aboutgitcodebugslistschat
path: root/util.c
blob: 2a5c5eef26e9744c518839b8e18fa502b6458e77 (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
// SPDX-License-Identifier: AGPL-3.0-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
 *
 * util.c - Convenience helpers
 *
 * Copyright (c) 2020-2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 */

#define _GNU_SOURCE
#include <sched.h>
#include <stdio.h>
#include <stdint.h>
#include <stddef.h>
#include <unistd.h>
#include <linux/ipv6.h>
#include <arpa/inet.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <netinet/tcp.h>
#include <netinet/udp.h>
#include <sys/epoll.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <syslog.h>
#include <stdarg.h>
#include <string.h>
#include <time.h>
#include <errno.h>

#include "util.h"
#include "passt.h"

#define logfn(name, level)						\
void name(const char *format, ...) {					\
	char ts[sizeof("Mmm dd hh:mm:ss.")];				\
	struct timespec tp;						\
	struct tm *tm;							\
	va_list args;							\
									\
	if (setlogmask(0) & LOG_MASK(LOG_DEBUG)) {			\
		clock_gettime(CLOCK_REALTIME, &tp);			\
		tm = gmtime(&tp.tv_sec);				\
		strftime(ts, sizeof(ts), "%b %d %T.", tm);		\
									\
		fprintf(stderr, "%s%04lu: ", ts,			\
			tp.tv_nsec / (100 * 1000));			\
	}								\
									\
	va_start(args, format);						\
	vsyslog(level, format, args);					\
	va_end(args);							\
									\
	if (setlogmask(0) & LOG_MASK(LOG_DEBUG) ||			\
	    setlogmask(0) == LOG_MASK(LOG_EMERG)) {			\
		va_start(args, format);					\
		vfprintf(stderr, format, args); 			\
		va_end(args);						\
		if (format[strlen(format)] != '\n')			\
			fprintf(stderr, "\n");				\
	}								\
}

logfn(err,   LOG_ERR)
logfn(warn,  LOG_WARNING)
logfn(info,  LOG_INFO)
logfn(debug, LOG_DEBUG)

/**
 * ipv6_l4hdr() - Find pointer to L4 header in IPv6 packet and extract protocol
 * @ip6h:	IPv6 header
 * @proto:	Filled with L4 protocol number
 *
 * Return: pointer to L4 header, NULL if not found
 */
char *ipv6_l4hdr(struct ipv6hdr *ip6h, uint8_t *proto)
{
	int offset, len, hdrlen;
	struct ipv6_opt_hdr *o;
	uint8_t nh;

	len = ntohs(ip6h->payload_len);
	offset = 0;

	while (offset < len) {
		if (!offset) {
			nh = ip6h->nexthdr;
			hdrlen = sizeof(struct ipv6hdr);
		} else {
			o = (struct ipv6_opt_hdr *)(((char *)ip6h) + offset);
			nh = o->nexthdr;
			hdrlen = (o->hdrlen + 1) * 8;
		}

		if (nh == 59)
			return NULL;

		if (nh == 0   || nh == 43  || nh == 44  || nh == 50  ||
		    nh == 51  || nh == 60  || nh == 135 || nh == 139 ||
		    nh == 140 || nh == 253 || nh == 254) {
			offset += hdrlen;
		} else {
			*proto = nh;
			return (char *)(ip6h + 1) + offset;
		}
	}

	return NULL;
}

/**
 * sock_l4() - Create and bind socket for given L4, add to epoll list
 * @c:		Execution context
 * @af:		Address family, AF_INET or AF_INET6
 * @proto:	Protocol number
 * @port:	Port, host order
 * @bind_type:	Type of address for binding
 * @data:	epoll reference portion for protocol handlers
 *
 * Return: newly created socket, -1 on error
 */
int sock_l4(struct ctx *c, int af, uint8_t proto, uint16_t port,
	    enum bind_type bind_addr, uint32_t data)
{
	union epoll_ref ref = { .proto = proto, .data = data };
	struct sockaddr_in addr4 = {
		.sin_family = AF_INET,
		.sin_port = htons(port),
	};
	struct sockaddr_in6 addr6 = {
		.sin6_family = AF_INET6,
		.sin6_port = htons(port),
	};
	const struct sockaddr *sa;
	struct epoll_event ev;
	int fd, sl, one = 1;

	if (proto != IPPROTO_TCP && proto != IPPROTO_UDP &&
	    proto != IPPROTO_ICMP && proto != IPPROTO_ICMPV6)
		return -1;	/* Not implemented. */

	if (proto == IPPROTO_TCP)
		fd = socket(af, SOCK_STREAM | SOCK_NONBLOCK, proto);
	else
		fd = socket(af, SOCK_DGRAM | SOCK_NONBLOCK, proto);
	if (fd < 0) {
		perror("L4 socket");
		return -1;
	}
	ref.s = fd;

	if (af == AF_INET) {
		if (bind_addr == BIND_LOOPBACK)
			addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
		else if (bind_addr == BIND_EXT)
			addr4.sin_addr.s_addr = c->addr4;
		else
			addr4.sin_addr.s_addr = htonl(INADDR_ANY);

