summaryrefslogtreecommitdiffstats
path: root/block/genhd.c
blob: cc32a0c704eb846c2abba312494c7272f4c74520 (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  gendisk handling
 *
 * Portions Copyright (C) 2020 Christoph Hellwig
 */

#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/fs.h>
#include <linux/kdev_t.h>
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/idr.h>
#include <linux/log2.h>
#include <linux/pm_runtime.h>
#include <linux/badblocks.h>
#include <linux/part_stat.h>
#include <linux/blktrace_api.h>

#include "blk-throttle.h"
#include "blk.h"
#include "blk-mq-sched.h"
#include "blk-rq-qos.h"
#include "blk-cgroup.h"

static struct kobject *block_depr;

/*
 * Unique, monotonically increasing sequential number associated with block
 * devices instances (i.e. incremented each time a device is attached).
 * Associating uevents with block devices in userspace is difficult and racy:
 * the uevent netlink socket is lossy, and on slow and overloaded systems has
 * a very high latency.
 * Block devices do not have exclusive owners in userspace, any process can set
 * one up (e.g. loop devices). Moreover, device names can be reused (e.g. loop0
 * can be reused again and again).
 * A userspace process setting up a block device and watching for its events
 * cannot thus reliably tell whether an event relates to the device it just set
 * up or another earlier instance with the same name.
 * This sequential number allows userspace processes to solve this problem, and
 * uniquely associate an uevent to the lifetime to a device.
 */
static atomic64_t diskseq;

/* for extended dynamic devt allocation, currently only one major is used */
#define NR_EXT_DEVT		(1 << MINORBITS)
static DEFINE_IDA(ext_devt_ida);

void set_capacity(struct gendisk *disk, sector_t sectors)
{
	bdev_set_nr_sectors(disk->part0, sectors);
}
EXPORT_SYMBOL(set_capacity);

/*
 * Set disk capacity and notify if the size is not currently zero and will not
 * be set to zero.  Returns true if a uevent was sent, otherwise false.
 */
bool set_capacity_and_notify(struct gendisk *disk, sector_t size)
{
	sector_t capacity = get_capacity(disk);
	char *envp[] = { "RESIZE=1", NULL };

	set_capacity(disk, size);

	/*
	 * Only print a message and send a uevent if the gendisk is user visible
	 * and alive.  This avoids spamming the log and udev when setting the
	 * initial capacity during probing.
	 */
	if (size == capacity ||
	    !disk_live(disk) ||
	    (disk->flags & GENHD_FL_HIDDEN))
		return false;

	pr_info("%s: detected capacity change from %lld to %lld\n",
		disk->disk_name, capacity, size);

	/*
	 * Historically we did not send a uevent for changes to/from an empty
	 * device.
	 */
	if (!capacity || !size)
		return false;
	kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
	return true;
}
EXPORT_SYMBOL_GPL(set_capacity_and_notify);

static void part_stat_read_all(struct block_device *part,
		struct disk_stats *stat)
{
	int cpu;

	memset(stat, 0, sizeof(struct disk_stats));
	for_each_possible_cpu(cpu) {
		struct disk_stats *ptr = per_cpu_ptr(part->bd_stats, cpu);
		int group;

		for (group = 0; group < NR_STAT_GROUPS; group++) {
			stat->nsecs[group] += ptr->nsecs[group];
			stat->sectors[group] += ptr->sectors[group];
			stat->ios[group] += ptr->ios[group];
			stat->merges[group] += ptr->merges[group];
		}

		stat->io_ticks += ptr->io_ticks;
	}
}

static unsigned int part_in_flight(struct block_device *part)
{
	unsigned int inflight = 0;
	int cpu;

	for_each_possible_cpu(cpu) {
		inflight += part_stat_local_read_cpu(part, in_flight[0], cpu) +
			    part_stat_local_read_cpu(part, in_flight[1], cpu);
	}
	if ((int)inflight < 0)
		inflight = 0;

	return inflight;
}

static void part_in_flight_rw(struct block_device *part,
		unsigned int inflight[2])
{
	int cpu;

	inflight[0] = 0;
	inflight[1] = 0;
	for_each_possible_cpu(cpu) {
		inflight[0] += part_stat_local_read_cpu(part, in_flight[0], cpu);
		inflight[1] += part_stat_local_read_cpu(part, in_flight[1], cpu);
	}
	if ((int)inflight[0] < 0)
		inflight[0] = 0;
	if ((int)inflight[1] < 0)
		inflight[1] = 0;
}

/*
 * Can be deleted altogether. Later.
 *
 */
#define BLKDEV_MAJOR_HASH_SIZE 255
static struct blk_major_name {
	struct blk_major_name *next;
	int major;
	char name[16];
#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
	void (*probe)(dev_t devt);
#endif
} *major_names[BLKDEV_MAJOR_HASH_SIZE];
static DEFINE_MUTEX(major_names_lock);
static DEFINE_SPINLOCK(major_names_spinlock);

/* index in the above - for now: assume no multimajor ranges */
static inline int major_to_index(unsigned major)
{
	return major % BLKDEV_MAJOR_HASH_SIZE;
}

