aboutsummaryrefslogtreecommitdiff
path: root/net/vhost-user.c
blob: 49c9a740c29229f474814f7e7c7083932bdb0abf (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
/*
 * vhost-user.c
 *
 * Copyright (c) 2013 Virtual Open Systems Sarl.
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#include "qemu/osdep.h"
#include "clients.h"
#include "net/vhost_net.h"
#include "net/vhost-user.h"
#include "hw/virtio/vhost-user.h"
#include "chardev/char-fe.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-net.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qemu/option.h"
#include "trace.h"

typedef struct NetVhostUserState {
    NetClientState nc;
    CharBackend chr; /* only queue index 0 */
    VhostUserState *vhost_user;
    VHostNetState *vhost_net;
    guint watch;
    uint64_t acked_features;
    bool started;
} NetVhostUserState;

VHostNetState *vhost_user_get_vhost_net(NetClientState *nc)
{
    NetVhostUserState *s = DO_UPCAST(NetVhostUserState, nc, nc);
    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_USER);
    return s->vhost_net;
}

uint64_t vhost_user_get_acked_features(NetClientState *nc)
{
    NetVhostUserState *s = DO_UPCAST(NetVhostUserState, nc, nc);
    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_USER);
    return s->acked_features;
}

static void vhost_user_stop(int queues, NetClientState *ncs[])
{
    NetVhostUserState *s;
    int i;

    for (i = 0; i < queues; i++) {
        assert(ncs[i]->info->type == NET_CLIENT_DRIVER_VHOST_USER);

        s = DO_UPCAST(NetVhostUserState, nc, ncs[i]);

        if (s->vhost_net) {
            /* save acked features */
            uint64_t features = vhost_net_get_acked_features(s->vhost_net);
            if (features) {
                s->acked_features = features;
            }
            vhost_net_cleanup(s->vhost_net);
        }
    }
}

static int vhost_user_start(int queues, NetClientState *ncs[],
                            VhostUserState *be)
{
    VhostNetOptions options;
    struct vhost_net *net = NULL;
    NetVhostUserState *s;
    int max_queues;
    int i;

    options.backend_type = VHOST_BACKEND_TYPE_USER;

    for (i = 0; i < queues; i++) {
        assert(ncs[i]->info->type == NET_CLIENT_DRIVER_VHOST_USER);

        s = DO_UPCAST(NetVhostUserState, nc, ncs[i]);

        options.net_backend = ncs[i];
        options.opaque      = be;
        options.busyloop_timeout = 0;
        net = vhost_net_init(&options);
        if (!net) {
            error_report("failed to init vhost_net for queue %d", i);
            goto err;
        }

        if (i == 0) {
            max_queues = vhost_net_get_max_queues(net);
            if (queues > max_queues) {
                error_report("you are asking more queues than supported: %d",
                             max_queues);
                goto err;
            }
        }

        if (s->vhost_net) {
            vhost_net_cleanup(s->vhost_net);
            g_free(s->vhost_net);
        }
        s->vhost_net = net;
    }

    return 0;

err:
    if (net) {
        vhost_net_cleanup(net);
        g_free(net);
    }
    vhost_user_stop(i, ncs);
    return -1;
}

static ssize_t vhost_user_receive(NetClientState *nc, const uint8_t *buf,
                                  size_t size)
{
    /* In case of RARP (message size is 60) notify backup to send a fake RARP.
       This fake RARP will be sent by backend only for guest
       without GUEST_ANNOUNCE capability.
     */
    if (size == 60) {
        NetVhostUserState *s = DO_UPCAST(NetVhostUserState, nc, nc);
        int r;
        static int display_rarp_failure = 1;
        char mac_addr[6];

        /* extract guest mac address from the RARP message */
        memcpy(mac_addr, &buf[6], 6);

        r = vhost_net_notify_migration_done(s->vhost_net, mac_addr);

        if ((r != 0) && (display_rarp_failure)) {
            fprintf(stderr,
                    "Vhost user backend fails to broadcast fake RARP\n");
            fflush(stderr);
            display_rarp_failure = 0;
        }
    }

    return size;
}

static void net_vhost_user_cleanup(NetClientState *nc)
{
    NetVhostUserState *s = DO_UPCAST(NetVhostUserState, nc, nc);

    if (s->vhost_net) {
        vhost_net_cleanup(s->vhost_net);
        g_free(s->vhost_net);
        s->vhost_net = NULL;
    }
    if (nc->queue_index == 0) {
        if (s->watch) {
            g_source_remove(s->watch);
            s->watch = 0;
        }
        qemu_chr_fe_deinit(&s->chr, true);
        if (s->vhost_user) {
            vhost_user_cleanup(s->vhost_user);
            g_free(s->vhost_user);
            s->vhost_user = NULL;
        }
    }

