aboutgitcodebugslistschat
path: root/passt.c
blob: 978622113b6d8d8142e24f971c3167e117074d5c (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
// SPDX-License-Identifier: AGPL-3.0-or-later

/* PASST - Plug A Simple Socket Transport
 *
 * passt.c - Daemon implementation
 *
 * Copyright (c) 2020-2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 *
 * Grab Ethernet frames via AF_UNIX socket, build SOCK_DGRAM/SOCK_STREAM sockets
 * for each 5-tuple from TCP, UDP packets, perform connection tracking and
 * forward them. Forward packets received on sockets back to the UNIX domain
 * socket (typically, a socket virtio_net file descriptor from qemu).
 */

#include <stdio.h>
#include <sys/epoll.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <sys/ioctl.h>
#include <sys/un.h>
#include <ifaddrs.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmpv6.h>
#include <linux/if_link.h>
#include <net/ethernet.h>
#include <stdlib.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <net/if.h>
#include <netdb.h>
#include <string.h>
#include <errno.h>
#include <linux/ip.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <time.h>
#include <syslog.h>

#include "passt.h"
#include "arp.h"
#include "dhcp.h"
#include "ndp.h"
#include "util.h"
#include "icmp.h"
#include "tcp.h"
#include "udp.h"

#define EPOLL_EVENTS		10

#define TIMER_INTERVAL		20 /* ms, for protocol periodic handlers */

/**
 * sock_unix() - Create and bind AF_UNIX socket, add to epoll list
 *
 * Return: newly created socket, doesn't return on error
 */
static int sock_unix(void)
{
	int fd = socket(AF_UNIX, SOCK_STREAM, 0);
	struct sockaddr_un addr = {
		.sun_family = AF_UNIX,
		.sun_path = UNIX_SOCK_PATH,
	};

	if (fd < 0) {
		perror("UNIX socket");
		exit(EXIT_FAILURE);
	}

	unlink(UNIX_SOCK_PATH);
	if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) < 0) {
		perror("UNIX socket bind");
		exit(EXIT_FAILURE);
	}
	return fd;
}

/**
 * struct nl_request - Netlink request filled and sent by get_routes()
 * @nlh:	Netlink message header
 * @rtm:	Routing Netlink message
 */
struct nl_request {
	struct nlmsghdr nlh;
	struct rtmsg rtm;
};

/**
 * get_routes() - Get default route and fill in routable interface name
 * @c:		Execution context
 */
static void get_routes(struct ctx *c)
{
	struct nl_request req = {
		.nlh.nlmsg_type = RTM_GETROUTE,
		.nlh.nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP | NLM_F_EXCL,
		.nlh.nlmsg_len = sizeof(struct nl_request),
		.nlh.nlmsg_seq = 1,
		.rtm.rtm_family = AF_INET,
		.rtm.rtm_table = RT_TABLE_MAIN,
		.rtm.rtm_scope = RT_SCOPE_UNIVERSE,
		.rtm.rtm_type = RTN_UNICAST,
	};
	struct sockaddr_nl addr = {
		.nl_family = AF_NETLINK,
	};
	struct nlmsghdr *nlh;
	struct rtattr *rta;
	struct rtmsg *rtm;
	char buf[BUFSIZ];
	int s, n, na;

	c->v6 = -1;

	s = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
	if (s < 0) {
		perror("netlink socket");
		goto out;
	}

	if (bind(s, (struct sockaddr *)&addr, sizeof(addr)) < 0) {
		perror("netlink bind");
		goto out;
	}

v6:
	if (send(s, &req, sizeof(req), 0) < 0) {
		perror("netlink send");
		goto out;
	}

	n = recv(s, &buf, sizeof(buf), 0);
	if (n < 0) {
		perror("netlink recv");
		goto out;
	}

	nlh = (struct nlmsghdr *)buf;
	for ( ; NLMSG_OK(nlh, n); nlh = NLMSG_NEXT(nlh, n)) {
		rtm = (struct rtmsg *)NLMSG_DATA(nlh);

