aboutgitcodebugslistschat
path: root/pasta.c
blob: e73b5af6c53f0a07bdc811ee8ada73f82e9c2d2f (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
// 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
 *
 * pasta.c - pasta (namespace) specific implementations
 *
 * Copyright (c) 2020-2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 *
 * #syscalls:pasta clone waitid exit exit_group rt_sigprocmask
 * #syscalls:pasta rt_sigreturn|sigreturn
 * #syscalls:pasta arm:sigreturn ppc64:sigreturn s390x:sigreturn
 */

#include <sched.h>
#include <stdio.h>
#include <string.h>
#include <errno.h>
#include <libgen.h>
#include <limits.h>
#include <stdlib.h>
#include <stdbool.h>
#include <stdint.h>
#include <unistd.h>
#include <syslog.h>
#include <sys/epoll.h>
#include <sys/inotify.h>
#include <sys/mount.h>
#include <sys/timerfd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/statfs.h>
#include <fcntl.h>
#include <sys/wait.h>
#include <signal.h>
#include <dirent.h>
#include <arpa/inet.h>
#include <netinet/in.h>
#include <net/ethernet.h>
#include <sys/syscall.h>
#include <linux/magic.h>

#include "util.h"
#include "passt.h"
#include "isolation.h"
#include "netlink.h"
#include "log.h"

/* PID of child, in case we created a namespace */
int pasta_child_pid;

/**
 * pasta_child_handler() - Exit once shell exits (if we started it), reap clones
 * @signal:	Unused, handler deals with SIGCHLD only
 */
void pasta_child_handler(int signal)
{
	siginfo_t infop;

	(void)signal;

	if (signal != SIGCHLD)
		return;

	if (pasta_child_pid &&
	    !waitid(P_PID, pasta_child_pid, &infop, WEXITED | WNOHANG)) {
		if (infop.si_pid == pasta_child_pid) {
			if (infop.si_code == CLD_EXITED)
				exit(infop.si_status);

			/* If killed by a signal, si_status is the number.
			 * Follow common shell convention of returning it + 128.
			 */
			exit(infop.si_status + 128);

			/* Nothing to do, detached PID namespace going away */
		}
	}

	waitid(P_ALL, 0, NULL, WEXITED | WNOHANG);
	waitid(P_ALL, 0, NULL, WEXITED | WNOHANG);
}

/**
 * pasta_wait_for_ns() - Busy loop until we can enter the target namespace
 * @arg:	Execution context
 *
 * Return: 0
 */
static int pasta_wait_for_ns(void *arg)
{
	struct ctx *c = (struct ctx *)arg;
	int flags = O_RDONLY | O_CLOEXEC;
	char ns[PATH_MAX];

	snprintf(ns, PATH_MAX, "/proc/%i/ns/net", pasta_child_pid);
	do {
		while ((c->pasta_netns_fd = open(ns, flags)) < 0) {
			if (errno != ENOENT)
				return 0;
		}
	} while (setns(c->pasta_netns_fd, CLONE_NEWNET) &&
		 !close(c->pasta_netns_fd));

	return 0;
}

/**
 * ns_check() - Check if we can enter configured namespaces
 * @arg:	Execution context
 *
 * Return: 0
 */
static int ns_check(void *arg)
{
	struct ctx *c = (struct ctx *)arg;

	if (setns(c->pasta_netns_fd, CLONE_NEWNET))
		c->pasta_netns_fd = -1;

	return 0;

}

/**
 * pasta_open_ns() - Open network namespace descriptors
 * @c:		Execution context
 * @netns:	network namespace path
 *
 * Return: 0 on success, negative error code otherwise
 */
void pasta_open_ns(struct ctx *c, const char *netns)
{
	int nfd = -1;

	nfd = open(netns, O_RDONLY | O_CLOEXEC);
	if (nfd < 0) {
		die("Couldn't open network namespace %s: %s",
		    netns, strerror(errno));
	}

	c->pasta_netns_fd = nfd;

