summaryrefslogtreecommitdiff
path: root/include/linux/blkdev.h
blob: 824e31dd752acb0f5cf5d5684b2aaed27778b796 (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
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Portions Copyright (C) 1992 Drew Eckhardt
 */
#ifndef _LINUX_BLKDEV_H
#define _LINUX_BLKDEV_H

#include <linux/types.h>
#include <linux/blk_types.h>
#include <linux/device.h>
#include <linux/list.h>
#include <linux/llist.h>
#include <linux/minmax.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/wait.h>
#include <linux/bio.h>
#include <linux/gfp.h>
#include <linux/kdev_t.h>
#include <linux/rcupdate.h>
#include <linux/percpu-refcount.h>
#include <linux/blkzoned.h>
#include <linux/sched.h>
#include <linux/sbitmap.h>
#include <linux/uuid.h>
#include <linux/xarray.h>

struct module;
struct request_queue;
struct elevator_queue;
struct blk_trace;
struct request;
struct sg_io_hdr;
struct blkcg_gq;
struct blk_flush_queue;
struct kiocb;
struct pr_ops;
struct rq_qos;
struct blk_queue_stats;
struct blk_stat_callback;
struct blk_crypto_profile;

extern const struct device_type disk_type;
extern const struct device_type part_type;
extern struct class block_class;

/*
 * Maximum number of blkcg policies allowed to be registered concurrently.
 * Defined here to simplify include dependency.
 */
#define BLKCG_MAX_POLS		6

#define DISK_MAX_PARTS			256
#define DISK_NAME_LEN			32

#define PARTITION_META_INFO_VOLNAMELTH	64
/*
 * Enough for the string representation of any kind of UUID plus NULL.
 * EFI UUID is 36 characters. MSDOS UUID is 11 characters.
 */
#define PARTITION_META_INFO_UUIDLTH	(UUID_STRING_LEN + 1)

struct partition_meta_info {
	char uuid[PARTITION_META_INFO_UUIDLTH];
	u8 volname[PARTITION_META_INFO_VOLNAMELTH];
};

/**
 * DOC: genhd capability flags
 *
 * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to
 * removable media.  When set, the device remains present even when media is not
 * inserted.  Shall not be set for devices which are removed entirely when the
 * media is removed.
 *
 * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events,
 * doesn't appear in sysfs, and can't be opened from userspace or using
 * blkdev_get*. Used for the underlying components of multipath devices.
 *
 * ``GENHD_FL_NO_PART``: partition support is disabled.  The kernel will not
 * scan for partitions from add_disk, and users can't add partitions manually.
 *
 */
enum {
	GENHD_FL_REMOVABLE			= 1 << 0,
	GENHD_FL_HIDDEN				= 1 << 1,
	GENHD_FL_NO_PART			= 1 << 2,
};

enum {
	DISK_EVENT_MEDIA_CHANGE			= 1 << 0, /* media changed */
	DISK_EVENT_EJECT_REQUEST		= 1 << 1, /* eject requested */
};

enum {
	/* Poll even if events_poll_msecs is unset */
	DISK_EVENT_FLAG_POLL			= 1 << 0,
	/* Forward events to udev */
	DISK_EVENT_FLAG_UEVENT			= 1 << 1,
	/* Block event polling when open for exclusive write */
	DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE	= 1 << 2,
};

struct disk_events;
struct badblocks;

struct blk_integrity {
	const struct blk_integrity_profile	*profile;
	unsigned char				flags;
	unsigned char				tuple_size;
	unsigned char				interval_exp;
	unsigned char				tag_size;
};

typedef unsigned int __bitwise blk_mode_t;

/* open for reading */
#define BLK_OPEN_READ		((__force blk_mode_t)(1 << 0))
/* open for writing */
#define BLK_OPEN_WRITE		((__force blk_mode_t)(1 << 1))
/* open exclusively (vs other exclusive openers */
#define BLK_OPEN_EXCL		((__force blk_mode_t)(1 << 2))
/* opened with O_NDELAY */
#define BLK_OPEN_NDELAY		((__force blk_mode_t)(1 << 3))
/* open for "writes" only for ioctls (specialy hack for floppy.c) */
#define BLK_OPEN_WRITE_IOCTL	((__force blk_mode_t)(1 << 4))

struct gendisk {
	/*
	 * major/first_minor/minors should not be set by any new driver, the
	 * block core will take care of allocating them automatically.
	 */
	int major;
	int first_minor;
	int minors;

	char disk_name[DISK_NAME_LEN];	/* name of major driver */

	unsigned short events;		/* supported events */
	unsigned short event_flags;	/* flags related to event processing */

	struct xarray part_tbl;
	struct block_device *part0;

	const struct block_device_operations *fops;
	struct request_queue *queue;
	void *private_data;

	struct bio_set bio_split;

	int flags;
	unsigned long state;
#define GD_NEED_PART_SCAN		0
#define GD_READ_ONLY			1
#define GD_DEAD				2
#define GD_NATIVE_CAPACITY		3
#define GD_ADDED			4
#define GD_SUPPRESS_PART_SCAN		5
#define GD_OWNS_QUEUE			6

	struct mutex open_mutex;	/* open/close mutex */
	unsigned open_partitions;	/* number of open partitions */

	struct backing_dev_info	*bdi;
	struct kobject queue_kobj;	/* the queue/ directory */
	struct kobject *slave_dir;
#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
	struct list_head slave_bdevs;
#endif
	struct timer_rand_state *random;
	atomic_t sync_io;		/* RAID */
	struct disk_events *ev;

