aboutgitcodebugslistschat
path: root/passt.c
blob: 2f538e4c02ef977cbbfa179ca0a93c0179a7cf7d (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
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
// 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/resource.h>
#include <sys/uio.h>
#include <ifaddrs.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <arpa/inet.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmpv6.h>
#include <linux/un.h>
#include <linux/if_link.h>
#include <net/ethernet.h>
#include <stdlib.h>
#include <unistd.h>
#include <net/if.h>
#include <netdb.h>
#include <string.h>
#include <errno.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <time.h>
#include <syslog.h>
#include <sys/stat.h>

#include "passt.h"
#include "arp.h"
#include "dhcp.h"
#include "ndp.h"
#include "dhcpv6.h"
#include "util.h"
#include "icmp.h"
#include "tcp.h"
#include "udp.h"
#include "pcap.h"

#define EPOLL_EVENTS		10

#define TAP_BUF_BYTES		(ETH_MAX_MTU * 8)
#define TAP_BUF_FILL		(TAP_BUF_BYTES - ETH_MAX_MTU - sizeof(uint32_t))
#define TAP_MSGS		(TAP_BUF_BYTES / sizeof(struct ethhdr) + 1)

#define PKT_BUF_BYTES		MAX(TAP_BUF_BYTES, SOCK_BUF_BYTES)
static char pkt_buf		[PKT_BUF_BYTES];

#define TIMER_INTERVAL		MIN(TCP_TIMER_INTERVAL, UDP_TIMER_INTERVAL)

#ifdef DEBUG
static char *ip_proto_str[IPPROTO_SCTP + 1] = {
	[IPPROTO_ICMP]		= "ICMP",
	[IPPROTO_TCP]		= "TCP",
	[IPPROTO_UDP]		= "UDP",
	[IPPROTO_ICMPV6]	= "ICMPV6",
	[IPPROTO_SCTP]		= "SCTP",
};

#define IP_PROTO_STR(n)							\
	(((n) <= IPPROTO_SCTP && ip_proto_str[(n)]) ? ip_proto_str[(n)] : "?")

#endif

/**
 * sock_unix() - Create and bind AF_UNIX socket, add to epoll list
 * @index:	Index used in socket path, filled on success
 *
 * Return: newly created socket, doesn't return on error
 */
static int sock_unix(int *index)
{
	int fd = socket(AF_UNIX, SOCK_STREAM, 0), ex;
	struct sockaddr_un addr = {
		.sun_family = AF_UNIX,
	};
	int i, ret;

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

	for (i = 1; i < UNIX_SOCK_MAX; i++) {
		snprintf(addr.sun_path, UNIX_PATH_MAX, UNIX_SOCK_PATH, i);

		ex = socket(AF_UNIX, SOCK_STREAM | SOCK_NONBLOCK, 0);
		ret = connect(ex, (const struct sockaddr *)&addr, sizeof(addr));
		if (!ret || errno != ECONNREFUSED) {
			close(ex);
			continue;
		}
		close(ex);

		unlink(addr.sun_path);
		if (!bind(fd, (const struct sockaddr *)&addr, sizeof(addr)))
			break;
	}

	if (i == UNIX_SOCK_MAX) {
		perror("UNIX socket bind");
		exit(EXIT_FAILURE);
	}

	info("UNIX domain socket bound at %s\n", addr.sun_path);
	chmod(addr.sun_path,
	      S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH);

	*index = i;

	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_seen = 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));
			memcpy(&c->addr6_seen, &in6_addr->sin6_addr,
			       sizeof(c->addr6_seen));
			memcpy(&c->addr6_ll_seen, &in6_addr->sin6_addr,
			       sizeof(c->addr6_seen));
			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)
{
	struct in6_addr *dns6 = &c->dns6[0];
	struct fqdn *s = c->dns_search;
	uint32_t *dns4 = &c->dns4[0];
	char buf[BUFSIZ], *p, *end;
	FILE *r;

	r = fopen("/etc/resolv.conf", "r");
	while (fgets(buf, BUFSIZ, r)) {
		if (strstr(buf, "nameserver ") == buf) {
			p = strrchr(buf, ' ');
			if (!p)
				continue;

