summaryrefslogtreecommitdiffstats
path: root/lib/librte_vhost/vhost_user/vhost-net-user.c
blob: df2bd6484f18a34d559ce5d3f678d39d4f4cafae (plain)
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
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <stdint.h>
#include <stdio.h>
#include <limits.h>
#include <stdlib.h>
#include <unistd.h>
#include <string.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/un.h>
#include <errno.h>
#include <pthread.h>

#include <rte_log.h>
#include <rte_virtio_net.h>

#include "fd_man.h"
#include "vhost-net-user.h"
#include "vhost-net.h"
#include "virtio-net-user.h"

#define MAX_VIRTIO_BACKLOG 128

static void vserver_new_vq_conn(int fd, void *data, int *remove);
static void vserver_message_handler(int fd, void *dat, int *remove);

struct connfd_ctx {
	struct vhost_server *vserver;
	uint32_t fh;
};

#define MAX_VHOST_SERVER 1024
struct _vhost_server {
	struct vhost_server *server[MAX_VHOST_SERVER];
	struct fdset fdset;
	int vserver_cnt;
	pthread_mutex_t server_mutex;
};

static struct _vhost_server g_vhost_server = {
	.fdset = {
		.fd = { [0 ... MAX_FDS - 1] = {-1, NULL, NULL, NULL, 0} },
		.fd_mutex = PTHREAD_MUTEX_INITIALIZER,
		.num = 0
	},
	.vserver_cnt = 0,
	.server_mutex = PTHREAD_MUTEX_INITIALIZER,
};

static const char *vhost_message_str[VHOST_USER_MAX] = {
	[VHOST_USER_NONE] = "VHOST_USER_NONE",
	[VHOST_USER_GET_FEATURES] = "VHOST_USER_GET_FEATURES",
	[VHOST_USER_SET_FEATURES] = "VHOST_USER_SET_FEATURES",
	[VHOST_USER_SET_OWNER] = "VHOST_USER_SET_OWNER",
	[VHOST_USER_RESET_OWNER] = "VHOST_USER_RESET_OWNER",
	[VHOST_USER_SET_MEM_TABLE] = "VHOST_USER_SET_MEM_TABLE",
	[VHOST_USER_SET_LOG_BASE] = "VHOST_USER_SET_LOG_BASE",
	[VHOST_USER_SET_LOG_FD] = "VHOST_USER_SET_LOG_FD",
	[VHOST_USER_SET_VRING_NUM] = "VHOST_USER_SET_VRING_NUM",
	[VHOST_USER_SET_VRING_ADDR] = "VHOST_USER_SET_VRING_ADDR",
	[VHOST_USER_SET_VRING_BASE] = "VHOST_USER_SET_VRING_BASE",
	[VHOST_USER_GET_VRING_BASE] = "VHOST_USER_GET_VRING_BASE",
	[VHOST_USER_SET_VRING_KICK] = "VHOST_USER_SET_VRING_KICK",
	[VHOST_USER_SET_VRING_CALL] = "VHOST_USER_SET_VRING_CALL",
	[VHOST_USER_SET_VRING_ERR]  = "VHOST_USER_SET_VRING_ERR",
	[VHOST_USER_GET_PROTOCOL_FEATURES]  = "VHOST_USER_GET_PROTOCOL_FEATURES",
	[VHOST_USER_SET_PROTOCOL_FEATURES]  = "VHOST_USER_SET_PROTOCOL_FEATURES",
	[VHOST_USER_GET_QUEUE_NUM]  = "VHOST_USER_GET_QUEUE_NUM",
	[VHOST_USER_SET_VRING_ENABLE]  = "VHOST_USER_SET_VRING_ENABLE",
	[VHOST_USER_SEND_RARP]  = "VHOST_USER_SEND_RARP",
};

