aboutgitcodebugslistschat
path: root/util.c
blob: b9f4e7d40b25fe6d9e3d4a12787133cf0ba0721c (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
// 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
 *
 * util.c - Convenience helpers
 *
 * Copyright (c) 2020-2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 */

#include <sched.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <net/ethernet.h>
#include <sys/epoll.h>
#include <fcntl.h>
#include <string.h>
#include <time.h>
#include <errno.h>
#include <stdbool.h>

#include "util.h"
#include "passt.h"
#include "packet.h"
#include "lineread.h"
#include "log.h"

#define IPV6_NH_OPT(nh)							\
	((nh) == 0   || (nh) == 43  || (nh) == 44  || (nh) == 50  ||	\
	 (nh) == 51  || (nh) == 60  || (nh) == 135 || (nh) == 139 ||	\
	 (nh) == 140 || (nh) == 253 || (nh) == 254)

/**
 * ipv6_l4hdr() - Find pointer to L4 header in IPv6 packet and extract protocol
 * @p:		Packet pool, packet number @index has IPv6 header at @offset
 * @index:	Index of packet in pool
 * @offset:	Pre-calculated IPv6 header offset
 * @proto:	Filled with L4 protocol number
 * @dlen:	Data length (payload excluding header extensions), set on return
 *
 * Return: pointer to L4 header, NULL if not found
 */
char *ipv6_l4hdr(const struct pool *p, int index, size_t offset, uint8_t *proto,
		 size_t *dlen)
{
	struct ipv6_opt_hdr *o;
	struct ipv6hdr *ip6h;
	char *base;
	int hdrlen;
	uint8_t nh;

	base = packet_get(p, index, 0, 0, NULL);
	ip6h = packet_get(p, index, offset, sizeof(*ip6h), dlen);
	if (!ip6h)
		return NULL;

	offset += sizeof(*ip6h);

	nh = ip6h->nexthdr;
	if (!IPV6_NH_OPT(nh))
		goto found;

	while ((o = packet_get_try(p, index, offset, sizeof(*o), dlen))) {
		nh = o->nexthdr;
		hdrlen = (o->hdrlen + 1) * 8;

		if (IPV6_NH_OPT(nh))
			offset += hdrlen;
		else
			goto found;
	}

	return NULL;

found:
	if (nh == 59)
		return NULL;

	*proto = nh;
	return base + offset;
}

/**
 * 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
 * @bind_addr:	Address for binding, NULL for any
 * @ifname:	Interface for binding, NULL for any
 * @port:	Port, host order
 * @data:	epoll reference portion for protocol handlers
 *
 * Return: newly created socket, negative error code on failure
 */
int sock_l4(const struct ctx *c, int af, uint8_t proto,
	    const void *bind_addr, const char *ifname, uint16_t port,
	    uint32_t data)
{
	union epoll_ref ref = { .proto = proto, .data = data };
	struct sockaddr_in addr4 = {
		.sin_family = AF_INET,
		.sin_port = htons(port),
		{ 0 }, { 0 },
	};
	struct sockaddr_in6 addr6 = {
		.sin6_family = AF_INET6,
		.sin6_port = htons(port),
		0, IN6ADDR_ANY_INIT, 0,
	};
	const struct sockaddr *sa;
	bool dual_stack = false;
	int fd, sl, y = 1, ret;
	struct epoll_event ev;

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

	if (af == AF_UNSPEC) {
		if (!DUAL_STACK_SOCKETS || bind_addr)
			return -EINVAL;
		dual_stack = true;
		af = AF_INET6;
	}

	if (proto == IPPROTO_TCP)
		fd = socket(af, SOCK_STREAM | SOCK_NONBLOCK, proto);
	else
		fd = socket(af, SOCK_DGRAM | SOCK_NONBLOCK, proto);

	ret = -errno;
	if (fd < 0) {
		warn("L4 socket: %s", strerror(-ret));
		return ret;
	}

	if (fd > SOCKET_MAX) {
		close(fd);
		return -EBADF;
	}

	ref.s = fd;

	if (af == AF_INET) {
		if (bind_addr)
			addr4.sin_addr.s_addr = *(in_addr_t *)bind_addr;
		else
			addr4.sin_addr.s_addr = htonl(INADDR_ANY);

		sa = (const struct sockaddr *)&addr4;
		sl = sizeof(addr4);
	} else {
		if (bind_addr) {
			addr6.sin6_addr = *(struct in6_addr *)bind_addr;

			if (!memcmp(bind_addr, &c->ip6.addr_ll,
			    sizeof(c->ip6.addr_ll)))
				addr6.sin6_scope_id = c->ifi6;
		} else {
			addr6.sin6_addr = in6addr_any;
		}

