summaryrefslogtreecommitdiffstats
path: root/drivers/block/virtio_blk.c
blob: c7d02bc9d945cf590931d479ff552b65a75fc3b3 (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
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
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
//#define DEBUG
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/virtio.h>
#include <linux/virtio_blk.h>
#include <linux/scatterlist.h>
#include <linux/string_helpers.h>
#include <scsi/scsi_cmnd.h>
#include <linux/idr.h>
#include <linux/blk-mq.h>
#include <linux/numa.h>

#define PART_BITS 4

static int major;
static DEFINE_IDA(vd_index_ida);

static struct workqueue_struct *virtblk_wq;

struct virtio_blk
{
	struct virtio_device *vdev;
	struct virtqueue *vq;
	spinlock_t vq_lock;

	/* The disk structure for the kernel. */
	struct gendisk *disk;

	/* Process context for config space updates */
	struct work_struct config_work;

	/* Lock for config space updates */
	struct mutex config_lock;

	/* enable config space updates */
	bool config_enable;

	/* What host tells us, plus 2 for header & tailer. */
	unsigned int sg_elems;

	/* Ida index - used to track minor number allocations. */
	int index;
};

struct virtblk_req
{
	struct request *req;
	struct virtio_blk_outhdr out_hdr;
	struct virtio_scsi_inhdr in_hdr;
	u8 status;
	struct scatterlist sg[];
};

static inline int virtblk_result(struct virtblk_req *vbr)
{
	switch (vbr->status) {
	case VIRTIO_BLK_S_OK:
		return 0;
	case VIRTIO_BLK_S_UNSUPP:
		return -ENOTTY;
	default:
		return -EIO;
	}
}

static int __virtblk_add_req(struct virtqueue *vq,
			     struct virtblk_req *vbr,
			     struct scatterlist *data_sg,
			     bool have_data)
{
	struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
	unsigned int num_out = 0, num_in = 0;
	int type = vbr->out_hdr.type & ~VIRTIO_BLK_T_OUT;

	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
	sgs[num_out++] = &hdr;

	/*
	 * If this is a packet command we need a couple of additional headers.
	 * Behind the normal outhdr we put a segment with the scsi command
	 * block, and before the normal inhdr we put the sense data and the
	 * inhdr with additional status information.
	 */
	if (type == VIRTIO_BLK_T_SCSI_CMD) {
		sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
		sgs[num_out++] = &cmd;
	}

	if (have_data) {
		if (vbr->out_hdr.type & VIRTIO_BLK_T_OUT)
			sgs[num_out++] = data_sg;
		else
			sgs[num_out + num_in++] = data_sg;
	}

	if (type == VIRTIO_BLK_T_SCSI_CMD) {
		sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
		sgs[num_out + num_in++] = &sense;
		sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
		sgs[num_out + num_in++] = &inhdr;
	}

	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
	sgs[num_out + num_in++] = &status;

	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
}

static inline void virtblk_request_done(struct request *req)
{
	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
	int error = virtblk_result(vbr);

	if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
		req->resid_len = vbr->in_hdr.residual;
		req->sense_len = vbr->in_hdr.sense_len;
		req->errors = vbr->in_hdr.errors;
	} else if (req->cmd_type == REQ_TYPE_SPECIAL) {
		req->errors = (error != 0);
	}

	blk_mq_end_io(req, error);
}

static void virtblk_done(struct virtqueue *vq)
{
	struct virtio_blk *vblk = vq->vdev->priv;
	bool req_done = false;
	struct virtblk_req *vbr;
	unsigned long flags;
	unsigned int len;

	spin_lock_irqsave(&vblk->vq_lock, flags);
	do {
		virtqueue_disable_cb(vq);
		while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
			blk_mq_complete_request(vbr->req);
			req_done = true;
		}
		if (unlikely(virtqueue_is_broken(vq)))
			break;
	} while (!virtqueue_enable_cb(vq));
	spin_unlock_irqrestore(&vblk->vq_lock, flags);

