aboutsummaryrefslogtreecommitdiff
path: root/hw/block/vhost-user-blk.c
blob: f5e9682703f3433c4b363003f90f09e1a1b0e509 (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
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
/*
 * vhost-user-blk host device
 *
 * Copyright(C) 2017 Intel Corporation.
 *
 * Authors:
 *  Changpeng Liu <changpeng.liu@intel.com>
 *
 * Largely based on the "vhost-user-scsi.c" and "vhost-scsi.c" implemented by:
 * Felipe Franciosi <felipe@nutanix.com>
 * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
 * Nicholas Bellinger <nab@risingtidesystems.com>
 *
 * This work is licensed under the terms of the GNU LGPL, version 2 or later.
 * See the COPYING.LIB file in the top-level directory.
 *
 */

#include "qemu/osdep.h"
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "qemu/cutils.h"
#include "hw/qdev-core.h"
#include "hw/qdev-properties.h"
#include "hw/qdev-properties-system.h"
#include "hw/virtio/vhost.h"
#include "hw/virtio/vhost-user-blk.h"
#include "hw/virtio/virtio.h"
#include "hw/virtio/virtio-bus.h"
#include "hw/virtio/virtio-access.h"
#include "sysemu/sysemu.h"
#include "sysemu/runstate.h"

static const int user_feature_bits[] = {
    VIRTIO_BLK_F_SIZE_MAX,
    VIRTIO_BLK_F_SEG_MAX,
    VIRTIO_BLK_F_GEOMETRY,
    VIRTIO_BLK_F_BLK_SIZE,
    VIRTIO_BLK_F_TOPOLOGY,
    VIRTIO_BLK_F_MQ,
    VIRTIO_BLK_F_RO,
    VIRTIO_BLK_F_FLUSH,
    VIRTIO_BLK_F_CONFIG_WCE,
    VIRTIO_BLK_F_DISCARD,
    VIRTIO_BLK_F_WRITE_ZEROES,
    VIRTIO_F_VERSION_1,
    VIRTIO_RING_F_INDIRECT_DESC,
    VIRTIO_RING_F_EVENT_IDX,
    VIRTIO_F_NOTIFY_ON_EMPTY,
    VHOST_INVALID_FEATURE_BIT
};

static void vhost_user_blk_update_config(VirtIODevice *vdev, uint8_t *config)
{
    VHostUserBlk *s = VHOST_USER_BLK(vdev);

    /* Our num_queues overrides the device backend */
    virtio_stw_p(vdev, &s->blkcfg.num_queues, s->num_queues);

    memcpy(config, &s->blkcfg, sizeof(struct virtio_blk_config));
}

static void vhost_user_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
{
    VHostUserBlk *s = VHOST_USER_BLK(vdev);
    struct virtio_blk_config *blkcfg = (struct virtio_blk_config *)config;
    int ret;

    if (blkcfg->wce == s->blkcfg.wce) {
        return;
    }

    ret = vhost_dev_set_config(&s->dev, &blkcfg->wce,
                               offsetof(struct virtio_blk_config, wce),
                               sizeof(blkcfg->wce),
                               VHOST_SET_CONFIG_TYPE_MASTER);
    if (ret) {
        error_report("set device config space failed");
        return;
    }

    s->blkcfg.wce = blkcfg->wce;
}

static int vhost_user_blk_handle_config_change(struct vhost_dev *dev)
{
    int ret;
    struct virtio_blk_config blkcfg;
    VHostUserBlk *s = VHOST_USER_BLK(dev->vdev);

    ret = vhost_dev_get_config(dev, (uint8_t *)&blkcfg,
                               sizeof(struct virtio_blk_config));
    if (ret < 0) {
        error_report("get config space failed");
        return -1;
    }