#ifdef CONFIG_BLK_DEV_ZONED
	/*
	 * Zoned block device information for request dispatch control.
	 * nr_zones is the total number of zones of the device. This is always
	 * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones
	 * bits which indicates if a zone is conventional (bit set) or
	 * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones
	 * bits which indicates if a zone is write locked, that is, if a write
	 * request targeting the zone was dispatched.
	 *
	 * Reads of this information must be protected with blk_queue_enter() /
	 * blk_queue_exit(). Modifying this information is only allowed while
	 * no requests are being processed. See also blk_mq_freeze_queue() and
	 * blk_mq_unfreeze_queue().
	 */
	unsigned int		nr_zones;
	unsigned int		max_open_zones;
	unsigned int		max_active_zones;
	unsigned long		*conv_zones_bitmap;
	unsigned long		*seq_zones_wlock;
#endif /* CONFIG_BLK_DEV_ZONED */

#if IS_ENABLED(CONFIG_CDROM)
	struct cdrom_device_info *cdi;
#endif
	int node_id;
	struct badblocks *bb;
	struct lockdep_map lockdep_map;
	u64 diskseq;
	blk_mode_t open_mode;

	/*
	 * Independent sector access ranges. This is always NULL for
	 * devices that do not have multiple independent access ranges.
	 */
	struct blk_independent_access_ranges *ia_ranges;
};

static inline bool disk_live(struct gendisk *disk)
{
	return !inode_unhashed(disk->part0->bd_inode);
}

/**
 * disk_openers - returns how many openers are there for a disk
 * @disk: disk to check
 *
 * This returns the number of openers for a disk.  Note that this value is only
 * stable if disk->open_mutex is held.
 *
 * Note: Due to a quirk in the block layer open code, each open partition is
 * only counted once even if there are multiple openers.
 */
static inline unsigned int disk_openers(struct gendisk *disk)
{
	return atomic_read(&disk->part0->bd_openers);
}

/*
 * The gendisk is refcounted by the part0 block_device, and the bd_device
 * therein is also used for device model presentation in sysfs.
 */
#define dev_to_disk(device) \
	(dev_to_bdev(device)->bd_disk)
#define disk_to_dev(disk) \
	(&((disk)->part0->bd_device))

#if IS_REACHABLE(CONFIG_CDROM)
#define disk_to_cdi(disk)	((disk)->cdi)
#else
#define disk_to_cdi(disk)	NULL
#endif

static inline dev_t disk_devt(struct gendisk *disk)
{
	return MKDEV(disk->major, disk->first_minor);
}

static inline int blk_validate_block_size(unsigned long bsize)
{
	if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
		return -EINVAL;

	return 0;
}

static inline bool blk_op_is_passthrough(blk_opf_t op)
{
	op &= REQ_OP_MASK;
	return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
}

/*
 * Zoned block device models (zoned limit).
 *
 * Note: This needs to be ordered from the least to the most severe
 * restrictions for the inheritance in blk_stack_limits() to work.
 */
enum blk_zoned_model {
	BLK_ZONED_NONE = 0,	/* Regular block device */
	BLK_ZONED_HA,		/* Host-aware zoned block device */
	BLK_ZONED_HM,		/* Host-managed zoned block device */
};

/*
 * BLK_BOUNCE_NONE:	never bounce (default)
 * BLK_BOUNCE_HIGH:	bounce all highmem pages
 */
enum blk_bounce {
	BLK_BOUNCE_NONE,
	BLK_BOUNCE_HIGH,
};

struct queue_limits {
	enum blk_bounce		bounce;
	unsigned long		seg_boundary_mask;
	unsigned long		virt_boundary_mask;

	unsigned int		max_hw_sectors;
	unsigned int		max_dev_sectors;
	unsigned int		chunk_sectors;
	unsigned int		max_sectors;
	unsigned int		max_user_sectors;
	unsigned int		max_segment_size;
	unsigned int		physical_block_size;
	unsigned int		logical_block_size;
	unsigned int		alignment_offset;
	unsigned int		io_min;
	unsigned int		io_opt;
	unsigned int		max_discard_sectors;
	unsigned int		max_hw_discard_sectors;
	unsigned int		max_secure_erase_sectors;
	unsigned int		max_write_zeroes_sectors;
	unsigned int		max_zone_append_sectors;
	unsigned int		discard_granularity;
	unsigned int		discard_alignment;
	unsigned int		zone_write_granularity;

	unsigned short		max_segments;
	unsigned short		max_integrity_segments;
	unsigned short		max_discard_segments;

	unsigned char		misaligned;
	unsigned char		discard_misaligned;
	unsigned char		raid_partial_stripes_expensive;
	enum blk_zoned_model	zoned;

	/*
	 * Drivers that set dma_alignment to less than 511 must be prepared to
	 * handle individual bvec's that are not a multiple of a SECTOR_SIZE
	 * due to possible offsets.
	 */
	unsigned int		dma_alignment;
};

typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
			       void *data);

void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);

#ifdef CONFIG_BLK_DEV_ZONED
#define BLK_ALL_ZONES  ((unsigned int)-1)
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
			unsigned int nr_zones, report_zones_cb cb, void *data);
unsigned int bdev_nr_zones(struct block_device *bdev);
extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
			    sector_t sectors, sector_t nr_sectors,
			    gfp_t gfp_mask);
int blk_revalidate_disk_zones(struct gendisk *disk,
			      void (*update_driver_data)(struct gendisk *disk));
#else /* CONFIG_BLK_DEV_ZONED */
static inline unsigned int bdev_nr_zones(struct block_device *bdev)
{
	return 0;
}
#endif /* CONFIG_BLK_DEV_ZONED */