	/* In case queue is stopped waiting for more buffers. */
	if (req_done)
		blk_mq_start_stopped_hw_queues(vblk->disk->queue);
}

static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
{
	struct virtio_blk *vblk = hctx->queue->queuedata;
	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
	unsigned long flags;
	unsigned int num;
	const bool last = (req->cmd_flags & REQ_END) != 0;
	int err;

	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);

	vbr->req = req;
	if (req->cmd_flags & REQ_FLUSH) {
		vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
		vbr->out_hdr.sector = 0;
		vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
	} else {
		switch (req->cmd_type) {
		case REQ_TYPE_FS:
			vbr->out_hdr.type = 0;
			vbr->out_hdr.sector = blk_rq_pos(vbr->req);
			vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
			break;
		case REQ_TYPE_BLOCK_PC:
			vbr->out_hdr.type = VIRTIO_BLK_T_SCSI_CMD;
			vbr->out_hdr.sector = 0;
			vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
			break;
		case REQ_TYPE_SPECIAL:
			vbr->out_hdr.type = VIRTIO_BLK_T_GET_ID;
			vbr->out_hdr.sector = 0;
			vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
			break;
		default:
			/* We don't put anything else in the queue. */
			BUG();
		}
	}

	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
	if (num) {
		if (rq_data_dir(vbr->req) == WRITE)
			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
		else
			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
	}

	spin_lock_irqsave(&vblk->vq_lock, flags);
	err = __virtblk_add_req(vblk->vq, vbr, vbr->sg, num);
	if (err) {
		virtqueue_kick(vblk->vq);
		spin_unlock_irqrestore(&vblk->vq_lock, flags);
		blk_mq_stop_hw_queue(hctx);
		/* Out of mem doesn't actually happen, since we fall back
		 * to direct descriptors */
		if (err == -ENOMEM || err == -ENOSPC)
			return BLK_MQ_RQ_QUEUE_BUSY;
		return BLK_MQ_RQ_QUEUE_ERROR;
	}

	if (last)
		virtqueue_kick(vblk->vq);

	spin_unlock_irqrestore(&vblk->vq_lock, flags);
	return BLK_MQ_RQ_QUEUE_OK;
}

/* return id (s/n) string for *disk to *id_str
 */
static int virtblk_get_id(struct gendisk *disk, char *id_str)
{
	struct virtio_blk *vblk = disk->private_data;
	struct request *req;
	struct bio *bio;
	int err;

	bio = bio_map_kern(vblk->disk->queue, id_str, VIRTIO_BLK_ID_BYTES,
			   GFP_KERNEL);
	if (IS_ERR(bio))
		return PTR_ERR(bio);

	req = blk_make_request(vblk->disk->queue, bio, GFP_KERNEL);
	if (IS_ERR(req)) {
		bio_put(bio);
		return PTR_ERR(req);
	}

	req->cmd_type = REQ_TYPE_SPECIAL;
	err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
	blk_put_request(req);

	return err;
}

static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
			     unsigned int cmd, unsigned long data)
{
	struct gendisk *disk = bdev->bd_disk;
	struct virtio_blk *vblk = disk->private_data;

	/*
	 * Only allow the generic SCSI ioctls if the host can support it.
	 */
	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
		return -ENOTTY;

	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
				  (void __user *)data);
}

/* We provide getgeo only to please some old bootloader/partitioning tools */
static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
{
	struct virtio_blk *vblk = bd->bd_disk->private_data;