		sa = (const struct sockaddr *)&addr4;
		sl = sizeof(addr4);
	} else {
		if (bind_addr == BIND_LOOPBACK) {
			addr6.sin6_addr = in6addr_loopback;
		} else if (bind_addr == BIND_EXT) {
			addr6.sin6_addr = c->addr6;
		} else if (bind_addr == BIND_LL) {
			addr6.sin6_addr = c->addr6_ll;
			addr6.sin6_scope_id = if_nametoindex(c->ifn);
		} else {
			addr6.sin6_addr = in6addr_any;
		}

		sa = (const struct sockaddr *)&addr6;
		sl = sizeof(addr6);

		setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &one, sizeof(one));
	}

	setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one));

	if (bind(fd, sa, sl) < 0) {
		/* We'll fail to bind to low ports if we don't have enough
		 * capabilities, and we'll fail to bind on already bound ports,
		 * this is fine. This might also fail for ICMP because of a
		 * broken SELinux policy, see icmp_tap_handler().
		 */
		if (proto != IPPROTO_ICMP && proto != IPPROTO_ICMPV6) {
			close(fd);
			return 0;
		}
	}

	if (proto == IPPROTO_TCP && listen(fd, 128) < 0) {
		perror("TCP socket listen");
		close(fd);
		return -1;
	}

	ev.events = EPOLLIN;
	ev.data.u64 = ref.u64;
	if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, fd, &ev) == -1) {
		perror("L4 epoll_ctl");
		return -1;
	}

	return fd;
}

/**
 * sock_probe_mem() - Check if setting high SO_SNDBUF and SO_RCVBUF is allowed
 * @c:		Execution context
 */
void sock_probe_mem(struct ctx *c)
{
	int v = INT_MAX / 2, s;
	socklen_t sl;

	if ((s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)) < 0) {
		c->low_wmem = c->low_rmem = 1;
		return;
	}

	sl = sizeof(v);
	if (setsockopt(s, SOL_SOCKET, SO_SNDBUF, &v, sizeof(v))	||
	    getsockopt(s, SOL_SOCKET, SO_SNDBUF, &v, &sl) || v < SNDBUF_BIG)
		c->low_wmem = 1;

	v = INT_MAX / 2;
	if (setsockopt(s, SOL_SOCKET, SO_RCVBUF, &v, sizeof(v))	||
	    getsockopt(s, SOL_SOCKET, SO_RCVBUF, &v, &sl) || v < RCVBUF_BIG)
		c->low_rmem = 1;

	close(s);
}


/**
 * timespec_diff_ms() - Report difference in milliseconds between two timestamps
 * @a:		Minuend timestamp
 * @b:		Subtrahend timestamp
 *
 * Return: difference in milliseconds
 */
int timespec_diff_ms(struct timespec *a, struct timespec *b)
{
	if (a->tv_nsec < b->tv_nsec) {
		return (b->tv_nsec - a->tv_nsec) / 1000000 +
		       (a->tv_sec - b->tv_sec - 1) * 1000;
	}

	return (a->tv_nsec - b->tv_nsec) / 1000000 +
	       (a->tv_sec - b->tv_sec) * 1000;
}

/**
 * bitmap_set() - Set single bit in bitmap
 * @map:	Pointer to bitmap
 * @bit:	Bit number to set
 */
void bitmap_set(uint8_t *map, int bit)
{
	map[bit / 8] |= 1 << (bit % 8);
}

/**
 * bitmap_set() - Clear single bit in bitmap
 * @map:	Pointer to bitmap
 * @bit:	Bit number to clear
 */
void bitmap_clear(uint8_t *map, int bit)
{
	map[bit / 8] &= ~(1 << (bit % 8));
}

/**
 * bitmap_isset() - Check for set bit in bitmap
 * @map:	Pointer to bitmap
 * @bit:	Bit number to check
 *
 * Return: non-zero if given bit is set, zero if it's not
 */
int bitmap_isset(uint8_t *map, int bit)
{
	return map[bit / 8] & (1 << bit % 8);
}

/**
 * procfs_scan_listen() - Set bits for listening TCP or UDP sockets from procfs
 * @name:	Corresponding name of file under /proc/net/
 * @map:	Bitmap where numbers of ports in listening state will be set
 * @exclude:	Bitmap of ports to exclude from setting (and clear)
 */
void procfs_scan_listen(char *name, uint8_t *map, uint8_t *exclude)
{
	char line[200], path[PATH_MAX];
	unsigned long port;
	unsigned int state;
	FILE *fp;

	snprintf(path, PATH_MAX, "/proc/net/%s", name);
	if (!(fp = fopen(path, "r")))
		return;

	fgets(line, sizeof(line), fp);
	while (fgets(line, sizeof(line), fp)) {
		if (sscanf(line, "%*u: %*x:%lx %*x:%*x %x", &port, &state) != 2)
			continue;

		/* See enum in kernel's include/net/tcp_states.h */
		if ((strstr(name, "tcp") && state != 0x0a) ||
		    (strstr(name, "udp") && state != 0x07))
			continue;

		if (bitmap_isset(exclude, port))
			bitmap_clear(map, port);
		else
			bitmap_set(map, port);
	}

	fclose(fp);
}

/**
 * ns_enter() - Enter configured network and user namespaces
 * @c:		Execution context
 *
 * Return: 0 on success, -1 on failure
 */
int ns_enter(struct ctx *c)
{
	if (!c->netns_only && setns(c->pasta_userns_fd, 0))
		return -errno;

	if (setns(c->pasta_netns_fd, 0))
		return -errno;

	return 0;
}