta->rta_type != IFLA_ADDRESS)
				continue;

			memcpy(mac, RTA_DATA(rta), ETH_ALEN);
		}
	}
	return status;
}

/**
 * nl_link_set_mac() - Set link MAC address
 * @s:		Netlink socket
 * @ns:		Use netlink socket in namespace
 * @ifi:	Interface index
 * @mac:	MAC address to set
 *
 * Return: 0 on success, negative error code on failure
 */
int nl_link_set_mac(int s, unsigned int ifi, const void *mac)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct ifinfomsg ifm;
		struct rtattr rta;
		unsigned char mac[ETH_ALEN];
	} req = {
		.ifm.ifi_family	  = AF_UNSPEC,
		.ifm.ifi_index	  = ifi,
		.rta.rta_type	  = IFLA_ADDRESS,
		.rta.rta_len	  = RTA_LENGTH(ETH_ALEN),
	};

	memcpy(req.mac, mac, ETH_ALEN);

	return nl_do(s, &req, RTM_NEWLINK, 0, sizeof(req));
}

/**
 * nl_link_up() - Bring link up
 * @s:		Netlink socket
 * @ifi:	Interface index
 * @mtu:	If non-zero, set interface MTU
 *
 * Return: 0 on success, negative error code on failure
 */
int nl_link_up(int s, unsigned int ifi, int mtu)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct ifinfomsg ifm;
		struct rtattr rta;
		unsigned int mtu;
	} req = {
		.ifm.ifi_family	  = AF_UNSPEC,
		.ifm.ifi_index	  = ifi,
		.ifm.ifi_flags	  = IFF_UP,
		.ifm.ifi_change	  = IFF_UP,
		.rta.rta_type	  = IFLA_MTU,
		.rta.rta_len	  = RTA_LENGTH(sizeof(unsigned int)),
		.mtu		  = mtu,
	};
	ssize_t len = sizeof(req);

	if (!mtu)
		/* Shorten request to drop MTU attribute */
		len = offsetof(struct req_t, rta);

	return nl_do(s, &req, RTM_NEWLINK, 0, len);
}