	/* see if the host passed in geometry config */
	if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) {
		virtio_cread(vblk->vdev, struct virtio_blk_config,
			     geometry.cylinders, &geo->cylinders);
		virtio_cread(vblk->vdev, struct virtio_blk_config,
			     geometry.heads, &geo->heads);
		virtio_cread(vblk->vdev, struct virtio_blk_config,
			     geometry.sectors, &geo->sectors);
	} else {
		/* some standard values, similar to sd */
		geo->heads = 1 << 6;
		geo->sectors = 1 << 5;
		geo->cylinders = get_capacity(bd->bd_disk) >> 11;
	}
	return 0;
}

static const struct block_device_operations virtblk_fops = {
	.ioctl  = virtblk_ioctl,
	.owner  = THIS_MODULE,
	.getgeo = virtblk_getgeo,
};

static int index_to_minor(int index)
{
	return index << PART_BITS;
}

static int minor_to_index(int minor)
{
	return minor >> PART_BITS;
}

static ssize_t virtblk_serial_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);
	int err;

	/* sysfs gives us a PAGE_SIZE buffer */
	BUILD_BUG_ON(PAGE_SIZE < VIRTIO_BLK_ID_BYTES);

	buf[VIRTIO_BLK_ID_BYTES] = '\0';
	err = virtblk_get_id(disk, buf);
	if (!err)
		return strlen(buf);

	if (err == -EIO) /* Unsupported? Make it empty. */
		return 0;

	return err;
}
DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);

static void virtblk_config_changed_work(struct work_struct *work)
{
	struct virtio_blk *vblk =
		container_of(work, struct virtio_blk, config_work);
	struct virtio_device *vdev = vblk->vdev;
	struct request_queue *q = vblk->disk->queue;
	char cap_str_2[10], cap_str_10[10];
	char *envp[] = { "RESIZE=1", NULL };
	u64 capacity, size;

	mutex_lock(&vblk->config_lock);
	if (!vblk->config_enable)
		goto done;

	/* Host must always specify the capacity. */
	virtio_cread(vdev, struct virtio_blk_config, capacity, &capacity);

	/* If capacity is too big, truncate with warning. */
	if ((sector_t)capacity != capacity) {
		dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
			 (unsigned long long)capacity);
		capacity = (sector_t)-1;
	}

	size = capacity * queue_logical_block_size(q);
	string_get_size(size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
	string_get_size(size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10));

	dev_notice(&vdev->dev,
		  "new size: %llu %d-byte logical blocks (%s/%s)\n",
		  (unsigned long long)capacity,
		  queue_logical_block_size(q),
		  cap_str_10, cap_str_2);

	set_capacity(vblk->disk, capacity);
	revalidate_disk(vblk->disk);
	kobject_uevent_env(&disk_to_dev(vblk->disk)->kobj, KOBJ_CHANGE, envp);
done:
	mutex_unlock(&vblk->config_lock);
}

static void virtblk_config_changed(struct virtio_device *vdev)
{
	struct virtio_blk *vblk = vdev->priv;

	queue_work(virtblk_wq, &vblk->config_work);
}

static int init_vq(struct virtio_blk *vblk)
{
	int err = 0;

	/* We expect one virtqueue, for output. */
	vblk->vq = virtio_find_single_vq(vblk->vdev, virtblk_done, "requests");
	if (IS_ERR(vblk->vq))
		err = PTR_ERR(vblk->vq);

	return err;
}

/*
 * Legacy naming scheme used for virtio devices.  We are stuck with it for
 * virtio blk but don't ever use it for any new driver.
 */
static int virtblk_name_format(char *prefix, int index, char *buf, int buflen)
{
	const int base = 'z' - 'a' + 1;
	char *begin = buf + strlen(prefix);
	char *end = buf + buflen;
	char *p;
	int unit;

	p = end - 1;
	*p = '\0';
	unit = base;
	do {
		if (p == begin)
			return -EINVAL;
		*--p = 'a' + (index % unit);
		index = (index / unit) - 1;
	} while (index >= 0);

	memmove(begin, p, end - p);
	memcpy(buf, prefix, strlen(prefix));

	return 0;
}

static int virtblk_get_cache_mode(struct virtio_device *vdev)
{
	u8 writeback;
	int err;

