summaryrefslogtreecommitdiffstats
path: root/drivers/block/virtio_blk.c
blob: 145606dc52db1e5214a2080c113643cc1eeba0db (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
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
// SPDX-License-Identifier: GPL-2.0-only
//#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/interrupt.h>
#include <linux/virtio.h>
#include <linux/virtio_blk.h>
#include <linux/scatterlist.h>
#include <linux/string_helpers.h>
#include <linux/idr.h>
#include <linux/blk-mq.h>
#include <linux/blk-mq-virtio.h>
#include <linux/numa.h>
#include <uapi/linux/virtio_ring.h>

#define PART_BITS 4
#define VQ_NAME_LEN 16
#define MAX_DISCARD_SEGMENTS 256u

static int major;
static DEFINE_IDA(vd_index_ida);

static struct workqueue_struct *virtblk_wq;

struct virtio_blk_vq {
	struct virtqueue *vq;
	spinlock_t lock;
	char name[VQ_NAME_LEN];
} ____cacheline_aligned_in_smp;

struct virtio_blk {
	/*
	 * This mutex must be held by anything that may run after
	 * virtblk_remove() sets vblk->vdev to NULL.
	 *
	 * blk-mq, virtqueue processing, and sysfs attribute code paths are
	 * shut down before vblk->vdev is set to NULL and therefore do not need
	 * to hold this mutex.
	 */
	struct mutex vdev_mutex;
	struct virtio_device *vdev;

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

	/* Block layer tags. */
	struct blk_mq_tag_set tag_set;

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

	/*
	 * Tracks references from block_device_operations open/release and
	 * virtio_driver probe/remove so this object can be freed once no
	 * longer in use.
	 */
	refcount_t refs;

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

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

	/* num of vqs */
	int num_vqs;
	struct virtio_blk_vq *vqs;
};

struct virtblk_req {
	struct virtio_blk_outhdr out_hdr;
	u8 status;
	struct scatterlist sg[];
};

static inline blk_status_t virtblk_result(struct virtblk_req *vbr)
{
	switch (vbr->status) {
	case VIRTIO_BLK_S_OK:
		return BLK_STS_OK;
	case VIRTIO_BLK_S_UNSUPP:
		return BLK_STS_NOTSUPP;
	default:
		return BLK_STS_IOERR;
	}
}

static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
		struct scatterlist *data_sg, bool have_data)
{
	struct scatterlist hdr, status, *sgs[3];
	unsigned int num_out = 0, num_in = 0;

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

	if (have_data) {
		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
			sgs[num_out++] = data_sg;
		else
			sgs[num_out + num_in++] = data_sg;
	}

	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 int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap)
{
	unsigned short segments = blk_rq_nr_discard_segments(req);
	unsigned short n = 0;
	struct virtio_blk_discard_write_zeroes *range;
	struct bio *bio;
	u32 flags = 0;

	if (unmap)
		flags |= VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP;

	range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC);
	if (!range)
		return -ENOMEM;

	/*
	 * Single max discard segment means multi-range discard isn't
	 * supported, and block layer only runs contiguity merge like
	 * normal RW request. So we can't reply on bio for retrieving
	 * each range info.
	 */
	if (queue_max_discard_segments(req->q) == 1) {
		range[0].flags = cpu_to_le32(flags);
		range[0].num_sectors = cpu_to_le32(blk_rq_sectors(req));
		range[0].sector = cpu_to_le64(blk_rq_pos(req));
		n = 1;
	} else {
		__rq_for_each_bio(bio, req) {
			u64 sector = bio->bi_iter.bi_sector;
			u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT;

			range[n].flags = cpu_to_le32(flags);
			range[n].num_sectors = cpu_to_le32(num_sectors);
			range[n].sector = cpu_to_le64(sector);
			n++;
		}
	}

	WARN_ON_ONCE(n != segments);

	req->special_vec.bv_page = virt_to_page(range);
	req->special_vec.bv_offset = offset_in_page(range);
	req->special_vec.bv_len = sizeof(*range) * segments;
	req->rq_flags |= RQF_SPECIAL_PAYLOAD;

	return 0;
}

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

	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
		kfree(page_address(req->special_vec.bv_page) +
		      req->special_vec.bv_offset);
	}

	blk_mq_end_request(req, virtblk_result(vbr));
}

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

	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
	do {
		virtqueue_disable_cb(vq);
		while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
			struct request *req = blk_mq_rq_from_pdu(vbr);

			if (likely(!blk_should_fake_timeout(req->q)))
				blk_mq_complete_request(req);
			req_done = true;
		}
		if (unlikely(virtqueue_is_broken(vq)))
			break;
	} while (!virtqueue_enable_cb(vq));

