aboutgitcodebugslistschat
path: root/netlink.c
blob: a41dc63276f4e08e8542a8efa63ea61752fcc6b6 (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
// 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"

#define NLBUFSIZ	(8192 * sizeof(struct nlmsghdr)) /* See netlink(7) */

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

/**
 * 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_req() - Send netlink request and read response
 * @ns:		Use netlink socket in namespace
 * @buf:	Buffer for response (at least NLBUFSIZ long)
 * @req:	Request with netlink header
 * @len:	Request length
 *
 * Return: received length on success, negative error code on failure
 */
static int nl_req(int ns, char *buf, const void *req, ssize_t len)
{
	int s = ns ? nl_sock_ns : nl_sock, done = 0;
	char flush[NLBUFSIZ];
	ssize_t n;

	while (!done && (n = recv(s, flush, sizeof(flush), MSG_DONTWAIT)) > 0) {
		struct nlmsghdr *nh = (struct nlmsghdr *)flush;
		size_t nm = n;

		for ( ; NLMSG_OK(nh, nm); nh = NLMSG_NEXT(nh, nm)) {
			if (nh->nlmsg_type == NLMSG_DONE ||
			    nh->nlmsg_type == NLMSG_ERROR) {
				done = 1;
				break;
			}
		}
	}

	if ((send(s, req, len, 0) < len) ||
	    (len = recv(s, buf, NLBUFSIZ, 0)) < 0)
		return -errno;

	return len;
}

/**
 * nl_get_ext_if() - Get interface index supporting IP version being probed
 * @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(sa_family_t af)
{
	struct { struct nlmsghdr nlh; struct rtmsg rtm; } req = {
		.nlh.nlmsg_type	 = RTM_GETROUTE,
		.nlh.nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP,
		.nlh.nlmsg_len	 = NLMSG_LENGTH(sizeof(struct rtmsg)),
		.nlh.nlmsg_seq	 = nl_seq++,

		.rtm.rtm_table	 = RT_TABLE_MAIN,
		.rtm.rtm_scope	 = RT_SCOPE_UNIVERSE,
		.rtm.rtm_type	 = RTN_UNICAST,
		.rtm.rtm_family	 = af,
	};
	struct nlmsghdr *nh;
	struct rtattr *rta;
	char buf[NLBUFSIZ];
	ssize_t n;
	size_t na;

	if ((n = nl_req(0, buf, &req, sizeof(req))) < 0)
		return 0;

	nh = (struct nlmsghdr *)buf;

	for ( ; NLMSG_OK(nh, n); nh = NLMSG_NEXT(nh, n)) {
		struct rtmsg *rtm = (struct rtmsg *)NLMSG_DATA(nh);

		if (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)) {
			unsigned int ifi;

			if (rta->rta_type != RTA_OIF)
				continue;

			ifi = *(unsigned int *)RTA_DATA(rta);

			return ifi;
		}
	}

	return 0;
}

/**
 * nl_route() - Get/set/copy routes for given interface and address family
 * @op:		Requested operation
 * @ifi:	Interface index in outer network namespace
 * @ifi_ns:	Interface index in target namespace for NL_SET, NL_DUP
 * @af:		Address family
 * @gw:		Default gateway to fill on NL_GET, to set on NL_SET
 */
void nl_route(enum nl_op op, unsigned int ifi, unsigned int ifi_ns,
	      sa_family_t af, 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;
				uint32_t d;
				struct rtattr rta_gw;
				uint32_t a;
			} r4;
		} set;
	} req = {
		.nlh.nlmsg_type	  = op == NL_SET ? RTM_NEWROUTE : RTM_GETROUTE,
		.nlh.nlmsg_flags  = NLM_F_REQUEST,
		.nlh.nlmsg_seq	  = nl_seq++,

		.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		  = op == NL_SET ? ifi_ns : ifi,
	};
	unsigned dup_routes = 0;
	ssize_t n, nlmsgs_size;
	struct nlmsghdr *nh;
	struct rtattr *rta;
	char buf[NLBUFSIZ];
	struct rtmsg *rtm;
	size_t na;

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

			req.nlh.nlmsg_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));

			req.nlh.nlmsg_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;

			req.set.r4.a = *(uint32_t *)gw;
			req.set.r4.rta_gw.rta_type = RTA_GATEWAY;
			req.set.r4.rta_gw.rta_len = rta_len;
		}

		req.rtm.rtm_protocol = RTPROT_BOOT;
		req.nlh.nlmsg_flags |= NLM_F_ACK | NLM_F_EXCL | NLM_F_CREATE;
	} else {
		req.nlh.nlmsg_len = offsetof(struct req_t, set.r6);
		req.nlh.nlmsg_flags |= NLM_F_DUMP;
	}

	if ((n = nl_req(op == NL_SET, buf, &req, req.nlh.nlmsg_len)) < 0)
		return;

	if (op == NL_SET)
		return;

	nh = (struct nlmsghdr *)buf;
	nlmsgs_size = n;

	for ( ; NLMSG_OK(nh, n); nh = NLMSG_NEXT(nh, n)) {
		if (nh->nlmsg_type != RTM_NEWROUTE)
			goto next;

		if (op == NL_DUP) {
			nh->nlmsg_seq = nl_seq++;
			nh->nlmsg_pid = 0;
			nh->nlmsg_flags &= ~NLM_F_DUMP_FILTERED;
			nh->nlmsg_flags |= NLM_F_REQUEST | NLM_F_ACK |
					   NLM_F_CREATE;
			dup_routes++;
		}

		rtm = (struct rtmsg *)NLMSG_DATA(nh);
		if (op == NL_GET && rtm->rtm_dst_len)
			continue;

