summaryrefslogtreecommitdiffstats
path: root/drivers/block/virtio_blk.c
blob: 42dea7601d8799279b17aaa4929b93503f721e3a (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
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
// 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 <linux/vmalloc.h>
#include <uapi/linux/virtio_ring.h>

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

/* The maximum number of sg elements that fit into a virtqueue */
#define VIRTIO_BLK_MAX_SG_ELEMS 32768

#ifdef CONFIG_ARCH_NO_SG_CHAIN
#define VIRTIO_BLK_INLINE_SG_CNT	0
#else
#define VIRTIO_BLK_INLINE_SG_CNT	2
#endif

static unsigned int num_request_queues;
module_param(num_request_queues, uint, 0644);
MODULE_PARM_DESC(num_request_queues,
		 "Limit the number of request queues to use for blk device. "
		 "0 for no limit. "
		 "Values > nr_cpu_ids truncated to nr_cpu_ids.");

static unsigned int poll_queues;
module_param(poll_queues, uint, 0644);
MODULE_PARM_DESC(poll_queues, "The number of dedicated virtqueues for polling I/O");

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;

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

	/* num of vqs */
	int num_vqs;
	int io_queues[HCTX_MAX_TYPES];
	struct virtio_blk_vq *vqs;

	/* For zoned device */
	unsigned int zone_sectors;
};

struct virtblk_req {
	/* Out header */
	struct virtio_blk_outhdr out_hdr;

	/* In header */
	union {
		u8 status;

		/*
		 * The zone append command has an extended in header.
		 * The status field in zone_append_in_hdr must always
		 * be the last byte.
		 */
		struct {
			__virtio64 sector;
			u8 status;
		} zone_append;
	} in_hdr;

	size_t in_hdr_len;

	struct sg_table sg_table;
	struct scatterlist sg[];
};

static inline blk_status_t virtblk_result(u8 status)
{
	switch (status) {
	case VIRTIO_BLK_S_OK:
		return BLK_STS_OK;
	case VIRTIO_BLK_S_UNSUPP:
		return BLK_STS_NOTSUPP;
	case VIRTIO_BLK_S_ZONE_OPEN_RESOURCE:
		return BLK_STS_ZONE_OPEN_RESOURCE;
	case VIRTIO_BLK_S_ZONE_ACTIVE_RESOURCE:
		return BLK_STS_ZONE_ACTIVE_RESOURCE;
	case VIRTIO_BLK_S_IOERR:
	case VIRTIO_BLK_S_ZONE_UNALIGNED_WP:
	default:
		return BLK_STS_IOERR;
	}
}

static inline struct virtio_blk_vq *get_virtio_blk_vq(struct blk_mq_hw_ctx *hctx)
{
	struct virtio_blk *vblk = hctx->queue->queuedata;
	struct virtio_blk_vq *vq = &vblk->vqs[hctx->queue_num];

	return vq;
}

static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr)
{
	struct scatterlist out_hdr, in_hdr, *sgs[3];
	unsigned int num_out = 0, num_in = 0;

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

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

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

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

static int virtblk_setup_discard_write_zeroes_erase(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);

	bvec_set_virt(&req->special_vec, range, sizeof(*range) * segments);
	req->rq_flags |= RQF_SPECIAL_PAYLOAD;

	return 0;
}

static void virtblk_unmap_data(struct request *req, struct virtblk_req *vbr)
{
	if (blk_rq_nr_phys_segments(req))
		sg_free_table_chained(&vbr->sg_table,
				      VIRTIO_BLK_INLINE_SG_CNT);
}

static int virtblk_map_data(struct blk_mq_hw_ctx *hctx, struct request *req,
		struct virtblk_req *vbr)
{
	int err;

	if (!blk_rq_nr_phys_segments(req))
		return 0;

	vbr->sg_table.sgl = vbr->sg;
	err = sg_alloc_table_chained(&vbr->sg_table,
				     blk_rq_nr_phys_segments(req),
				     vbr->sg_table.sgl,
				     VIRTIO_BLK_INLINE_SG_CNT);
	if (unlikely(err))
		return -ENOMEM;

	return blk_rq_map_sg(hctx->queue, req, vbr->sg_table.sgl);
}

static void virtblk_cleanup_cmd(struct request *req)
{
	if (req->rq_flags & RQF_SPECIAL_PAYLOAD)
		kfree(bvec_virt(&req->special_vec));
}

static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev,
				      struct request *req,
				      struct virtblk_req *vbr)
{
	size_t in_hdr_len = sizeof(vbr->in_hdr.status);
	bool unmap = false;
	u32 type;
	u64 sector = 0;

	if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) && op_is_zone_mgmt(req_op(req)))
		return BLK_STS_NOTSUPP;