	/* In case queue is stopped waiting for more buffers. */
	if (req_done)
		blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
	spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
}

static void virtio_commit_rqs(struct blk_mq_hw_ctx *hctx)
{
	struct virtio_blk *vblk = hctx->queue->queuedata;
	struct virtio_blk_vq *vq = &vblk->vqs[hctx->queue_num];
	bool kick;

	spin_lock_irq(&vq->lock);
	kick = virtqueue_kick_prepare(vq->vq);
	spin_unlock_irq(&vq->lock);

	if (kick)
		virtqueue_notify(vq->vq);
}

static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
			   const struct blk_mq_queue_data *bd)
{
	struct virtio_blk *vblk = hctx->queue->queuedata;
	struct request *req = bd->rq;
	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
	unsigned long flags;
	unsigned int num;
	int qid = hctx->queue_num;
	int err;
	bool notify = false;
	bool unmap = false;
	u32 type;

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

	switch (req_op(req)) {
	case REQ_OP_READ:
	case REQ_OP_WRITE:
		type = 0;
		break;
	case REQ_OP_FLUSH:
		type = VIRTIO_BLK_T_FLUSH;
		break;
	case REQ_OP_DISCARD:
		type = VIRTIO_BLK_T_DISCARD;
		break;
	case REQ_OP_WRITE_ZEROES:
		type = VIRTIO_BLK_T_WRITE_ZEROES;
		unmap = !(req->cmd_flags & REQ_NOUNMAP);
		break;
	case REQ_OP_DRV_IN:
		type = VIRTIO_BLK_T_GET_ID;
		break;
	default:
		WARN_ON_ONCE(1);
		return BLK_STS_IOERR;
	}

	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
	vbr->out_hdr.sector = type ?
		0 : cpu_to_virtio64(vblk->vdev, blk_rq_pos(req));
	vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req));

	blk_mq_start_request(req);

	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) {
		err = virtblk_setup_discard_write_zeroes(req, unmap);
		if (err)
			return BLK_STS_RESOURCE;
	}

	num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
	if (num) {
		if (rq_data_dir(req) == WRITE)
			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
		else
			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
	}

	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
	err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
	if (err) {
		virtqueue_kick(vblk->vqs[qid].vq);
		/* Don't stop the queue if -ENOMEM: we may have failed to
		 * bounce the buffer due to global resource outage.
		 */
		if (err == -ENOSPC)
			blk_mq_stop_hw_queue(hctx);
		spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
		switch (err) {
		case -ENOSPC:
			return BLK_STS_DEV_RESOURCE;
		case -ENOMEM:
			return BLK_STS_RESOURCE;
		default:
			return BLK_STS_IOERR;
		}
	}

	if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
		notify = true;
	spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);

	if (notify)
		virtqueue_notify(vblk->vqs[qid].vq);
	return BLK_STS_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_queue *q = vblk->disk->queue;
	struct request *req;
	int err;

	req = blk_get_request(q, REQ_OP_DRV_IN, 0);
	if (IS_ERR(req))
		return PTR_ERR(req);

	err = blk_rq_map_kern(q, req, id_str, VIRTIO_BLK_ID_BYTES, GFP_KERNEL);
	if (err)
		goto out;

	blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
	err = blk_status_to_errno(virtblk_result(blk_mq_rq_to_pdu(req)));
out:
	blk_put_request(req);
	return err;
}

static void virtblk_get(struct virtio_blk *vblk)
{
	refcount_inc(&vblk->refs);
}

static void virtblk_put(struct virtio_blk *vblk)
{
	if (refcount_dec_and_test(&vblk->refs)) {
		ida_simple_remove(&vd_index_ida, vblk->index);
		mutex_destroy(&vblk->vdev_mutex);
		kfree(vblk);
	}
}

static int virtblk_open(struct block_device *bd, fmode_t mode)
{
	struct virtio_blk *vblk = bd->bd_disk->private_data;
	int ret = 0;

	mutex_lock(&vblk->vdev_mutex);

	if (vblk->vdev)
		virtblk_get(vblk);
	else
		ret = -ENXIO;

	mutex_unlock(&vblk->vdev_mutex);
	return ret;
}

static void virtblk_release(struct gendisk *disk, fmode_t mode)
{
	struct virtio_blk *vblk = disk->private_data;

	virtblk_put(vblk);
}

/* 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;
	int ret = 0;

	mutex_lock(&vblk->vdev_mutex);

	if (!vblk->vdev) {
		ret = -ENXIO;
		goto out;
	}

	/* 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;
	}
out:
	mutex_unlock(&vblk->vdev_mutex);
	return ret;
}

static const struct block_device_operations virtblk_fops = {
	.owner  = THIS_MODULE,
	.open = virtblk_open,
	.release = virtblk_release,
	.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 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;
}

static DEVICE_ATTR_RO(serial);

