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
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
|
/*
* Sharing QEMU block devices via vhost-user protocal
*
* Parts of the code based on nbd/server.c.
*
* Copyright (c) Coiby Xu <coiby.xu@gmail.com>.
* Copyright (c) 2020 Red Hat, Inc.
*
* 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 "block/block.h"
#include "vhost-user-blk-server.h"
#include "qapi/error.h"
#include "qom/object_interfaces.h"
#include "sysemu/block-backend.h"
#include "util/block-helpers.h"
enum {
VHOST_USER_BLK_MAX_QUEUES = 1,
};
struct virtio_blk_inhdr {
unsigned char status;
};
typedef struct VuBlockReq {
VuVirtqElement *elem;
int64_t sector_num;
size_t size;
struct virtio_blk_inhdr *in;
struct virtio_blk_outhdr out;
VuServer *server;
struct VuVirtq *vq;
} VuBlockReq;
static void vu_block_req_complete(VuBlockReq *req)
{
VuDev *vu_dev = &req->server->vu_dev;
/* IO size with 1 extra status byte */
vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1);
vu_queue_notify(vu_dev, req->vq);
if (req->elem) {
free(req->elem);
}
g_free(req);
}
static VuBlockDev *get_vu_block_device_by_server(VuServer *server)
{
return container_of(server, VuBlockDev, vu_server);
}
static int coroutine_fn
vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov,
uint32_t iovcnt, uint32_t type)
{
struct virtio_blk_discard_write_zeroes desc;
ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc));
if (unlikely(size != sizeof(desc))) {
error_report("Invalid size %zd, expect %zu", size, sizeof(desc));
return -EINVAL;
}
VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server);
uint64_t range[2] = { le64_to_cpu(desc.sector) << 9,
le32_to_cpu(desc.num_sectors) << 9 };
if (type == VIRTIO_BLK_T_DISCARD) {
if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) {
return 0;
}
} else if (type == VIRTIO_BLK_T_WRITE_ZEROES) {
if (blk_co_pwrite_zeroes(vdev_blk->backend,
range[0], range[1], 0) == 0) {
return 0;
}
}
return -EINVAL;
}
static void coroutine_fn vu_block_flush(VuBlockReq *req)
{
VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server);
BlockBackend *backend = vdev_blk->backend;
blk_co_flush(backend);
}
struct req_data {
VuServer *server;
VuVirtq *vq;
VuVirtqElement *elem;
};
static void coroutine_fn vu_block_virtio_process_req(void *opaque)
{
struct req_data *data = opaque;
VuServer *server = data->server;
VuVirtq *vq = data->vq;
VuVirtqElement *elem = data->elem;
uint32_t type;
VuBlockReq *req;
VuBlockDev *vdev_blk = get_vu_block_device_by_server(server);
BlockBackend *backend = vdev_blk->backend;
struct iovec *in_iov = elem->in_sg;
struct iovec *out_iov = elem->out_sg;
unsigned in_num = elem->in_num;
unsigned out_num = elem->out_num;
/* refer to hw/block/virtio_blk.c */
if (elem->out_num < 1 || elem->in_num < 1) {
error_report("virtio-blk request missing headers");
free(elem);
return;
}
req = g_new0(VuBlockReq, 1);
req->server = server;
req->vq = vq;
req->elem = elem;
if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out,
sizeof(req->out)) != sizeof(req->out))) {
error_report("virtio-blk request outhdr too short");
goto err;
}
iov_discard_front(&out_iov, &out_num, sizeof(req->out));
if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
error_report("virtio-blk request inhdr too short");
goto err;
}
/* We always touch the last byte, so just see how big in_iov is. */
req->in = (void *)in_iov[in_num - 1].iov_base
+ in_iov[in_num - 1].iov_len
- sizeof(struct virtio_blk_inhdr);
iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr));
type = le32_to_cpu(req->out.type);
switch (type & ~VIRTIO_BLK_T_BARRIER) {
case VIRTIO_BLK_T_IN:
case VIRTIO_BLK_T_OUT: {
ssize_t ret = 0;
bool is_write = type & VIRTIO_BLK_T_OUT;
req->sector_num = le64_to_cpu(req->out.sector);