	NS_CALL(ns_check, c);

	if (c->pasta_netns_fd < 0)
		die("Couldn't switch to pasta namespaces: %s", strerror(errno));

	if (!c->no_netns_quit) {
		char buf[PATH_MAX] = { 0 };

		strncpy(buf, netns, PATH_MAX - 1);
		strncpy(c->netns_base, basename(buf), PATH_MAX - 1);
		strncpy(buf, netns, PATH_MAX - 1);
		strncpy(c->netns_dir, dirname(buf), PATH_MAX - 1);
	}
}

/**
 * struct pasta_spawn_cmd_arg - Argument for pasta_spawn_cmd()
 * @exe:	Executable to run
 * @argv:	Command and arguments to run
 */
struct pasta_spawn_cmd_arg {
	const char *exe;
	char *const *argv;
};

/**
 * pasta_spawn_cmd() - Prepare new netns, start command or shell
 * @arg:	See @pasta_spawn_cmd_arg
 *
 * Return: this function never returns
 */
static int pasta_spawn_cmd(void *arg)
{
	const struct pasta_spawn_cmd_arg *a;
	sigset_t set;

	/* We run in a detached PID and mount namespace: mount /proc over */
	if (mount("", "/proc", "proc", 0, NULL))
		warn("Couldn't mount /proc: %s", strerror(errno));

	if (write_file("/proc/sys/net/ipv4/ping_group_range", "0 0"))
		warn("Cannot set ping_group_range, ICMP requests might fail");

	/* Wait for the parent to be ready: see main() */
	sigemptyset(&set);
	sigaddset(&set, SIGUSR1);
	sigwaitinfo(&set, NULL);

	a = (const struct pasta_spawn_cmd_arg *)arg;
	execvp(a->exe, a->argv);

	perror("execvp");
	exit(EXIT_FAILURE);
}

/**
 * pasta_start_ns() - Fork command in new namespace if target ns is not given
 * @c:		Execution context
 * @uid:	UID we're running as in the init namespace
 * @gid:	GID we're running as in the init namespace
 * @argc:	Number of arguments for spawned command
 * @argv:	Command to spawn and arguments
 */
void pasta_start_ns(struct ctx *c, uid_t uid, gid_t gid,
		    int argc, char *argv[])
{
	struct pasta_spawn_cmd_arg arg = {
		.exe = argv[0],
		.argv = argv,
	};
	char uidmap[BUFSIZ], gidmap[BUFSIZ];
	char ns_fn_stack[NS_FN_STACK_SIZE];
	char *sh_argv[] = { NULL, NULL };
	char sh_arg0[PATH_MAX + 1];
	sigset_t set;

	c->foreground = 1;
	if (!c->debug)
		c->quiet = 1;

	/* Configure user and group mappings */
	snprintf(uidmap, BUFSIZ, "0 %u 1", uid);
	snprintf(gidmap, BUFSIZ, "0 %u 1", gid);

	if (write_file("/proc/self/uid_map", uidmap) ||
	    write_file("/proc/self/setgroups", "deny") ||
	    write_file("/proc/self/gid_map", gidmap)) {
		warn("Couldn't configure user mappings");
	}

	if (argc == 0) {
		arg.exe = getenv("SHELL");
		if (!arg.exe)
			arg.exe = "/bin/sh";

		if ((size_t)snprintf(sh_arg0, sizeof(sh_arg0),
				     "-%s", arg.exe) >= sizeof(sh_arg0))
			die("$SHELL is too long (%zu bytes)", strlen(arg.exe));

		sh_argv[0] = sh_arg0;
		arg.argv = sh_argv;
	}

	/* Block SIGUSR1 in child, we queue it in main() when we're ready */
	sigemptyset(&set);
	sigaddset(&set, SIGUSR1);
	sigprocmask(SIG_BLOCK, &set, NULL);

	pasta_child_pid = do_clone(pasta_spawn_cmd, ns_fn_stack,
				   sizeof(ns_fn_stack),
				   CLONE_NEWIPC | CLONE_NEWPID | CLONE_NEWNET |
				   CLONE_NEWUTS | CLONE_NEWNS  | SIGCHLD,
				   (void *)&arg);

	if (pasta_child_pid == -1) {
		perror("clone");
		exit(EXIT_FAILURE);
	}

	NS_CALL(pasta_wait_for_ns, c);
	if (c->pasta_netns_fd < 0)
		die("Failed to join network namespace: %s", strerror(errno));
}