    /* valid for resize only */
    if (blkcfg.capacity != s->blkcfg.capacity) {
        s->blkcfg.capacity = blkcfg.capacity;
        memcpy(dev->vdev->config, &s->blkcfg, sizeof(struct virtio_blk_config));
        virtio_notify_config(dev->vdev);
    }

    return 0;
}

const VhostDevConfigOps blk_ops = {
    .vhost_dev_config_notifier = vhost_user_blk_handle_config_change,
};

static int vhost_user_blk_start(VirtIODevice *vdev)
{
    VHostUserBlk *s = VHOST_USER_BLK(vdev);
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
    int i, ret;

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

    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
    if (ret < 0) {
        error_report("Error enabling host notifiers: %d", -ret);
        return ret;
    }

    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
    if (ret < 0) {
        error_report("Error binding guest notifier: %d", -ret);
        goto err_host_notifiers;
    }

    s->dev.acked_features = vdev->guest_features;

    ret = vhost_dev_prepare_inflight(&s->dev, vdev);
    if (ret < 0) {
        error_report("Error set inflight format: %d", -ret);
        goto err_guest_notifiers;
    }

    if (!s->inflight->addr) {
        ret = vhost_dev_get_inflight(&s->dev, s->queue_size, s->inflight);
        if (ret < 0) {
            error_report("Error get inflight: %d", -ret);
            goto err_guest_notifiers;
        }
    }

    ret = vhost_dev_set_inflight(&s->dev, s->inflight);
    if (ret < 0) {
        error_report("Error set inflight: %d", -ret);
        goto err_guest_notifiers;
    }

    ret = vhost_dev_start(&s->dev, vdev);
    if (ret < 0) {
        error_report("Error starting vhost: %d", -ret);
        goto err_guest_notifiers;
    }
    s->started_vu = true;

    /* guest_notifier_mask/pending not used yet, so just unmask
     * everything here. virtio-pci will do the right thing by
     * enabling/disabling irqfd.
     */
    for (i = 0; i < s->dev.nvqs; i++) {
        vhost_virtqueue_mask(&s->dev, vdev, i, false);
    }

    return ret;

err_guest_notifiers:
    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
err_host_notifiers:
    vhost_dev_disable_notifiers(&s->dev, vdev);
    return ret;
}

static void vhost_user_blk_stop(VirtIODevice *vdev)
{
    VHostUserBlk *s = VHOST_USER_BLK(vdev);
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
    int ret;

    if (!s->started_vu) {
        return;
    }
    s->started_vu = false;

    if (!k->set_guest_notifiers) {
        return;
    }

    vhost_dev_stop(&s->dev, vdev);

    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
    if (ret < 0) {
        error_report("vhost guest notifier cleanup failed: %d", ret);
        return;
    }

    vhost_dev_disable_notifiers(&s->dev, vdev);
}

static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status)
{
    VHostUserBlk *s = VHOST_USER_BLK(vdev);
    bool should_start = virtio_device_started(vdev, status);
    int ret;

    if (!vdev->vm_running) {
        should_start = false;
    }

    if (!s->connected) {
        return;
    }

    if (s->dev.started == should_start) {
        return;
    }

    if (should_start) {
        ret = vhost_user_blk_start(vdev);
        if (ret < 0) {
            error_report("vhost-user-blk: vhost start failed: %s",
                         strerror(-ret));
            qemu_chr_fe_disconnect(&s->chardev);
        }
    } else {
        vhost_user_blk_stop(vdev);
    }

}

static uint64_t vhost_user_blk_get_features(VirtIODevice *vdev,
                                            uint64_t features,
                                            Error **errp)
{
    VHostUserBlk *s = VHOST_USER_BLK(vdev);