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

		if (!dual_stack)
			if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY,
				       &y, sizeof(y)))
				debug("Failed to set IPV6_V6ONLY on socket %i",
				      fd);
	}

	if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &y, sizeof(y)))
		debug("Failed to set SO_REUSEADDR on socket %i", fd);

	if (ifname) {
		/* Supported since kernel version 5.7, commit c427bfec18f2
		 * ("net: core: enable SO_BINDTODEVICE for non-root users"). If
		 * it's unsupported, don't bind the socket at all, because the
		 * user might rely on this to filter incoming connections.
		 */
		if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE,
			       ifname, strlen(ifname))) {
			ret = -errno;
			warn("Can't bind socket for %s port %u to %s, closing",
			     ip_proto_str[proto], port, ifname);
			close(fd);
			return ret;
		}
	}

	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) {
			ret = -errno;
			close(fd);
			return ret;
		}
	}

	if (proto == IPPROTO_TCP && listen(fd, 128) < 0) {
		ret = -errno;
		warn("TCP socket listen: %s", strerror(-ret));
		close(fd);
		return ret;
	}

	ev.events = EPOLLIN;
	ev.data.u64 = ref.u64;
	if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, fd, &ev) == -1) {
		ret = -errno;
		warn("L4 epoll_ctl: %s", strerror(-ret));
		return ret;
	}

	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) ||
	    (size_t)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) ||
	    (size_t)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(const struct timespec *a, const 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)
{
	unsigned long *word = (unsigned long *)map + BITMAP_WORD(bit);

	*word |= BITMAP_BIT(bit);
}

/**
 * bitmap_clear() - Clear single bit in bitmap
 * @map:	Pointer to bitmap
 * @bit:	Bit number to clear
 */
void bitmap_clear(uint8_t *map, int bit)
{
	unsigned long *word = (unsigned long *)map + BITMAP_WORD(bit);

	*word &= ~BITMAP_BIT(bit);
}

/**
 * bitmap_isset() - Check for set bit in bitmap
 * @map:	Pointer to bitmap
 * @bit:	Bit number to check
 *
 * Return: one if given bit is set, zero if it's not
 */
int bitmap_isset(const uint8_t *map, int bit)
{
	unsigned long *word = (unsigned long *)map + BITMAP_WORD(bit);

	return !!(*word & BITMAP_BIT(bit));
}

/**
 * procfs_scan_listen() - Set bits for listening TCP or UDP sockets from procfs
 * @proto:	IPPROTO_TCP or IPPROTO_UDP
 * @ip_version:	IP version, V4 or V6
 * @ns:		Use saved file descriptors for namespace if set
 * @map:	Bitmap where numbers of ports in listening state will be set
 * @exclude:	Bitmap of ports to exclude from setting (and clear)
 *
 * #syscalls:pasta lseek
 * #syscalls:pasta ppc64le:_llseek ppc64:_llseek armv6l:_llseek armv7l:_llseek
 */
void procfs_scan_listen(struct ctx *c, uint8_t proto, int ip_version, int ns,
			uint8_t *map, uint8_t *exclude)
{
	char *path, *line;
	struct lineread lr;
	unsigned long port;
	unsigned int state;
	int *fd;

	if (proto == IPPROTO_TCP) {
		fd = &c->proc_net_tcp[ip_version][ns];
		if (ip_version == V4)
			path = "/proc/net/tcp";
		else
			path = "/proc/net/tcp6";
	} else {
		fd = &c->proc_net_udp[ip_version][ns];
		if (ip_version == V4)
			path = "/proc/net/udp";
		else
			path = "/proc/net/udp6";
	}

	if (*fd != -1) {
		if (lseek(*fd, 0, SEEK_SET)) {
			warn("lseek() failed on %s: %s", path, strerror(errno));
			return;
		}
	} else if ((*fd = open(path, O_RDONLY | O_CLOEXEC)) < 0) {
		return;
	}

	lineread_init(&lr, *fd);
	lineread_get(&lr, &line); /* throw away header */
	while (lineread_get(&lr, &line) > 0) {
		/* NOLINTNEXTLINE(cert-err34-c): != 2 if conversion fails */
		if (sscanf(line, "%*u: %*x:%lx %*x:%*x %x", &port, &state) != 2)
			continue;

		/* See enum in kernel's include/net/tcp_states.h */
		if ((proto == IPPROTO_TCP && state != 0x0a) ||
		    (proto == IPPROTO_UDP && state != 0x07))
			continue;