/**
 * pasta_ns_conf() - Set up loopback and tap interfaces in namespace as needed
 * @c:		Execution context
 */
void pasta_ns_conf(struct ctx *c)
{
	int rc = 0;

	rc = nl_link_up(nl_sock_ns, 1 /* lo */, 0);
	if (rc < 0)
		die("Couldn't bring up loopback interface in namespace: %s",
		    strerror(-rc));

	/* Get or set MAC in target namespace */
	if (MAC_IS_ZERO(c->mac_guest))
		nl_link_get_mac(nl_sock_ns, c->pasta_ifi, c->mac_guest);
	else
		rc = nl_link_set_mac(nl_sock_ns, c->pasta_ifi, c->mac_guest);
	if (rc < 0)
		die("Couldn't set MAC address in namespace: %s",
		    strerror(-rc));

	if (c->pasta_conf_ns) {
		nl_link_up(nl_sock_ns, c->pasta_ifi, c->mtu);

		if (c->ifi4) {
			if (c->no_copy_addrs) {
				rc = nl_addr_set(nl_sock_ns, c->pasta_ifi,
						 AF_INET,
						 &c->ip4.addr,
						 c->ip4.prefix_len);
			} else {
				rc = nl_addr_dup(nl_sock, c->ifi4,
						 nl_sock_ns, c->pasta_ifi,
						 AF_INET);
			}

			if (rc < 0) {
				die("Couldn't set IPv4 address(es) in namespace: %s",
				    strerror(-rc));
			}

			if (c->no_copy_routes) {
				rc = nl_route_set_def(nl_sock_ns, c->pasta_ifi,
						      AF_INET, &c->ip4.gw);
			} else {
				rc = nl_route_dup(nl_sock, c->ifi4, nl_sock_ns,
						  c->pasta_ifi, AF_INET);
			}

			if (rc < 0) {
				die("Couldn't set IPv4 route(s) in guest: %s",
				    strerror(-rc));
			}
		}

		if (c->ifi6) {
			if (c->no_copy_addrs) {
				rc = nl_addr_set(nl_sock_ns, c->pasta_ifi,
						 AF_INET6, &c->ip6.addr, 64);
			} else {
				rc = nl_addr_dup(nl_sock, c->ifi6,
						 nl_sock_ns, c->pasta_ifi,
						 AF_INET6);
			}

			if (rc < 0) {
				die("Couldn't set IPv6 address(es) in namespace: %s",
				    strerror(-rc));
			}

			if (c->no_copy_routes) {
				rc = nl_route_set_def(nl_sock_ns, c->pasta_ifi,
						      AF_INET6, &c->ip6.gw);
			} else {
				rc = nl_route_dup(nl_sock, c->ifi6,
						  nl_sock_ns, c->pasta_ifi,
						  AF_INET6);
			}

			if (rc < 0) {
				die("Couldn't set IPv6 route(s) in guest: %s",
				    strerror(-rc));
			}
		}
	}

	proto_update_l2_buf(c->mac_guest, NULL);
}

/**
 * pasta_netns_quit_timer() - Set up fallback timer to monitor namespace
 *
 * Return: timerfd file descriptor, negative error code on failure
 */
static int pasta_netns_quit_timer(void)
{
	int fd = timerfd_create(CLOCK_MONOTONIC, TFD_CLOEXEC);
	struct itimerspec it = { { 1, 0 }, { 1, 0 } }; /* one-second interval */

	if (fd == -1) {
		err("timerfd_create(): %s", strerror(errno));
		return -errno;
	}