int64_t offset = req->sector_num * vdev_blk->blk_size;
QEMUIOVector qiov;
if (is_write) {
qemu_iovec_init_external(&qiov, out_iov, out_num);
ret = blk_co_pwritev(backend, offset, qiov.size,
&qiov, 0);
} else {
qemu_iovec_init_external(&qiov, in_iov, in_num);
ret = blk_co_preadv(backend, offset, qiov.size,
&qiov, 0);
}
if (ret >= 0) {
req->in->status = VIRTIO_BLK_S_OK;
} else {
req->in->status = VIRTIO_BLK_S_IOERR;
}
break;
}
case VIRTIO_BLK_T_FLUSH:
vu_block_flush(req);
req->in->status = VIRTIO_BLK_S_OK;
break;
case VIRTIO_BLK_T_GET_ID: {
size_t size = MIN(iov_size(&elem->in_sg[0], in_num),
VIRTIO_BLK_ID_BYTES);
snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk");
req->in->status = VIRTIO_BLK_S_OK;
req->size = elem->in_sg[0].iov_len;
break;
}
case VIRTIO_BLK_T_DISCARD:
case VIRTIO_BLK_T_WRITE_ZEROES: {
int rc;
rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1],
out_num, type);
if (rc == 0) {
req->in->status = VIRTIO_BLK_S_OK;
} else {
req->in->status = VIRTIO_BLK_S_IOERR;
}
break;
}
default:
req->in->status = VIRTIO_BLK_S_UNSUPP;
break;
}
vu_block_req_complete(req);
return;
err:
free(elem);
g_free(req);
return;
}
static void vu_block_process_vq(VuDev *vu_dev, int idx)
{
VuServer *server;
VuVirtq *vq;
struct req_data *req_data;
server = container_of(vu_dev, VuServer, vu_dev);
assert(server);
vq = vu_get_queue(vu_dev, idx);
assert(vq);
VuVirtqElement *elem;
while (1) {
elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) +
sizeof(VuBlockReq));
if (elem) {
req_data = g_new0(struct req_data, 1);
req_data->server = server;
req_data->vq = vq;
req_data->elem = elem;
Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req,
req_data);
aio_co_enter(server->ioc->ctx, co);
} else {
break;
}
}
}
static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started)
{
VuVirtq *vq;
assert(vu_dev);
vq = vu_get_queue(vu_dev, idx);
vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL);
}
static uint64_t vu_block_get_features(VuDev *dev)
{
uint64_t features;
VuServer *server = container_of(dev, VuServer, vu_dev);
VuBlockDev *vdev_blk = get_vu_block_device_by_server(server);
features = 1ull << VIRTIO_BLK_F_SIZE_MAX |
1ull << VIRTIO_BLK_F_SEG_MAX |
1ull << VIRTIO_BLK_F_TOPOLOGY |
1ull << VIRTIO_BLK_F_BLK_SIZE |
1ull << VIRTIO_BLK_F_FLUSH |
1ull << VIRTIO_BLK_F_DISCARD |
1ull << VIRTIO_BLK_F_WRITE_ZEROES |
1ull << VIRTIO_BLK_F_CONFIG_WCE |
1ull << VIRTIO_F_VERSION_1 |
1ull << VIRTIO_RING_F_INDIRECT_DESC |
1ull << VIRTIO_RING_F_EVENT_IDX |
1ull << VHOST_USER_F_PROTOCOL_FEATURES;
if (!vdev_blk->writable) {
features |= 1ull << VIRTIO_BLK_F_RO;
}
return features;
}
static uint64_t vu_block_get_protocol_features(VuDev *dev)
{
return 1ull << VHOST_USER_PROTOCOL_F_CONFIG |
1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD;
}
static int
vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len)
{
VuServer *server = container_of(vu_dev, VuServer, vu_dev);
VuBlockDev *vdev_blk = get_vu_block_device_by_server(server);
memcpy(config, &vdev_blk->blkcfg, len);
return 0;
}
static int
vu_block_set_config(VuDev *vu_dev, const uint8_t *data,
uint32_t offset, uint32_t size, uint32_t flags)
{
VuServer *server = container_of(vu_dev, VuServer, vu_dev);
VuBlockDev *vdev_blk = get_vu_block_device_by_server(server);
uint8_t wce;
/* don't support live migration */
if (flags != VHOST_SET_CONFIG_TYPE_MASTER) {
return -EINVAL;
}
if (offset != offsetof(struct virtio_blk_config, wce) ||
size != 1) {
return -EINVAL;
}
wce = *data;
vdev_blk->blkcfg.wce = wce;
blk_set_enable_write_cache(vdev_blk->backend, wce);
return 0;
}
/*
* When the client disconnects, it sends a VHOST_USER_NONE request
* and vu_process_message will simple call exit which cause the VM
* to exit abruptly.