		if (rtm->rtm_dst_len ||
		    (rtm->rtm_family != AF_INET && rtm->rtm_family != AF_INET6))
			continue;

		rta = (struct rtattr *)RTM_RTA(rtm);
		na = RTM_PAYLOAD(nlh);
		for ( ; RTA_OK(rta, na); rta = RTA_NEXT(rta, na)) {
			if (rta->rta_type == RTA_GATEWAY &&
			    rtm->rtm_family == AF_INET && !c->v4) {
				memcpy(&c->gw4, RTA_DATA(rta), sizeof(c->gw4));
				c->v4 = 1;
			}

			if (rta->rta_type == RTA_GATEWAY &&
			    rtm->rtm_family == AF_INET6 && !c->v6) {
				memcpy(&c->gw6, RTA_DATA(rta), sizeof(c->gw6));
				c->v6 = 1;
			}

			if (rta->rta_type == RTA_OIF && !*c->ifn) {
				if_indextoname(*(unsigned *)RTA_DATA(rta),
					       c->ifn);
			}
		}

		if (nlh->nlmsg_type == NLMSG_DONE)
			break;
	}

	if (c->v6 == -1) {
		c->v6 = 0;
		req.rtm.rtm_family = AF_INET6;
		req.nlh.nlmsg_seq++;
		recv(s, &buf, sizeof(buf), 0);
		goto v6;
	}

out:
	close(s);

	if (!(c->v4 || c->v6) || !*c->ifn) {
		err("No routing information");
		exit(EXIT_FAILURE);
	}
}

/**
 * get_addrs() - Fetch MAC, IP addresses, masks of external routable interface
 * @c:		Execution context
 */
static void get_addrs(struct ctx *c)
{
	struct ifreq ifr = {
		.ifr_addr.sa_family = AF_INET,
	};
	struct ifaddrs *ifaddr, *ifa;
	int s, v4 = 0, v6 = 0;

	if (getifaddrs(&ifaddr) == -1) {
		perror("getifaddrs");
		goto out;
	}

	for (ifa = ifaddr; ifa; ifa = ifa->ifa_next) {
		struct sockaddr_in *in_addr;
		struct sockaddr_in6 *in6_addr;

		if (strcmp(ifa->ifa_name, c->ifn))
			continue;

		if (!ifa->ifa_addr)
			continue;

		if (ifa->ifa_addr->sa_family == AF_INET && !v4) {
			in_addr = (struct sockaddr_in *)ifa->ifa_addr;
			c->addr4 = in_addr->sin_addr.s_addr;
			in_addr = (struct sockaddr_in *)ifa->ifa_netmask;
			c->mask4 = in_addr->sin_addr.s_addr;
			v4 = 1;
		} else if (ifa->ifa_addr->sa_family == AF_INET6 && !v6) {
			in6_addr = (struct sockaddr_in6 *)ifa->ifa_addr;
			memcpy(&c->addr6, &in6_addr->sin6_addr,
			       sizeof(c->addr6));
			v6 = 1;
		}

		if (v4 == c->v4 && v6 == c->v6)
			break;
	}

	freeifaddrs(ifaddr);

	if (v4 != c->v4 || v6 != c->v6)
		goto out;

	s = socket(AF_INET, SOCK_DGRAM, 0);
	if (s < 0) {
		perror("socket SIOCGIFHWADDR");
		goto out;
	}

	strncpy(ifr.ifr_name, c->ifn, IF_NAMESIZE);
	if (ioctl(s, SIOCGIFHWADDR, &ifr) < 0) {
		perror("SIOCGIFHWADDR");
		goto out;
	}

	close(s);
	memcpy(c->mac, ifr.ifr_hwaddr.sa_data, ETH_ALEN);

	return;
out:
	err("Couldn't get addresses for routable interface");
	exit(EXIT_FAILURE);
}