	/* Set fields for all request types */
	vbr->out_hdr.ioprio = cpu_to_virtio32(vdev, req_get_ioprio(req));

	switch (req_op(req)) {
	case REQ_OP_READ:
		type = VIRTIO_BLK_T_IN;
		sector = blk_rq_pos(req);
		break;
	case REQ_OP_WRITE:
		type = VIRTIO_BLK_T_OUT;
		sector = blk_rq_pos(req);
		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_SECURE_ERASE:
		type = VIRTIO_BLK_T_SECURE_ERASE;
		break;
	case REQ_OP_ZONE_OPEN:
		type = VIRTIO_BLK_T_ZONE_OPEN;
		sector = blk_rq_pos(req);
		break;
	case REQ_OP_ZONE_CLOSE:
		type = VIRTIO_BLK_T_ZONE_CLOSE;
		sector = blk_rq_pos(req);
		break;
	case REQ_OP_ZONE_FINISH:
		type = VIRTIO_BLK_T_ZONE_FINISH;
		sector = blk_rq_pos(req);
		break;
	case REQ_OP_ZONE_APPEND:
		type = VIRTIO_BLK_T_ZONE_APPEND;
		sector = blk_rq_pos(req);
		in_hdr_len = sizeof(vbr->in_hdr.zone_append);
		break;
	case REQ_OP_ZONE_RESET:
		type = VIRTIO_BLK_T_ZONE_RESET;
		sector = blk_rq_pos(req);
		break;
	case REQ_OP_ZONE_RESET_ALL:
		type = VIRTIO_BLK_T_ZONE_RESET_ALL;
		break;
	case REQ_OP_DRV_IN:
		/*
		 * Out header has already been prepared by the caller (virtblk_get_id()
		 * or virtblk_submit_zone_report()), nothing to do here.
		 */
		return 0;
	default:
		WARN_ON_ONCE(1);
		return BLK_STS_IOERR;
	}

	/* Set fields for non-REQ_OP_DRV_IN request types */
	vbr->in_hdr_len = in_hdr_len;
	vbr->out_hdr.type = cpu_to_virtio32(vdev, type);
	vbr->out_hdr.sector = cpu_to_virtio64(vdev, sector);

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

	return 0;
}

/*
 * The status byte is always the last byte of the virtblk request
 * in-header. This helper fetches its value for all in-header formats
 * that are currently defined.
 */
static inline u8 virtblk_vbr_status(struct virtblk_req *vbr)
{
	return *((u8 *)&vbr->in_hdr + vbr->in_hdr_len - 1);
}

static inline void virtblk_request_done(struct request *req)
{
	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
	blk_status_t status = virtblk_result(virtblk_vbr_status(vbr));
	struct virtio_blk *vblk = req->mq_hctx->queue->queuedata;

	virtblk_unmap_data(req, vbr);
	virtblk_cleanup_cmd(req);

	if (req_op(req) == REQ_OP_ZONE_APPEND)
		req->__sector = virtio64_to_cpu(vblk->vdev,
						vbr->in_hdr.zone_append.sector);

	blk_mq_end_request(req, status);
}

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;
		}
	} 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 virtblk_fail_to_queue(struct request *req, int rc)
{
	virtblk_cleanup_cmd(req);
	switch (rc) {
	case -ENOSPC:
		return BLK_STS_DEV_RESOURCE;
	case -ENOMEM:
		return BLK_STS_RESOURCE;
	default:
		return BLK_STS_IOERR;
	}
}

static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
					struct virtio_blk *vblk,
					struct request *req,
					struct virtblk_req *vbr)
{
	blk_status_t status;
	int num;

	status = virtblk_setup_cmd(vblk->vdev, req, vbr);
	if (unlikely(status))
		return status;

	num = virtblk_map_data(hctx, req, vbr);
	if (unlikely(num < 0))
		return virtblk_fail_to_queue(req, -ENOMEM);
	vbr->sg_table.nents = num;

	blk_mq_start_request(req);

	return BLK_STS_OK;
}

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;
	int qid = hctx->queue_num;
	bool notify = false;
	blk_status_t status;
	int err;

	status = virtblk_prep_rq(hctx, vblk, req, vbr);
	if (unlikely(status))
		return status;