/**
 * Create a unix domain socket, bind to path and listen for connection.
 * @return
 *  socket fd or -1 on failure
 */
static int
uds_socket(const char *path)
{
	struct sockaddr_un un;
	int sockfd;
	int ret;

	if (path == NULL)
		return -1;

	sockfd = socket(AF_UNIX, SOCK_STREAM, 0);
	if (sockfd < 0)
		return -1;
	RTE_LOG(INFO, VHOST_CONFIG, "socket created, fd:%d\n", sockfd);

	memset(&un, 0, sizeof(un));
	un.sun_family = AF_UNIX;
	snprintf(un.sun_path, sizeof(un.sun_path), "%s", path);
	ret = bind(sockfd, (struct sockaddr *)&un, sizeof(un));
	if (ret == -1) {
		RTE_LOG(ERR, VHOST_CONFIG, "fail to bind fd:%d, remove file:%s and try again.\n",
			sockfd, path);
		goto err;
	}
	RTE_LOG(INFO, VHOST_CONFIG, "bind to %s\n", path);

	ret = listen(sockfd, MAX_VIRTIO_BACKLOG);
	if (ret == -1)
		goto err;

	return sockfd;

err:
	close(sockfd);
	return -1;
}

/* return bytes# of read on success or negative val on failure. */
static int
read_fd_message(int sockfd, char *buf, int buflen, int *fds, int fd_num)
{
	struct iovec iov;
	struct msghdr msgh;
	size_t fdsize = fd_num * sizeof(int);
	char control[CMSG_SPACE(fdsize)];
	struct cmsghdr *cmsg;
	int ret;

	memset(&msgh, 0, sizeof(msgh));
	iov.iov_base = buf;
	iov.iov_len  = buflen;

	msgh.msg_iov = &iov;
	msgh.msg_iovlen = 1;
	msgh.msg_control = control;
	msgh.msg_controllen = sizeof(control);

	ret = recvmsg(sockfd, &msgh, 0);
	if (ret <= 0) {
		RTE_LOG(ERR, VHOST_CONFIG, "recvmsg failed\n");
		return ret;
	}

	if (msgh.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) {
		RTE_LOG(ERR, VHOST_CONFIG, "truncted msg\n");
		return -1;
	}

	for (cmsg = CMSG_FIRSTHDR(&msgh); cmsg != NULL;
		cmsg = CMSG_NXTHDR(&msgh, cmsg)) {
		if ((cmsg->cmsg_level == SOL_SOCKET) &&
			(cmsg->cmsg_type == SCM_RIGHTS)) {
			memcpy(fds, CMSG_DATA(cmsg), fdsize);
			break;
		}
	}

	return ret;
}

/* return bytes# of read on success or negative val on failure. */
static int
read_vhost_message(int sockfd, struct VhostUserMsg *msg)
{
	int ret;

	ret = read_fd_message(sockfd, (char *)msg, VHOST_USER_HDR_SIZE,
		msg->fds, VHOST_MEMORY_MAX_NREGIONS);
	if (ret <= 0)
		return ret;

	if (msg && msg->size) {
		if (msg->size > sizeof(msg->payload)) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"invalid msg size: %d\n", msg->size);
			return -1;
		}
		ret = read(sockfd, &msg->payload, msg->size);
		if (ret <= 0)
			return ret;
		if (ret != (int)msg->size) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"read control message failed\n");
			return -1;
		}
	}

	return ret;
}

static int
send_fd_message(int sockfd, char *buf, int buflen, int *fds, int fd_num)
{

	struct iovec iov;
	struct msghdr msgh;
	size_t fdsize = fd_num * sizeof(int);
	char control[CMSG_SPACE(fdsize)];
	struct cmsghdr *cmsg;
	int ret;

	memset(&msgh, 0, sizeof(msgh));
	iov.iov_base = buf;
	iov.iov_len = buflen;

	msgh.msg_iov = &iov;
	msgh.msg_iovlen = 1;

	if (fds && fd_num > 0) {
		msgh.msg_control = control;
		msgh.msg_controllen = sizeof(control);
		cmsg = CMSG_FIRSTHDR(&msgh);
		cmsg->cmsg_len = CMSG_LEN(fdsize);
		cmsg->cmsg_level = SOL_SOCKET;
		cmsg->cmsg_type = SCM_RIGHTS;
		memcpy(CMSG_DATA(cmsg), fds, fdsize);
	} else {
		msgh.msg_control = NULL;
		msgh.msg_controllen = 0;
	}

	do {
		ret = sendmsg(sockfd, &msgh, 0);
	} while (ret < 0 && errno == EINTR);

	if (ret < 0) {
		RTE_LOG(ERR, VHOST_CONFIG,  "sendmsg error\n");
		return ret;
	}