    /* Turn on pre-defined features */
    virtio_add_feature(&features, VIRTIO_BLK_F_SEG_MAX);
    virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
    virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
    virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
    virtio_add_feature(&features, VIRTIO_BLK_F_FLUSH);
    virtio_add_feature(&features, VIRTIO_BLK_F_RO);
    virtio_add_feature(&features, VIRTIO_BLK_F_DISCARD);
    virtio_add_feature(&features, VIRTIO_BLK_F_WRITE_ZEROES);

    if (s->config_wce) {
        virtio_add_feature(&features, VIRTIO_BLK_F_CONFIG_WCE);
    }
    if (s->num_queues > 1) {
        virtio_add_feature(&features, VIRTIO_BLK_F_MQ);
    }

    return vhost_get_features(&s->dev, user_feature_bits, features);
}

static void vhost_user_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
    VHostUserBlk *s = VHOST_USER_BLK(vdev);
    int i, ret;

    if (!vdev->start_on_kick) {
        return;
    }

    if (!s->connected) {
        return;
    }

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

    /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
     * vhost here instead of waiting for .set_status().
     */
    ret = vhost_user_blk_start(vdev);
    if (ret < 0) {
        error_report("vhost-user-blk: vhost start failed: %s",
                     strerror(-ret));
        qemu_chr_fe_disconnect(&s->chardev);
        return;
    }

    /* Kick right away to begin processing requests already in vring */
    for (i = 0; i < s->dev.nvqs; i++) {
        VirtQueue *kick_vq = virtio_get_queue(vdev, i);

        if (!virtio_queue_get_desc_addr(vdev, i)) {
            continue;
        }
        event_notifier_set(virtio_queue_get_host_notifier(kick_vq));
    }
}

static void vhost_user_blk_reset(VirtIODevice *vdev)
{
    VHostUserBlk *s = VHOST_USER_BLK(vdev);

    vhost_dev_free_inflight(s->inflight);
}

static int vhost_user_blk_connect(DeviceState *dev)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
    VHostUserBlk *s = VHOST_USER_BLK(vdev);
    int ret = 0;

    if (s->connected) {
        return 0;
    }
    s->connected = true;

    s->dev.nvqs = s->num_queues;
    s->dev.vqs = s->vhost_vqs;
    s->dev.vq_index = 0;
    s->dev.backend_features = 0;

    vhost_dev_set_config_notifier(&s->dev, &blk_ops);

    ret = vhost_dev_init(&s->dev, &s->vhost_user, VHOST_BACKEND_TYPE_USER, 0);
    if (ret < 0) {
        error_report("vhost-user-blk: vhost initialization failed: %s",
                     strerror(-ret));
        return ret;
    }

    /* restore vhost state */
    if (virtio_device_started(vdev, vdev->status)) {
        ret = vhost_user_blk_start(vdev);
        if (ret < 0) {
            error_report("vhost-user-blk: vhost start failed: %s",
                         strerror(-ret));
            return ret;
        }
    }

    return 0;
}

static void vhost_user_blk_disconnect(DeviceState *dev)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
    VHostUserBlk *s = VHOST_USER_BLK(vdev);

    if (!s->connected) {
        return;
    }
    s->connected = false;

    vhost_user_blk_stop(vdev);

    vhost_dev_cleanup(&s->dev);
}

static void vhost_user_blk_event(void *opaque, QEMUChrEvent event,
                                 bool realized);

static void vhost_user_blk_event_realize(void *opaque, QEMUChrEvent event)
{
    vhost_user_blk_event(opaque, event, false);
}

static void vhost_user_blk_event_oper(void *opaque, QEMUChrEvent event)
{
    vhost_user_blk_event(opaque, event, true);
}

static void vhost_user_blk_chr_closed_bh(void *opaque)
{
    DeviceState *dev = opaque;
    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
    VHostUserBlk *s = VHOST_USER_BLK(vdev);

    vhost_user_blk_disconnect(dev);
    qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL,
            vhost_user_blk_event_oper, NULL, opaque, NULL, true);
}