#ifdef CONFIG_PROC_FS
void blkdev_show(struct seq_file *seqf, off_t offset)
{
	struct blk_major_name *dp;

	spin_lock(&major_names_spinlock);
	for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next)
		if (dp->major == offset)
			seq_printf(seqf, "%3d %s\n", dp->major, dp->name);
	spin_unlock(&major_names_spinlock);
}
#endif /* CONFIG_PROC_FS */

/**
 * __register_blkdev - register a new block device
 *
 * @major: the requested major device number [1..BLKDEV_MAJOR_MAX-1]. If
 *         @major = 0, try to allocate any unused major number.
 * @name: the name of the new block device as a zero terminated string
 * @probe: pre-devtmpfs / pre-udev callback used to create disks when their
 *	   pre-created device node is accessed. When a probe call uses
 *	   add_disk() and it fails the driver must cleanup resources. This
 *	   interface may soon be removed.
 *
 * The @name must be unique within the system.
 *
 * The return value depends on the @major input parameter:
 *
 *  - if a major device number was requested in range [1..BLKDEV_MAJOR_MAX-1]
 *    then the function returns zero on success, or a negative error code
 *  - if any unused major number was requested with @major = 0 parameter
 *    then the return value is the allocated major number in range
 *    [1..BLKDEV_MAJOR_MAX-1] or a negative error code otherwise
 *
 * See Documentation/admin-guide/devices.txt for the list of allocated
 * major numbers.
 *
 * Use register_blkdev instead for any new code.
 */
int __register_blkdev(unsigned int major, const char *name,
		void (*probe)(dev_t devt))
{
	struct blk_major_name **n, *p;
	int index, ret = 0;

	mutex_lock(&major_names_lock);

	/* temporary */
	if (major == 0) {
		for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) {
			if (major_names[index] == NULL)
				break;
		}

		if (index == 0) {
			printk("%s: failed to get major for %s\n",
			       __func__, name);
			ret = -EBUSY;
			goto out;
		}
		major = index;
		ret = major;
	}

	if (major >= BLKDEV_MAJOR_MAX) {
		pr_err("%s: major requested (%u) is greater than the maximum (%u) for %s\n",
		       __func__, major, BLKDEV_MAJOR_MAX-1, name);

		ret = -EINVAL;
		goto out;
	}

	p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL);
	if (p == NULL) {
		ret = -ENOMEM;
		goto out;
	}

	p->major = major;
#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
	p->probe = probe;
#endif
	strscpy(p->name, name, sizeof(p->name));
	p->next = NULL;
	index = major_to_index(major);

	spin_lock(&major_names_spinlock);
	for (n = &major_names[index]; *n; n = &(*n)->next) {
		if ((*n)->major == major)
			break;
	}
	if (!*n)
		*n = p;
	else
		ret = -EBUSY;
	spin_unlock(&major_names_spinlock);

	if (ret < 0) {
		printk("register_blkdev: cannot get major %u for %s\n",
		       major, name);
		kfree(p);
	}
out:
	mutex_unlock(&major_names_lock);
	return ret;
}
EXPORT_SYMBOL(__register_blkdev);

void unregister_blkdev(unsigned int major, const char *name)
{
	struct blk_major_name **n;
	struct blk_major_name *p = NULL;
	int index = major_to_index(major);

	mutex_lock(&major_names_lock);
	spin_lock(&major_names_spinlock);
	for (n = &major_names[index]; *n; n = &(*n)->next)
		if ((*n)->major == major)
			break;
	if (!*n || strcmp((*n)->name, name)) {
		WARN_ON(1);
	} else {
		p = *n;
		*n = p->next;
	}
	spin_unlock(&major_names_spinlock);
	mutex_unlock(&major_names_lock);
	kfree(p);
}

EXPORT_SYMBOL(unregister_blkdev);

int blk_alloc_ext_minor(void)
{
	int idx;

	idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT - 1, GFP_KERNEL);
	if (idx == -ENOSPC)
		return -EBUSY;
	return idx;
}

void blk_free_ext_minor(unsigned int minor)
{
	ida_free(&ext_devt_ida, minor);
}

void disk_uevent(struct gendisk *disk, enum kobject_action action)
{
	struct block_device *part;
	unsigned long idx;

	rcu_read_lock();
	xa_for_each(&disk->part_tbl, idx, part) {
		if (bdev_is_partition(part) && !bdev_nr_sectors(part))
			continue;
		if (!kobject_get_unless_zero(&part->bd_device.kobj))
			continue;

		rcu_read_unlock();
		kobject_uevent(bdev_kobj(part), action);
		put_device(&part->bd_device);
		rcu_read_lock();
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(disk_uevent);

int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode)
{
	struct block_device *bdev;
	int ret = 0;

	if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN))
		return -EINVAL;
	if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
		return -EINVAL;
	if (disk->open_partitions)
		return -EBUSY;

	/*
	 * If the device is opened exclusively by current thread already, it's
	 * safe to scan partitons, otherwise, use bd_prepare_to_claim() to
	 * synchronize with other exclusive openers and other partition
	 * scanners.
	 */
	if (!(mode & BLK_OPEN_EXCL)) {
		ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions,
					  NULL);
		if (ret)
			return ret;
	}

	set_bit(GD_NEED_PART_SCAN, &disk->state);
	bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL, NULL,
				 NULL);
	if (IS_ERR(bdev))
		ret =  PTR_ERR(bdev);
	else
		blkdev_put(bdev, NULL);