* To avoid this issue, process VHOST_USER_NONE request ahead
* of vu_process_message.
*
*/
static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply)
{
if (vmsg->request == VHOST_USER_NONE) {
dev->panic(dev, "disconnect");
return true;
}
return false;
}
static const VuDevIface vu_block_iface = {
.get_features = vu_block_get_features,
.queue_set_started = vu_block_queue_set_started,
.get_protocol_features = vu_block_get_protocol_features,
.get_config = vu_block_get_config,
.set_config = vu_block_set_config,
.process_msg = vu_block_process_msg,
};
static void blk_aio_attached(AioContext *ctx, void *opaque)
{
VuBlockDev *vub_dev = opaque;
aio_context_acquire(ctx);
vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx);
aio_context_release(ctx);
}
static void blk_aio_detach(void *opaque)
{
VuBlockDev *vub_dev = opaque;
AioContext *ctx = vub_dev->vu_server.ctx;
aio_context_acquire(ctx);
vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL);
aio_context_release(ctx);
}
static void
vu_block_initialize_config(BlockDriverState *bs,
struct virtio_blk_config *config, uint32_t blk_size)
{
config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
config->blk_size = blk_size;
config->size_max = 0;
config->seg_max = 128 - 2;
config->min_io_size = 1;
config->opt_io_size = 1;
config->num_queues = VHOST_USER_BLK_MAX_QUEUES;
config->max_discard_sectors = 32768;
config->max_discard_seg = 1;
config->discard_sector_alignment = config->blk_size >> 9;
config->max_write_zeroes_sectors = 32768;
config->max_write_zeroes_seg = 1;
}
static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp)
{
BlockBackend *blk;
Error *local_error = NULL;
const char *node_name = vu_block_device->node_name;
bool writable = vu_block_device->writable;
uint64_t perm = BLK_PERM_CONSISTENT_READ;
int ret;
AioContext *ctx;
BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error);
if (!bs) {
error_propagate(errp, local_error);
return NULL;
}
if (bdrv_is_read_only(bs)) {
writable = false;
}
if (writable) {
perm |= BLK_PERM_WRITE;
}
ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
bdrv_invalidate_cache(bs, NULL);
aio_context_release(ctx);
/*
* Don't allow resize while the vhost user server is running,
* otherwise we don't care what happens with the node.
*/
blk = blk_new(bdrv_get_aio_context(bs), perm,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD);
ret = blk_insert_bs(blk, bs, errp);
if (ret < 0) {
goto fail;
}
blk_set_enable_write_cache(blk, false);
blk_set_allow_aio_context_change(blk, true);
vu_block_device->blkcfg.wce = 0;
vu_block_device->backend = blk;
if (!vu_block_device->blk_size) {
vu_block_device->blk_size = BDRV_SECTOR_SIZE;
}
vu_block_device->blkcfg.blk_size = vu_block_device->blk_size;
blk_set_guest_block_size(blk, vu_block_device->blk_size);
vu_block_initialize_config(bs, &vu_block_device->blkcfg,
vu_block_device->blk_size);
return vu_block_device;
fail:
blk_unref(blk);
return NULL;
}
static void vu_block_deinit(VuBlockDev *vu_block_device)
{
if (vu_block_device->backend) {
blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached,
blk_aio_detach, vu_block_device);
}
blk_unref(vu_block_device->backend);
}
static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device)
{
vhost_user_server_stop(&vu_block_device->vu_server);
vu_block_deinit(vu_block_device);
}
static void vhost_user_blk_server_start(VuBlockDev *vu_block_device,
Error **errp)
{
AioContext *ctx;
SocketAddress *addr = vu_block_device->addr;
if (!vu_block_init(vu_block_device, errp)) {
return;
}
ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend));
if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx,
VHOST_USER_BLK_MAX_QUEUES,
NULL, &vu_block_iface,
errp)) {
goto error;
}
blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached,
blk_aio_detach, vu_block_device);