	if (timerfd_settime(fd, 0, &it, NULL) < 0) {
		err("timerfd_settime(): %s", strerror(errno));
		close(fd);
		return -errno;
	}

	return fd;
}

/**
 * pasta_netns_quit_init() - Watch network namespace to quit once it's gone
 * @c:		Execution context
 */
void pasta_netns_quit_init(const struct ctx *c)
{
	union epoll_ref ref = { .type = EPOLL_TYPE_NSQUIT_INOTIFY };
	struct epoll_event ev = { .events = EPOLLIN };
	int flags = O_NONBLOCK | O_CLOEXEC;
	struct statfs s = { 0 };
	bool try_inotify = true;
	int fd = -1, dir_fd;

	if (c->mode != MODE_PASTA || c->no_netns_quit || !*c->netns_base)
		return;

	if ((dir_fd = open(c->netns_dir, O_CLOEXEC | O_RDONLY)) < 0)
		die("netns dir open: %s, exiting", strerror(errno));

	if (fstatfs(dir_fd, &s)          || s.f_type == DEVPTS_SUPER_MAGIC ||
	    s.f_type == PROC_SUPER_MAGIC || s.f_type == SYSFS_MAGIC)
		try_inotify = false;

	if (try_inotify && (fd = inotify_init1(flags)) < 0)
		warn("inotify_init1(): %s, use a timer", strerror(errno));

	if (fd >= 0 && inotify_add_watch(fd, c->netns_dir, IN_DELETE) < 0) {
		warn("inotify_add_watch(): %s, use a timer",
		     strerror(errno));
		close(fd);
		fd = -1;
	}

	if (fd < 0) {
		if ((fd = pasta_netns_quit_timer()) < 0)
			die("Failed to set up fallback netns timer, exiting");

		ref.nsdir_fd = dir_fd;

		ref.type = EPOLL_TYPE_NSQUIT_TIMER;
	} else {
		close(dir_fd);
	}

	if (fd > FD_REF_MAX)
		die("netns monitor file number %i too big, exiting", fd);

	ref.fd = fd;
	ev.data.u64 = ref.u64;
	epoll_ctl(c->epollfd, EPOLL_CTL_ADD, fd, &ev);
}

/**
 * pasta_netns_quit_inotify_handler() - Handle inotify watch, exit if ns is gone
 * @c:		Execution context
 * @inotify_fd:	inotify file descriptor with watch on namespace directory
 */
void pasta_netns_quit_inotify_handler(struct ctx *c, int inotify_fd)
{
	char buf[sizeof(struct inotify_event) + NAME_MAX + 1];
	const struct inotify_event *in_ev = (struct inotify_event *)buf;

	if (read(inotify_fd, buf, sizeof(buf)) < (ssize_t)sizeof(*in_ev))
		return;

	if (strncmp(in_ev->name, c->netns_base, sizeof(c->netns_base)))
		return;

	info("Namespace %s is gone, exiting", c->netns_base);
	exit(EXIT_SUCCESS);
}

/**
 * pasta_netns_quit_timer_handler() - Handle timer, exit if ns is gone
 * @c:		Execution context
 * @ref:	epoll reference for timer descriptor
 */
void pasta_netns_quit_timer_handler(struct ctx *c, union epoll_ref ref)
{
	uint64_t expirations;
	ssize_t n;
	int fd;

	n = read(ref.fd, &expirations, sizeof(expirations));
	if (n < 0)
		die("Namespace watch timer read() error: %s", strerror(errno));
	if ((size_t)n < sizeof(expirations))
		warn("Namespace watch timer: short read(): %zi", n);

	fd = openat(ref.nsdir_fd, c->netns_base, O_PATH | O_CLOEXEC);
	if (fd < 0) {
		if (errno == EACCES)	/* Expected for existing procfs entry */
			return;

		info("Namespace %s is gone, exiting", c->netns_base);
		exit(EXIT_SUCCESS);
	}

	close(fd);
}