/* The queue's logical block size must be set before calling this */
static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize)
{
	struct virtio_device *vdev = vblk->vdev;
	struct request_queue *q = vblk->disk->queue;
	char cap_str_2[10], cap_str_10[10];
	unsigned long long nblocks;
	u64 capacity;

	/* 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;
	}

	nblocks = DIV_ROUND_UP_ULL(capacity, queue_logical_block_size(q) >> 9);

	string_get_size(nblocks, queue_logical_block_size(q),
			STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
	string_get_size(nblocks, queue_logical_block_size(q),
			STRING_UNITS_10, cap_str_10, sizeof(cap_str_10));

	dev_notice(&vdev->dev,
		   "[%s] %s%llu %d-byte logical blocks (%s/%s)\n",
		   vblk->disk->disk_name,
		   resize ? "new size: " : "",
		   nblocks,
		   queue_logical_block_size(q),
		   cap_str_10,
		   cap_str_2);

	set_capacity_and_notify(vblk->disk, capacity);
}

static void virtblk_config_changed_work(struct work_struct *work)
{
	struct virtio_blk *vblk =
		container_of(work, struct virtio_blk, config_work);

	virtblk_update_capacity(vblk, true);
}

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;
	int i;
	vq_callback_t **callbacks;
	const char **names;
	struct virtqueue **vqs;
	unsigned short num_vqs;
	struct virtio_device *vdev = vblk->vdev;
	struct irq_affinity desc = { 0, };

	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_MQ,
				   struct virtio_blk_config, num_queues,
				   &num_vqs);
	if (err)
		num_vqs = 1;

	num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs);

	vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
	if (!vblk->vqs)
		return -ENOMEM;

	names = kmalloc_array(num_vqs, sizeof(*names), GFP_KERNEL);
	callbacks = kmalloc_array(num_vqs, sizeof(*callbacks), GFP_KERNEL);
	vqs = kmalloc_array(num_vqs, sizeof(*vqs), GFP_KERNEL);
	if (!names || !callbacks || !vqs) {
		err = -ENOMEM;
		goto out;
	}

	for (i = 0; i < num_vqs; i++) {
		callbacks[i] = virtblk_done;
		snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i);
		names[i] = vblk->vqs[i].name;
	}

	/* Discover virtqueues and write information to configuration.  */
	err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc);
	if (err)
		goto out;

	for (i = 0; i < num_vqs; i++) {
		spin_lock_init(&vblk->vqs[i].lock);
		vblk->vqs[i].vq = vqs[i];
	}
	vblk->num_vqs = num_vqs;

out:
	kfree(vqs);
	kfree(callbacks);
	kfree(names);
	if (err)
		kfree(vblk->vqs);
	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 WCE is not configurable and flush is not available,
	 * assume no writeback cache is in use.
	 */
	if (err)
		writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH);

	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;

	blk_queue_write_cache(vblk->disk->queue, writeback, false);
}

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

static ssize_t
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));
	i = sysfs_match_string(virtblk_cache_types, buf);
	if (i < 0)
		return i;

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

static ssize_t
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 DEVICE_ATTR_RW(cache_type);

static struct attribute *virtblk_attrs[] = {
	&dev_attr_serial.attr,
	&dev_attr_cache_type.attr,
	NULL,
};

static umode_t virtblk_attrs_are_visible(struct kobject *kobj,
		struct attribute *a, int n)
{
	struct device *dev = kobj_to_dev(kobj);
	struct gendisk *disk = dev_to_disk(dev);
	struct virtio_blk *vblk = disk->private_data;
	struct virtio_device *vdev = vblk->vdev;

	if (a == &dev_attr_cache_type.attr &&
	    !virtio_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE))
		return S_IRUGO;

	return a->mode;
}

static const struct attribute_group virtblk_attr_group = {
	.attrs = virtblk_attrs,
	.is_visible = virtblk_attrs_are_visible,
};

static const struct attribute_group *virtblk_attr_groups[] = {
	&virtblk_attr_group,
	NULL,
};

static int virtblk_init_request(struct blk_mq_tag_set *set, struct request *rq,
		unsigned int hctx_idx, unsigned int numa_node)
{
	struct virtio_blk *vblk = set->driver_data;
	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);

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

static int virtblk_map_queues(struct blk_mq_tag_set *set)
{
	struct virtio_blk *vblk = set->driver_data;

	return blk_mq_virtio_map_queues(&set->map[HCTX_TYPE_DEFAULT],
					vblk->vdev, 0);
}

static const struct blk_mq_ops virtio_mq_ops = {
	.queue_rq	= virtio_queue_rq,
	.commit_rqs	= virtio_commit_rqs,
	.complete	= virtblk_request_done,
	.init_request	= virtblk_init_request,
	.map_queues	= virtblk_map_queues,
};

static unsigned int virtblk_queue_depth;
module_param_named(queue_depth, virtblk_queue_depth, uint, 0444);