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

				memcpy(gw, RTA_DATA(rta), RTA_PAYLOAD(rta));
				return;
			}

			if (op == NL_DUP && rta->rta_type == RTA_OIF)
				*(unsigned int *)RTA_DATA(rta) = ifi_ns;
		}

next:
		if (nh->nlmsg_type == NLMSG_DONE)
			break;
	}

	if (op == NL_DUP) {
		char resp[NLBUFSIZ];
		unsigned i;

		nh = (struct nlmsghdr *)buf;
		/* Routes might have dependencies between each other, and the
		 * kernel processes RTM_NEWROUTE messages sequentially. For n
		 * valid routes, we might need to send up to n requests to get
		 * all of them inserted. Routes that have been already inserted
		 * won't cause the whole request to fail, so we can simply
		 * repeat the whole request. This approach avoids the need to
		 * calculate dependencies: let the kernel do that.
		 */
		for (i = 0; i < dup_routes; i++)
			nl_req(1, resp, nh, nlmsgs_size);
	}
}

/**
 * nl_addr() - Get/set/copy IP addresses for given interface and address family
 * @op:		Requested operation
 * @ifi:	Interface index in outer network namespace
 * @ifi_ns:	Interface index in target namespace for NL_SET, NL_DUP
 * @af:		Address family
 * @addr:	Global address to fill on NL_GET, to set on NL_SET
 * @prefix_len:	Mask or prefix length, set or fetched (for IPv4)
 * @addr_l:	Link-scoped address to fill on NL_GET
 */
void nl_addr(enum nl_op op, unsigned int ifi, unsigned int ifi_ns,
	     sa_family_t af, void *addr, int *prefix_len, void *addr_l)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct ifaddrmsg ifa;
		union {
			struct {
				struct rtattr rta_l;
				uint32_t l;
				struct rtattr rta_a;
				uint32_t a;
			} a4;
			struct {
				struct rtattr rta_l;
				struct in6_addr l;
				struct rtattr rta_a;
				struct in6_addr a;
			} a6;
		} set;
	} req = {
		.nlh.nlmsg_type    = op == NL_SET ? RTM_NEWADDR : RTM_GETADDR,
		.nlh.nlmsg_flags   = NLM_F_REQUEST,
		.nlh.nlmsg_len     = NLMSG_LENGTH(sizeof(struct ifaddrmsg)),
		.nlh.nlmsg_seq     = nl_seq++,

		.ifa.ifa_family    = af,
		.ifa.ifa_index     = op == NL_SET ? ifi_ns : ifi,
		.ifa.ifa_prefixlen = op == NL_SET ? *prefix_len : 0,
	};
	ssize_t n, nlmsgs_size;
	struct ifaddrmsg *ifa;
	struct nlmsghdr *nh;
	struct rtattr *rta;
	char buf[NLBUFSIZ];
	size_t na;

	if (op == NL_SET) {
		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;

			req.nlh.nlmsg_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));

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

			req.set.a4.l = req.set.a4.a = *(uint32_t *)addr;
			req.set.a4.rta_l.rta_len = rta_len;
			req.set.a4.rta_l.rta_type = IFA_LOCAL;
			req.set.a4.rta_a.rta_len = rta_len;
			req.set.a4.rta_a.rta_type = IFA_ADDRESS;
		}

		req.ifa.ifa_scope = RT_SCOPE_UNIVERSE;
		req.nlh.nlmsg_flags |= NLM_F_CREATE | NLM_F_ACK | NLM_F_EXCL;
	} else {
		req.nlh.nlmsg_flags |= NLM_F_DUMP;
	}

	if ((n = nl_req(op == NL_SET, buf, &req, req.nlh.nlmsg_len)) < 0)
		return;

	if (op == NL_SET)
		return;

	nh = (struct nlmsghdr *)buf;
	nlmsgs_size = n;

	for ( ; NLMSG_OK(nh, n); nh = NLMSG_NEXT(nh, n)) {
		if (nh->nlmsg_type != RTM_NEWADDR)
			goto next;

		if (op == NL_DUP) {
			nh->nlmsg_seq = nl_seq++;
			nh->nlmsg_pid = 0;
			nh->nlmsg_flags &= ~NLM_F_DUMP_FILTERED;
			nh->nlmsg_flags |= NLM_F_REQUEST | NLM_F_ACK |
					   NLM_F_CREATE;
		}