/*
 * Independent access ranges: struct blk_independent_access_range describes
 * a range of contiguous sectors that can be accessed using device command
 * execution resources that are independent from the resources used for
 * other access ranges. This is typically found with single-LUN multi-actuator
 * HDDs where each access range is served by a different set of heads.
 * The set of independent ranges supported by the device is defined using
 * struct blk_independent_access_ranges. The independent ranges must not overlap
 * and must include all sectors within the disk capacity (no sector holes
 * allowed).
 * For a device with multiple ranges, requests targeting sectors in different
 * ranges can be executed in parallel. A request can straddle an access range
 * boundary.
 */
struct blk_independent_access_range {
	struct kobject		kobj;
	sector_t		sector;
	sector_t		nr_sectors;
};

struct blk_independent_access_ranges {
	struct kobject				kobj;
	bool					sysfs_registered;
	unsigned int				nr_ia_ranges;
	struct blk_independent_access_range	ia_range[];
};

struct request_queue {
	struct request		*last_merge;
	struct elevator_queue	*elevator;

	struct percpu_ref	q_usage_counter;

	struct blk_queue_stats	*stats;
	struct rq_qos		*rq_qos;
	struct mutex		rq_qos_mutex;

	const struct blk_mq_ops	*mq_ops;

	/* sw queues */
	struct blk_mq_ctx __percpu	*queue_ctx;

	unsigned int		queue_depth;

	/* hw dispatch queues */
	struct xarray		hctx_table;
	unsigned int		nr_hw_queues;

	/*
	 * The queue owner gets to use this for whatever they like.
	 * ll_rw_blk doesn't touch it.
	 */
	void			*queuedata;

	/*
	 * various queue flags, see QUEUE_* below
	 */
	unsigned long		queue_flags;
	/*
	 * Number of contexts that have called blk_set_pm_only(). If this
	 * counter is above zero then only RQF_PM requests are processed.
	 */
	atomic_t		pm_only;

	/*
	 * ida allocated id for this queue.  Used to index queues from
	 * ioctx.
	 */
	int			id;

	spinlock_t		queue_lock;

	struct gendisk		*disk;

	refcount_t		refs;

	/*
	 * mq queue kobject
	 */
	struct kobject *mq_kobj;

#ifdef  CONFIG_BLK_DEV_INTEGRITY
	struct blk_integrity integrity;
#endif	/* CONFIG_BLK_DEV_INTEGRITY */

#ifdef CONFIG_PM
	struct device		*dev;
	enum rpm_status		rpm_status;
#endif

	/*
	 * queue settings
	 */
	unsigned long		nr_requests;	/* Max # of requests */

	unsigned int		dma_pad_mask;

#ifdef CONFIG_BLK_INLINE_ENCRYPTION
	struct blk_crypto_profile *crypto_profile;
	struct kobject *crypto_kobject;
#endif

	unsigned int		rq_timeout;

	struct timer_list	timeout;
	struct work_struct	timeout_work;

	atomic_t		nr_active_requests_shared_tags;

	struct blk_mq_tags	*sched_shared_tags;

	struct list_head	icq_list;
#ifdef CONFIG_BLK_CGROUP
	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);
	struct blkcg_gq		*root_blkg;
	struct list_head	blkg_list;
	struct mutex		blkcg_mutex;
#endif

	struct queue_limits	limits;

	unsigned int		required_elevator_features;

	int			node;
#ifdef CONFIG_BLK_DEV_IO_TRACE
	struct blk_trace __rcu	*blk_trace;
#endif
	/*
	 * for flush operations
	 */
	struct blk_flush_queue	*fq;
	struct list_head	flush_list;

	struct list_head	requeue_list;
	spinlock_t		requeue_lock;
	struct delayed_work	requeue_work;

	struct mutex		sysfs_lock;
	struct mutex		sysfs_dir_lock;

	/*
	 * for reusing dead hctx instance in case of updating
	 * nr_hw_queues
	 */
	struct list_head	unused_hctx_list;
	spinlock_t		unused_hctx_lock;

	int			mq_freeze_depth;

#ifdef CONFIG_BLK_DEV_THROTTLING
	/* Throttle data */
	struct throtl_data *td;
#endif
	struct rcu_head		rcu_head;
	wait_queue_head_t	mq_freeze_wq;
	/*
	 * Protect concurrent access to q_usage_counter by
	 * percpu_ref_kill() and percpu_ref_reinit().
	 */
	struct mutex		mq_freeze_lock;

	int			quiesce_depth;

	struct blk_mq_tag_set	*tag_set;
	struct list_head	tag_set_list;

	struct dentry		*debugfs_dir;
	struct dentry		*sched_debugfs_dir;
	struct dentry		*rqos_debugfs_dir;
	/*
	 * Serializes all debugfs metadata operations using the above dentries.
	 */
	struct mutex		debugfs_mutex;

	bool			mq_sysfs_init_done;
};