    qemu_purge_queued_packets(nc);
}

static int vhost_user_set_vnet_endianness(NetClientState *nc,
                                          bool enable)
{
    /* Nothing to do.  If the server supports
     * VHOST_USER_PROTOCOL_F_CROSS_ENDIAN, it will get the
     * vnet header endianness from there.  If it doesn't, negotiation
     * fails.
     */
    return 0;
}

static bool vhost_user_has_vnet_hdr(NetClientState *nc)
{
    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_USER);

    return true;
}

static bool vhost_user_has_ufo(NetClientState *nc)
{
    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_USER);

    return true;
}

static NetClientInfo net_vhost_user_info = {
        .type = NET_CLIENT_DRIVER_VHOST_USER,
        .size = sizeof(NetVhostUserState),
        .receive = vhost_user_receive,
        .cleanup = net_vhost_user_cleanup,
        .has_vnet_hdr = vhost_user_has_vnet_hdr,
        .has_ufo = vhost_user_has_ufo,
        .set_vnet_be = vhost_user_set_vnet_endianness,
        .set_vnet_le = vhost_user_set_vnet_endianness,
};

static gboolean net_vhost_user_watch(GIOChannel *chan, GIOCondition cond,
                                           void *opaque)
{
    NetVhostUserState *s = opaque;

    qemu_chr_fe_disconnect(&s->chr);

    return TRUE;
}

static void net_vhost_user_event(void *opaque, QEMUChrEvent event);

static void chr_closed_bh(void *opaque)
{
    const char *name = opaque;
    NetClientState *ncs[MAX_QUEUE_NUM];
    NetVhostUserState *s;
    Error *err = NULL;
    int queues, i;

    queues = qemu_find_net_clients_except(name, ncs,
                                          NET_CLIENT_DRIVER_NIC,
                                          MAX_QUEUE_NUM);
    assert(queues < MAX_QUEUE_NUM);

    s = DO_UPCAST(NetVhostUserState, nc, ncs[0]);

    for (i = queues -1; i >= 0; i--) {
        s = DO_UPCAST(NetVhostUserState, nc, ncs[i]);

        if (s->vhost_net) {
            s->acked_features = vhost_net_get_acked_features(s->vhost_net);
        }
    }

    qmp_set_link(name, false, &err);

    qemu_chr_fe_set_handlers(&s->chr, NULL, NULL, net_vhost_user_event,
                             NULL, opaque, NULL, true);

    if (err) {
        error_report_err(err);
    }
}

static void net_vhost_user_event(void *opaque, QEMUChrEvent event)
{
    const char *name = opaque;
    NetClientState *ncs[MAX_QUEUE_NUM];
    NetVhostUserState *s;
    Chardev *chr;
    Error *err = NULL;
    int queues;

    queues = qemu_find_net_clients_except(name, ncs,
                                          NET_CLIENT_DRIVER_NIC,
                                          MAX_QUEUE_NUM);
    assert(queues < MAX_QUEUE_NUM);

    s = DO_UPCAST(NetVhostUserState, nc, ncs[0]);
    chr = qemu_chr_fe_get_driver(&s->chr);
    trace_vhost_user_event(chr->label, event);
    switch (event) {
    case CHR_EVENT_OPENED:
        if (vhost_user_start(queues, ncs, s->vhost_user) < 0) {
            qemu_chr_fe_disconnect(&s->chr);
            return;
        }
        s->watch = qemu_chr_fe_add_watch(&s->chr, G_IO_HUP,
                                         net_vhost_user_watch, s);
        qmp_set_link(name, true, &err);
        s->started = true;
        break;
    case CHR_EVENT_CLOSED:
        /* a close event may happen during a read/write, but vhost
         * code assumes the vhost_dev remains setup, so delay the
         * stop & clear to idle.
         * FIXME: better handle failure in vhost code, remove bh
         */
        if (s->watch) {
            AioContext *ctx = qemu_get_current_aio_context();

            g_source_remove(s->watch);
            s->watch = 0;
            qemu_chr_fe_set_handlers(&s->chr, NULL, NULL, NULL, NULL,
                                     NULL, NULL, false);

            aio_bh_schedule_oneshot(ctx, chr_closed_bh, opaque);
        }
        break;
    case CHR_EVENT_BREAK:
    case CHR_EVENT_MUX_IN:
    case CHR_EVENT_MUX_OUT:
        /* Ignore */
        break;
    }