	return ret;
}

static int
send_vhost_message(int sockfd, struct VhostUserMsg *msg)
{
	int ret;

	if (!msg)
		return 0;

	msg->flags &= ~VHOST_USER_VERSION_MASK;
	msg->flags |= VHOST_USER_VERSION;
	msg->flags |= VHOST_USER_REPLY_MASK;

	ret = send_fd_message(sockfd, (char *)msg,
		VHOST_USER_HDR_SIZE + msg->size, NULL, 0);

	return ret;
}

/* call back when there is new virtio connection.  */
static void
vserver_new_vq_conn(int fd, void *dat, __rte_unused int *remove)
{
	struct vhost_server *vserver = (struct vhost_server *)dat;
	int conn_fd;
	struct connfd_ctx *ctx;
	int fh;
	struct vhost_device_ctx vdev_ctx = { (pid_t)0, 0 };
	unsigned int size;

	conn_fd = accept(fd, NULL, NULL);
	RTE_LOG(INFO, VHOST_CONFIG,
		"new virtio connection is %d\n", conn_fd);
	if (conn_fd < 0)
		return;

	ctx = calloc(1, sizeof(*ctx));
	if (ctx == NULL) {
		close(conn_fd);
		return;
	}

	fh = vhost_new_device(vdev_ctx);
	if (fh == -1) {
		free(ctx);
		close(conn_fd);
		return;
	}

	vdev_ctx.fh = fh;
	size = strnlen(vserver->path, PATH_MAX);
	vhost_set_ifname(vdev_ctx, vserver->path,
		size);

	RTE_LOG(INFO, VHOST_CONFIG, "new device, handle is %d\n", fh);

	ctx->vserver = vserver;
	ctx->fh = fh;
	fdset_add(&g_vhost_server.fdset,
		conn_fd, vserver_message_handler, NULL, ctx);
}

/* callback when there is message on the connfd */
static void
vserver_message_handler(int connfd, void *dat, int *remove)
{
	struct vhost_device_ctx ctx;
	struct connfd_ctx *cfd_ctx = (struct connfd_ctx *)dat;
	struct VhostUserMsg msg;
	uint64_t features;
	int ret;

	ctx.fh = cfd_ctx->fh;
	ret = read_vhost_message(connfd, &msg);
	if (ret <= 0 || msg.request >= VHOST_USER_MAX) {
		if (ret < 0)
			RTE_LOG(ERR, VHOST_CONFIG,
				"vhost read message failed\n");
		else if (ret == 0)
			RTE_LOG(INFO, VHOST_CONFIG,
				"vhost peer closed\n");
		else
			RTE_LOG(ERR, VHOST_CONFIG,
				"vhost read incorrect message\n");

		close(connfd);
		*remove = 1;
		free(cfd_ctx);
		vhost_destroy_device(ctx);

		return;
	}

	RTE_LOG(INFO, VHOST_CONFIG, "read message %s\n",
		vhost_message_str[msg.request]);
	switch (msg.request) {
	case VHOST_USER_GET_FEATURES:
		ret = vhost_get_features(ctx, &features);
		msg.payload.u64 = features;
		msg.size = sizeof(msg.payload.u64);
		send_vhost_message(connfd, &msg);
		break;
	case VHOST_USER_SET_FEATURES:
		features = msg.payload.u64;
		vhost_set_features(ctx, &features);
		break;

	case VHOST_USER_GET_PROTOCOL_FEATURES:
		msg.payload.u64 = VHOST_USER_PROTOCOL_FEATURES;
		msg.size = sizeof(msg.payload.u64);
		send_vhost_message(connfd, &msg);
		break;
	case VHOST_USER_SET_PROTOCOL_FEATURES:
		user_set_protocol_features(ctx, msg.payload.u64);
		break;

	case VHOST_USER_SET_OWNER:
		vhost_set_owner(ctx);
		break;
	case VHOST_USER_RESET_OWNER:
		vhost_reset_owner(ctx);
		break;

	case VHOST_USER_SET_MEM_TABLE:
		user_set_mem_table(ctx, &msg);
		break;

	case VHOST_USER_SET_LOG_BASE:
		user_set_log_base(ctx, &msg);