	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE,
				   struct virtio_blk_config, wce,
				   &writeback);
	if (err)
		writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE);

	return writeback;
}

static void virtblk_update_cache_mode(struct virtio_device *vdev)
{
	u8 writeback = virtblk_get_cache_mode(vdev);
	struct virtio_blk *vblk = vdev->priv;

	if (writeback)
		blk_queue_flush(vblk->disk->queue, REQ_FLUSH);
	else
		blk_queue_flush(vblk->disk->queue, 0);

	revalidate_disk(vblk->disk);
}

static const char *const virtblk_cache_types[] = {
	"write through", "write back"
};

static ssize_t
virtblk_cache_type_store(struct device *dev, struct device_attribute *attr,
			 const char *buf, size_t count)
{
	struct gendisk *disk = dev_to_disk(dev);
	struct virtio_blk *vblk = disk->private_data;
	struct virtio_device *vdev = vblk->vdev;
	int i;

	BUG_ON(!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_CONFIG_WCE));
	for (i = ARRAY_SIZE(virtblk_cache_types); --i >= 0; )
		if (sysfs_streq(buf, virtblk_cache_types[i]))
			break;

	if (i < 0)
		return -EINVAL;

	virtio_cwrite8(vdev, offsetof(struct virtio_blk_config, wce), i);
	virtblk_update_cache_mode(vdev);
	return count;
}

static ssize_t
virtblk_cache_type_show(struct device *dev, struct device_attribute *attr,
			 char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);
	struct virtio_blk *vblk = disk->private_data;
	u8 writeback = virtblk_get_cache_mode(vblk->vdev);

	BUG_ON(writeback >= ARRAY_SIZE(virtblk_cache_types));
	return snprintf(buf, 40, "%s\n", virtblk_cache_types[writeback]);
}

static const struct device_attribute dev_attr_cache_type_ro =
	__ATTR(cache_type, S_IRUGO,
	       virtblk_cache_type_show, NULL);
static const struct device_attribute dev_attr_cache_type_rw =
	__ATTR(cache_type, S_IRUGO|S_IWUSR,
	       virtblk_cache_type_show, virtblk_cache_type_store);

static struct blk_mq_ops virtio_mq_ops = {
	.queue_rq	= virtio_queue_rq,
	.map_queue	= blk_mq_map_queue,
	.alloc_hctx	= blk_mq_alloc_single_hw_queue,
	.free_hctx	= blk_mq_free_single_hw_queue,
	.complete	= virtblk_request_done,
};

static struct blk_mq_reg virtio_mq_reg = {
	.ops		= &virtio_mq_ops,
	.nr_hw_queues	= 1,
	.queue_depth	= 0, /* Set in virtblk_probe */
	.numa_node	= NUMA_NO_NODE,
	.flags		= BLK_MQ_F_SHOULD_MERGE,
};
module_param_named(queue_depth, virtio_mq_reg.queue_depth, uint, 0444);

static int virtblk_init_vbr(void *data, struct blk_mq_hw_ctx *hctx,
			     struct request *rq, unsigned int nr)
{
	struct virtio_blk *vblk = data;
	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);

	sg_init_table(vbr->sg, vblk->sg_elems);
	return 0;
}

static int virtblk_probe(struct virtio_device *vdev)
{
	struct virtio_blk *vblk;
	struct request_queue *q;
	int err, index;

	u64 cap;
	u32 v, blk_size, sg_elems, opt_io_size;
	u16 min_io_size;
	u8 physical_block_exp, alignment_offset;

	err = ida_simple_get(&vd_index_ida, 0, minor_to_index(1 << MINORBITS),
			     GFP_KERNEL);
	if (err < 0)
		goto out;
	index = err;

	/* We need to know how many segments before we allocate. */
	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SEG_MAX,
				   struct virtio_blk_config, seg_max,
				   &sg_elems);

	/* We need at least one SG element, whatever they say. */
	if (err || !sg_elems)
		sg_elems = 1;

	/* We need an extra sg elements at head and tail. */
	sg_elems += 2;
	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
	if (!vblk) {
		err = -ENOMEM;
		goto out_free_index;
	}

	vblk->vdev = vdev;
	vblk->sg_elems = sg_elems;
	mutex_init(&vblk->config_lock);