			end = strpbrk(buf, "%\n");
			if (end)
				*end = 0;

			if (dns4 - &c->dns4[0] < ARRAY_SIZE(c->dns4) &&
			    inet_pton(AF_INET, p + 1, dns4))
				dns4++;

			if (dns6 - &c->dns6[0] < ARRAY_SIZE(c->dns6) &&
			    inet_pton(AF_INET6, p + 1, dns6))
				dns6++;
		} else if (strstr(buf, "search ") == buf &&
			   s == c->dns_search) {
			end = strpbrk(buf, "\n");
			if (end)
				*end = 0;

			p = strtok(buf, " \t");
			while ((p = strtok(NULL, " \t")) &&
			       s - c->dns_search < ARRAY_SIZE(c->dns_search)) {
				strncpy(s->n, p, sizeof(c->dns_search[0]));
				s++;
			}
		}
	}

	fclose(r);

	if (dns4 == c->dns4 && dns6 == c->dns6)
		warn("Couldn't get any nameserver address");
}

/**
 * tap4_handler() - IPv4 and ARP packet handler for tap file descriptor
 * @c:		Execution context
 * @msg:	Array of messages with the same L3 protocol
 * @count:	Count of messages with the same L3 protocol
 * @now:	Current timestamp
 *
 * Return: count of packets consumed by handlers
 */
static int tap4_handler(struct ctx *c, struct tap_msg *msg, size_t count,
			struct timespec *now)
{
	char buf_s[INET_ADDRSTRLEN] __attribute((__unused__));
	char buf_d[INET_ADDRSTRLEN] __attribute((__unused__));
	struct ethhdr *eh = (struct ethhdr *)msg[0].start;
	struct iphdr *iph, *prev_iph = NULL;
	struct udphdr *uh, *prev_uh = NULL;
	size_t len = msg[0].len;
	unsigned int i;
	char *l4h;

	if (!c->v4)
		return count;

	if (len < sizeof(*eh) + sizeof(*iph))
		return 1;

	if (arp(c, eh, len) || dhcp(c, eh, len))
		return 1;

	for (i = 0; i < count; i++) {
		len = msg[i].len;
		if (len < sizeof(*eh) + sizeof(*iph))
			return 1;

		eh = (struct ethhdr *)msg[i].start;
		iph = (struct iphdr *)(eh + 1);
		l4h = (char *)iph + iph->ihl * 4;

		c->addr4_seen = iph->saddr;

		msg[i].l4h = l4h;
		msg[i].l4_len = len - ((intptr_t)l4h - (intptr_t)eh);

		if (iph->protocol != IPPROTO_TCP &&
		    iph->protocol != IPPROTO_UDP)
			break;

		if (len < sizeof(*uh))
			break;

		uh = (struct udphdr *)l4h;

		if (!i) {
			prev_iph = iph;
			prev_uh = uh;
			continue;
		}

		if (iph->tos		!= prev_iph->tos	||
		    iph->frag_off	!= prev_iph->frag_off	||
		    iph->protocol	!= prev_iph->protocol	||
		    iph->saddr		!= prev_iph->saddr	||
		    iph->daddr		!= prev_iph->daddr	||
		    uh->source		!= prev_uh->source	||
		    uh->dest		!= prev_uh->dest)
			break;

		prev_iph = iph;
		prev_uh = uh;
	}

	eh = (struct ethhdr *)msg[0].start;
	iph = (struct iphdr *)(eh + 1);

	if (iph->protocol == IPPROTO_TCP || iph->protocol == IPPROTO_UDP ||
	    iph->protocol == IPPROTO_SCTP) {
		uh = (struct udphdr *)msg[0].l4h;

		if (msg[0].len < sizeof(*uh))
			return 1;

		debug("%s (%i) from tap: %s:%i -> %s:%i (%i packet%s)",
		      IP_PROTO_STR(iph->protocol), iph->protocol,
		      inet_ntop(AF_INET, &iph->saddr, buf_s, sizeof(buf_s)),
		      ntohs(uh->source),
		      inet_ntop(AF_INET, &iph->daddr, buf_d, sizeof(buf_d)),
		      ntohs(uh->dest),
		      i, i > 1 ? "s" : "");
	} else 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)));
	}

