aboutsummaryrefslogtreecommitdiff
path: root/hw/net/vhost_net.c
blob: 854997d9ba271eb9fc313493e09a4d1afba1fb49 (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
/*
 * vhost-net support
 *
 * Copyright Red Hat, Inc. 2010
 *
 * Authors:
 *  Michael S. Tsirkin <mst@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 */

#include "net/net.h"
#include "net/tap.h"

#include "hw/virtio/virtio-net.h"
#include "net/vhost_net.h"
#include "qemu/error-report.h"

#include "config.h"

#ifdef CONFIG_VHOST_NET
#include <linux/vhost.h>
#include <sys/socket.h>
#include <linux/kvm.h>
#include <fcntl.h>
#include <sys/ioctl.h>
#include <linux/virtio_ring.h>
#include <netpacket/packet.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <netinet/in.h>

#include <stdio.h>

#include "hw/virtio/vhost.h"
#include "hw/virtio/virtio-bus.h"

struct vhost_net {
    struct vhost_dev dev;
    struct vhost_virtqueue vqs[2];
    int backend;
    NetClientState *nc;
};

unsigned vhost_net_get_features(struct vhost_net *net, unsigned features)
{
    /* Clear features not supported by host kernel. */
    if (!(net->dev.features & (1 << VIRTIO_F_NOTIFY_ON_EMPTY))) {
        features &= ~(1 << VIRTIO_F_NOTIFY_ON_EMPTY);
    }
    if (!(net->dev.features & (1 << VIRTIO_RING_F_INDIRECT_DESC))) {
        features &= ~(1 << VIRTIO_RING_F_INDIRECT_DESC);
    }
    if (!(net->dev.features & (1 << VIRTIO_RING_F_EVENT_IDX))) {
        features &= ~(1 << VIRTIO_RING_F_EVENT_IDX);
    }
    if (!(net->dev.features & (1 << VIRTIO_NET_F_MRG_RXBUF))) {
        features &= ~(1 << VIRTIO_NET_F_MRG_RXBUF);
    }
    return features;
}

void vhost_net_ack_features(struct vhost_net *net, unsigned features)
{
    net->dev.acked_features = net->dev.backend_features;
    if (features & (1 << VIRTIO_F_NOTIFY_ON_EMPTY)) {
        net->dev.acked_features |= (1 << VIRTIO_F_NOTIFY_ON_EMPTY);
    }
    if (features & (1 << VIRTIO_RING_F_INDIRECT_DESC)) {
        net->dev.acked_features |= (1 << VIRTIO_RING_F_INDIRECT_DESC);
    }
    if (features & (1 << VIRTIO_RING_F_EVENT_IDX)) {
        net->dev.acked_features |= (1 << VIRTIO_RING_F_EVENT_IDX);
    }
    if (features & (1 << VIRTIO_NET_F_MRG_RXBUF)) {
        net->dev.acked_features |= (1 << VIRTIO_NET_F_MRG_RXBUF);
    }
}

static int vhost_net_get_fd(NetClientState *backend)
{
    switch (backend->info->type) {
    case NET_CLIENT_OPTIONS_KIND_TAP:
        return tap_get_fd(backend);
    default:
        fprintf(stderr, "vhost-net requires tap backend\n");
        return -EBADFD;
    }
}

struct vhost_net *vhost_net_init(NetClientState *backend, int devfd,
                                 bool force)
{
    int r;
    struct vhost_net *net = g_malloc(sizeof *net);
    if (!backend) {
        fprintf(stderr, "vhost-net requires backend to be setup\n");
        goto fail;
    }
    r = vhost_net_get_fd(backend);
    if (r < 0) {
        goto fail;
    }
    net->nc = backend;
    net->dev.backend_features = tap_has_vnet_hdr(backend) ? 0 :
        (1 << VHOST_NET_F_VIRTIO_NET_HDR);
    net->backend = r;

    net->dev.nvqs = 2;
    net->dev.vqs = net->vqs;

    r = vhost_dev_init(&net->dev, devfd, "/dev/vhost-net", force);
    if (r < 0) {
        goto fail;
    }
    if (!tap_has_vnet_hdr_len(backend,
                              sizeof(struct virtio_net_hdr_mrg_rxbuf))) {
        net->dev.features &= ~(1 << VIRTIO_NET_F_MRG_RXBUF);
    }
    if (~net->dev.features & net->dev.backend_features) {
        fprintf(stderr, "vhost lacks feature mask %" PRIu64 " for backend\n",
                (uint64_t)(~net->dev.features & net->dev.backend_features));
        vhost_dev_cleanup(&net->dev);
        goto fail;
    }