/* Keep blk_queue_flag_name[] in sync with the definitions below */
#define QUEUE_FLAG_STOPPED	0	/* queue is stopped */
#define QUEUE_FLAG_DYING	1	/* queue being torn down */
#define QUEUE_FLAG_NOMERGES     3	/* disable merge attempts */
#define QUEUE_FLAG_SAME_COMP	4	/* complete on same CPU-group */
#define QUEUE_FLAG_FAIL_IO	5	/* fake timeout */
#define QUEUE_FLAG_NONROT	6	/* non-rotational device (SSD) */
#define QUEUE_FLAG_VIRT		QUEUE_FLAG_NONROT /* paravirt device */
#define QUEUE_FLAG_IO_STAT	7	/* do disk/partitions IO accounting */
#define QUEUE_FLAG_NOXMERGES	9	/* No extended merges */
#define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
#define QUEUE_FLAG_SYNCHRONOUS	11	/* always completes in submit context */
#define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
#define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
#define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
#define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
#define QUEUE_FLAG_WC		17	/* Write back caching */
#define QUEUE_FLAG_FUA		18	/* device supports FUA writes */
#define QUEUE_FLAG_DAX		19	/* device supports DAX */
#define QUEUE_FLAG_STATS	20	/* track IO start and completion times */
#define QUEUE_FLAG_REGISTERED	22	/* queue has been registered to a disk */
#define QUEUE_FLAG_QUIESCED	24	/* queue has been quiesced */
#define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
#define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
#define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
#define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
#define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
#define QUEUE_FLAG_SQ_SCHED     30	/* single queue style io dispatch */
#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE	31 /* quiesce_tagset skip the queue*/

#define QUEUE_FLAG_MQ_DEFAULT	((1UL << QUEUE_FLAG_IO_STAT) |		\
				 (1UL << QUEUE_FLAG_SAME_COMP) |	\
				 (1UL << QUEUE_FLAG_NOWAIT))

void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);

#define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
#define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
#define blk_queue_init_done(q)	test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
#define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
#define blk_queue_noxmerges(q)	\
	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
#define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
#define blk_queue_stable_writes(q) \
	test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
#define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
#define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
#define blk_queue_zone_resetall(q)	\
	test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
#define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
#define blk_queue_pci_p2pdma(q)	\
	test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
#define blk_queue_rq_alloc_time(q)	\
	test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags)
#else
#define blk_queue_rq_alloc_time(q)	false
#endif

#define blk_noretry_request(rq) \
	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
			     REQ_FAILFAST_DRIVER))
#define blk_queue_quiesced(q)	test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
#define blk_queue_pm_only(q)	atomic_read(&(q)->pm_only)
#define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
#define blk_queue_sq_sched(q)	test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
#define blk_queue_skip_tagset_quiesce(q) \
	test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags)

extern void blk_set_pm_only(struct request_queue *q);
extern void blk_clear_pm_only(struct request_queue *q);

#define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)

#define dma_map_bvec(dev, bv, dir, attrs) \
	dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \
	(dir), (attrs))

static inline bool queue_is_mq(struct request_queue *q)
{
	return q->mq_ops;
}

#ifdef CONFIG_PM
static inline enum rpm_status queue_rpm_status(struct request_queue *q)
{
	return q->rpm_status;
}
#else
static inline enum rpm_status queue_rpm_status(struct request_queue *q)
{
	return RPM_ACTIVE;
}
#endif

static inline enum blk_zoned_model
blk_queue_zoned_model(struct request_queue *q)
{
	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
		return q->limits.zoned;
	return BLK_ZONED_NONE;
}

static inline bool blk_queue_is_zoned(struct request_queue *q)
{
	switch (blk_queue_zoned_model(q)) {
	case BLK_ZONED_HA:
	case BLK_ZONED_HM:
		return true;
	default:
		return false;
	}
}

#ifdef CONFIG_BLK_DEV_ZONED
static inline unsigned int disk_nr_zones(struct gendisk *disk)
{
	return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0;
}

static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
{
	if (!blk_queue_is_zoned(disk->queue))
		return 0;
	return sector >> ilog2(disk->queue->limits.chunk_sectors);
}

static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
{
	if (!blk_queue_is_zoned(disk->queue))
		return false;
	if (!disk->conv_zones_bitmap)
		return true;
	return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap);
}

static inline void disk_set_max_open_zones(struct gendisk *disk,
		unsigned int max_open_zones)
{
	disk->max_open_zones = max_open_zones;
}

static inline void disk_set_max_active_zones(struct gendisk *disk,
		unsigned int max_active_zones)
{
	disk->max_active_zones = max_active_zones;
}

static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
{
	return bdev->bd_disk->max_open_zones;
}

static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
{
	return bdev->bd_disk->max_active_zones;
}

#else /* CONFIG_BLK_DEV_ZONED */
static inline unsigned int disk_nr_zones(struct gendisk *disk)
{
	return 0;
}
static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
{
	return false;
}
static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
{
	return 0;
}
static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
{
	return 0;
}

static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
{
	return 0;
}
#endif /* CONFIG_BLK_DEV_ZONED */

static inline unsigned int blk_queue_depth(struct request_queue *q)
{
	if (q->queue_depth)
		return q->queue_depth;

	return q->nr_requests;
}

/*
 * default timeout for SG_IO if none specified
 */
#define BLK_DEFAULT_SG_TIMEOUT	(60 * HZ)
#define BLK_MIN_SG_TIMEOUT	(7 * HZ)