static void vhost_user_blk_event(void *opaque, QEMUChrEvent event,
                                 bool realized)
{
    DeviceState *dev = opaque;
    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
    VHostUserBlk *s = VHOST_USER_BLK(vdev);

    switch (event) {
    case CHR_EVENT_OPENED:
        if (vhost_user_blk_connect(dev) < 0) {
            qemu_chr_fe_disconnect(&s->chardev);
            return;
        }
        break;
    case CHR_EVENT_CLOSED:
        /*
         * Closing the connection should happen differently on device
         * initialization and operation stages.
         * On initalization, we want to re-start vhost_dev initialization
         * from the very beginning right away when the connection is closed,
         * so we clean up vhost_dev on each connection closing.
         * On operation, we want to postpone vhost_dev cleanup to let the
         * other code perform its own cleanup sequence using vhost_dev data
         * (e.g. vhost_dev_set_log).
         */
        if (realized && !runstate_check(RUN_STATE_SHUTDOWN)) {
            /*
             * A close event may happen during a read/write, but vhost
             * code assumes the vhost_dev remains setup, so delay the
             * stop & clear.
             */
            AioContext *ctx = qemu_get_current_aio_context();

            qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, NULL, NULL,
                    NULL, NULL, false);
            aio_bh_schedule_oneshot(ctx, vhost_user_blk_chr_closed_bh, opaque);

            /*
             * Move vhost device to the stopped state. The vhost-user device
             * will be clean up and disconnected in BH. This can be useful in
             * the vhost migration code. If disconnect was caught there is an
             * option for the general vhost code to get the dev state without
             * knowing its type (in this case vhost-user).
             */
            s->dev.started = false;
        } else {
            vhost_user_blk_disconnect(dev);
        }
        break;
    case CHR_EVENT_BREAK:
    case CHR_EVENT_MUX_IN:
    case CHR_EVENT_MUX_OUT:
        /* Ignore */
        break;
    }
}

static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
    VHostUserBlk *s = VHOST_USER_BLK(vdev);
    Error *err = NULL;
    int i, ret;

    if (!s->chardev.chr) {
        error_setg(errp, "vhost-user-blk: chardev is mandatory");
        return;
    }

    if (s->num_queues == VHOST_USER_BLK_AUTO_NUM_QUEUES) {
        s->num_queues = 1;
    }
    if (!s->num_queues || s->num_queues > VIRTIO_QUEUE_MAX) {
        error_setg(errp, "vhost-user-blk: invalid number of IO queues");
        return;
    }

    if (!s->queue_size) {
        error_setg(errp, "vhost-user-blk: queue size must be non-zero");
        return;
    }
    if (s->queue_size > VIRTQUEUE_MAX_SIZE) {
        error_setg(errp, "vhost-user-blk: queue size must not exceed %d",
                   VIRTQUEUE_MAX_SIZE);
        return;
    }

    if (!vhost_user_init(&s->vhost_user, &s->chardev, errp)) {
        return;
    }

    virtio_init(vdev, "virtio-blk", VIRTIO_ID_BLOCK,
                sizeof(struct virtio_blk_config));

    s->virtqs = g_new(VirtQueue *, s->num_queues);
    for (i = 0; i < s->num_queues; i++) {
        s->virtqs[i] = virtio_add_queue(vdev, s->queue_size,
                                        vhost_user_blk_handle_output);
    }

    s->inflight = g_new0(struct vhost_inflight, 1);
    s->vhost_vqs = g_new0(struct vhost_virtqueue, s->num_queues);
    s->connected = false;

    qemu_chr_fe_set_handlers(&s->chardev,  NULL, NULL,
                             vhost_user_blk_event_realize, NULL, (void *)dev,
                             NULL, true);

reconnect:
    if (qemu_chr_fe_wait_connected(&s->chardev, &err) < 0) {
        error_report_err(err);
        goto virtio_err;
    }

    /* check whether vhost_user_blk_connect() failed or not */
    if (!s->connected) {
        goto reconnect;
    }

    ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg,
                               sizeof(struct virtio_blk_config));
    if (ret < 0) {
        error_report("vhost-user-blk: get block config failed");
        goto reconnect;
    }

    /* we're fully initialized, now we can operate, so change the handler */
    qemu_chr_fe_set_handlers(&s->chardev,  NULL, NULL,
                             vhost_user_blk_event_oper, NULL, (void *)dev,
                             NULL, true);
    return;

virtio_err:
    g_free(s->vhost_vqs);
    s->vhost_vqs = NULL;
    g_free(s->inflight);
    s->inflight = NULL;
    for (i = 0; i < s->num_queues; i++) {
        virtio_delete_queue(s->virtqs[i]);
    }
    g_free(s->virtqs);
    virtio_cleanup(vdev);
    vhost_user_cleanup(&s->vhost_user);
}

static void vhost_user_blk_device_unrealize(DeviceState *dev)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
    VHostUserBlk *s = VHOST_USER_BLK(dev);
    int i;

    virtio_set_status(vdev, 0);
    qemu_chr_fe_set_handlers(&s->chardev,  NULL, NULL, NULL,
                             NULL, NULL, NULL, false);
    vhost_dev_cleanup(&s->dev);
    vhost_dev_free_inflight(s->inflight);
    g_free(s->vhost_vqs);
    s->vhost_vqs = NULL;
    g_free(s->inflight);
    s->inflight = NULL;

    for (i = 0; i < s->num_queues; i++) {
        virtio_delete_queue(s->virtqs[i]);
    }
    g_free(s->virtqs);
    virtio_cleanup(vdev);
    vhost_user_cleanup(&s->vhost_user);
}

static void vhost_user_blk_instance_init(Object *obj)
{
    VHostUserBlk *s = VHOST_USER_BLK(obj);

    device_add_bootindex_property(obj, &s->bootindex, "bootindex",
                                  "/disk@0,0", DEVICE(obj));
}

static const VMStateDescription vmstate_vhost_user_blk = {
    .name = "vhost-user-blk",
    .minimum_version_id = 1,
    .version_id = 1,
    .fields = (VMStateField[]) {
        VMSTATE_VIRTIO_DEVICE,
        VMSTATE_END_OF_LIST()
    },
};

static Property vhost_user_blk_properties[] = {
    DEFINE_PROP_CHR("chardev", VHostUserBlk, chardev),
    DEFINE_PROP_UINT16("num-queues", VHostUserBlk, num_queues,
                       VHOST_USER_BLK_AUTO_NUM_QUEUES),
    DEFINE_PROP_UINT32("queue-size", VHostUserBlk, queue_size, 128),
    DEFINE_PROP_BIT("config-wce", VHostUserBlk, config_wce, 0, true),
    DEFINE_PROP_END_OF_LIST(),
};

static void vhost_user_blk_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);

    device_class_set_props(dc, vhost_user_blk_properties);
    dc->vmsd = &vmstate_vhost_user_blk;
    set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
    vdc->realize = vhost_user_blk_device_realize;
    vdc->unrealize = vhost_user_blk_device_unrealize;
    vdc->get_config = vhost_user_blk_update_config;
    vdc->set_config = vhost_user_blk_set_config;
    vdc->get_features = vhost_user_blk_get_features;
    vdc->set_status = vhost_user_blk_set_status;
    vdc->reset = vhost_user_blk_reset;
}

static const TypeInfo vhost_user_blk_info = {
    .name = TYPE_VHOST_USER_BLK,
    .parent = TYPE_VIRTIO_DEVICE,
    .instance_size = sizeof(VHostUserBlk),
    .instance_init = vhost_user_blk_instance_init,
    .class_init = vhost_user_blk_class_init,
};

static void virtio_register_types(void)
{
    type_register_static(&vhost_user_blk_info);
}

type_init(virtio_register_types)