	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
	vblk->config_enable = true;

	err = init_vq(vblk);
	if (err)
		goto out_free_vblk;
	spin_lock_init(&vblk->vq_lock);

	/* FIXME: How many partitions?  How long is a piece of string? */
	vblk->disk = alloc_disk(1 << PART_BITS);
	if (!vblk->disk) {
		err = -ENOMEM;
		goto out_free_vq;
	}

	/* Default queue sizing is to fill the ring. */
	if (!virtio_mq_reg.queue_depth) {
		virtio_mq_reg.queue_depth = vblk->vq->num_free;
		/* ... but without indirect descs, we use 2 descs per req */
		if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
			virtio_mq_reg.queue_depth /= 2;
	}
	virtio_mq_reg.cmd_size =
		sizeof(struct virtblk_req) +
		sizeof(struct scatterlist) * sg_elems;

	q = vblk->disk->queue = blk_mq_init_queue(&virtio_mq_reg, vblk);
	if (!q) {
		err = -ENOMEM;
		goto out_put_disk;
	}

	blk_mq_init_commands(q, virtblk_init_vbr, vblk);

	q->queuedata = vblk;

	virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN);

	vblk->disk->major = major;
	vblk->disk->first_minor = index_to_minor(index);
	vblk->disk->private_data = vblk;
	vblk->disk->fops = &virtblk_fops;
	vblk->disk->driverfs_dev = &vdev->dev;
	vblk->index = index;

	/* configure queue flush support */
	virtblk_update_cache_mode(vdev);

	/* If disk is read-only in the host, the guest should obey */
	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
		set_disk_ro(vblk->disk, 1);

	/* Host must always specify the capacity. */
	virtio_cread(vdev, struct virtio_blk_config, capacity, &cap);

	/* If capacity is too big, truncate with warning. */
	if ((sector_t)cap != cap) {
		dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
			 (unsigned long long)cap);
		cap = (sector_t)-1;
	}
	set_capacity(vblk->disk, cap);

	/* We can handle whatever the host told us to handle. */
	blk_queue_max_segments(q, vblk->sg_elems-2);

	/* No need to bounce any requests */
	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);

	/* No real sector limit. */
	blk_queue_max_hw_sectors(q, -1U);

	/* Host can optionally specify maximum segment size and number of
	 * segments. */
	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SIZE_MAX,
				   struct virtio_blk_config, size_max, &v);
	if (!err)
		blk_queue_max_segment_size(q, v);
	else
		blk_queue_max_segment_size(q, -1U);

	/* Host can optionally specify the block size of the device */
	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
				   struct virtio_blk_config, blk_size,
				   &blk_size);
	if (!err)
		blk_queue_logical_block_size(q, blk_size);
	else
		blk_size = queue_logical_block_size(q);

	/* Use topology information if available */
	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
				   struct virtio_blk_config, physical_block_exp,
				   &physical_block_exp);
	if (!err && physical_block_exp)
		blk_queue_physical_block_size(q,
				blk_size * (1 << physical_block_exp));

	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
				   struct virtio_blk_config, alignment_offset,
				   &alignment_offset);
	if (!err && alignment_offset)
		blk_queue_alignment_offset(q, blk_size * alignment_offset);

	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
				   struct virtio_blk_config, min_io_size,
				   &min_io_size);
	if (!err && min_io_size)
		blk_queue_io_min(q, blk_size * min_io_size);