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

		if (op == NL_DUP && (ifa->ifa_scope == RT_SCOPE_LINK ||
				     ifa->ifa_index != ifi)) {
			ifa->ifa_family = AF_UNSPEC;
			goto next;
		}

		if (ifa->ifa_index != ifi)
			goto next;

		if (op == NL_DUP)
			ifa->ifa_index = ifi_ns;

		for (rta = IFA_RTA(ifa), na = RTM_PAYLOAD(nh); RTA_OK(rta, na);
		     rta = RTA_NEXT(rta, na)) {
			if (op == NL_DUP && rta->rta_type == IFA_LABEL)
				rta->rta_type = IFA_UNSPEC;

			if (op == NL_DUP || rta->rta_type != IFA_ADDRESS)
				continue;

			if (af == AF_INET && addr && !*(uint32_t *)addr) {
				memcpy(addr, RTA_DATA(rta), RTA_PAYLOAD(rta));
				*prefix_len = ifa->ifa_prefixlen;
			} else if (af == AF_INET6 && addr &&
				 ifa->ifa_scope == RT_SCOPE_UNIVERSE &&
				 IN6_IS_ADDR_UNSPECIFIED(addr)) {
				memcpy(addr, RTA_DATA(rta), RTA_PAYLOAD(rta));
			}

			if (addr_l &&
			    af == AF_INET6 && ifa->ifa_scope == RT_SCOPE_LINK &&
			    IN6_IS_ADDR_UNSPECIFIED(addr_l))
				memcpy(addr_l, RTA_DATA(rta), RTA_PAYLOAD(rta));
		}
next:
		if (nh->nlmsg_type == NLMSG_DONE)
			break;
	}

	if (op == NL_DUP) {
		char resp[NLBUFSIZ];

		nh = (struct nlmsghdr *)buf;
		nl_req(1, resp, nh, nlmsgs_size);
	}
}

/**
 * nl_link_get_mac() - Get link MAC address
 * @ns:		Use netlink socket in namespace
 * @ifi:	Interface index
 * @mac:	Fill with current MAC address
 */
void nl_link_get_mac(int ns, unsigned int ifi, void *mac)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct ifinfomsg ifm;
	} req = {
		.nlh.nlmsg_type	  = RTM_GETLINK,
		.nlh.nlmsg_len	  = sizeof(req),
		.nlh.nlmsg_flags  = NLM_F_REQUEST | NLM_F_ACK,
		.nlh.nlmsg_seq	  = nl_seq++,
		.ifm.ifi_family	  = AF_UNSPEC,
		.ifm.ifi_index	  = ifi,
	};
	struct nlmsghdr *nh;
	char buf[NLBUFSIZ];
	ssize_t n;

	n = nl_req(ns, buf, &req, sizeof(req));
	if (n < 0)
		return;

	for (nh = (struct nlmsghdr *)buf;
	     NLMSG_OK(nh, n) && nh->nlmsg_type != NLMSG_DONE;
	     nh = NLMSG_NEXT(nh, n)) {
		struct ifinfomsg *ifm = (struct ifinfomsg *)NLMSG_DATA(nh);
		struct rtattr *rta;
		size_t na;

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

		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);
			break;
		}
	}
}

/**
 * nl_link_set_mac() - Set link MAC address
 * @ns:		Use netlink socket in namespace
 * @ifi:	Interface index
 * @mac:	MAC address to set
 */
void nl_link_set_mac(int ns, unsigned int ifi, void *mac)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct ifinfomsg ifm;
		struct rtattr rta;
		unsigned char mac[ETH_ALEN];
	} req = {
		.nlh.nlmsg_type	  = RTM_NEWLINK,
		.nlh.nlmsg_len	  = sizeof(req),
		.nlh.nlmsg_flags  = NLM_F_REQUEST | NLM_F_ACK,
		.nlh.nlmsg_seq	  = nl_seq++,
		.ifm.ifi_family	  = AF_UNSPEC,
		.ifm.ifi_index	  = ifi,
		.rta.rta_type	  = IFLA_ADDRESS,
		.rta.rta_len	  = RTA_LENGTH(ETH_ALEN),
	};
	char buf[NLBUFSIZ];

	memcpy(req.mac, mac, ETH_ALEN);

	nl_req(ns, buf, &req, sizeof(req));
}

/**
 * nl_link_up() - Bring link up
 * @ns:		Use netlink socket in namespace
 * @ifi:	Interface index
 * @mtu:	If non-zero, set interface MTU
 */
void nl_link_up(int ns, unsigned int ifi, int mtu)
{
	struct req_t {
		struct nlmsghdr nlh;
		struct ifinfomsg ifm;
		struct rtattr rta;
		unsigned int mtu;
	} req = {
		.nlh.nlmsg_type   = RTM_NEWLINK,
		.nlh.nlmsg_len    = sizeof(req),
		.nlh.nlmsg_flags  = NLM_F_REQUEST | NLM_F_ACK,
		.nlh.nlmsg_seq	  = nl_seq++,
		.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,
	};
	char buf[NLBUFSIZ];

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

	nl_req(ns, buf, &req, req.nlh.nlmsg_len);
}