vu_block_device->running = true;
return;
error:
vu_block_deinit(vu_block_device);
}
static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp)
{
if (vus->running) {
error_setg(errp, "The property can't be modified "
"while the server is running");
return false;
}
return true;
}
static void vu_set_node_name(Object *obj, const char *value, Error **errp)
{
VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
if (!vu_prop_modifiable(vus, errp)) {
return;
}
if (vus->node_name) {
g_free(vus->node_name);
}
vus->node_name = g_strdup(value);
}
static char *vu_get_node_name(Object *obj, Error **errp)
{
VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
return g_strdup(vus->node_name);
}
static void free_socket_addr(SocketAddress *addr)
{
g_free(addr->u.q_unix.path);
g_free(addr);
}
static void vu_set_unix_socket(Object *obj, const char *value,
Error **errp)
{
VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
if (!vu_prop_modifiable(vus, errp)) {
return;
}
if (vus->addr) {
free_socket_addr(vus->addr);
}
SocketAddress *addr = g_new0(SocketAddress, 1);
addr->type = SOCKET_ADDRESS_TYPE_UNIX;
addr->u.q_unix.path = g_strdup(value);
vus->addr = addr;
}
static char *vu_get_unix_socket(Object *obj, Error **errp)
{
VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
return g_strdup(vus->addr->u.q_unix.path);
}
static bool vu_get_block_writable(Object *obj, Error **errp)
{
VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
return vus->writable;
}
static void vu_set_block_writable(Object *obj, bool value, Error **errp)
{
VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
if (!vu_prop_modifiable(vus, errp)) {
return;
}
vus->writable = value;
}
static void vu_get_blk_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
uint32_t value = vus->blk_size;
visit_type_uint32(v, name, &value, errp);
}
static void vu_set_blk_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
Error *local_err = NULL;
uint32_t value;
if (!vu_prop_modifiable(vus, errp)) {
return;
}
visit_type_uint32(v, name, &value, &local_err);
if (local_err) {
goto out;
}
check_block_size(object_get_typename(obj), name, value, &local_err);
if (local_err) {
goto out;
}
vus->blk_size = value;
out:
error_propagate(errp, local_err);
}
static void vhost_user_blk_server_instance_finalize(Object *obj)
{
VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj);
vhost_user_blk_server_stop(vub);
/*
* Unlike object_property_add_str, object_class_property_add_str
* doesn't have a release method. Thus manual memory freeing is
* needed.
*/
free_socket_addr(vub->addr);
g_free(vub->node_name);
}
static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp)
{
VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj);
vhost_user_blk_server_start(vub, errp);
}
static void vhost_user_blk_server_class_init(ObjectClass *klass,
void *class_data)
{
UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass);
ucc->complete = vhost_user_blk_server_complete;
object_class_property_add_bool(klass, "writable",
vu_get_block_writable,
vu_set_block_writable);
object_class_property_add_str(klass, "node-name",
vu_get_node_name,
vu_set_node_name);
object_class_property_add_str(klass, "unix-socket",
vu_get_unix_socket,
vu_set_unix_socket);
object_class_property_add(klass, "logical-block-size", "uint32",
vu_get_blk_size, vu_set_blk_size,
NULL, NULL);
}
static const TypeInfo vhost_user_blk_server_info = {
.name = TYPE_VHOST_USER_BLK_SERVER,
.parent = TYPE_OBJECT,
.instance_size = sizeof(VuBlockDev),
.instance_finalize = vhost_user_blk_server_instance_finalize,
.class_init = vhost_user_blk_server_class_init,
.interfaces = (InterfaceInfo[]) {
{TYPE_USER_CREATABLE},
{}
},
};
static void vhost_user_blk_server_register_types(void)
{
type_register_static(&vhost_user_blk_server_info);
}
type_init(vhost_user_blk_server_register_types)
|