		/* it needs a reply */
		msg.size = sizeof(msg.payload.u64);
		send_vhost_message(connfd, &msg);
		break;
	case VHOST_USER_SET_LOG_FD:
		close(msg.fds[0]);
		RTE_LOG(INFO, VHOST_CONFIG, "not implemented.\n");
		break;

	case VHOST_USER_SET_VRING_NUM:
		vhost_set_vring_num(ctx, &msg.payload.state);
		break;
	case VHOST_USER_SET_VRING_ADDR:
		vhost_set_vring_addr(ctx, &msg.payload.addr);
		break;
	case VHOST_USER_SET_VRING_BASE:
		vhost_set_vring_base(ctx, &msg.payload.state);
		break;

	case VHOST_USER_GET_VRING_BASE:
		ret = user_get_vring_base(ctx, &msg.payload.state);
		msg.size = sizeof(msg.payload.state);
		send_vhost_message(connfd, &msg);
		break;

	case VHOST_USER_SET_VRING_KICK:
		user_set_vring_kick(ctx, &msg);
		break;
	case VHOST_USER_SET_VRING_CALL:
		user_set_vring_call(ctx, &msg);
		break;

	case VHOST_USER_SET_VRING_ERR:
		if (!(msg.payload.u64 & VHOST_USER_VRING_NOFD_MASK))
			close(msg.fds[0]);
		RTE_LOG(INFO, VHOST_CONFIG, "not implemented\n");
		break;

	case VHOST_USER_GET_QUEUE_NUM:
		msg.payload.u64 = VHOST_MAX_QUEUE_PAIRS;
		msg.size = sizeof(msg.payload.u64);
		send_vhost_message(connfd, &msg);
		break;

	case VHOST_USER_SET_VRING_ENABLE:
		user_set_vring_enable(ctx, &msg.payload.state);
		break;
	case VHOST_USER_SEND_RARP:
		user_send_rarp(ctx, &msg);
		break;

	default:
		break;

	}
}

/**
 * Creates and initialise the vhost server.
 */
int
rte_vhost_driver_register(const char *path)
{
	struct vhost_server *vserver;

	pthread_mutex_lock(&g_vhost_server.server_mutex);

	if (g_vhost_server.vserver_cnt == MAX_VHOST_SERVER) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"error: the number of servers reaches maximum\n");
		pthread_mutex_unlock(&g_vhost_server.server_mutex);
		return -1;
	}

	vserver = calloc(sizeof(struct vhost_server), 1);
	if (vserver == NULL) {
		pthread_mutex_unlock(&g_vhost_server.server_mutex);
		return -1;
	}

	vserver->listenfd = uds_socket(path);
	if (vserver->listenfd < 0) {
		free(vserver);
		pthread_mutex_unlock(&g_vhost_server.server_mutex);
		return -1;
	}

	vserver->path = strdup(path);

	fdset_add(&g_vhost_server.fdset, vserver->listenfd,
		vserver_new_vq_conn, NULL, vserver);

	g_vhost_server.server[g_vhost_server.vserver_cnt++] = vserver;
	pthread_mutex_unlock(&g_vhost_server.server_mutex);

	return 0;
}


/**
 * Unregister the specified vhost server
 */
int
rte_vhost_driver_unregister(const char *path)
{
	int i;
	int count;

	pthread_mutex_lock(&g_vhost_server.server_mutex);

	for (i = 0; i < g_vhost_server.vserver_cnt; i++) {
		if (!strcmp(g_vhost_server.server[i]->path, path)) {
			fdset_del(&g_vhost_server.fdset,
				g_vhost_server.server[i]->listenfd);

			close(g_vhost_server.server[i]->listenfd);
			free(g_vhost_server.server[i]->path);
			free(g_vhost_server.server[i]);

			unlink(path);

			count = --g_vhost_server.vserver_cnt;
			g_vhost_server.server[i] = g_vhost_server.server[count];
			g_vhost_server.server[count] = NULL;
			pthread_mutex_unlock(&g_vhost_server.server_mutex);

			return 0;
		}
	}
	pthread_mutex_unlock(&g_vhost_server.server_mutex);

	return -1;
}

int
rte_vhost_driver_session_start(void)
{
	fdset_event_dispatch(&g_vhost_server.fdset);
	return 0;
}