/**
 * get_dns() - Get nameserver addresses from local /etc/resolv.conf
 * @c:		Execution context
 */
static void get_dns(struct ctx *c)
{
	char buf[BUFSIZ], *p, *end;
	int dns4 = 0, dns6 = 0;
	FILE *r;

	r = fopen("/etc/resolv.conf", "r");
	while (fgets(buf, BUFSIZ, r) && !(dns4 && dns6)) {
		if (!strstr(buf, "nameserver "))
			continue;
		p = strrchr(buf, ' ');
		end = strpbrk(buf, "%\n");
		if (end)
			*end = 0;
		if (p && inet_pton(AF_INET, p + 1, &c->dns4))
			dns4 = 1;
		if (p && inet_pton(AF_INET6, p + 1, &c->dns6))
			dns6 = 1;
	}

	fclose(r);
	if (dns4 || dns6)
		return;

	err("Couldn't get any nameserver address");
	exit(EXIT_FAILURE);
}

/**
 * tap4_handler() - IPv4 and ARP packet handler for tap file descriptor
 * @c:		Execution context
 * @len:	Total L2 packet length
 * @in:		Packet buffer, L2 headers
 */
static void tap4_handler(struct ctx *c, char *in, size_t len)
{
	struct ethhdr *eh = (struct ethhdr *)in;
	struct iphdr *iph = (struct iphdr *)(eh + 1);
	char buf_s[BUFSIZ] __attribute((__unused__));
	char buf_d[BUFSIZ] __attribute((__unused__));
	char *l4h;

	if (arp(c, eh, len) || dhcp(c, eh, len))
		return;

	if (len < sizeof(*eh) + sizeof(*iph))
		return;

	l4h = (char *)iph + iph->ihl * 4;
	len -= (intptr_t)l4h - (intptr_t)eh;

	if (iph->protocol == IPPROTO_ICMP) {
		debug("icmp from tap: %s -> %s",
		      inet_ntop(AF_INET, &iph->saddr, buf_s, sizeof(buf_s)),
		      inet_ntop(AF_INET, &iph->daddr, buf_d, sizeof(buf_d)));
	} else {
		struct tcphdr *th = (struct tcphdr *)l4h;

		if (len < sizeof(*th) && len < sizeof(struct udphdr))
			return;

		debug("%s from tap: %s:%i -> %s:%i",
		      getprotobynumber(iph->protocol)->p_name,
		      inet_ntop(AF_INET, &iph->saddr, buf_s, sizeof(buf_s)),
		      ntohs(th->source),
		      inet_ntop(AF_INET, &iph->daddr, buf_d, sizeof(buf_d)),
		      ntohs(th->dest));
	}

	if (iph->protocol == IPPROTO_TCP)
		tcp_tap_handler(c, AF_INET, &iph->daddr, l4h, len);
	else if (iph->protocol == IPPROTO_UDP)
		udp_tap_handler(c, AF_INET, &iph->daddr, l4h, len);
	else if (iph->protocol == IPPROTO_ICMP)
		icmp_tap_handler(c, AF_INET, &iph->daddr, l4h, len);
}

/**
 * tap6_handler() - IPv6 packet handler for tap file descriptor
 * @c:		Execution context
 * @len:	Total L2 packet length
 * @in:		Packet buffer, L2 headers
 */
static void tap6_handler(struct ctx *c, char *in, size_t len)
{
	struct ethhdr *eh = (struct ethhdr *)in;
	struct ipv6hdr *ip6h = (struct ipv6hdr *)(eh + 1);
	char buf_s[BUFSIZ] __attribute((__unused__));
	char buf_d[BUFSIZ] __attribute((__unused__));
	uint8_t proto;
	char *l4h;

	if (len < sizeof(*eh) + sizeof(*ip6h))
		return;

	if (ndp(c, eh, len))
		return;

	l4h = ipv6_l4hdr(ip6h, &proto);