	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
	err = virtblk_add_req(vblk->vqs[qid].vq, vbr);
	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);
		virtblk_unmap_data(req, vbr);
		return virtblk_fail_to_queue(req, err);
	}

	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;
}

static bool virtblk_prep_rq_batch(struct request *req)
{
	struct virtio_blk *vblk = req->mq_hctx->queue->queuedata;
	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);

	return virtblk_prep_rq(req->mq_hctx, vblk, req, vbr) == BLK_STS_OK;
}

static bool virtblk_add_req_batch(struct virtio_blk_vq *vq,
					struct request **rqlist)
{
	unsigned long flags;
	int err;
	bool kick;

	spin_lock_irqsave(&vq->lock, flags);

	while (!rq_list_empty(*rqlist)) {
		struct request *req = rq_list_pop(rqlist);
		struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);

		err = virtblk_add_req(vq->vq, vbr);
		if (err) {
			virtblk_unmap_data(req, vbr);
			virtblk_cleanup_cmd(req);
			blk_mq_requeue_request(req, true);
		}
	}

	kick = virtqueue_kick_prepare(vq->vq);
	spin_unlock_irqrestore(&vq->lock, flags);

	return kick;
}

static void virtio_queue_rqs(struct request **rqlist)
{
	struct request *req, *next, *prev = NULL;
	struct request *requeue_list = NULL;

	rq_list_for_each_safe(rqlist, req, next) {
		struct virtio_blk_vq *vq = get_virtio_blk_vq(req->mq_hctx);
		bool kick;

		if (!virtblk_prep_rq_batch(req)) {
			rq_list_move(rqlist, &requeue_list, req, prev);
			req = prev;
			if (!req)
				continue;
		}

		if (!next || req->mq_hctx != next->mq_hctx) {
			req->rq_next = NULL;
			kick = virtblk_add_req_batch(vq, rqlist);
			if (kick)
				virtqueue_notify(vq->vq);

			*rqlist = next;
			prev = NULL;
		} else
			prev = req;
	}

	*rqlist = requeue_list;
}

#ifdef CONFIG_BLK_DEV_ZONED
static void *virtblk_alloc_report_buffer(struct virtio_blk *vblk,
					  unsigned int nr_zones,
					  size_t *buflen)
{
	struct request_queue *q = vblk->disk->queue;
	size_t bufsize;
	void *buf;

	nr_zones = min_t(unsigned int, nr_zones,
			 get_capacity(vblk->disk) >> ilog2(vblk->zone_sectors));

	bufsize = sizeof(struct virtio_blk_zone_report) +
		nr_zones * sizeof(struct virtio_blk_zone_descriptor);
	bufsize = min_t(size_t, bufsize,
			queue_max_hw_sectors(q) << SECTOR_SHIFT);
	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);

	while (bufsize >= sizeof(struct virtio_blk_zone_report)) {
		buf = __vmalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
		if (buf) {
			*buflen = bufsize;
			return buf;
		}
		bufsize >>= 1;
	}

	return NULL;
}

static int virtblk_submit_zone_report(struct virtio_blk *vblk,
				       char *report_buf, size_t report_len,
				       sector_t sector)
{
	struct request_queue *q = vblk->disk->queue;
	struct request *req;
	struct virtblk_req *vbr;
	int err;