	if (iph->protocol == IPPROTO_TCP)
		return tcp_tap_handler(c, AF_INET, &iph->daddr, msg, i, now);

	if (iph->protocol == IPPROTO_UDP)
		return udp_tap_handler(c, AF_INET, &iph->daddr, msg, i, now);

	if (iph->protocol == IPPROTO_ICMP)
		icmp_tap_handler(c, AF_INET, &iph->daddr, msg, 1, now);

	return 1;
}

/**
 * tap6_handler() - IPv6 packet handler for tap file descriptor
 * @c:		Execution context
 * @msg:	Array of messages with the same L3 protocol
 * @count:	Count of messages with the same L3 protocol
 * @now:	Current timestamp
 */
static int tap6_handler(struct ctx *c, struct tap_msg *msg, size_t count,
			struct timespec *now)
{
	char buf_s[INET6_ADDRSTRLEN] __attribute((__unused__));
	char buf_d[INET6_ADDRSTRLEN] __attribute((__unused__));
	struct ethhdr *eh = (struct ethhdr *)msg[0].start;
	struct udphdr *uh, *prev_uh = NULL;
	uint8_t proto = 0, prev_proto = 0;
	size_t len = msg[0].len;
	struct ipv6hdr *ip6h;
	unsigned int i;
	char *l4h;

	if (!c->v6)
		return count;

	if (len < sizeof(*eh) + sizeof(*ip6h))
		return 1;

	if (ndp(c, eh, len) || dhcpv6(c, eh, len))
		return 1;

	for (i = 0; i < count; i++) {
		struct ipv6hdr *p_ip6h;

		len = msg[i].len;
		if (len < sizeof(*eh) + sizeof(*ip6h))
			return 1;

		eh = (struct ethhdr *)msg[i].start;
		ip6h = (struct ipv6hdr *)(eh + 1);
		l4h = ipv6_l4hdr(ip6h, &proto);

		msg[i].l4h = l4h;
		msg[i].l4_len = len - ((intptr_t)l4h - (intptr_t)eh);

		if (IN6_IS_ADDR_LINKLOCAL(&ip6h->saddr))
			c->addr6_ll_seen = ip6h->saddr;
		else
			c->addr6_seen = ip6h->saddr;

		ip6h->saddr = c->addr6;

		if (proto != IPPROTO_TCP && proto != IPPROTO_UDP)
			break;

		if (len < sizeof(*uh))
			break;

		uh = (struct udphdr *)l4h;

		if (!i) {
			p_ip6h = ip6h;
			prev_proto = proto;
			prev_uh = uh;
			continue;
		}

		if (proto		!= prev_proto		||
		    memcmp(&ip6h->saddr, &p_ip6h->saddr, sizeof(ip6h->saddr)) ||
		    memcmp(&ip6h->daddr, &p_ip6h->daddr, sizeof(ip6h->daddr)) ||
		    uh->source		!= prev_uh->source	||
		    uh->dest		!= prev_uh->dest)
			break;

		p_ip6h = ip6h;
		prev_proto = proto;
		prev_uh = uh;
	}

	if (prev_proto)
		proto = prev_proto;

	eh = (struct ethhdr *)msg[0].start;
	ip6h = (struct ipv6hdr *)(eh + 1);

	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 if (proto == IPPROTO_TCP || proto == IPPROTO_UDP ||
		   proto == IPPROTO_SCTP) {
		uh = (struct udphdr *)msg[0].l4h;

		if (msg[0].len < sizeof(*uh))
			return 1;

		debug("%s (%i) from tap: [%s]:%i\n\t-> [%s]:%i (%i packet%s)",
		      IP_PROTO_STR(proto), proto,
		      inet_ntop(AF_INET6, &ip6h->saddr, buf_s, sizeof(buf_s)),
		      ntohs(uh->source),
		      inet_ntop(AF_INET6, &ip6h->daddr, buf_d, sizeof(buf_d)),
		      ntohs(uh->dest),
		      i, i > 1 ? "s" : "");
	}

