public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
blob ec28e41997e8d1b241c7af70e2a57cfa9db9840e 7466 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
 
// 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
 *
 * icmp.c - ICMP/ICMPv6 echo proxy
 *
 * Copyright (c) 2021 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 */

#include <errno.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <netinet/in.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>
#include <stdio.h>
#include <limits.h>
#include <stdint.h>
#include <stddef.h>
#include <string.h>
#include <sys/epoll.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <unistd.h>
#include <time.h>

#include <linux/icmpv6.h>

#include "packet.h"
#include "util.h"
#include "passt.h"
#include "tap.h"
#include "log.h"
#include "siphash.h"
#include "inany.h"
#include "icmp.h"
#include "flow_table.h"

#define ICMP_ECHO_TIMEOUT	60 /* s, timeout for ICMP socket activity */
#define ICMP_NUM_IDS		(1U << 16)

/* Sides of a flow as we use them for ping streams */
#define	SOCKSIDE	0
#define	TAPSIDE		1

#define PINGF(idx)		(&(FLOW(idx)->ping))

/* Indexed by ICMP echo identifier */
static struct icmp_ping_flow *icmp_id_map[IP_VERSIONS][ICMP_NUM_IDS];

/**
 * icmp_sock_handler() - Handle new data from ICMP or ICMPv6 socket
 * @c:		Execution context
 * @ref:	epoll reference
 */
void icmp_sock_handler(const struct ctx *c, union epoll_ref ref)
{
	struct icmp_ping_flow *pingf = PINGF(ref.flowside.flow);
	union sockaddr_inany sr;
	socklen_t sl = sizeof(sr);
	char buf[USHRT_MAX];
	uint16_t seq;
	ssize_t n;

	if (c->no_icmp)
		return;

	ASSERT(pingf);

	n = recvfrom(ref.fd, buf, sizeof(buf), 0, &sr.sa, &sl);
	if (n < 0) {
		flow_err(pingf, "recvfrom() error: %s", strerror(errno));
		return;
	}

	if (pingf->f.type == FLOW_PING4) {
		struct icmphdr *ih4 = (struct icmphdr *)buf;

		if (sr.sa_family != AF_INET || (size_t)n < sizeof(*ih4) ||
		    ih4->type != ICMP_ECHOREPLY)
			goto unexpected;

		/* Adjust packet back to guest-side ID */
		ih4->un.echo.id = htons(pingf->id);
		seq = ntohs(ih4->un.echo.sequence);
	} else if (pingf->f.type == FLOW_PING6) {
		struct icmp6hdr *ih6 = (struct icmp6hdr *)buf;

		if (sr.sa_family != AF_INET6 || (size_t)n < sizeof(*ih6) ||
		    ih6->icmp6_type != ICMPV6_ECHO_REPLY)
			goto unexpected;

		/* Adjust packet back to guest-side ID */
		ih6->icmp6_identifier = htons(pingf->id);
		seq = ntohs(ih6->icmp6_sequence);
	} else {
		ASSERT(0);
	}

	/* In PASTA mode, we'll get any reply we send, discard them. */
	if (c->mode == MODE_PASTA) {
		if (pingf->seq == seq)
			return;

		pingf->seq = seq;
	}

	flow_dbg(pingf, "echo reply to tap, ID: %"PRIu16", seq: %"PRIu16,
		 pingf->id, seq);

	if (pingf->f.type == FLOW_PING4)
		tap_icmp4_send(c, sr.sa4.sin_addr, tap_ip4_daddr(c), buf, n);
	else if (pingf->f.type == FLOW_PING6)
		tap_icmp6_send(c, &sr.sa6.sin6_addr,
			       tap_ip6_daddr(c, &sr.sa6.sin6_addr), buf, n);
	return;

unexpected:
	flow_err(pingf, "Unexpected packet on ping socket");
}

/**
 * icmp_ping_close() - Close and clean up a ping flow
 * @c:		Execution context
 * @pingf:	ping flow entry to close
 */
static void icmp_ping_close(const struct ctx *c,
			    const struct icmp_ping_flow *pingf)
{
	uint16_t id = pingf->id;

	epoll_ctl(c->epollfd, EPOLL_CTL_DEL, pingf->sock, NULL);
	close(pingf->sock);

	if (pingf->f.type == FLOW_PING4)
		icmp_id_map[V4][id] = NULL;
	else
		icmp_id_map[V6][id] = NULL;
}

/**
 * icmp_ping_new() - Prepare a new ping socket for a new id
 * @c:		Execution context
 * @id_sock:	Socket fd and other information
 * @af:		Address family, AF_INET or AF_INET6
 * @id:		ICMP id for the new socket
 *
 * Return: Newly opened ping flow, or NULL on failure
 */
static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c,
					    struct icmp_ping_flow **id_sock,
					    sa_family_t af, uint16_t id)
{
	uint8_t flowtype = af == AF_INET ? FLOW_PING4 : FLOW_PING6;
	union epoll_ref ref = { .type = EPOLL_TYPE_PING };
	union flow *flow = flow_alloc();
	struct icmp_ping_flow *pingf;
	const void *bind_addr;
	const char *bind_if;

	if (!flow)
		return NULL;

	pingf = FLOW_START(flow, flowtype, ping, TAPSIDE);

	pingf->seq = -1;
	pingf->id = id;

	if (af == AF_INET) {
		bind_addr = &c->ip4.addr_out;
		bind_if = c->ip4.ifname_out;
	} else {
		bind_addr = &c->ip6.addr_out;
		bind_if = c->ip6.ifname_out;
	}

	ref.flowside = FLOW_SIDX(flow, SOCKSIDE);
	pingf->sock = sock_l4(c, af, flow_proto[flowtype], bind_addr, bind_if,
			      0, ref.data);

	if (pingf->sock < 0) {
		warn("Cannot open \"ping\" socket. You might need to:");
		warn("  sysctl -w net.ipv4.ping_group_range=\"0 2147483647\"");
		warn("...echo requests/replies will fail.");
		goto cancel;
	}

	if (pingf->sock > FD_REF_MAX)
		goto cancel;

	flow_dbg(pingf, "new socket %i for echo ID %"PRIu16, pingf->sock, id);