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

	vbr = blk_mq_rq_to_pdu(req);
	vbr->in_hdr_len = sizeof(vbr->in_hdr.status);
	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_ZONE_REPORT);
	vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, sector);

	err = blk_rq_map_kern(q, req, report_buf, report_len, GFP_KERNEL);
	if (err)
		goto out;

	blk_execute_rq(req, false);
	err = blk_status_to_errno(virtblk_result(vbr->in_hdr.status));
out:
	blk_mq_free_request(req);
	return err;
}

static int virtblk_parse_zone(struct virtio_blk *vblk,
			       struct virtio_blk_zone_descriptor *entry,
			       unsigned int idx, report_zones_cb cb, void *data)
{
	struct blk_zone zone = { };

	zone.start = virtio64_to_cpu(vblk->vdev, entry->z_start);
	if (zone.start + vblk->zone_sectors <= get_capacity(vblk->disk))
		zone.len = vblk->zone_sectors;
	else
		zone.len = get_capacity(vblk->disk) - zone.start;
	zone.capacity = virtio64_to_cpu(vblk->vdev, entry->z_cap);
	zone.wp = virtio64_to_cpu(vblk->vdev, entry->z_wp);

	switch (entry->z_type) {
	case VIRTIO_BLK_ZT_SWR:
		zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ;
		break;
	case VIRTIO_BLK_ZT_SWP:
		zone.type = BLK_ZONE_TYPE_SEQWRITE_PREF;
		break;
	case VIRTIO_BLK_ZT_CONV:
		zone.type = BLK_ZONE_TYPE_CONVENTIONAL;
		break;
	default:
		dev_err(&vblk->vdev->dev, "zone %llu: invalid type %#x\n",
			zone.start, entry->z_type);
		return -EIO;
	}

	switch (entry->z_state) {
	case VIRTIO_BLK_ZS_EMPTY:
		zone.cond = BLK_ZONE_COND_EMPTY;
		break;
	case VIRTIO_BLK_ZS_CLOSED:
		zone.cond = BLK_ZONE_COND_CLOSED;
		break;
	case VIRTIO_BLK_ZS_FULL:
		zone.cond = BLK_ZONE_COND_FULL;
		zone.wp = zone.start + zone.len;
		break;
	case VIRTIO_BLK_ZS_EOPEN:
		zone.cond = BLK_ZONE_COND_EXP_OPEN;
		break;
	case VIRTIO_BLK_ZS_IOPEN:
		zone.cond = BLK_ZONE_COND_IMP_OPEN;
		break;
	case VIRTIO_BLK_ZS_NOT_WP:
		zone.cond = BLK_ZONE_COND_NOT_WP;
		break;
	case VIRTIO_BLK_ZS_RDONLY:
		zone.cond = BLK_ZONE_COND_READONLY;
		zone.wp = ULONG_MAX;
		break;
	case VIRTIO_BLK_ZS_OFFLINE:
		zone.cond = BLK_ZONE_COND_OFFLINE;
		zone.wp = ULONG_MAX;
		break;
	default:
		dev_err(&vblk->vdev->dev, "zone %llu: invalid condition %#x\n",
			zone.start, entry->z_state);
		return -EIO;
	}

	/*
	 * The callback below checks the validity of the reported
	 * entry data, no need to further validate it here.
	 */
	return cb(&zone, idx, data);
}

static int virtblk_report_zones(struct gendisk *disk, sector_t sector,
				 unsigned int nr_zones, report_zones_cb cb,
				 void *data)
{
	struct virtio_blk *vblk = disk->private_data;
	struct virtio_blk_zone_report *report;
	unsigned long long nz, i;
	size_t buflen;
	unsigned int zone_idx = 0;
	int ret;

	if (WARN_ON_ONCE(!vblk->zone_sectors))
		return -EOPNOTSUPP;

	report = virtblk_alloc_report_buffer(vblk, nr_zones, &buflen);
	if (!report)
		return -ENOMEM;

	mutex_lock(&vblk->vdev_mutex);

