public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
blob 2a4e65a9e21a5750696279fcba63e65940926f53 8746 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
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
 
// 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
 *
 * passt.c - Daemon implementation
 *
 * Copyright (c) 2020-2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 *
 * Grab Ethernet frames from AF_UNIX socket (in "passt" mode) or tap device (in
 * "pasta" mode), 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) or to the tap device (typically,
 * created in a separate network namespace).
 */

#include <sys/epoll.h>
#include <fcntl.h>
#include <sys/mman.h>
#include <sys/resource.h>
#include <stdbool.h>
#include <stdlib.h>
#include <unistd.h>
#include <netdb.h>
#include <string.h>
#include <errno.h>
#include <time.h>
#include <syslog.h>
#include <sys/prctl.h>
#include <netinet/if_ether.h>

#include "util.h"
#include "passt.h"
#include "dhcp.h"
#include "dhcpv6.h"
#include "isolation.h"
#include "pcap.h"
#include "tap.h"
#include "conf.h"
#include "pasta.h"
#include "arch.h"
#include "log.h"

#define EPOLL_EVENTS		8

#define __TIMER_INTERVAL	MIN(TCP_TIMER_INTERVAL, UDP_TIMER_INTERVAL)
#define TIMER_INTERVAL		MIN(__TIMER_INTERVAL, ICMP_TIMER_INTERVAL)

char pkt_buf[PKT_BUF_BYTES]	__attribute__ ((aligned(PAGE_SIZE)));

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

/**
 * sock_handler() - Event handler for L4 sockets
 * @c:		Execution context
 * @ref:	epoll reference
 * @events:	epoll events
 * @now:	Current timestamp
 */
static void sock_handler(struct ctx *c, union epoll_ref ref,
			 uint32_t events, const struct timespec *now)
{
	trace("%s: %s packet from socket %i (events: 0x%08x)",
	      c->mode == MODE_PASST ? "passt" : "pasta",
	      IP_PROTO_STR(ref.r.proto), ref.r.s, events);

	if (!c->no_tcp && ref.r.proto == IPPROTO_TCP)
		tcp_sock_handler( c, ref, events, now);
	else if (!c->no_udp && ref.r.proto == IPPROTO_UDP)
		udp_sock_handler( c, ref, events, now);
	else if (!c->no_icmp &&
		 (ref.r.proto == IPPROTO_ICMP || ref.r.proto == IPPROTO_ICMPV6))
		icmp_sock_handler(c, ref, events, now);
}

/**
 * post_handler() - Run periodic and deferred tasks for L4 protocol handlers
 * @c:		Execution context
 * @now:	Current timestamp
 */
static void post_handler(struct ctx *c, const struct timespec *now)
{
#define CALL_PROTO_HANDLER(c, now, lc, uc)				\
	do {								\
		extern void						\
		lc ## _defer_handler (struct ctx *c)			\
		__attribute__ ((weak));					\
									\
		if (!c->no_ ## lc) {					\
			if (lc ## _defer_handler)			\
				lc ## _defer_handler(c);		\
									\
			if (timespec_diff_ms((now), &c->lc.timer_run)	\
			    >= uc ## _TIMER_INTERVAL) {			\
				lc ## _timer(c, now);			\
				c->lc.timer_run = *now;			\
			}						\
		} 							\
	} while (0)

	/* NOLINTNEXTLINE(bugprone-branch-clone): intervals can be the same */
	CALL_PROTO_HANDLER(c, now, tcp, TCP);
	/* NOLINTNEXTLINE(bugprone-branch-clone): intervals can be the same */
	CALL_PROTO_HANDLER(c, now, udp, UDP);
	/* NOLINTNEXTLINE(bugprone-branch-clone): intervals can be the same */
	CALL_PROTO_HANDLER(c, now, icmp, ICMP);

#undef CALL_PROTO_HANDLER
}

/**
 * timer_init() - Set initial timestamp for timer runs to current time
 * @c:		Execution context
 * @now:	Current timestamp
 */
static void timer_init(struct ctx *c, const struct timespec *now)
{
	c->tcp.timer_run = c->udp.timer_run = c->icmp.timer_run = *now;
}

/**
 * proto_update_l2_buf() - Update scatter-gather L2 buffers in protocol handlers
 * @eth_d:	Ethernet destination address, NULL if unchanged
 * @eth_s:	Ethernet source address, NULL if unchanged
 * @ip_da:	Pointer to IPv4 destination address, NULL if unchanged
 */
void proto_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s,
			 const struct in_addr *ip_da)
{
	tcp_update_l2_buf(eth_d, eth_s, ip_da);
	udp_update_l2_buf(eth_d, eth_s, ip_da);
}

/**
 * exit_handler() - Signal handler for SIGQUIT and SIGTERM
 * @unused:	Unused, handler deals with SIGQUIT and SIGTERM only
 *
 * TODO: After unsharing the PID namespace and forking, SIG_DFL for SIGTERM and
 * SIGQUIT unexpectedly doesn't cause the process to terminate, figure out why.
 *
 * #syscalls exit_group
 */
void exit_handler(int signal)
{
	(void)signal;

	exit(EXIT_SUCCESS);
}

/**
 * main() - Entry point and main loop
 * @argc:	Argument count
 * @argv:	Options, plus optional target PID for pasta mode
 *
 * Return: non-zero on failure
 *
 * #syscalls read write writev
 * #syscalls socket bind connect getsockopt setsockopt s390x:socketcall close
 * #syscalls recvfrom sendto shutdown
 * #syscalls armv6l:recv armv7l:recv ppc64le:recv
 * #syscalls armv6l:send armv7l:send ppc64le:send
 * #syscalls accept4|accept listen epoll_ctl epoll_wait|epoll_pwait epoll_pwait
 * #syscalls clock_gettime armv6l:clock_gettime64 armv7l:clock_gettime64
 */
int main(int argc, char **argv)
{
	int nfds, i, devnull_fd = -1, pidfile_fd = -1, quit_fd;
	struct epoll_event events[EPOLL_EVENTS];
	char *log_name, argv0[PATH_MAX], *name;
	struct ctx c = { 0 };
	struct rlimit limit;
	struct timespec now;
	struct sigaction sa;

	arch_avx2_exec(argv);