	*id_sock = pingf;

	return pingf;

cancel:
	flow_alloc_cancel(flow);
	return NULL;
}

/**
 * icmp_tap_handler() - Handle packets from tap
 * @c:		Execution context
 * @pif:	pif on which the packet is arriving
 * @af:		Address family, AF_INET or AF_INET6
 * @saddr:	Source address
 * @daddr:	Destination address
 * @p:		Packet pool, single packet with ICMP/ICMPv6 header
 * @now:	Current timestamp
 *
 * Return: count of consumed packets (always 1, even if malformed)
 */
int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af,
		     const void *saddr, const void *daddr,
		     const struct pool *p, const struct timespec *now)
{
	union sockaddr_inany sa = { .sa_family = af };
	const socklen_t sl = af == AF_INET ? sizeof(sa.sa4) : sizeof(sa.sa6);
	struct icmp_ping_flow *pingf, **id_sock;
	uint16_t id, seq;
	size_t plen;
	void *pkt;

	(void)saddr;
	ASSERT(pif == PIF_TAP);

	if (af == AF_INET) {
		const struct icmphdr *ih;

		if (!(pkt = packet_get(p, 0, 0, sizeof(*ih), &plen)))
			return 1;

		ih =  (struct icmphdr *)pkt;
		plen += sizeof(*ih);

		if (ih->type != ICMP_ECHO)
			return 1;

		id = ntohs(ih->un.echo.id);
		id_sock = &icmp_id_map[V4][id];
		seq = ntohs(ih->un.echo.sequence);
		sa.sa4.sin_addr = *(struct in_addr *)daddr;
	} else if (af == AF_INET6) {
		const struct icmp6hdr *ih;

		if (!(pkt = packet_get(p, 0, 0, sizeof(*ih), &plen)))
			return 1;

		ih = (struct icmp6hdr *)pkt;
		plen += sizeof(*ih);

		if (ih->icmp6_type != ICMPV6_ECHO_REQUEST)
			return 1;

		id = ntohs(ih->icmp6_identifier);
		id_sock = &icmp_id_map[V6][id];
		seq = ntohs(ih->icmp6_sequence);
		sa.sa6.sin6_addr = *(struct in6_addr *)daddr;
		sa.sa6.sin6_scope_id = c->ifi6;
	} else {
		ASSERT(0);
	}

	if (!(pingf = *id_sock))
		if (!(pingf = icmp_ping_new(c, id_sock, af, id)))
			return 1;

	pingf->ts = now->tv_sec;

	if (sendto(pingf->sock, pkt, plen, MSG_NOSIGNAL, &sa.sa, sl) < 0)
		flow_dbg(pingf, "failed to relay request to socket: %s",
			 strerror(errno));
	else
		flow_dbg(pingf,
			 "echo request to socket, ID: %"PRIu16", seq: %"PRIu16,
			 id, seq);

	return 1;
}

/**
 * icmp_ping_timer() - Handler for timed events related to a given flow
 * @c:		Execution context
 * @flow:	flow table entry to check for timeout
 * @now:	Current timestamp
 *
 * Return: true if the flow is ready to free, false otherwise
 */
bool icmp_ping_timer(const struct ctx *c, union flow *flow,
		     const struct timespec *now)
{
	const struct icmp_ping_flow *pingf = &flow->ping;

	if (now->tv_sec - pingf->ts <= ICMP_ECHO_TIMEOUT)
		return false;

	icmp_ping_close(c, pingf);
	return true;
}

debug log:

solving ec28e419 ...
found ec28e419 in https://archives.passt.top/passt-dev/20240229041534.2573559-4-david@gibson.dropbear.id.au/
found 63adafcf in https://archives.passt.top/passt-dev/20240229041534.2573559-3-david@gibson.dropbear.id.au/
found 1caf791d in https://archives.passt.top/passt-dev/20240229041534.2573559-2-david@gibson.dropbear.id.au/
found fb2fcafc in https://passt.top/passt
preparing index
index prepared:
100644 fb2fcafc8b8693bb71f49973979752291d9876ca	icmp.c

applying [1/3] https://archives.passt.top/passt-dev/20240229041534.2573559-2-david@gibson.dropbear.id.au/
diff --git a/icmp.c b/icmp.c
index fb2fcafc..1caf791d 100644


applying [2/3] https://archives.passt.top/passt-dev/20240229041534.2573559-3-david@gibson.dropbear.id.au/
diff --git a/icmp.c b/icmp.c
index 1caf791d..63adafcf 100644


applying [3/3] https://archives.passt.top/passt-dev/20240229041534.2573559-4-david@gibson.dropbear.id.au/
diff --git a/icmp.c b/icmp.c
index 63adafcf..ec28e419 100644

Checking patch icmp.c...
Applied patch icmp.c cleanly.
Checking patch icmp.c...
Applied patch icmp.c cleanly.
Checking patch icmp.c...
Applied patch icmp.c cleanly.

index at:
100644 ec28e41997e8d1b241c7af70e2a57cfa9db9840e	icmp.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).