    if (err) {
        error_report_err(err);
    }
}

static int net_vhost_user_init(NetClientState *peer, const char *device,
                               const char *name, const char *chardev,
                               Chardev *chr, int queues)
{
    Error *err = NULL;
    NetClientState *nc, *nc0 = NULL;
    NetVhostUserState *s = NULL;
    VhostUserState *user;
    int i;
    NetdevVhostUserOptions *stored;

    assert(name);
    assert(queues > 0);

    user = g_new0(struct VhostUserState, 1);
    for (i = 0; i < queues; i++) {
        nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name);
        nc->info_str = g_strdup_printf("vhost-user%d to %s", i, chr->label);
        nc->queue_index = i;
        if (!nc0) {
            nc0 = nc;
            s = DO_UPCAST(NetVhostUserState, nc, nc);
            if (!qemu_chr_fe_init(&s->chr, chr, &err) ||
                !vhost_user_init(user, &s->chr, &err)) {
                error_report_err(err);
                goto err;
            }
        }
        s = DO_UPCAST(NetVhostUserState, nc, nc);
        s->vhost_user = user;
    }

    s = DO_UPCAST(NetVhostUserState, nc, nc0);
    do {
        if (qemu_chr_fe_wait_connected(&s->chr, &err) < 0) {
            error_report_err(err);
            goto err;
        }
        qemu_chr_fe_set_handlers(&s->chr, NULL, NULL,
                                 net_vhost_user_event, NULL, nc0->name, NULL,
                                 true);
    } while (!s->started);

    assert(s->vhost_net);

    /* Store startup parameters */
    nc0->stored_config = g_new0(NetdevInfo, 1);
    nc0->stored_config->type = NET_BACKEND_VHOST_USER;
    stored = &nc0->stored_config->u.vhost_user;

    stored->chardev = g_strdup(chardev);

    stored->has_queues = true;
    stored->queues = queues;

    return 0;

err:
    if (user) {
        vhost_user_cleanup(user);
        g_free(user);
        if (s) {
            s->vhost_user = NULL;
        }
    }
    if (nc0) {
        qemu_del_net_client(nc0);
    }

    return -1;
}

static Chardev *net_vhost_claim_chardev(
    const NetdevVhostUserOptions *opts, Error **errp)
{
    Chardev *chr = qemu_chr_find(opts->chardev);

    if (chr == NULL) {
        error_setg(errp, "chardev \"%s\" not found", opts->chardev);
        return NULL;
    }

    if (!qemu_chr_has_feature(chr, QEMU_CHAR_FEATURE_RECONNECTABLE)) {
        error_setg(errp, "chardev \"%s\" is not reconnectable",
                   opts->chardev);
        return NULL;
    }
    if (!qemu_chr_has_feature(chr, QEMU_CHAR_FEATURE_FD_PASS)) {
        error_setg(errp, "chardev \"%s\" does not support FD passing",
                   opts->chardev);
        return NULL;
    }

    return chr;
}

static int net_vhost_check_net(void *opaque, QemuOpts *opts, Error **errp)
{
    const char *name = opaque;
    const char *driver, *netdev;

    driver = qemu_opt_get(opts, "driver");
    netdev = qemu_opt_get(opts, "netdev");

    if (!driver || !netdev) {
        return 0;
    }

    if (strcmp(netdev, name) == 0 &&
        !g_str_has_prefix(driver, "virtio-net-")) {
        error_setg(errp, "vhost-user requires frontend driver virtio-net-*");
        return -1;
    }

    return 0;
}

int net_init_vhost_user(const Netdev *netdev, const char *name,
                        NetClientState *peer, Error **errp)
{
    int queues;
    const NetdevVhostUserOptions *vhost_user_opts;
    Chardev *chr;

    assert(netdev->type == NET_CLIENT_DRIVER_VHOST_USER);
    vhost_user_opts = &netdev->u.vhost_user;

    chr = net_vhost_claim_chardev(vhost_user_opts, errp);
    if (!chr) {
        return -1;
    }

    /* verify net frontend */
    if (qemu_opts_foreach(qemu_find_opts("device"), net_vhost_check_net,
                          (char *)name, errp)) {
        return -1;
    }

    queues = vhost_user_opts->has_queues ? vhost_user_opts->queues : 1;
    if (queues < 1 || queues > MAX_QUEUE_NUM) {
        error_setg(errp,
                   "vhost-user number of queues must be in range [1, %d]",
                   MAX_QUEUE_NUM);
        return -1;
    }

    return net_vhost_user_init(peer, "vhost_user", name,
                               vhost_user_opts->chardev, chr, queues);
}