	/* TODO: Assign MAC address to guest so that, together with prefix
	 * assigned via NDP, address matches the one from the host.
	 */
	c->addr6_guest = ip6h->saddr;
	ip6h->saddr = c->addr6;

	len -= (intptr_t)l4h - (intptr_t)eh;

	if (proto == IPPROTO_ICMPV6) {
		debug("icmpv6 from tap: %s ->\n\t%s",
		      inet_ntop(AF_INET6, &ip6h->saddr, buf_s, sizeof(buf_s)),
		      inet_ntop(AF_INET6, &ip6h->daddr, buf_d, sizeof(buf_d)));
	} else {
		struct tcphdr *th = (struct tcphdr *)l4h;

		if (len < sizeof(*th) && len < sizeof(struct udphdr))
			return;

		debug("%s from tap: [%s]:%i\n\t-> [%s]:%i",
		      getprotobynumber(proto)->p_name,
		      inet_ntop(AF_INET6, &ip6h->saddr, buf_s, sizeof(buf_s)),
		      ntohs(th->source),
		      inet_ntop(AF_INET6, &ip6h->daddr, buf_d, sizeof(buf_d)),
		      ntohs(th->dest));
	}

	if (proto == IPPROTO_TCP)
		tcp_tap_handler(c, AF_INET6, &ip6h->daddr, l4h, len);
	else if (proto == IPPROTO_UDP)
		udp_tap_handler(c, AF_INET6, &ip6h->daddr, l4h, len);
	else if (proto == IPPROTO_ICMPV6)
		icmp_tap_handler(c, AF_INET6, &ip6h->daddr, l4h, len);
}

/**
 * tap_handler() - Packet handler for tap file descriptor
 * @c:		Execution context
 *
 * Return: -ECONNRESET if tap connection was lost, 0 otherwise
 */
static int tap_handler(struct ctx *c)
{
	char buf[ETH_MAX_MTU];
	struct ethhdr *eh;
	uint32_t vnet_len;
	ssize_t n;

	eh = (struct ethhdr *)buf;

	while ((n = recv(c->fd_unix, &vnet_len, 4, MSG_DONTWAIT)) == 4) {
		n = recv(c->fd_unix, buf, ntohl(vnet_len), MSG_DONTWAIT);

		if (n < (ssize_t)sizeof(*eh))
			break;

		switch (ntohs(eh->h_proto)) {
		case ETH_P_IP:
		case ETH_P_ARP:
			tap4_handler(c, buf, n);
			break;
		case ETH_P_IPV6:
			tap6_handler(c, buf, n);
			break;
		default:
			break;
		}
	}

	if (n >= 0 || errno == EINTR || errno == EAGAIN || errno == EWOULDBLOCK)
		return 0;

	epoll_ctl(c->epollfd, EPOLL_CTL_DEL, c->fd_unix, NULL);
	close(c->fd_unix);

	return -ECONNRESET;
}

/**
 * sock_handler() - Event handler for L4 sockets
 * @c:		Execution context
 * @fd:		File descriptor associated to event
 * @events	epoll events
 */
static void sock_handler(struct ctx *c, int fd, uint32_t events)
{
	socklen_t sl;
	int so;

	sl = sizeof(so);

	if (getsockopt(fd, SOL_SOCKET, SO_PROTOCOL, &so, &sl))
		return;

	debug("%s: packet from socket %i", getprotobynumber(so)->p_name, fd);

	if (so == IPPROTO_ICMP || so == IPPROTO_ICMPV6)
		icmp_sock_handler(c, fd, events);
	else if (so == IPPROTO_TCP)
		tcp_sock_handler(c, fd, events);
	else if (so == IPPROTO_UDP)
		udp_sock_handler(c, fd, events);
}

/**
 * timer_handler() - Run periodic tasks for L4 protocol handlers
 * @c:		Execution context
 * @last:	Timestamp of last run, updated on return
 */
static void timer_handler(struct ctx *c, struct timespec *last)
{
	struct timespec tmp;

	clock_gettime(CLOCK_MONOTONIC, &tmp);
	if (timespec_diff_ms(&tmp, last) < TIMER_INTERVAL)
		return;

	tcp_timer(c, &tmp);