	if (proto == IPPROTO_TCP)
		return tcp_tap_handler(c, AF_INET6, &ip6h->daddr, msg, i, now);

	if (proto == IPPROTO_UDP)
		return udp_tap_handler(c, AF_INET6, &ip6h->daddr, msg, i, now);

	if (proto == IPPROTO_ICMPV6)
		icmp_tap_handler(c, AF_INET6, &ip6h->daddr, msg, 1, now);

	return 1;
}

/**
 * tap_handler() - Packet handler for tap file descriptor
 * @c:		Execution context
 * @now:	Current timestamp
 *
 * Return: -ECONNRESET if tap connection was lost, 0 otherwise
 */
static int tap_handler(struct ctx *c, struct timespec *now)
{
	struct tap_msg msg[TAP_MSGS];
	int msg_count, same, i;
	struct ethhdr *eh;
	char *p = pkt_buf;
	ssize_t n, rem;

	while ((n = recv(c->fd_unix, p, TAP_BUF_FILL, MSG_DONTWAIT)) > 0) {
		msg_count = 0;

		while (n > (ssize_t)sizeof(uint32_t)) {
			ssize_t len = ntohl(*(uint32_t *)p);

			p += sizeof(uint32_t);
			n -= sizeof(uint32_t);

			if (len < (ssize_t)sizeof(*eh))
				return 0;

			/* At most one packet might not fit in a single read */
			if (len > n) {
				rem = recv(c->fd_unix, p + n, len - n,
					   MSG_DONTWAIT);
				if ((n += rem) != len)
					return 0;
			}

			pcap(p, len);

			msg[msg_count].start = p;
			msg[msg_count++].len = len;

			n -= len;
			p += len;
		}

		i = 0;
		while (i < msg_count) {
			eh = (struct ethhdr *)msg[i].start;

			memcpy(c->mac_guest, eh->h_source, ETH_ALEN);

			switch (ntohs(eh->h_proto)) {
			case ETH_P_ARP:
				tap4_handler(c, msg + i, 1, now);
				i++;
				break;
			case ETH_P_IP:
				for (same = 1; i + same < msg_count &&
					       same < UIO_MAXIOV; same++) {
					struct tap_msg *next = &msg[i + same];

					eh = (struct ethhdr *)next->start;
					if (ntohs(eh->h_proto) != ETH_P_IP)
						break;
				}

				i += tap4_handler(c, msg + i, same, now);
				break;
			case ETH_P_IPV6:
				for (same = 1; i + same < msg_count &&
					       same < UIO_MAXIOV; same++) {
					struct tap_msg *next = &msg[i + same];

					eh = (struct ethhdr *)next->start;
					if (ntohs(eh->h_proto) != ETH_P_IPV6)
						break;
				}

				i += tap6_handler(c, msg + i, same, now);
				break;
			default:
				i++;
				break;
			}
		}

		p = pkt_buf;
	}

	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
 * @s:		Socket associated to event
 * @events:	epoll events
 * @now:	Current timestamp
 */
static void sock_handler(struct ctx *c, int s, uint32_t events,
			 struct timespec *now)
{
	socklen_t sl;
	int proto;

	sl = sizeof(proto);

	if (    FD_PROTO(s, udp)   && !FD_PROTO(s, icmp) && !FD_PROTO(s, tcp))
		proto = IPPROTO_UDP;
	else if (FD_PROTO(s, tcp)  && !FD_PROTO(s, icmp) && !FD_PROTO(s, udp))
		proto = IPPROTO_TCP;
	else if (FD_PROTO(s, icmp) && !FD_PROTO(s, udp)  && !FD_PROTO(s, tcp))
		proto = IPPROTO_ICMP;	/* Fits ICMPv6 below, too */
	else if (getsockopt(s, SOL_SOCKET, SO_PROTOCOL, &proto, &sl))
		proto = -1;

	if (proto == -1) {
		epoll_ctl(c->epollfd, EPOLL_CTL_DEL, s, NULL);
		close(s);
		return;
	}

	debug("%s (%i): packet from socket %i", IP_PROTO_STR(proto), proto, s);

	if (proto == IPPROTO_ICMP || proto == IPPROTO_ICMPV6)
		icmp_sock_handler(c, s, events, pkt_buf, now);
	else if (proto == IPPROTO_TCP)
		tcp_sock_handler( c, s, events, pkt_buf, now);
	else if (proto == IPPROTO_UDP)
		udp_sock_handler( c, s, events, pkt_buf, now);
}