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

	while (zone_idx < nr_zones && sector < get_capacity(vblk->disk)) {
		memset(report, 0, buflen);

		ret = virtblk_submit_zone_report(vblk, (char *)report,
						 buflen, sector);
		if (ret)
			goto fail_report;

		nz = min_t(u64, virtio64_to_cpu(vblk->vdev, report->nr_zones),
			   nr_zones);
		if (!nz)
			break;

		for (i = 0; i < nz && zone_idx < nr_zones; i++) {
			ret = virtblk_parse_zone(vblk, &report->zones[i],
						 zone_idx, cb, data);
			if (ret)
				goto fail_report;

			sector = virtio64_to_cpu(vblk->vdev,
						 report->zones[i].z_start) +
				 vblk->zone_sectors;
			zone_idx++;
		}
	}

	if (zone_idx > 0)
		ret = zone_idx;
	else
		ret = -EINVAL;
fail_report:
	mutex_unlock(&vblk->vdev_mutex);
	kvfree(report);
	return ret;
}

static int virtblk_read_zoned_limits(struct virtio_blk *vblk,
		struct queue_limits *lim)
{
	struct virtio_device *vdev = vblk->vdev;
	u32 v, wg;

	dev_dbg(&vdev->dev, "probing host-managed zoned device\n");

	lim->zoned = true;

	virtio_cread(vdev, struct virtio_blk_config,
		     zoned.max_open_zones, &v);
	lim->max_open_zones = v;
	dev_dbg(&vdev->dev, "max open zones = %u\n", v);

	virtio_cread(vdev, struct virtio_blk_config,
		     zoned.max_active_zones, &v);
	lim->max_active_zones = v;
	dev_dbg(&vdev->dev, "max active zones = %u\n", v);

	virtio_cread(vdev, struct virtio_blk_config,
		     zoned.write_granularity, &wg);
	if (!wg) {
		dev_warn(&vdev->dev, "zero write granularity reported\n");
		return -ENODEV;
	}
	lim->physical_block_size = wg;
	lim->io_min = wg;

	dev_dbg(&vdev->dev, "write granularity = %u\n", wg);

	/*
	 * virtio ZBD specification doesn't require zones to be a power of
	 * two sectors in size, but the code in this driver expects that.
	 */
	virtio_cread(vdev, struct virtio_blk_config, zoned.zone_sectors,
		     &vblk->zone_sectors);
	if (vblk->zone_sectors == 0 || !is_power_of_2(vblk->zone_sectors)) {
		dev_err(&vdev->dev,
			"zoned device with non power of two zone size %u\n",
			vblk->zone_sectors);
		return -ENODEV;
	}
	lim->chunk_sectors = vblk->zone_sectors;
	dev_dbg(&vdev->dev, "zone sectors = %u\n", vblk->zone_sectors);

	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
		dev_warn(&vblk->vdev->dev,
			 "ignoring negotiated F_DISCARD for zoned device\n");
		lim->max_hw_discard_sectors = 0;
	}

	virtio_cread(vdev, struct virtio_blk_config,
		     zoned.max_append_sectors, &v);
	if (!v) {
		dev_warn(&vdev->dev, "zero max_append_sectors reported\n");
		return -ENODEV;
	}
	if ((v << SECTOR_SHIFT) < wg) {
		dev_err(&vdev->dev,
			"write granularity %u exceeds max_append_sectors %u limit\n",
			wg, v);
		return -ENODEV;
	}
	lim->max_zone_append_sectors = v;
	dev_dbg(&vdev->dev, "max append sectors = %u\n", v);

	return 0;
}
#else
/*
 * Zoned block device support is not configured in this kernel, host-managed
 * zoned devices can't be supported.
 */
#define virtblk_report_zones       NULL
static inline int virtblk_read_zoned_limits(struct virtio_blk *vblk,
		struct queue_limits *lim)
{
	dev_err(&vblk->vdev->dev,
		"virtio_blk: zoned devices are not supported");
	return -EOPNOTSUPP;
}
#endif /* CONFIG_BLK_DEV_ZONED */

/* 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;
	struct virtblk_req *vbr;
	int err;

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

	vbr = blk_mq_rq_to_pdu(req);
	vbr->in_hdr_len = sizeof(vbr->in_hdr.status);
	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
	vbr->out_hdr.sector = 0;

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

	blk_execute_rq(req, false);
	err = blk_status_to_errno(virtblk_result(vbr->in_hdr.status));
out:
	blk_mq_free_request(req);
	return err;
}