/* This should not be used directly - use rq_for_each_segment */
#define for_each_bio(_bio)		\
	for (; _bio; _bio = _bio->bi_next)

int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
				 const struct attribute_group **groups);
static inline int __must_check add_disk(struct gendisk *disk)
{
	return device_add_disk(NULL, disk, NULL);
}
void del_gendisk(struct gendisk *gp);
void invalidate_disk(struct gendisk *disk);
void set_disk_ro(struct gendisk *disk, bool read_only);
void disk_uevent(struct gendisk *disk, enum kobject_action action);

static inline int get_disk_ro(struct gendisk *disk)
{
	return disk->part0->bd_read_only ||
		test_bit(GD_READ_ONLY, &disk->state);
}

static inline int bdev_read_only(struct block_device *bdev)
{
	return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
}

bool set_capacity_and_notify(struct gendisk *disk, sector_t size);
bool disk_force_media_change(struct gendisk *disk, unsigned int events);

void add_disk_randomness(struct gendisk *disk) __latent_entropy;
void rand_initialize_disk(struct gendisk *disk);

static inline sector_t get_start_sect(struct block_device *bdev)
{
	return bdev->bd_start_sect;
}

static inline sector_t bdev_nr_sectors(struct block_device *bdev)
{
	return bdev->bd_nr_sectors;
}

static inline loff_t bdev_nr_bytes(struct block_device *bdev)
{
	return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT;
}

static inline sector_t get_capacity(struct gendisk *disk)
{
	return bdev_nr_sectors(disk->part0);
}

static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
{
	return bdev_nr_sectors(sb->s_bdev) >>
		(sb->s_blocksize_bits - SECTOR_SHIFT);
}

int bdev_disk_changed(struct gendisk *disk, bool invalidate);

void put_disk(struct gendisk *disk);
struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);

/**
 * blk_alloc_disk - allocate a gendisk structure
 * @node_id: numa node to allocate on
 *
 * Allocate and pre-initialize a gendisk structure for use with BIO based
 * drivers.
 *
 * Context: can sleep
 */
#define blk_alloc_disk(node_id)						\
({									\
	static struct lock_class_key __key;				\
									\
	__blk_alloc_disk(node_id, &__key);				\
})

int __register_blkdev(unsigned int major, const char *name,
		void (*probe)(dev_t devt));
#define register_blkdev(major, name) \
	__register_blkdev(major, name, NULL)
void unregister_blkdev(unsigned int major, const char *name);

bool disk_check_media_change(struct gendisk *disk);
int __invalidate_device(struct block_device *bdev, bool kill_dirty);
void set_capacity(struct gendisk *disk, sector_t size);

#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk);
#else
static inline int bd_link_disk_holder(struct block_device *bdev,
				      struct gendisk *disk)
{
	return 0;
}
static inline void bd_unlink_disk_holder(struct block_device *bdev,
					 struct gendisk *disk)
{
}
#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */

dev_t part_devt(struct gendisk *disk, u8 partno);
void inc_diskseq(struct gendisk *disk);
void blk_request_module(dev_t devt);

extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
void submit_bio_noacct(struct bio *bio);
struct bio *bio_split_to_limits(struct bio *bio);

extern int blk_lld_busy(struct request_queue *q);
extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags);
extern void blk_queue_exit(struct request_queue *q);
extern void blk_sync_queue(struct request_queue *q);

/* Helper to convert REQ_OP_XXX to its string format XXX */
extern const char *blk_op_str(enum req_op op);

int blk_status_to_errno(blk_status_t status);
blk_status_t errno_to_blk_status(int errno);

/* only poll the hardware once, don't continue until a completion was found */
#define BLK_POLL_ONESHOT		(1 << 0)
int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags);
int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
			unsigned int flags);

static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
{
	return bdev->bd_queue;	/* this is never NULL */
}

/* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */
const char *blk_zone_cond_str(enum blk_zone_cond zone_cond);

static inline unsigned int bio_zone_no(struct bio *bio)
{
	return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
}

static inline unsigned int bio_zone_is_seq(struct bio *bio)
{
	return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
}

/*
 * Return how much of the chunk is left to be used for I/O at a given offset.
 */
static inline unsigned int blk_chunk_sectors_left(sector_t offset,
		unsigned int chunk_sectors)
{
	if (unlikely(!is_power_of_2(chunk_sectors)))
		return chunk_sectors - sector_div(offset, chunk_sectors);
	return chunk_sectors - (offset & (chunk_sectors - 1));
}

/*
 * Access functions for manipulating queue properties
 */
void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit);
extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
extern void blk_queue_max_segments(struct request_queue *, unsigned short);
extern void blk_queue_max_discard_segments(struct request_queue *,
		unsigned short);
void blk_queue_max_secure_erase_sectors(struct request_queue *q,
		unsigned int max_sectors);
extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
extern void blk_queue_max_discard_sectors(struct request_queue *q,
		unsigned int max_discard_sectors);
extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
		unsigned int max_write_same_sectors);
extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
		unsigned int max_zone_append_sectors);
extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
void blk_queue_zone_write_granularity(struct request_queue *q,
				      unsigned int size);
extern void blk_queue_alignment_offset(struct request_queue *q,
				       unsigned int alignment);
void disk_update_readahead(struct gendisk *disk);
extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
extern void blk_set_stacking_limits(struct queue_limits *lim);
extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
			    sector_t offset);
extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
			      sector_t offset);
extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
extern void blk_queue_dma_alignment(struct request_queue *, int);
extern void blk_queue_update_dma_alignment(struct request_queue *, int);
extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);

struct blk_independent_access_ranges *
disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
void disk_set_independent_access_ranges(struct gendisk *disk,
				struct blk_independent_access_ranges *iars);