	*last = tmp;
}

/**
 * usage() - Print usage and exit
 * @name:	Executable name
 */
void usage(const char *name)
{
	fprintf(stderr, "Usage: %s\n", name);

	exit(EXIT_FAILURE);
}

/**
 * main() - Entry point and main loop
 * @argc:	Argument count
 * @argv:	Interface names
 *
 * Return: 0 once interrupted, non-zero on failure
 */
int main(int argc, char **argv)
{
	struct epoll_event events[EPOLL_EVENTS];
	char buf6[3][INET6_ADDRSTRLEN];
	char buf4[4][INET_ADDRSTRLEN];
	struct epoll_event ev = { 0 };
	struct timespec last_time;
	struct ctx c = { 0 };
	int nfds, i, fd_unix;

	if (argc != 1)
		usage(argv[0]);

	if (clock_gettime(CLOCK_MONOTONIC, &last_time)) {
		perror("clock_gettime");
		exit(EXIT_FAILURE);
	}

	c.epollfd = epoll_create1(0);
	if (c.epollfd == -1) {
		perror("epoll_create1");
		exit(EXIT_FAILURE);
	}

	if (icmp_sock_init(&c) || tcp_sock_init(&c) || udp_sock_init(&c))
		exit(EXIT_FAILURE);

	fd_unix = sock_unix();

	openlog("passt", 0, LOG_DAEMON);
	if (daemon(0, 0)) {
		fprintf(stderr, "Failed to fork into background\n");
		exit(EXIT_FAILURE);
	}

	get_routes(&c);
	get_addrs(&c);
	get_dns(&c);

	if (c.v4) {
		info("ARP:");
		info("    address: %02x:%02x:%02x:%02x:%02x:%02x from %s",
		     c.mac[0], c.mac[1], c.mac[2], c.mac[3], c.mac[4], c.mac[5],
		     c.ifn);
		info("DHCP:");
		info("    assign: %s",
		     inet_ntop(AF_INET, &c.addr4, buf4[0], sizeof(buf4[0])));
		info("    mask: %s",
		     inet_ntop(AF_INET, &c.mask4, buf4[0], sizeof(buf4[0])));
		info("    router: %s",
		     inet_ntop(AF_INET, &c.gw4,   buf4[2], sizeof(buf4[2])));
		info("    DNS: %s",
		     inet_ntop(AF_INET, &c.dns4,  buf4[3], sizeof(buf4[3])));
	}
	if (c.v6) {
		info("NDP:");
		info("    assign: %s",
		     inet_ntop(AF_INET6, &c.addr6, buf6[0], sizeof(buf6[0])));
		info("    router: %s",
		     inet_ntop(AF_INET6, &c.gw6,   buf6[1], sizeof(buf6[1])));
		info("    DNS: %s",
		     inet_ntop(AF_INET6, &c.dns6,  buf6[2], sizeof(buf6[2])));
	}

listen:
	listen(fd_unix, 1);
	info("You can now start qrap:");
	info("    ./qrap 5 kvm ... -net socket,fd=5 -net nic,model=virtio");
	info("or directly qemu, patched with:");
	info("    qemu/0001-net-Allow-also-UNIX-domain-sockets-to-be-used-as-net.patch");
	info("as follows:");
	info("kvm ... -net socket,connect="
	     UNIX_SOCK_PATH " -net nic,model=virtio");

	c.fd_unix = accept(fd_unix, NULL, NULL);
	ev.events = EPOLLIN | EPOLLET | EPOLLRDHUP | EPOLLERR | EPOLLHUP;
	ev.data.fd = c.fd_unix;
	epoll_ctl(c.epollfd, EPOLL_CTL_ADD, c.fd_unix, &ev);

	clock_gettime(CLOCK_MONOTONIC, &last_time);

loop:
	nfds = epoll_wait(c.epollfd, events, EPOLL_EVENTS, TIMER_INTERVAL);
	if (nfds == -1 && errno != EINTR) {
		perror("epoll_wait");
		exit(EXIT_FAILURE);
	}

	for (i = 0; i < nfds; i++) {
		if (events[i].data.fd == c.fd_unix) {
			if (tap_handler(&c))
				goto listen;
		} else {
			sock_handler(&c, events[i].data.fd, events[i].events);
		}
	}

	timer_handler(&c, &last_time);

	goto loop;

	return 0;
}