/* 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 void virtblk_free_disk(struct gendisk *disk)
{
	struct virtio_blk *vblk = disk->private_data;

	ida_free(&vd_index_ida, vblk->index);
	mutex_destroy(&vblk->vdev_mutex);
	kfree(vblk);
}

static const struct block_device_operations virtblk_fops = {
	.owner  	= THIS_MODULE,
	.getgeo		= virtblk_getgeo,
	.free_disk	= virtblk_free_disk,
	.report_zones	= virtblk_report_zones,
};

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);

	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;
	unsigned short i;
	vq_callback_t **callbacks;
	const char **names;
	struct virtqueue **vqs;
	unsigned short num_vqs;
	unsigned short num_poll_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;

	if (!err && !num_vqs) {
		dev_err(&vdev->dev, "MQ advertised but zero queues reported\n");
		return -EINVAL;
	}

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

	num_poll_vqs = min_t(unsigned int, poll_queues, num_vqs - 1);

	vblk->io_queues[HCTX_TYPE_DEFAULT] = num_vqs - num_poll_vqs;
	vblk->io_queues[HCTX_TYPE_READ] = 0;
	vblk->io_queues[HCTX_TYPE_POLL] = num_poll_vqs;

	dev_info(&vdev->dev, "%d/%d/%d default/read/poll queues\n",
				vblk->io_queues[HCTX_TYPE_DEFAULT],
				vblk->io_queues[HCTX_TYPE_READ],
				vblk->io_queues[HCTX_TYPE_POLL]);

	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 - num_poll_vqs; i++) {
		callbacks[i] = virtblk_done;
		snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%u", i);
		names[i] = vblk->vqs[i].name;
	}

	for (; i < num_vqs; i++) {
		callbacks[i] = NULL;
		snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%u", 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 sysfs_emit(buf, "%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 void virtblk_map_queues(struct blk_mq_tag_set *set)
{
	struct virtio_blk *vblk = set->driver_data;
	int i, qoff;

	for (i = 0, qoff = 0; i < set->nr_maps; i++) {
		struct blk_mq_queue_map *map = &set->map[i];

		map->nr_queues = vblk->io_queues[i];
		map->queue_offset = qoff;
		qoff += map->nr_queues;

		if (map->nr_queues == 0)
			continue;

		/*
		 * Regular queues have interrupts and hence CPU affinity is
		 * defined by the core virtio code, but polling queues have
		 * no interrupts so we let the block layer assign CPU affinity.
		 */
		if (i == HCTX_TYPE_POLL)
			blk_mq_map_queues(&set->map[i]);
		else
			blk_mq_virtio_map_queues(&set->map[i], vblk->vdev, 0);
	}
}

static void virtblk_complete_batch(struct io_comp_batch *iob)
{
	struct request *req;

	rq_list_for_each(&iob->req_list, req) {
		virtblk_unmap_data(req, blk_mq_rq_to_pdu(req));
		virtblk_cleanup_cmd(req);
	}
	blk_mq_end_request_batch(iob);
}

static int virtblk_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
{
	struct virtio_blk *vblk = hctx->queue->queuedata;
	struct virtio_blk_vq *vq = get_virtio_blk_vq(hctx);
	struct virtblk_req *vbr;
	unsigned long flags;
	unsigned int len;
	int found = 0;

	spin_lock_irqsave(&vq->lock, flags);

	while ((vbr = virtqueue_get_buf(vq->vq, &len)) != NULL) {
		struct request *req = blk_mq_rq_from_pdu(vbr);

		found++;
		if (!blk_mq_complete_request_remote(req) &&
		    !blk_mq_add_to_batch(req, iob, virtblk_vbr_status(vbr),
						virtblk_complete_batch))
			virtblk_request_done(req);
	}

	if (found)
		blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);

	spin_unlock_irqrestore(&vq->lock, flags);

	return found;
}

static const struct blk_mq_ops virtio_mq_ops = {
	.queue_rq	= virtio_queue_rq,
	.queue_rqs	= virtio_queue_rqs,
	.commit_rqs	= virtio_commit_rqs,
	.complete	= virtblk_request_done,
	.map_queues	= virtblk_map_queues,
	.poll		= virtblk_poll,
};