/*
 * Elevator features for blk_queue_required_elevator_features:
 */
/* Supports zoned block devices sequential write constraint */
#define ELEVATOR_F_ZBD_SEQ_WRITE	(1U << 0)

extern void blk_queue_required_elevator_features(struct request_queue *q,
						 unsigned int features);
extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
					      struct device *dev);

bool __must_check blk_get_queue(struct request_queue *);
extern void blk_put_queue(struct request_queue *);

void blk_mark_disk_dead(struct gendisk *disk);

#ifdef CONFIG_BLOCK
/*
 * blk_plug permits building a queue of related requests by holding the I/O
 * fragments for a short period. This allows merging of sequential requests
 * into single larger request. As the requests are moved from a per-task list to
 * the device's request_queue in a batch, this results in improved scalability
 * as the lock contention for request_queue lock is reduced.
 *
 * It is ok not to disable preemption when adding the request to the plug list
 * or when attempting a merge. For details, please see schedule() where
 * blk_flush_plug() is called.
 */
struct blk_plug {
	struct request *mq_list; /* blk-mq requests */

	/* if ios_left is > 1, we can batch tag/rq allocations */
	struct request *cached_rq;
	unsigned short nr_ios;

	unsigned short rq_count;

	bool multiple_queues;
	bool has_elevator;
	bool nowait;

	struct list_head cb_list; /* md requires an unplug callback */
};

struct blk_plug_cb;
typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool);
struct blk_plug_cb {
	struct list_head list;
	blk_plug_cb_fn callback;
	void *data;
};
extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug,
					     void *data, int size);
extern void blk_start_plug(struct blk_plug *);
extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short);
extern void blk_finish_plug(struct blk_plug *);

void __blk_flush_plug(struct blk_plug *plug, bool from_schedule);
static inline void blk_flush_plug(struct blk_plug *plug, bool async)
{
	if (plug)
		__blk_flush_plug(plug, async);
}

int blkdev_issue_flush(struct block_device *bdev);
long nr_blockdev_pages(void);
#else /* CONFIG_BLOCK */
struct blk_plug {
};

static inline void blk_start_plug_nr_ios(struct blk_plug *plug,
					 unsigned short nr_ios)
{
}

static inline void blk_start_plug(struct blk_plug *plug)
{
}

static inline void blk_finish_plug(struct blk_plug *plug)
{
}

static inline void blk_flush_plug(struct blk_plug *plug, bool async)
{
}

static inline int blkdev_issue_flush(struct block_device *bdev)
{
	return 0;
}

static inline long nr_blockdev_pages(void)
{
	return 0;
}
#endif /* CONFIG_BLOCK */

extern void blk_io_schedule(void);

int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp_mask);
int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop);
int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp);

#define BLKDEV_ZERO_NOUNMAP	(1 << 0)  /* do not free blocks */
#define BLKDEV_ZERO_NOFALLBACK	(1 << 1)  /* don't write explicit zeroes */

extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
		unsigned flags);
extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp_mask, unsigned flags);

static inline int sb_issue_discard(struct super_block *sb, sector_t block,
		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
{
	return blkdev_issue_discard(sb->s_bdev,
				    block << (sb->s_blocksize_bits -
					      SECTOR_SHIFT),
				    nr_blocks << (sb->s_blocksize_bits -
						  SECTOR_SHIFT),
				    gfp_mask);
}
static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
		sector_t nr_blocks, gfp_t gfp_mask)
{
	return blkdev_issue_zeroout(sb->s_bdev,
				    block << (sb->s_blocksize_bits -
					      SECTOR_SHIFT),
				    nr_blocks << (sb->s_blocksize_bits -
						  SECTOR_SHIFT),
				    gfp_mask, 0);
}

static inline bool bdev_is_partition(struct block_device *bdev)
{
	return bdev->bd_partno;
}

enum blk_default_limits {
	BLK_MAX_SEGMENTS	= 128,
	BLK_SAFE_MAX_SECTORS	= 255,
	BLK_MAX_SEGMENT_SIZE	= 65536,
	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
};

#define BLK_DEF_MAX_SECTORS 2560u

static inline unsigned long queue_segment_boundary(const struct request_queue *q)
{
	return q->limits.seg_boundary_mask;
}

static inline unsigned long queue_virt_boundary(const struct request_queue *q)
{
	return q->limits.virt_boundary_mask;
}

static inline unsigned int queue_max_sectors(const struct request_queue *q)
{
	return q->limits.max_sectors;
}

static inline unsigned int queue_max_bytes(struct request_queue *q)
{
	return min_t(unsigned int, queue_max_sectors(q), INT_MAX >> 9) << 9;
}

static inline unsigned int queue_max_hw_sectors(const struct request_queue *q)
{
	return q->limits.max_hw_sectors;
}

static inline unsigned short queue_max_segments(const struct request_queue *q)
{
	return q->limits.max_segments;
}

static inline unsigned short queue_max_discard_segments(const struct request_queue *q)
{
	return q->limits.max_discard_segments;
}

static inline unsigned int queue_max_segment_size(const struct request_queue *q)
{
	return q->limits.max_segment_size;
}

static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
{

	const struct queue_limits *l = &q->limits;

	return min(l->max_zone_append_sectors, l->max_sectors);
}

static inline unsigned int
bdev_max_zone_append_sectors(struct block_device *bdev)
{
	return queue_max_zone_append_sectors(bdev_get_queue(bdev));
}

static inline unsigned int bdev_max_segments(struct block_device *bdev)
{
	return queue_max_segments(bdev_get_queue(bdev));
}

static inline unsigned queue_logical_block_size(const struct request_queue *q)
{
	int retval = 512;