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

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

	if (!vdev->config->get) {
		dev_err(&vdev->dev, "%s failure: config access disabled\n",
			__func__);
		return -EINVAL;
	}

	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;
	}

	/* This reference is dropped in virtblk_remove(). */
	refcount_set(&vblk->refs, 1);
	mutex_init(&vblk->vdev_mutex);

	vblk->vdev = vdev;
	vblk->sg_elems = sg_elems;

	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);

	err = init_vq(vblk);
	if (err)
		goto out_free_vblk;

	/* 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 (!virtblk_queue_depth) {
		virtblk_queue_depth = vblk->vqs[0].vq->num_free;
		/* ... but without indirect descs, we use 2 descs per req */
		if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
			virtblk_queue_depth /= 2;
	}

	memset(&vblk->tag_set, 0, sizeof(vblk->tag_set));
	vblk->tag_set.ops = &virtio_mq_ops;
	vblk->tag_set.queue_depth = virtblk_queue_depth;
	vblk->tag_set.numa_node = NUMA_NO_NODE;
	vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
	vblk->tag_set.cmd_size =
		sizeof(struct virtblk_req) +
		sizeof(struct scatterlist) * sg_elems;
	vblk->tag_set.driver_data = vblk;
	vblk->tag_set.nr_hw_queues = vblk->num_vqs;

	err = blk_mq_alloc_tag_set(&vblk->tag_set);
	if (err)
		goto out_put_disk;

	q = blk_mq_init_queue(&vblk->tag_set);
	if (IS_ERR(q)) {
		err = -ENOMEM;
		goto out_free_tags;
	}
	vblk->disk->queue = q;

	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->flags |= GENHD_FL_EXT_DEVT;
	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);

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

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

	max_size = virtio_max_dma_size(vdev);

	/* 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)
		max_size = min(max_size, v);

	blk_queue_max_segment_size(q, max_size);

	/* 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);

	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
		q->limits.discard_granularity = blk_size;

		virtio_cread(vdev, struct virtio_blk_config,
			     discard_sector_alignment, &v);
		q->limits.discard_alignment = v ? v << SECTOR_SHIFT : 0;

		virtio_cread(vdev, struct virtio_blk_config,
			     max_discard_sectors, &v);
		blk_queue_max_discard_sectors(q, v ? v : UINT_MAX);

		virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
			     &v);
		blk_queue_max_discard_segments(q,
					       min_not_zero(v,
							    MAX_DISCARD_SEGMENTS));

		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
	}

	if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
		virtio_cread(vdev, struct virtio_blk_config,
			     max_write_zeroes_sectors, &v);
		blk_queue_max_write_zeroes_sectors(q, v ? v : UINT_MAX);
	}

	virtblk_update_capacity(vblk, false);
	virtio_device_ready(vdev);

	device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups);
	return 0;

out_free_tags:
	blk_mq_free_tag_set(&vblk->tag_set);
out_put_disk:
	put_disk(vblk->disk);
out_free_vq:
	vdev->config->del_vqs(vdev);
	kfree(vblk->vqs);
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;

	/* Make sure no work handler is accessing the device. */
	flush_work(&vblk->config_work);

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

	blk_mq_free_tag_set(&vblk->tag_set);

	mutex_lock(&vblk->vdev_mutex);

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

	/* Virtqueues are stopped, nothing can use vblk->vdev anymore. */
	vblk->vdev = NULL;

	put_disk(vblk->disk);
	vdev->config->del_vqs(vdev);
	kfree(vblk->vqs);

	mutex_unlock(&vblk->vdev_mutex);

	virtblk_put(vblk);
}

#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);

	/* Make sure no work handler is accessing the device. */
	flush_work(&vblk->config_work);

	blk_mq_quiesce_queue(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;

	ret = init_vq(vdev->priv);
	if (ret)
		return ret;

	virtio_device_ready(vdev);

	blk_mq_unquiesce_queue(vblk->disk->queue);
	return 0;
}
#endif

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

static unsigned int features_legacy[] = {
	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_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
	VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES,
}
;
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_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
	VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES,
};

static struct virtio_driver virtio_blk = {
	.feature_table			= features,
	.feature_table_size		= ARRAY_SIZE(features),
	.feature_table_legacy		= features_legacy,
	.feature_table_size_legacy	= ARRAY_SIZE(features_legacy),
	.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_virtio_driver(&virtio_blk);
	unregister_blkdev(major, "virtblk");
	destroy_workqueue(virtblk_wq);
}
module_init(init);
module_exit(fini);

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