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

static int virtblk_read_limits(struct virtio_blk *vblk,
		struct queue_limits *lim)
{
	struct virtio_device *vdev = vblk->vdev;
	u32 v, blk_size, max_size, sg_elems, opt_io_size;
	u32 max_discard_segs = 0;
	u32 discard_granularity = 0;
	u16 min_io_size;
	u8 physical_block_exp, alignment_offset;
	size_t max_dma_size;
	int 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;

	/* Prevent integer overflows and honor max vq size */
	sg_elems = min_t(u32, sg_elems, VIRTIO_BLK_MAX_SG_ELEMS - 2);

	/* We can handle whatever the host told us to handle. */
	lim->max_segments = sg_elems;

	/* No real sector limit. */
	lim->max_hw_sectors = UINT_MAX;

	max_dma_size = virtio_max_dma_size(vdev);
	max_size = max_dma_size > U32_MAX ? U32_MAX : max_dma_size;

	/* 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);

	lim->max_segment_size = 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) {
		err = blk_validate_block_size(blk_size);
		if (err) {
			dev_err(&vdev->dev,
				"virtio_blk: invalid block size: 0x%x\n",
				blk_size);
			return err;
		}

		lim->logical_block_size = blk_size;
	} else
		blk_size = lim->logical_block_size;

	/* 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)
		lim->physical_block_size = 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)
		lim->alignment_offset = 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)
		lim->io_min = 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)
		lim->io_opt = blk_size * opt_io_size;

	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
		virtio_cread(vdev, struct virtio_blk_config,
			     discard_sector_alignment, &discard_granularity);

		virtio_cread(vdev, struct virtio_blk_config,
			     max_discard_sectors, &v);
		lim->max_hw_discard_sectors = v ? v : UINT_MAX;

		virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
			     &max_discard_segs);
	}

	if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
		virtio_cread(vdev, struct virtio_blk_config,
			     max_write_zeroes_sectors, &v);
		lim->max_write_zeroes_sectors = v ? v : UINT_MAX;
	}

	/* The discard and secure erase limits are combined since the Linux
	 * block layer uses the same limit for both commands.
	 *
	 * If both VIRTIO_BLK_F_SECURE_ERASE and VIRTIO_BLK_F_DISCARD features
	 * are negotiated, we will use the minimum between the limits.
	 *
	 * discard sector alignment is set to the minimum between discard_sector_alignment
	 * and secure_erase_sector_alignment.
	 *
	 * max discard sectors is set to the minimum between max_discard_seg and
	 * max_secure_erase_seg.
	 */
	if (virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) {

		virtio_cread(vdev, struct virtio_blk_config,
			     secure_erase_sector_alignment, &v);

		/* secure_erase_sector_alignment should not be zero, the device should set a
		 * valid number of sectors.
		 */
		if (!v) {
			dev_err(&vdev->dev,
				"virtio_blk: secure_erase_sector_alignment can't be 0\n");
			return -EINVAL;
		}

		discard_granularity = min_not_zero(discard_granularity, v);

		virtio_cread(vdev, struct virtio_blk_config,
			     max_secure_erase_sectors, &v);

		/* max_secure_erase_sectors should not be zero, the device should set a
		 * valid number of sectors.
		 */
		if (!v) {
			dev_err(&vdev->dev,
				"virtio_blk: max_secure_erase_sectors can't be 0\n");
			return -EINVAL;
		}

		lim->max_secure_erase_sectors = v;

		virtio_cread(vdev, struct virtio_blk_config,
			     max_secure_erase_seg, &v);

		/* max_secure_erase_seg should not be zero, the device should set a
		 * valid number of segments
		 */
		if (!v) {
			dev_err(&vdev->dev,
				"virtio_blk: max_secure_erase_seg can't be 0\n");
			return -EINVAL;
		}

		max_discard_segs = min_not_zero(max_discard_segs, v);
	}

	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD) ||
	    virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) {
		/* max_discard_seg and discard_granularity will be 0 only
		 * if max_discard_seg and discard_sector_alignment fields in the virtio
		 * config are 0 and VIRTIO_BLK_F_SECURE_ERASE feature is not negotiated.
		 * In this case, we use default values.
		 */
		if (!max_discard_segs)
			max_discard_segs = sg_elems;