	if (q && q->limits.logical_block_size)
		retval = q->limits.logical_block_size;

	return retval;
}

static inline unsigned int bdev_logical_block_size(struct block_device *bdev)
{
	return queue_logical_block_size(bdev_get_queue(bdev));
}

static inline unsigned int queue_physical_block_size(const struct request_queue *q)
{
	return q->limits.physical_block_size;
}

static inline unsigned int bdev_physical_block_size(struct block_device *bdev)
{
	return queue_physical_block_size(bdev_get_queue(bdev));
}

static inline unsigned int queue_io_min(const struct request_queue *q)
{
	return q->limits.io_min;
}

static inline int bdev_io_min(struct block_device *bdev)
{
	return queue_io_min(bdev_get_queue(bdev));
}

static inline unsigned int queue_io_opt(const struct request_queue *q)
{
	return q->limits.io_opt;
}

static inline int bdev_io_opt(struct block_device *bdev)
{
	return queue_io_opt(bdev_get_queue(bdev));
}

static inline unsigned int
queue_zone_write_granularity(const struct request_queue *q)
{
	return q->limits.zone_write_granularity;
}

static inline unsigned int
bdev_zone_write_granularity(struct block_device *bdev)
{
	return queue_zone_write_granularity(bdev_get_queue(bdev));
}

int bdev_alignment_offset(struct block_device *bdev);
unsigned int bdev_discard_alignment(struct block_device *bdev);

static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev)
{
	return bdev_get_queue(bdev)->limits.max_discard_sectors;
}

static inline unsigned int bdev_discard_granularity(struct block_device *bdev)
{
	return bdev_get_queue(bdev)->limits.discard_granularity;
}

static inline unsigned int
bdev_max_secure_erase_sectors(struct block_device *bdev)
{
	return bdev_get_queue(bdev)->limits.max_secure_erase_sectors;
}

static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
{
	struct request_queue *q = bdev_get_queue(bdev);

	if (q)
		return q->limits.max_write_zeroes_sectors;

	return 0;
}

static inline bool bdev_nonrot(struct block_device *bdev)
{
	return blk_queue_nonrot(bdev_get_queue(bdev));
}

static inline bool bdev_synchronous(struct block_device *bdev)
{
	return test_bit(QUEUE_FLAG_SYNCHRONOUS,
			&bdev_get_queue(bdev)->queue_flags);
}

static inline bool bdev_stable_writes(struct block_device *bdev)
{
	return test_bit(QUEUE_FLAG_STABLE_WRITES,
			&bdev_get_queue(bdev)->queue_flags);
}

static inline bool bdev_write_cache(struct block_device *bdev)
{
	return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags);
}

static inline bool bdev_fua(struct block_device *bdev)
{
	return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags);
}

static inline bool bdev_nowait(struct block_device *bdev)
{
	return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
}

static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
{
	return blk_queue_zoned_model(bdev_get_queue(bdev));
}

static inline bool bdev_is_zoned(struct block_device *bdev)
{
	return blk_queue_is_zoned(bdev_get_queue(bdev));
}

static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec)
{
	return disk_zone_no(bdev->bd_disk, sec);
}

/* Whether write serialization is required for @op on zoned devices. */
static inline bool op_needs_zoned_write_locking(enum req_op op)
{
	return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES;
}

static inline bool bdev_op_is_zoned_write(struct block_device *bdev,
					  enum req_op op)
{
	return bdev_is_zoned(bdev) && op_needs_zoned_write_locking(op);
}

static inline sector_t bdev_zone_sectors(struct block_device *bdev)
{
	struct request_queue *q = bdev_get_queue(bdev);

	if (!blk_queue_is_zoned(q))
		return 0;
	return q->limits.chunk_sectors;
}

static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev,
						   sector_t sector)
{
	return sector & (bdev_zone_sectors(bdev) - 1);
}

static inline bool bdev_is_zone_start(struct block_device *bdev,
				      sector_t sector)
{
	return bdev_offset_from_zone_start(bdev, sector) == 0;
}

static inline int queue_dma_alignment(const struct request_queue *q)
{
	return q ? q->limits.dma_alignment : 511;
}

static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
{
	return queue_dma_alignment(bdev_get_queue(bdev));
}

static inline bool bdev_iter_is_aligned(struct block_device *bdev,
					struct iov_iter *iter)
{
	return iov_iter_is_aligned(iter, bdev_dma_alignment(bdev),
				   bdev_logical_block_size(bdev) - 1);
}

static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
				 unsigned int len)
{
	unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask;
	return !(addr & alignment) && !(len & alignment);
}

/* assumes size > 256 */
static inline unsigned int blksize_bits(unsigned int size)
{
	return order_base_2(size >> SECTOR_SHIFT) + SECTOR_SHIFT;
}

static inline unsigned int block_size(struct block_device *bdev)
{
	return 1 << bdev->bd_inode->i_blkbits;
}

int kblockd_schedule_work(struct work_struct *work);
int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);

#define MODULE_ALIAS_BLOCKDEV(major,minor) \
	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
	MODULE_ALIAS("block-major-" __stringify(major) "-*")

#ifdef CONFIG_BLK_INLINE_ENCRYPTION

bool blk_crypto_register(struct blk_crypto_profile *profile,
			 struct request_queue *q);

#else /* CONFIG_BLK_INLINE_ENCRYPTION */

static inline bool blk_crypto_register(struct blk_crypto_profile *profile,
				       struct request_queue *q)
{
	return true;
}