	//isolate_initial();

	c.pasta_netns_fd = c.fd_tap = c.fd_tap_listen = -1;

	sigemptyset(&sa.sa_mask);
	sa.sa_flags = 0;
	sa.sa_handler = exit_handler;
	sigaction(SIGTERM, &sa, NULL);
	sigaction(SIGQUIT, &sa, NULL);

	if (argc < 1)
		exit(EXIT_FAILURE);

	strncpy(argv0, argv[0], PATH_MAX - 1);
	name = basename(argv0);
	if (strstr(name, "pasta")) {
		sa.sa_handler = pasta_child_handler;
		if (sigaction(SIGCHLD, &sa, NULL) || signal(SIGPIPE, SIG_IGN)) {
			err("Couldn't install signal handlers");
			exit(EXIT_FAILURE);
		}

		c.mode = MODE_PASTA;
		log_name = "pasta";
	} else if (strstr(name, "passt")) {
		c.mode = MODE_PASST;
		log_name = "passt";
	} else {
		exit(EXIT_FAILURE);
	}

	madvise(pkt_buf, TAP_BUF_BYTES, MADV_HUGEPAGE);

	__openlog(log_name, 0, LOG_DAEMON);

	/* Meaning we don't know yet: log everything. LOG_EMERG is unused */
	__setlogmask(LOG_MASK(LOG_EMERG));

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

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

	conf(&c, argc, argv);
	trace_init(c.trace);

	if (c.stderr || isatty(fileno(stdout)))
		__openlog(log_name, LOG_PERROR, LOG_DAEMON);

	if (c.debug)
		__setlogmask(LOG_UPTO(LOG_DEBUG));
	else if (c.quiet)
		__setlogmask(LOG_UPTO(LOG_ERR));
	else
		__setlogmask(LOG_UPTO(LOG_INFO));

	quit_fd = pasta_netns_quit_init(&c);

	tap_sock_init(&c);

	clock_gettime(CLOCK_MONOTONIC, &now);

	if ((!c.no_udp && udp_init(&c)) || (!c.no_tcp && tcp_init(&c)))
		exit(EXIT_FAILURE);

	if (!c.no_icmp)
		icmp_init();

	proto_update_l2_buf(c.mac_guest, c.mac, &c.ip4.addr);

	if (c.ifi4 && !c.no_dhcp)
		dhcp_init();

	if (c.ifi6 && !c.no_dhcpv6)
		dhcpv6_init(&c);

	pcap_init(&c);

	if (!c.foreground) {
		if ((devnull_fd = open("/dev/null", O_RDWR | O_CLOEXEC)) < 0) {
			perror("/dev/null open");
			exit(EXIT_FAILURE);
		}
	}

	if (*c.pid_file) {
		if ((pidfile_fd = open(c.pid_file,
				       O_CREAT | O_TRUNC | O_WRONLY | O_CLOEXEC,
				       S_IRUSR | S_IWUSR)) < 0) {
			perror("PID file open");
			exit(EXIT_FAILURE);
		}
	}

#if 0
	if (isolate_prefork(&c)) {
		err("Failed to sandbox process, exiting\n");
		exit(EXIT_FAILURE);
	}
#endif

	if (!c.foreground)
		__daemon(pidfile_fd, devnull_fd);
	else
		write_pidfile(pidfile_fd, getpid());

	//isolate_postfork(&c);

	timer_init(&c, &now);

loop:
	/* NOLINTNEXTLINE(bugprone-branch-clone): intervals can be the same */
	/* cppcheck-suppress [duplicateValueTernary, unmatchedSuppression] */
	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++) {
		union epoll_ref ref = *((union epoll_ref *)&events[i].data.u64);
		int fd = events[i].data.fd;

		if (fd == c.fd_tap || fd == c.fd_tap_listen)
			tap_handler(&c, fd, events[i].events, &now);
		else if (fd == quit_fd)
			pasta_netns_quit_handler(&c, fd);
		else
			sock_handler(&c, ref, events[i].events, &now);
	}

	post_handler(&c, &now);

	goto loop;
}

debug log:

solving 2a4e65a ...
found 2a4e65a in https://archives.passt.top/passt-dev/20221117184938.2270462-7-rjones@redhat.com/
found 8b2c50d in https://passt.top/passt
preparing index
index prepared:
100644 8b2c50d78ff567d83b0c9d74bf6011c2e1ce7f11	passt.c

applying [1/1] https://archives.passt.top/passt-dev/20221117184938.2270462-7-rjones@redhat.com/
diff --git a/passt.c b/passt.c
index 8b2c50d..2a4e65a 100644

Checking patch passt.c...
Applied patch passt.c cleanly.

index at:
100644 2a4e65a9e21a5750696279fcba63e65940926f53	passt.c

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).