		lim->max_discard_segments =
			min(max_discard_segs, MAX_DISCARD_SEGMENTS);

		if (discard_granularity)
			lim->discard_granularity =
				discard_granularity << SECTOR_SHIFT;
		else
			lim->discard_granularity = blk_size;
	}

	if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) {
		u8 model;

		virtio_cread(vdev, struct virtio_blk_config, zoned.model, &model);
		switch (model) {
		case VIRTIO_BLK_Z_NONE:
		case VIRTIO_BLK_Z_HA:
			/* treat host-aware devices as non-zoned */
			return 0;
		case VIRTIO_BLK_Z_HM:
			err = virtblk_read_zoned_limits(vblk, lim);
			if (err)
				return err;
			break;
		default:
			dev_err(&vdev->dev, "unsupported zone model %d\n", model);
			return -EINVAL;
		}
	}

	return 0;
}

static int virtblk_probe(struct virtio_device *vdev)
{
	struct virtio_blk *vblk;
	struct queue_limits lim = { };
	int err, index;
	unsigned int queue_depth;

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

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

	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
	if (!vblk) {
		err = -ENOMEM;
		goto out_free_index;
	}

	mutex_init(&vblk->vdev_mutex);

	vblk->vdev = vdev;

	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);

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

	/* Default queue sizing is to fill the ring. */
	if (!virtblk_queue_depth) {
		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))
			queue_depth /= 2;
	} else {
		queue_depth = virtblk_queue_depth;
	}

	memset(&vblk->tag_set, 0, sizeof(vblk->tag_set));
	vblk->tag_set.ops = &virtio_mq_ops;
	vblk->tag_set.queue_depth = 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) * VIRTIO_BLK_INLINE_SG_CNT;
	vblk->tag_set.driver_data = vblk;
	vblk->tag_set.nr_hw_queues = vblk->num_vqs;
	vblk->tag_set.nr_maps = 1;
	if (vblk->io_queues[HCTX_TYPE_POLL])
		vblk->tag_set.nr_maps = 3;

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

	err = virtblk_read_limits(vblk, &lim);
	if (err)
		goto out_free_tags;

	vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, &lim, vblk);
	if (IS_ERR(vblk->disk)) {
		err = PTR_ERR(vblk->disk);
		goto out_free_tags;
	}

	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->minors = 1 << PART_BITS;
	vblk->disk->private_data = vblk;
	vblk->disk->fops = &virtblk_fops;
	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);

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

	/*
	 * All steps that follow use the VQs therefore they need to be
	 * placed after the virtio_device_ready() call above.
	 */
	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) {
		blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue);
		err = blk_revalidate_disk_zones(vblk->disk, NULL);
		if (err)
			goto out_cleanup_disk;
	}

	err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups);
	if (err)
		goto out_cleanup_disk;

	return 0;

out_cleanup_disk:
	put_disk(vblk->disk);
out_free_tags:
	blk_mq_free_tag_set(&vblk->tag_set);
out_free_vq:
	vdev->config->del_vqs(vdev);
	kfree(vblk->vqs);
out_free_vblk:
	kfree(vblk);
out_free_index:
	ida_free(&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_mq_free_tag_set(&vblk->tag_set);

	mutex_lock(&vblk->vdev_mutex);

	/* Stop all the virtqueues. */
	virtio_reset_device(vdev);

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

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

	mutex_unlock(&vblk->vdev_mutex);

	put_disk(vblk->disk);
}

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

	/* Ensure no requests in virtqueues before deleting vqs. */
	blk_mq_freeze_queue(vblk->disk->queue);

	/* Ensure we don't receive any more interrupts */
	virtio_reset_device(vdev);

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

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

	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_unfreeze_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,
	VIRTIO_BLK_F_SECURE_ERASE,
}
;
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,
	VIRTIO_BLK_F_SECURE_ERASE, VIRTIO_BLK_F_ZONED,
};

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 virtio_blk_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 virtio_blk_fini(void)
{
	unregister_virtio_driver(&virtio_blk);
	unregister_blkdev(major, "virtblk");
	destroy_workqueue(virtblk_wq);
}
module_init(virtio_blk_init);
module_exit(virtio_blk_fini);

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