    /* Set sane init value. Override when guest acks. */
    vhost_net_ack_features(net, 0);
    return net;
fail:
    g_free(net);
    return NULL;
}

bool vhost_net_query(VHostNetState *net, VirtIODevice *dev)
{
    return vhost_dev_query(&net->dev, dev);
}

static int vhost_net_start_one(struct vhost_net *net,
                               VirtIODevice *dev,
                               int vq_index)
{
    struct vhost_vring_file file = { };
    int r;

    if (net->dev.started) {
        return 0;
    }

    net->dev.nvqs = 2;
    net->dev.vqs = net->vqs;
    net->dev.vq_index = vq_index;

    r = vhost_dev_enable_notifiers(&net->dev, dev);
    if (r < 0) {
        goto fail_notifiers;
    }

    r = vhost_dev_start(&net->dev, dev);
    if (r < 0) {
        goto fail_start;
    }

    net->nc->info->poll(net->nc, false);
    qemu_set_fd_handler(net->backend, NULL, NULL, NULL);
    file.fd = net->backend;
    for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
        r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file);
        if (r < 0) {
            r = -errno;
            goto fail;
        }
    }
    return 0;
fail:
    file.fd = -1;
    while (file.index-- > 0) {
        int r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file);
        assert(r >= 0);
    }
    net->nc->info->poll(net->nc, true);
    vhost_dev_stop(&net->dev, dev);
fail_start:
    vhost_dev_disable_notifiers(&net->dev, dev);
fail_notifiers:
    return r;
}

static void vhost_net_stop_one(struct vhost_net *net,
                               VirtIODevice *dev)
{
    struct vhost_vring_file file = { .fd = -1 };

    if (!net->dev.started) {
        return;
    }

    for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
        int r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file);
        assert(r >= 0);
    }
    net->nc->info->poll(net->nc, true);
    vhost_dev_stop(&net->dev, dev);
    vhost_dev_disable_notifiers(&net->dev, dev);
}

int vhost_net_start(VirtIODevice *dev, NetClientState *ncs,
                    int total_queues)
{
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(dev)));
    VirtioBusState *vbus = VIRTIO_BUS(qbus);
    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
    int r, i = 0;

    if (!k->set_guest_notifiers) {
        error_report("binding does not support guest notifiers");
        r = -ENOSYS;
        goto err;
    }

    for (i = 0; i < total_queues; i++) {
        r = vhost_net_start_one(tap_get_vhost_net(ncs[i].peer), dev, i * 2);

        if (r < 0) {
            goto err;
        }
    }

    r = k->set_guest_notifiers(qbus->parent, total_queues * 2, true);
    if (r < 0) {
        error_report("Error binding guest notifier: %d", -r);
        goto err;
    }

    return 0;

err:
    while (--i >= 0) {
        vhost_net_stop_one(tap_get_vhost_net(ncs[i].peer), dev);
    }
    return r;
}

void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs,
                    int total_queues)
{
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(dev)));
    VirtioBusState *vbus = VIRTIO_BUS(qbus);
    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
    int i, r;

    r = k->set_guest_notifiers(qbus->parent, total_queues * 2, false);
    if (r < 0) {
        fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", r);
        fflush(stderr);
    }
    assert(r >= 0);

    for (i = 0; i < total_queues; i++) {
        vhost_net_stop_one(tap_get_vhost_net(ncs[i].peer), dev);
    }
}

void vhost_net_cleanup(struct vhost_net *net)
{
    vhost_dev_cleanup(&net->dev);
    g_free(net);
}

bool vhost_net_virtqueue_pending(VHostNetState *net, int idx)
{
    return vhost_virtqueue_pending(&net->dev, idx);
}

void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
                              int idx, bool mask)
{
    vhost_virtqueue_mask(&net->dev, dev, idx, mask);
}
#else
struct vhost_net *vhost_net_init(NetClientState *backend, int devfd,
                                 bool force)
{
    error_report("vhost-net support is not compiled in");
    return NULL;
}

bool vhost_net_query(VHostNetState *net, VirtIODevice *dev)
{
    return false;
}

int vhost_net_start(VirtIODevice *dev,
                    NetClientState *ncs,
                    int total_queues)
{
    return -ENOSYS;
}
void vhost_net_stop(VirtIODevice *dev,
                    NetClientState *ncs,
                    int total_queues)
{
}

void vhost_net_cleanup(struct vhost_net *net)
{
}

unsigned vhost_net_get_features(struct vhost_net *net, unsigned features)
{
    return features;
}
void vhost_net_ack_features(struct vhost_net *net, unsigned features)
{
}

bool vhost_net_virtqueue_pending(VHostNetState *net, int idx)
{
    return false;
}

void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
                              int idx, bool mask)
{
}
#endif