#endif /* CONFIG_BLK_INLINE_ENCRYPTION */

enum blk_unique_id {
	/* these match the Designator Types specified in SPC */
	BLK_UID_T10	= 1,
	BLK_UID_EUI64	= 2,
	BLK_UID_NAA	= 3,
};

#define NFL4_UFLG_MASK			0x0000003F

struct block_device_operations {
	void (*submit_bio)(struct bio *bio);
	int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob,
			unsigned int flags);
	int (*open)(struct gendisk *disk, blk_mode_t mode);
	void (*release)(struct gendisk *disk);
	int (*ioctl)(struct block_device *bdev, blk_mode_t mode,
			unsigned cmd, unsigned long arg);
	int (*compat_ioctl)(struct block_device *bdev, blk_mode_t mode,
			unsigned cmd, unsigned long arg);
	unsigned int (*check_events) (struct gendisk *disk,
				      unsigned int clearing);
	void (*unlock_native_capacity) (struct gendisk *);
	int (*getgeo)(struct block_device *, struct hd_geometry *);
	int (*set_read_only)(struct block_device *bdev, bool ro);
	void (*free_disk)(struct gendisk *disk);
	/* this callback is with swap_lock and sometimes page table lock held */
	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
	int (*report_zones)(struct gendisk *, sector_t sector,
			unsigned int nr_zones, report_zones_cb cb, void *data);
	char *(*devnode)(struct gendisk *disk, umode_t *mode);
	/* returns the length of the identifier or a negative errno: */
	int (*get_unique_id)(struct gendisk *disk, u8 id[16],
			enum blk_unique_id id_type);
	struct module *owner;
	const struct pr_ops *pr_ops;

	/*
	 * Special callback for probing GPT entry at a given sector.
	 * Needed by Android devices, used by GPT scanner and MMC blk
	 * driver.
	 */
	int (*alternative_gpt_sector)(struct gendisk *disk, sector_t *sector);
};

#ifdef CONFIG_COMPAT
extern int blkdev_compat_ptr_ioctl(struct block_device *, blk_mode_t,
				      unsigned int, unsigned long);
#else
#define blkdev_compat_ptr_ioctl NULL
#endif

static inline void blk_wake_io_task(struct task_struct *waiter)
{
	/*
	 * If we're polling, the task itself is doing the completions. For
	 * that case, we don't need to signal a wakeup, it's enough to just
	 * mark us as RUNNING.
	 */
	if (waiter == current)
		__set_current_state(TASK_RUNNING);
	else
		wake_up_process(waiter);
}

unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op,
				 unsigned long start_time);
void bdev_end_io_acct(struct block_device *bdev, enum req_op op,
		      unsigned int sectors, unsigned long start_time);

unsigned long bio_start_io_acct(struct bio *bio);
void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
		struct block_device *orig_bdev);

/**
 * bio_end_io_acct - end I/O accounting for bio based drivers
 * @bio:	bio to end account for
 * @start_time:	start time returned by bio_start_io_acct()
 */
static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
{
	return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev);
}

int bdev_read_only(struct block_device *bdev);
int set_blocksize(struct block_device *bdev, int size);

int lookup_bdev(const char *pathname, dev_t *dev);

void blkdev_show(struct seq_file *seqf, off_t offset);

#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_MAX	512
#else
#define BLKDEV_MAJOR_MAX	0
#endif

struct blk_holder_ops {
	void (*mark_dead)(struct block_device *bdev);
};

/*
 * Return the correct open flags for blkdev_get_by_* for super block flags
 * as stored in sb->s_flags.
 */
#define sb_open_mode(flags) \
	(BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))

struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
		const struct blk_holder_ops *hops);
struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
		void *holder, const struct blk_holder_ops *hops);
int bd_prepare_to_claim(struct block_device *bdev, void *holder,
		const struct blk_holder_ops *hops);
void bd_abort_claiming(struct block_device *bdev, void *holder);
void blkdev_put(struct block_device *bdev, void *holder);

/* just for blk-cgroup, don't use elsewhere */
struct block_device *blkdev_get_no_open(dev_t dev);
void blkdev_put_no_open(struct block_device *bdev);

struct block_device *I_BDEV(struct inode *inode);

#ifdef CONFIG_BLOCK
void invalidate_bdev(struct block_device *bdev);
int sync_blockdev(struct block_device *bdev);
int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
int sync_blockdev_nowait(struct block_device *bdev);
void sync_bdevs(bool wait);
void bdev_statx_dioalign(struct inode *inode, struct kstat *stat);
void printk_all_partitions(void);
int __init early_lookup_bdev(const char *pathname, dev_t *dev);
#else
static inline void invalidate_bdev(struct block_device *bdev)
{
}
static inline int sync_blockdev(struct block_device *bdev)
{
	return 0;
}
static inline int sync_blockdev_nowait(struct block_device *bdev)
{
	return 0;
}
static inline void sync_bdevs(bool wait)
{
}
static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
{
}
static inline void printk_all_partitions(void)
{
}
static inline int early_lookup_bdev(const char *pathname, dev_t *dev)
{
	return -EINVAL;
}
#endif /* CONFIG_BLOCK */

int fsync_bdev(struct block_device *bdev);

int freeze_bdev(struct block_device *bdev);
int thaw_bdev(struct block_device *bdev);

struct io_comp_batch {
	struct request *req_list;
	bool need_ts;
	void (*complete)(struct io_comp_batch *);
};

#define DEFINE_IO_COMP_BATCH(name)	struct io_comp_batch name = { }

#endif /* _LINUX_BLKDEV_H */