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

/**
 * ns_enter() - Enter configured user (unless already joined) and network ns
 * @c:		Execution context
 *
 * Return: 0, won't return on failure
 *
 * #syscalls:pasta setns
 */
int ns_enter(const struct ctx *c)
{
	if (setns(c->pasta_netns_fd, CLONE_NEWNET))
		exit(EXIT_FAILURE);

	return 0;
}

/**
 * ns_is_init() - Is the caller running in the "init" user namespace?
 *
 * Return: true if caller is in init, false otherwise, won't return on failure
 */
bool ns_is_init(void)
{
	const char root_uid_map[] = "         0          0 4294967295\n";
	char buf[sizeof(root_uid_map)] = { 0 };
	bool ret = true;
	int fd;

	if ((fd = open("/proc/self/uid_map", O_RDONLY | O_CLOEXEC)) < 0) {
		die("Can't determine if we're in init namespace: %s",
		    strerror(errno));
	}

	if (read(fd, buf, sizeof(root_uid_map)) != sizeof(root_uid_map) - 1 ||
	    strncmp(buf, root_uid_map, sizeof(root_uid_map)))
		ret = false;

	close(fd);
	return ret;
}

/**
 * pid_file() - Write PID to file, if requested to do so, and close it
 * @fd:		Open PID file descriptor, closed on exit, -1 to skip writing it
 * @pid:	PID value to write
 */
void write_pidfile(int fd, pid_t pid)
{
	char pid_buf[12];
	int n;

	if (fd == -1)
		return;

	n = snprintf(pid_buf, sizeof(pid_buf), "%i\n", pid);

	if (write(fd, pid_buf, n) < 0) {
		perror("PID file write");
		exit(EXIT_FAILURE);
	}

	close(fd);
}

/**
 * __daemon() - daemon()-like function writing PID file before parent exits
 * @pidfile_fd:	Open PID file descriptor
 * @devnull_fd:	Open file descriptor for /dev/null
 *
 * Return: child PID on success, won't return on failure
 */
int __daemon(int pidfile_fd, int devnull_fd)
{
	pid_t pid = fork();

	if (pid == -1) {
		perror("fork");
		exit(EXIT_FAILURE);
	}

	if (pid) {
		write_pidfile(pidfile_fd, pid);
		exit(EXIT_SUCCESS);
	}

	errno = 0;

	setsid();

	dup2(devnull_fd, STDIN_FILENO);
	dup2(devnull_fd, STDOUT_FILENO);
	dup2(devnull_fd, STDERR_FILENO);
	close(devnull_fd);

	if (errno)
		exit(EXIT_FAILURE);

	return 0;
}

/**
 * fls() - Find last (most significant) bit set in word
 * @x:		Word
 *
 * Return: position of most significant bit set, starting from 0, -1 if none
 */
int fls(unsigned long x)
{
	int y = 0;

	if (!x)
		return -1;

	while (x >>= 1)
		y++;

	return y;
}

/**
 * write_file() - Replace contents of file with a string
 * @path:	File to write
 * @buf:	String to write
 *
 * Return: 0 on success, -1 on any error
 */
int write_file(const char *path, const char *buf)
{
	int fd = open(path, O_WRONLY | O_TRUNC | O_CLOEXEC);
	size_t len = strlen(buf);

	if (fd < 0) {
		warn("Could not open %s: %s", path, strerror(errno));
		return -1;
	}

	while (len) {
		ssize_t rc = write(fd, buf, len);

		if (rc <= 0) {
			warn("Couldn't write to %s: %s", path, strerror(errno));
			break;
		}

		buf += rc;
		len -= rc;
	}

	close(fd);
	return len == 0 ? 0 : -1;
}

#ifdef __ia64__
/* Needed by do_clone() below: glibc doesn't export the prototype of __clone2(),
 * use the description from clone(2).
 */
int __clone2(int (*fn)(void *), void *stack_base, size_t stack_size, int flags,
	     void *arg, ... /* pid_t *parent_tid, struct user_desc *tls,
	     pid_t *child_tid */ );
#endif

/**
 * do_clone() - Wrapper of __clone2() for ia64, clone() for other architectures
 * @fn:		Entry point for child
 * @stack_area:	Stack area for child: we'll point callees to the middle of it
 * @stack_size:	Total size of stack area, passed to callee divided by two
 * @flags:	clone() system call flags
 * @arg:	Argument to @fn
 *
 * Return: thread ID of child, -1 on failure
 */
int do_clone(int (*fn)(void *), char *stack_area, size_t stack_size, int flags,
	     void *arg)
{
#ifdef __ia64__
	return __clone2(fn, stack_area + stack_size / 2, stack_size / 2,
			flags, arg);
#else
	return clone(fn, stack_area + stack_size / 2, flags, arg);
#endif
}