	/*
	 * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set,
	 * and this will cause that re-assemble partitioned raid device will
	 * creat partition for underlying disk.
	 */
	clear_bit(GD_NEED_PART_SCAN, &disk->state);
	if (!(mode & BLK_OPEN_EXCL))
		bd_abort_claiming(disk->part0, disk_scan_partitions);
	return ret;
}

/**
 * device_add_disk - add disk information to kernel list
 * @parent: parent device for the disk
 * @disk: per-device partitioning information
 * @groups: Additional per-device sysfs groups
 *
 * This function registers the partitioning information in @disk
 * with the kernel.
 */
int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
				 const struct attribute_group **groups)

{
	struct device *ddev = disk_to_dev(disk);
	int ret;

	/* Only makes sense for bio-based to set ->poll_bio */
	if (queue_is_mq(disk->queue) && disk->fops->poll_bio)
		return -EINVAL;

	/*
	 * The disk queue should now be all set with enough information about
	 * the device for the elevator code to pick an adequate default
	 * elevator if one is needed, that is, for devices requesting queue
	 * registration.
	 */
	elevator_init_mq(disk->queue);

	/* Mark bdev as having a submit_bio, if needed */
	disk->part0->bd_has_submit_bio = disk->fops->submit_bio != NULL;

	/*
	 * If the driver provides an explicit major number it also must provide
	 * the number of minors numbers supported, and those will be used to
	 * setup the gendisk.
	 * Otherwise just allocate the device numbers for both the whole device
	 * and all partitions from the extended dev_t space.
	 */
	ret = -EINVAL;
	if (disk->major) {
		if (WARN_ON(!disk->minors))
			goto out_exit_elevator;

		if (disk->minors > DISK_MAX_PARTS) {
			pr_err("block: can't allocate more than %d partitions\n",
				DISK_MAX_PARTS);
			disk->minors = DISK_MAX_PARTS;
		}
		if (disk->first_minor + disk->minors > MINORMASK + 1)
			goto out_exit_elevator;
	} else {
		if (WARN_ON(disk->minors))
			goto out_exit_elevator;

		ret = blk_alloc_ext_minor();
		if (ret < 0)
			goto out_exit_elevator;
		disk->major = BLOCK_EXT_MAJOR;
		disk->first_minor = ret;
	}

	/* delay uevents, until we scanned partition table */
	dev_set_uevent_suppress(ddev, 1);

	ddev->parent = parent;
	ddev->groups = groups;
	dev_set_name(ddev, "%s", disk->disk_name);
	if (!(disk->flags & GENHD_FL_HIDDEN))
		ddev->devt = MKDEV(disk->major, disk->first_minor);
	ret = device_add(ddev);
	if (ret)
		goto out_free_ext_minor;

	ret = disk_alloc_events(disk);
	if (ret)
		goto out_device_del;

	ret = sysfs_create_link(block_depr, &ddev->kobj,
				kobject_name(&ddev->kobj));
	if (ret)
		goto out_device_del;

	/*
	 * avoid probable deadlock caused by allocating memory with
	 * GFP_KERNEL in runtime_resume callback of its all ancestor
	 * devices
	 */
	pm_runtime_set_memalloc_noio(ddev, true);

	disk->part0->bd_holder_dir =
		kobject_create_and_add("holders", &ddev->kobj);
	if (!disk->part0->bd_holder_dir) {
		ret = -ENOMEM;
		goto out_del_block_link;
	}
	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
	if (!disk->slave_dir) {
		ret = -ENOMEM;
		goto out_put_holder_dir;
	}

	ret = blk_register_queue(disk);
	if (ret)
		goto out_put_slave_dir;

	if (!(disk->flags & GENHD_FL_HIDDEN)) {
		ret = bdi_register(disk->bdi, "%u:%u",
				   disk->major, disk->first_minor);
		if (ret)
			goto out_unregister_queue;
		bdi_set_owner(disk->bdi, ddev);
		ret = sysfs_create_link(&ddev->kobj,
					&disk->bdi->dev->kobj, "bdi");
		if (ret)
			goto out_unregister_bdi;

		/* Make sure the first partition scan will be proceed */
		if (get_capacity(disk) && !(disk->flags & GENHD_FL_NO_PART) &&
		    !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
			set_bit(GD_NEED_PART_SCAN, &disk->state);

		bdev_add(disk->part0, ddev->devt);
		if (get_capacity(disk))
			disk_scan_partitions(disk, BLK_OPEN_READ);

		/*
		 * Announce the disk and partitions after all partitions are
		 * created. (for hidden disks uevents remain suppressed forever)
		 */
		dev_set_uevent_suppress(ddev, 0);
		disk_uevent(disk, KOBJ_ADD);
	} else {
		/*
		 * Even if the block_device for a hidden gendisk is not
		 * registered, it needs to have a valid bd_dev so that the
		 * freeing of the dynamic major works.
		 */
		disk->part0->bd_dev = MKDEV(disk->major, disk->first_minor);
	}

	disk_update_readahead(disk);
	disk_add_events(disk);
	set_bit(GD_ADDED, &disk->state);
	return 0;

