public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
blob bce30d4f2e608da8a9395742d4fc681ba8b5eda5 6067 bytes (raw)

  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
 
// 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
 *
 * pasta.c - pasta (namespace) specific implementations
 *
 * Copyright (c) 2020-2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 *
 * #syscalls:pasta clone unshare waitid kill execve exit_group rt_sigprocmask
 * #syscalls:pasta geteuid getdents64|getdents readlink|readlinkat setsid
 * #syscalls:pasta nanosleep clock_nanosleep
 */

#include <sched.h>
#include <stdio.h>
#include <string.h>
#include <errno.h>
#include <limits.h>
#include <stdlib.h>
#include <stdint.h>
#include <unistd.h>
#include <syslog.h>
#include <sys/types.h>
#include <sys/stat.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 "util.h"
#include "passt.h"
#include "netlink.h"

/* PID of child, in case we created a namespace, and its procfs link */
static int pasta_child_pid;
static char pasta_child_ns[PATH_MAX];

/**
 * pasta_ns_cleanup() - Look for processes in namespace, terminate them
 */
static void pasta_ns_cleanup(void)
{
	char proc_path[PATH_MAX], ns_link[PATH_MAX], buf[BUFSIZ];
	int recheck = 0, found = 0, waited = 0;
	int dir_fd, n;

	if (!*pasta_child_ns)
		return;

loop:
	if ((dir_fd = open("/proc", O_RDONLY | O_DIRECTORY)) < 0)
		return;

	while ((n = syscall(SYS_getdents64, dir_fd, buf, BUFSIZ)) > 0) {
		struct dirent *dp = (struct dirent *)buf;
		int pos = 0;

		while (dp->d_reclen && pos < n) {
			pid_t pid;

			errno = 0;
			pid = strtol(dp->d_name, NULL, 0);
			if (!pid || errno)
				goto next;

			snprintf(proc_path, PATH_MAX, "/proc/%i/ns/net", pid);
			if (readlink(proc_path, ns_link, PATH_MAX) < 0)
				goto next;

			if (!strncmp(ns_link, pasta_child_ns, PATH_MAX)) {
				found = 1;
				if (waited)
					kill(pid, SIGKILL);
				else
					kill(pid, SIGQUIT);
			}
next:
			dp = (struct dirent *)(buf + (pos += dp->d_reclen));
		}
	}

	close(dir_fd);

	if (!found)
		return;

	if (waited) {
		if (recheck) {
			info("Some processes in namespace didn't quit");
		} else {
			found = 0;
			recheck = 1;
			goto loop;
		}
		return;
	}

	info("Waiting for all processes in namespace to terminate");
	sleep(1);
	waited = 1;
	goto loop;
}

/**
 * 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 (pasta_child_pid &&
	    !waitid(P_PID, pasta_child_pid, &infop, WEXITED | WNOHANG)) {
		if (infop.si_pid == pasta_child_pid) {
			pasta_ns_cleanup();
			exit(EXIT_SUCCESS);
		}
	}

	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;
	char ns[PATH_MAX];

	if (c->netns_only)
		goto netns;

	snprintf(ns, PATH_MAX, "/proc/%i/ns/user", pasta_child_pid);
	do
		while ((c->pasta_userns_fd = open(ns, O_RDONLY)) < 0);
	while (setns(c->pasta_userns_fd, CLONE_NEWUSER) &&
	       !close(c->pasta_userns_fd));

netns:
	snprintf(ns, PATH_MAX, "/proc/%i/ns/net", pasta_child_pid);
	do
		while ((c->pasta_netns_fd = open(ns, O_RDONLY)) < 0);
	while (setns(c->pasta_netns_fd, CLONE_NEWNET) &&
	       !close(c->pasta_netns_fd));

	return 0;
}

/**
 * pasta_start_ns() - Fork shell in new namespace if target ns is not given
 * @c:		Execution context
 */
void pasta_start_ns(struct ctx *c)
{
	int euid = geteuid(), fd;
	char *shell;

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

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

	if (pasta_child_pid) {
		char proc_path[PATH_MAX];

		NS_CALL(pasta_wait_for_ns, c);

		snprintf(proc_path, PATH_MAX, "/proc/%i/ns/net",
			 pasta_child_pid);
		if (readlink(proc_path, pasta_child_ns, PATH_MAX) < 0)
			warn("Cannot read link to ns, won't clean up on exit");

		return;
	}

	if (unshare(CLONE_NEWNET | (c->netns_only ? 0 : CLONE_NEWUSER))) {
		perror("unshare");
		exit(EXIT_FAILURE);
	}

	if (!c->netns_only) {
		char buf[BUFSIZ];

		snprintf(buf, BUFSIZ, "%i %i %i", 0, euid, 1);

		fd = open("/proc/self/uid_map", O_WRONLY);
		if (write(fd, buf, strlen(buf)) < 0)
			warn("Cannot set uid_map in namespace");
		close(fd);

		fd = open("/proc/self/setgroups", O_WRONLY);
		if (write(fd, "deny", sizeof("deny")) < 0)
			warn("Cannot write to setgroups in namespace");
		close(fd);

		fd = open("/proc/self/gid_map", O_WRONLY);
		if (write(fd, buf, strlen(buf)) < 0)
			warn("Cannot set gid_map in namespace");
		close(fd);
	}

	fd = open("/proc/sys/net/ipv4/ping_group_range", O_WRONLY);
	if (write(fd, "0 0", strlen("0 0")) < 0)
		warn("Cannot set ping_group_range, ICMP requests might fail");
	close(fd);

	shell = getenv("SHELL") ? getenv("SHELL") : "/bin/sh";
	if (strstr(shell, "/bash"))
		execve(shell, ((char *[]) { shell, "-l", NULL }), environ);
	else
		execve(shell, ((char *[]) { shell, NULL }), environ);

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

/**
 * pasta_ns_conf() - Set up loopback and tap interfaces in namespace as needed
 * @c:		Execution context
 */
void pasta_ns_conf(struct ctx *c)
{
	nl_link(1, 1 /* lo */, MAC_ZERO, 1, 0);

	if (c->pasta_conf_ns) {
		int prefix_len;

		nl_link(1, c->pasta_ifi, c->mac_guest, 1, c->mtu);

		if (c->v4) {
			prefix_len = __builtin_popcount(c->mask4);
			nl_addr(1, c->pasta_ifi, AF_INET, &c->addr4,
				&prefix_len, NULL);
			nl_route(1, c->pasta_ifi, AF_INET, &c->gw4);
		}

		if (c->v6) {
			prefix_len = 64;
			nl_addr(1, c->pasta_ifi, AF_INET6, &c->addr6,
				&prefix_len, NULL);
			nl_route(1, c->pasta_ifi, AF_INET6, &c->gw6);
		}
	} else {
		nl_link(1, c->pasta_ifi, c->mac_guest, 0, 0);
	}

	proto_update_l2_buf(c->mac_guest, NULL, NULL);
}

debug log:

solving bce30d4 ...
found bce30d4 in https://passt.top/passt

Code repositories for project(s) associated with this public inbox

	https://passt.top/passt

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for IMAP folder(s).