/**
 * timer_handler() - Run periodic tasks for L4 protocol handlers
 * @c:		Execution context
 * @now:	Current timestamp
 */
static void timer_handler(struct ctx *c, struct timespec *now)
{
	if (timespec_diff_ms(now, &c->tcp.timer_run) >= TCP_TIMER_INTERVAL) {
		tcp_timer(c, now);
		c->tcp.timer_run = *now;
	}

	if (timespec_diff_ms(now, &c->udp.timer_run) >= UDP_TIMER_INTERVAL) {
		udp_timer(c, now);
		c->udp.timer_run = *now;
	}
}

/**
 * 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];
	int nfds, i, fd_unix, sock_index;
	char buf6[INET6_ADDRSTRLEN];
	char buf4[INET_ADDRSTRLEN];
	struct epoll_event ev = { 0 };
	struct ctx c = { 0 };
	struct rlimit limit;
	struct timespec now;

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

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

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

	if (getrlimit(RLIMIT_NOFILE, &limit)) {
		perror("getrlimit");
		exit(EXIT_FAILURE);
	}
	limit.rlim_cur = limit.rlim_max;
	if (setrlimit(RLIMIT_NOFILE, &limit)) {
		perror("setrlimit");
		exit(EXIT_FAILURE);
	}

#if DEBUG
	openlog("passt", 0, LOG_DAEMON);
#else
	openlog("passt", isatty(fileno(stdout)) ? 0 : LOG_PERROR, LOG_DAEMON);
#endif

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

	fd_unix = sock_unix(&sock_index);

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

	if (c.v6)
		dhcpv6_init(&c);

	memset(&c.mac_guest, 0xff, sizeof(c.mac_guest));

	pcap_init(sock_index);

	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, sizeof(buf4)));
		info("    mask: %s",
		     inet_ntop(AF_INET, &c.mask4,  buf4, sizeof(buf4)));
		info("    router: %s",
		     inet_ntop(AF_INET, &c.gw4,    buf4, sizeof(buf4)));
		for (i = 0; c.dns4[i]; i++) {
			if (!i)
				info("    DNS:");
			inet_ntop(AF_INET, &c.dns4[i], buf4, sizeof(buf4));
			info("        %s", buf4);
		}
		for (i = 0; *c.dns_search[i].n; i++) {
			if (!i)
				info("        search:");
			info("            %s", c.dns_search[i].n);
		}
	}
	if (c.v6) {
		info("NDP/DHCPv6:");
		info("    assign: %s",
		     inet_ntop(AF_INET6, &c.addr6, buf6, sizeof(buf6)));
		info("    router: %s",
		     inet_ntop(AF_INET6, &c.gw6,   buf6, sizeof(buf6)));
		for (i = 0; !IN6_IS_ADDR_UNSPECIFIED(&c.dns6[i]); i++) {
			if (!i)
				info("    DNS:");
			inet_ntop(AF_INET6, &c.dns6[i], buf6, sizeof(buf6));
			info("        %s", buf6);
		}
		for (i = 0; *c.dns_search[i].n; i++) {
			if (!i)
				info("        search:");
			info("            %s", c.dns_search[i].n);
		}
	}

listen:
	listen(fd_unix, 0);
	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", sock_index);

#ifndef DEBUG
	if (isatty(fileno(stdout)) && daemon(0, 0)) {
		fprintf(stderr, "Failed to fork into background\n");
		exit(EXIT_FAILURE);
	}
#endif

	c.fd_unix = accept(fd_unix, NULL, NULL);

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

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

	clock_gettime(CLOCK_MONOTONIC, &now);

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

	timer_handler(&c, &now);

	goto loop;

	return 0;
}