out_unregister_bdi:
	if (!(disk->flags & GENHD_FL_HIDDEN))
		bdi_unregister(disk->bdi);
out_unregister_queue:
	blk_unregister_queue(disk);
	rq_qos_exit(disk->queue);
out_put_slave_dir:
	kobject_put(disk->slave_dir);
	disk->slave_dir = NULL;
out_put_holder_dir:
	kobject_put(disk->part0->bd_holder_dir);
out_del_block_link:
	sysfs_remove_link(block_depr, dev_name(ddev));
out_device_del:
	device_del(ddev);
out_free_ext_minor:
	if (disk->major == BLOCK_EXT_MAJOR)
		blk_free_ext_minor(disk->first_minor);
out_exit_elevator:
	if (disk->queue->elevator)
		elevator_exit(disk->queue);
	return ret;
}
EXPORT_SYMBOL(device_add_disk);

static void blk_report_disk_dead(struct gendisk *disk, bool surprise)
{
	struct block_device *bdev;
	unsigned long idx;

	rcu_read_lock();
	xa_for_each(&disk->part_tbl, idx, bdev) {
		if (!kobject_get_unless_zero(&bdev->bd_device.kobj))
			continue;
		rcu_read_unlock();

		bdev_mark_dead(bdev, surprise);

		put_device(&bdev->bd_device);
		rcu_read_lock();
	}
	rcu_read_unlock();
}

static void __blk_mark_disk_dead(struct gendisk *disk)
{
	/*
	 * Fail any new I/O.
	 */
	if (test_and_set_bit(GD_DEAD, &disk->state))
		return;

	if (test_bit(GD_OWNS_QUEUE, &disk->state))
		blk_queue_flag_set(QUEUE_FLAG_DYING, disk->queue);

	/*
	 * Stop buffered writers from dirtying pages that can't be written out.
	 */
	set_capacity(disk, 0);

	/*
	 * Prevent new I/O from crossing bio_queue_enter().
	 */
	blk_queue_start_drain(disk->queue);
}

/**
 * blk_mark_disk_dead - mark a disk as dead
 * @disk: disk to mark as dead
 *
 * Mark as disk as dead (e.g. surprise removed) and don't accept any new I/O
 * to this disk.
 */
void blk_mark_disk_dead(struct gendisk *disk)
{
	__blk_mark_disk_dead(disk);
	blk_report_disk_dead(disk, true);
}
EXPORT_SYMBOL_GPL(blk_mark_disk_dead);

/**
 * del_gendisk - remove the gendisk
 * @disk: the struct gendisk to remove
 *
 * Removes the gendisk and all its associated resources. This deletes the
 * partitions associated with the gendisk, and unregisters the associated
 * request_queue.
 *
 * This is the counter to the respective __device_add_disk() call.
 *
 * The final removal of the struct gendisk happens when its refcount reaches 0
 * with put_disk(), which should be called after del_gendisk(), if
 * __device_add_disk() was used.
 *
 * Drivers exist which depend on the release of the gendisk to be synchronous,
 * it should not be deferred.
 *
 * Context: can sleep
 */
void del_gendisk(struct gendisk *disk)
{
	struct request_queue *q = disk->queue;
	struct block_device *part;
	unsigned long idx;

	might_sleep();

	if (WARN_ON_ONCE(!disk_live(disk) && !(disk->flags & GENHD_FL_HIDDEN)))
		return;

	disk_del_events(disk);

	/*
	 * Prevent new openers by unlinked the bdev inode.
	 */
	mutex_lock(&disk->open_mutex);
	xa_for_each(&disk->part_tbl, idx, part)
		remove_inode_hash(part->bd_inode);
	mutex_unlock(&disk->open_mutex);

	/*
	 * Tell the file system to write back all dirty data and shut down if
	 * it hasn't been notified earlier.
	 */
	if (!test_bit(GD_DEAD, &disk->state))
		blk_report_disk_dead(disk, false);
	__blk_mark_disk_dead(disk);

	/*
	 * Drop all partitions now that the disk is marked dead.
	 */
	mutex_lock(&disk->open_mutex);
	xa_for_each_start(&disk->part_tbl, idx, part, 1)
		drop_partition(part);
	mutex_unlock(&disk->open_mutex);

	if (!(disk->flags & GENHD_FL_HIDDEN)) {
		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");

		/*
		 * Unregister bdi before releasing device numbers (as they can
		 * get reused and we'd get clashes in sysfs).
		 */
		bdi_unregister(disk->bdi);
	}

	blk_unregister_queue(disk);

	kobject_put(disk->part0->bd_holder_dir);
	kobject_put(disk->slave_dir);
	disk->slave_dir = NULL;

	part_stat_set_all(disk->part0, 0);
	disk->part0->bd_stamp = 0;
	sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
	device_del(disk_to_dev(disk));

	blk_mq_freeze_queue_wait(q);

	blk_throtl_cancel_bios(disk);

	blk_sync_queue(q);
	blk_flush_integrity();

	if (queue_is_mq(q))
		blk_mq_cancel_work_sync(q);

	blk_mq_quiesce_queue(q);
	if (q->elevator) {
		mutex_lock(&q->sysfs_lock);
		elevator_exit(q);
		mutex_unlock(&q->sysfs_lock);
	}
	rq_qos_exit(q);
	blk_mq_unquiesce_queue(q);