	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
				   struct virtio_blk_config, opt_io_size,
				   &opt_io_size);
	if (!err && opt_io_size)
		blk_queue_io_opt(q, blk_size * opt_io_size);

	add_disk(vblk->disk);
	err = device_create_file(disk_to_dev(vblk->disk), &dev_attr_serial);
	if (err)
		goto out_del_disk;

	if (virtio_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE))
		err = device_create_file(disk_to_dev(vblk->disk),
					 &dev_attr_cache_type_rw);
	else
		err = device_create_file(disk_to_dev(vblk->disk),
					 &dev_attr_cache_type_ro);
	if (err)
		goto out_del_disk;
	return 0;

out_del_disk:
	del_gendisk(vblk->disk);
	blk_cleanup_queue(vblk->disk->queue);
out_put_disk:
	put_disk(vblk->disk);
out_free_vq:
	vdev->config->del_vqs(vdev);
out_free_vblk:
	kfree(vblk);
out_free_index:
	ida_simple_remove(&vd_index_ida, index);
out:
	return err;
}

static void virtblk_remove(struct virtio_device *vdev)
{
	struct virtio_blk *vblk = vdev->priv;
	int index = vblk->index;
	int refc;

	/* Prevent config work handler from accessing the device. */
	mutex_lock(&vblk->config_lock);
	vblk->config_enable = false;
	mutex_unlock(&vblk->config_lock);

	del_gendisk(vblk->disk);
	blk_cleanup_queue(vblk->disk->queue);

	/* Stop all the virtqueues. */
	vdev->config->reset(vdev);

	flush_work(&vblk->config_work);

	refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount);
	put_disk(vblk->disk);
	vdev->config->del_vqs(vdev);
	kfree(vblk);

	/* Only free device id if we don't have any users */
	if (refc == 1)
		ida_simple_remove(&vd_index_ida, index);
}

#ifdef CONFIG_PM_SLEEP
static int virtblk_freeze(struct virtio_device *vdev)
{
	struct virtio_blk *vblk = vdev->priv;

	/* Ensure we don't receive any more interrupts */
	vdev->config->reset(vdev);

	/* Prevent config work handler from accessing the device. */
	mutex_lock(&vblk->config_lock);
	vblk->config_enable = false;
	mutex_unlock(&vblk->config_lock);

	flush_work(&vblk->config_work);

	blk_mq_stop_hw_queues(vblk->disk->queue);

	vdev->config->del_vqs(vdev);
	return 0;
}

static int virtblk_restore(struct virtio_device *vdev)
{
	struct virtio_blk *vblk = vdev->priv;
	int ret;

	vblk->config_enable = true;
	ret = init_vq(vdev->priv);
	if (!ret)
		blk_mq_start_stopped_hw_queues(vblk->disk->queue);

	return ret;
}
#endif

static const struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
	{ 0 },
};

static unsigned int features[] = {
	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
	VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE
};

static struct virtio_driver virtio_blk = {
	.feature_table		= features,
	.feature_table_size	= ARRAY_SIZE(features),
	.driver.name		= KBUILD_MODNAME,
	.driver.owner		= THIS_MODULE,
	.id_table		= id_table,
	.probe			= virtblk_probe,
	.remove			= virtblk_remove,
	.config_changed		= virtblk_config_changed,
#ifdef CONFIG_PM_SLEEP
	.freeze			= virtblk_freeze,
	.restore		= virtblk_restore,
#endif
};

static int __init init(void)
{
	int error;

	virtblk_wq = alloc_workqueue("virtio-blk", 0, 0);
	if (!virtblk_wq)
		return -ENOMEM;

	major = register_blkdev(0, "virtblk");
	if (major < 0) {
		error = major;
		goto out_destroy_workqueue;
	}

	error = register_virtio_driver(&virtio_blk);
	if (error)
		goto out_unregister_blkdev;
	return 0;

out_unregister_blkdev:
	unregister_blkdev(major, "virtblk");
out_destroy_workqueue:
	destroy_workqueue(virtblk_wq);
	return error;
}

static void __exit fini(void)
{
	unregister_blkdev(major, "virtblk");
	unregister_virtio_driver(&virtio_blk);
	destroy_workqueue(virtblk_wq);
}
module_init(init);
module_exit(fini);

MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_DESCRIPTION("Virtio block driver");
MODULE_LICENSE("GPL");