	/*
	 * If the disk does not own the queue, allow using passthrough requests
	 * again.  Else leave the queue frozen to fail all I/O.
	 */
	if (!test_bit(GD_OWNS_QUEUE, &disk->state)) {
		blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
		__blk_mq_unfreeze_queue(q, true);
	} else {
		if (queue_is_mq(q))
			blk_mq_exit_queue(q);
	}
}
EXPORT_SYMBOL(del_gendisk);

/**
 * invalidate_disk - invalidate the disk
 * @disk: the struct gendisk to invalidate
 *
 * A helper to invalidates the disk. It will clean the disk's associated
 * buffer/page caches and reset its internal states so that the disk
 * can be reused by the drivers.
 *
 * Context: can sleep
 */
void invalidate_disk(struct gendisk *disk)
{
	struct block_device *bdev = disk->part0;

	invalidate_bdev(bdev);
	bdev->bd_inode->i_mapping->wb_err = 0;
	set_capacity(disk, 0);
}
EXPORT_SYMBOL(invalidate_disk);

/* sysfs access to bad-blocks list. */
static ssize_t disk_badblocks_show(struct device *dev,
					struct device_attribute *attr,
					char *page)
{
	struct gendisk *disk = dev_to_disk(dev);

	if (!disk->bb)
		return sprintf(page, "\n");

	return badblocks_show(disk->bb, page, 0);
}

static ssize_t disk_badblocks_store(struct device *dev,
					struct device_attribute *attr,
					const char *page, size_t len)
{
	struct gendisk *disk = dev_to_disk(dev);

	if (!disk->bb)
		return -ENXIO;

	return badblocks_store(disk->bb, page, len, 0);
}

#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
void blk_request_module(dev_t devt)
{
	unsigned int major = MAJOR(devt);
	struct blk_major_name **n;

	mutex_lock(&major_names_lock);
	for (n = &major_names[major_to_index(major)]; *n; n = &(*n)->next) {
		if ((*n)->major == major && (*n)->probe) {
			(*n)->probe(devt);
			mutex_unlock(&major_names_lock);
			return;
		}
	}
	mutex_unlock(&major_names_lock);

	if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0)
		/* Make old-style 2.4 aliases work */
		request_module("block-major-%d", MAJOR(devt));
}
#endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */

#ifdef CONFIG_PROC_FS
/* iterator */
static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos)
{
	loff_t skip = *pos;
	struct class_dev_iter *iter;
	struct device *dev;

	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
	if (!iter)
		return ERR_PTR(-ENOMEM);

	seqf->private = iter;
	class_dev_iter_init(iter, &block_class, NULL, &disk_type);
	do {
		dev = class_dev_iter_next(iter);
		if (!dev)
			return NULL;
	} while (skip--);

	return dev_to_disk(dev);
}

static void *disk_seqf_next(struct seq_file *seqf, void *v, loff_t *pos)
{
	struct device *dev;

	(*pos)++;
	dev = class_dev_iter_next(seqf->private);
	if (dev)
		return dev_to_disk(dev);

	return NULL;
}

static void disk_seqf_stop(struct seq_file *seqf, void *v)
{
	struct class_dev_iter *iter = seqf->private;

	/* stop is called even after start failed :-( */
	if (iter) {
		class_dev_iter_exit(iter);
		kfree(iter);
		seqf->private = NULL;
	}
}

static void *show_partition_start(struct seq_file *seqf, loff_t *pos)
{
	void *p;

	p = disk_seqf_start(seqf, pos);
	if (!IS_ERR_OR_NULL(p) && !*pos)
		seq_puts(seqf, "major minor  #blocks  name\n\n");
	return p;
}

static int show_partition(struct seq_file *seqf, void *v)
{
	struct gendisk *sgp = v;
	struct block_device *part;
	unsigned long idx;

	if (!get_capacity(sgp) || (sgp->flags & GENHD_FL_HIDDEN))
		return 0;

	rcu_read_lock();
	xa_for_each(&sgp->part_tbl, idx, part) {
		if (!bdev_nr_sectors(part))
			continue;
		seq_printf(seqf, "%4d  %7d %10llu %pg\n",
			   MAJOR(part->bd_dev), MINOR(part->bd_dev),
			   bdev_nr_sectors(part) >> 1, part);
	}
	rcu_read_unlock();
	return 0;
}

static const struct seq_operations partitions_op = {
	.start	= show_partition_start,
	.next	= disk_seqf_next,
	.stop	= disk_seqf_stop,
	.show	= show_partition
};
#endif

static int __init genhd_device_init(void)
{
	int error;

	error = class_register(&block_class);
	if (unlikely(error))
		return error;
	blk_dev_init();

	register_blkdev(BLOCK_EXT_MAJOR, "blkext");

	/* create top-level block dir */
	block_depr = kobject_create_and_add("block", NULL);
	return 0;
}

subsys_initcall(genhd_device_init);

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

	return sprintf(buf, "%d\n", disk->minors);
}

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

	return sprintf(buf, "%d\n",
		(disk->flags & GENHD_FL_NO_PART) ? 1 : DISK_MAX_PARTS);
}

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

	return sprintf(buf, "%d\n",
		       (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0));
}

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

	return sprintf(buf, "%d\n",
		       (disk->flags & GENHD_FL_HIDDEN ? 1 : 0));
}

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

	return sprintf(buf, "%d\n", get_disk_ro(disk) ? 1 : 0);
}

ssize_t part_size_show(struct device *dev,
		       struct device_attribute *attr, char *buf)
{
	return sprintf(buf, "%llu\n", bdev_nr_sectors(dev_to_bdev(dev)));
}

ssize_t part_stat_show(struct device *dev,
		       struct device_attribute *attr, char *buf)
{
	struct block_device *bdev = dev_to_bdev(dev);
	struct request_queue *q = bdev_get_queue(bdev);
	struct disk_stats stat;
	unsigned int inflight;

	if (queue_is_mq(q))
		inflight = blk_mq_in_flight(q, bdev);
	else
		inflight = part_in_flight(bdev);

	if (inflight) {
		part_stat_lock();
		update_io_ticks(bdev, jiffies, true);
		part_stat_unlock();
	}
	part_stat_read_all(bdev, &stat);
	return sprintf(buf,
		"%8lu %8lu %8llu %8u "
		"%8lu %8lu %8llu %8u "
		"%8u %8u %8u "
		"%8lu %8lu %8llu %8u "
		"%8lu %8u"
		"\n",
		stat.ios[STAT_READ],
		stat.merges[STAT_READ],
		(unsigned long long)stat.sectors[STAT_READ],
		(unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC),
		stat.ios[STAT_WRITE],
		stat.merges[STAT_WRITE],
		(unsigned long long)stat.sectors[STAT_WRITE],
		(unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC),
		inflight,
		jiffies_to_msecs(stat.io_ticks),
		(unsigned int)div_u64(stat.nsecs[STAT_READ] +
				      stat.nsecs[STAT_WRITE] +
				      stat.nsecs[STAT_DISCARD] +
				      stat.nsecs[STAT_FLUSH],
						NSEC_PER_MSEC),
		stat.ios[STAT_DISCARD],
		stat.merges[STAT_DISCARD],
		(unsigned long long)stat.sectors[STAT_DISCARD],
		(unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC),
		stat.ios[STAT_FLUSH],
		(unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC));
}

ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
			   char *buf)
{
	struct block_device *bdev = dev_to_bdev(dev);
	struct request_queue *q = bdev_get_queue(bdev);
	unsigned int inflight[2];

	if (queue_is_mq(q))
		blk_mq_in_flight_rw(q, bdev, inflight);
	else
		part_in_flight_rw(bdev, inflight);

	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
}

static ssize_t disk_capability_show(struct device *dev,
				    struct device_attribute *attr, char *buf)
{
	dev_warn_once(dev, "the capability attribute has been deprecated.\n");
	return sprintf(buf, "0\n");
}

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

	return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0));
}

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

	return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0));
}

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

	return sprintf(buf, "%llu\n", disk->diskseq);
}

static DEVICE_ATTR(range, 0444, disk_range_show, NULL);
static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL);
static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL);
static DEVICE_ATTR(hidden, 0444, disk_hidden_show, NULL);
static DEVICE_ATTR(ro, 0444, disk_ro_show, NULL);
static DEVICE_ATTR(size, 0444, part_size_show, NULL);
static DEVICE_ATTR(alignment_offset, 0444, disk_alignment_offset_show, NULL);
static DEVICE_ATTR(discard_alignment, 0444, disk_discard_alignment_show, NULL);
static DEVICE_ATTR(capability, 0444, disk_capability_show, NULL);
static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
static DEVICE_ATTR(diskseq, 0444, diskseq_show, NULL);

#ifdef CONFIG_FAIL_MAKE_REQUEST
ssize_t part_fail_show(struct device *dev,
		       struct device_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_make_it_fail);
}

ssize_t part_fail_store(struct device *dev,
			struct device_attribute *attr,
			const char *buf, size_t count)
{
	int i;

	if (count > 0 && sscanf(buf, "%d", &i) > 0)
		dev_to_bdev(dev)->bd_make_it_fail = i;

	return count;
}

static struct device_attribute dev_attr_fail =
	__ATTR(make-it-fail, 0644, part_fail_show, part_fail_store);
#endif /* CONFIG_FAIL_MAKE_REQUEST */

#ifdef CONFIG_FAIL_IO_TIMEOUT
static struct device_attribute dev_attr_fail_timeout =
	__ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store);
#endif

static struct attribute *disk_attrs[] = {
	&dev_attr_range.attr,
	&dev_attr_ext_range.attr,
	&dev_attr_removable.attr,
	&dev_attr_hidden.attr,
	&dev_attr_ro.attr,
	&dev_attr_size.attr,
	&dev_attr_alignment_offset.attr,
	&dev_attr_discard_alignment.attr,
	&dev_attr_capability.attr,
	&dev_attr_stat.attr,
	&dev_attr_inflight.attr,
	&dev_attr_badblocks.attr,
	&dev_attr_events.attr,
	&dev_attr_events_async.attr,
	&dev_attr_events_poll_msecs.attr,
	&dev_attr_diskseq.attr,
#ifdef CONFIG_FAIL_MAKE_REQUEST
	&dev_attr_fail.attr,
#endif
#ifdef CONFIG_FAIL_IO_TIMEOUT
	&dev_attr_fail_timeout.attr,
#endif
	NULL
};

static umode_t disk_visible(struct kobject *kobj, struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, typeof(*dev), kobj);
	struct gendisk *disk = dev_to_disk(dev);

	if (a == &dev_attr_badblocks.attr && !disk->bb)
		return 0;
	return a->mode;
}

static struct attribute_group disk_attr_group = {
	.attrs = disk_attrs,
	.is_visible = disk_visible,
};

static const struct attribute_group *disk_attr_groups[] = {
	&disk_attr_group,
#ifdef CONFIG_BLK_DEV_IO_TRACE
	&blk_trace_attr_group,
#endif
#ifdef CONFIG_BLK_DEV_INTEGRITY
	&blk_integrity_attr_group,
#endif
	NULL
};

/**
 * disk_release - releases all allocated resources of the gendisk
 * @dev: the device representing this disk
 *
 * This function releases all allocated resources of the gendisk.
 *
 * Drivers which used __device_add_disk() have a gendisk with a request_queue
 * assigned. Since the request_queue sits on top of the gendisk for these
 * drivers we also call blk_put_queue() for them, and we expect the
 * request_queue refcount to reach 0 at this point, and so the request_queue
 * will also be freed prior to the disk.
 *
 * Context: can sleep
 */
static void disk_release(struct device *dev)
{
	struct gendisk *disk = dev_to_disk(dev);

	might_sleep();
	WARN_ON_ONCE(disk_live(disk));

	blk_trace_remove(disk->queue);

	/*
	 * To undo the all initialization from blk_mq_init_allocated_queue in
	 * case of a probe failure where add_disk is never called we have to
	 * call blk_mq_exit_queue here. We can't do this for the more common
	 * teardown case (yet) as the tagset can be gone by the time the disk
	 * is released once it was added.
	 */
	if (queue_is_mq(disk->queue) &&
	    test_bit(GD_OWNS_QUEUE, &disk->state) &&
	    !test_bit(GD_ADDED, &disk->state))
		blk_mq_exit_queue(disk->queue);

	blkcg_exit_disk(disk);

	bioset_exit(&disk->bio_split);

	disk_release_events(disk);
	kfree(disk->random);
	disk_free_zone_bitmaps(disk);
	xa_destroy(&disk->part_tbl);

	disk->queue->disk = NULL;
	blk_put_queue(disk->queue);

	if (test_bit(GD_ADDED, &disk->state) && disk->fops->free_disk)
		disk->fops->free_disk(disk);

	iput(disk->part0->bd_inode);	/* frees the disk */
}

static int block_uevent(const struct device *dev, struct kobj_uevent_env *env)
{
	const struct gendisk *disk = dev_to_disk(dev);

	return add_uevent_var(env, "DISKSEQ=%llu", disk->diskseq);
}

struct class block_class = {
	.name		= "block",
	.dev_uevent	= block_uevent,
};

static char *block_devnode(const struct device *dev, umode_t *mode,
			   kuid_t *uid, kgid_t *gid)
{
	struct gendisk *disk = dev_to_disk(dev);

	if (disk->fops->devnode)
		return disk->fops->devnode(disk, mode);
	return NULL;
}

const struct device_type disk_type = {
	.name		= "disk",
	.groups		= disk_attr_groups,
	.release	= disk_release,
	.devnode	= block_devnode,
};

#ifdef CONFIG_PROC_FS
/*
 * aggregate disk stat collector.  Uses the same stats that the sysfs
 * entries do, above, but makes them available through one seq_file.
 *
 * The output looks suspiciously like /proc/partitions with a bunch of
 * extra fields.
 */
static int diskstats_show(struct seq_file *seqf, void *v)
{
	struct gendisk *gp = v;
	struct block_device *hd;
	unsigned int inflight;
	struct disk_stats stat;
	unsigned long idx;

	/*
	if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next)
		seq_puts(seqf,	"major minor name"
				"     rio rmerge rsect ruse wio wmerge "
				"wsect wuse running use aveq"
				"\n\n");
	*/

	rcu_read_lock();
	xa_for_each(&gp->part_tbl, idx, hd) {
		if (bdev_is_partition(hd) && !bdev_nr_sectors(hd))
			continue;
		if (queue_is_mq(gp->queue))
			inflight = blk_mq_in_flight(gp->queue, hd);
		else
			inflight = part_in_flight(hd);

		if (inflight) {
			part_stat_lock();
			update_io_ticks(hd, jiffies, true);
			part_stat_unlock();
		}
		part_stat_read_all(hd, &stat);
		seq_printf(seqf, "%4d %7d %pg "
			   "%lu %lu %lu %u "
			   "%lu %lu %lu %u "
			   "%u %u %u "
			   "%lu %lu %lu %u "
			   "%lu %u"
			   "\n",
			   MAJOR(hd->bd_dev), MINOR(hd->bd_dev), hd,
			   stat.ios[STAT_READ],
			   stat.merges[STAT_READ],
			   stat.sectors[STAT_READ],
			   (unsigned int)div_u64(stat.nsecs[STAT_READ],
							NSEC_PER_MSEC),
			   stat.ios[STAT_WRITE],
			   stat.merges[STAT_WRITE],
			   stat.sectors[STAT_WRITE],
			   (unsigned int)div_u64(stat.nsecs[STAT_WRITE],
							NSEC_PER_MSEC),
			   inflight,
			   jiffies_to_msecs(stat.io_ticks),
			   (unsigned int)div_u64(stat.nsecs[STAT_READ] +
						 stat.nsecs[STAT_WRITE] +
						 stat.nsecs[STAT_DISCARD] +
						 stat.nsecs[STAT_FLUSH],
							NSEC_PER_MSEC),
			   stat.ios[STAT_DISCARD],
			   stat.merges[STAT_DISCARD],
			   stat.sectors[STAT_DISCARD],
			   (unsigned int)div_u64(stat.nsecs[STAT_DISCARD],
						 NSEC_PER_MSEC),
			   stat.ios[STAT_FLUSH],
			   (unsigned int)div_u64(stat.nsecs[STAT_FLUSH],
						 NSEC_PER_MSEC)
			);
	}
	rcu_read_unlock();

	return 0;
}

static const struct seq_operations diskstats_op = {
	.start	= disk_seqf_start,
	.next	= disk_seqf_next,
	.stop	= disk_seqf_stop,
	.show	= diskstats_show
};

static int __init proc_genhd_init(void)
{
	proc_create_seq("diskstats", 0, NULL, &diskstats_op);
	proc_create_seq("partitions", 0, NULL, &partitions_op);
	return 0;
}
module_init(proc_genhd_init);
#endif /* CONFIG_PROC_FS */

dev_t part_devt(struct gendisk *disk, u8 partno)
{
	struct block_device *part;
	dev_t devt = 0;

	rcu_read_lock();
	part = xa_load(&disk->part_tbl, partno);
	if (part)
		devt = part->bd_dev;
	rcu_read_unlock();

	return devt;
}

struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
		struct lock_class_key *lkclass)
{
	struct gendisk *disk;

	disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
	if (!disk)
		return NULL;

	if (bioset_init(&disk->bio_split, BIO_POOL_SIZE, 0, 0))
		goto out_free_disk;

	disk->bdi = bdi_alloc(node_id);
	if (!disk->bdi)
		goto out_free_bioset;

	/* bdev_alloc() might need the queue, set before the first call */
	disk->queue = q;

	disk->part0 = bdev_alloc(disk, 0);
	if (!disk->part0)
		goto out_free_bdi;

	disk->node_id = node_id;
	mutex_init(&disk->open_mutex);
	xa_init(&disk->part_tbl);
	if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL))
		goto out_destroy_part_tbl;

	if (blkcg_init_disk(disk))
		goto out_erase_part0;

	rand_initialize_disk(disk);
	disk_to_dev(disk)->class = &block_class;
	disk_to_dev(disk)->type = &disk_type;
	device_initialize(disk_to_dev(disk));
	inc_diskseq(disk);
	q->disk = disk;
	lockdep_init_map(&disk->lockdep_map, "(bio completion)", lkclass, 0);
#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
	INIT_LIST_HEAD(&disk->slave_bdevs);
#endif
	return disk;

out_erase_part0:
	xa_erase(&disk->part_tbl, 0);
out_destroy_part_tbl:
	xa_destroy(&disk->part_tbl);
	disk->part0->bd_disk = NULL;
	iput(disk->part0->bd_inode);
out_free_bdi:
	bdi_put(disk->bdi);
out_free_bioset:
	bioset_exit(&disk->bio_split);
out_free_disk:
	kfree(disk);
	return NULL;
}

struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
{
	struct request_queue *q;
	struct gendisk *disk;

	q = blk_alloc_queue(node);
	if (!q)
		return NULL;

	disk = __alloc_disk_node(q, node, lkclass);
	if (!disk) {
		blk_put_queue(q);
		return NULL;
	}
	set_bit(GD_OWNS_QUEUE, &disk->state);
	return disk;
}
EXPORT_SYMBOL(__blk_alloc_disk);

/**
 * put_disk - decrements the gendisk refcount
 * @disk: the struct gendisk to decrement the refcount for
 *
 * This decrements the refcount for the struct gendisk. When this reaches 0
 * we'll have disk_release() called.
 *
 * Note: for blk-mq disk put_disk must be called before freeing the tag_set
 * when handling probe errors (that is before add_disk() is called).
 *
 * Context: Any context, but the last reference must not be dropped from
 *          atomic context.
 */
void put_disk(struct gendisk *disk)
{
	if (disk)
		put_device(disk_to_dev(disk));
}
EXPORT_SYMBOL(put_disk);

static void set_disk_ro_uevent(struct gendisk *gd, int ro)
{
	char event[] = "DISK_RO=1";
	char *envp[] = { event, NULL };

	if (!ro)
		event[8] = '0';
	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
}

/**
 * set_disk_ro - set a gendisk read-only
 * @disk:	gendisk to operate on
 * @read_only:	%true to set the disk read-only, %false set the disk read/write
 *
 * This function is used to indicate whether a given disk device should have its
 * read-only flag set. set_disk_ro() is typically used by device drivers to
 * indicate whether the underlying physical device is write-protected.
 */
void set_disk_ro(struct gendisk *disk, bool read_only)
{
	if (read_only) {
		if (test_and_set_bit(GD_READ_ONLY, &disk->state))
			return;
	} else {
		if (!test_and_clear_bit(GD_READ_ONLY, &disk->state))
			return;
	}
	set_disk_ro_uevent(disk, read_only);
}
EXPORT_SYMBOL(set_disk_ro);

void inc_diskseq(struct gendisk *disk)
{
	disk->diskseq = atomic64_inc_return(&diskseq);
}