summaryrefslogtreecommitdiff
path: root/block/bdev.c
blob: 93b1188d7e58d47f447f0e3c6369aa482fdde559 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 2001  Andrea Arcangeli <andrea@suse.de> SuSE
 *  Copyright (C) 2016 - 2020 Christoph Hellwig
 */

#include <linux/init.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/major.h>
#include <linux/device_cgroup.h>
#include <linux/blkdev.h>
#include <linux/blk-integrity.h>
#include <linux/backing-dev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/magic.h>
#include <linux/buffer_head.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/cleancache.h>
#include <linux/part_stat.h>
#include <linux/uaccess.h>
#include "../fs/internal.h"
#include "blk.h"

struct bdev_inode {
	struct block_device bdev;
	struct inode vfs_inode;
};

static inline struct bdev_inode *BDEV_I(struct inode *inode)
{
	return container_of(inode, struct bdev_inode, vfs_inode);
}

struct block_device *I_BDEV(struct inode *inode)
{
	return &BDEV_I(inode)->bdev;
}
EXPORT_SYMBOL(I_BDEV);

static void bdev_write_inode(struct block_device *bdev)
{
	struct inode *inode = bdev->bd_inode;
	int ret;

	spin_lock(&inode->i_lock);
	while (inode->i_state & I_DIRTY) {
		spin_unlock(&inode->i_lock);
		ret = write_inode_now(inode, true);
		if (ret) {
			char name[BDEVNAME_SIZE];
			pr_warn_ratelimited("VFS: Dirty inode writeback failed "
					    "for block device %s (err=%d).\n",
					    bdevname(bdev, name), ret);
		}
		spin_lock(&inode->i_lock);
	}
	spin_unlock(&inode->i_lock);
}

/* Kill _all_ buffers and pagecache , dirty or not.. */
static void kill_bdev(struct block_device *bdev)
{
	struct address_space *mapping = bdev->bd_inode->i_mapping;

	if (mapping_empty(mapping))
		return;

	invalidate_bh_lrus();
	truncate_inode_pages(mapping, 0);
}

/* Invalidate clean unused buffers and pagecache. */
void invalidate_bdev(struct block_device *bdev)
{
	struct address_space *mapping = bdev->bd_inode->i_mapping;

	if (mapping->nrpages) {
		invalidate_bh_lrus();
		lru_add_drain_all();	/* make sure all lru add caches are flushed */
		invalidate_mapping_pages(mapping, 0, -1);
	}
	/* 99% of the time, we don't need to flush the cleancache on the bdev.
	 * But, for the strange corners, lets be cautious
	 */
	cleancache_invalidate_inode(mapping);
}
EXPORT_SYMBOL(invalidate_bdev);

/*
 * Drop all buffers & page cache for given bdev range. This function bails
 * with error if bdev has other exclusive owner (such as filesystem).
 */
int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
			loff_t lstart, loff_t lend)
{
	/*
	 * If we don't hold exclusive handle for the device, upgrade to it
	 * while we discard the buffer cache to avoid discarding buffers
	 * under live filesystem.
	 */
	if (!(mode & FMODE_EXCL)) {
		int err = bd_prepare_to_claim(bdev, truncate_bdev_range);
		if (err)
			goto invalidate;
	}

	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
	if (!(mode & FMODE_EXCL))
		bd_abort_claiming(bdev, truncate_bdev_range);
	return 0;

invalidate:
	/*
	 * Someone else has handle exclusively open. Try invalidating instead.
	 * The 'end' argument is inclusive so the rounding is safe.
	 */
	return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
					     lstart >> PAGE_SHIFT,
					     lend >> PAGE_SHIFT);
}

static void set_init_blocksize(struct block_device *bdev)
{
	unsigned int bsize = bdev_logical_block_size(bdev);
	loff_t size = i_size_read(bdev->bd_inode);

	while (bsize < PAGE_SIZE) {
		if (size & bsize)
			break;
		bsize <<= 1;
	}
	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
}

int set_blocksize(struct block_device *bdev, int size)
{
	/* Size must be a power of two, and between 512 and PAGE_SIZE */
	if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
		return -EINVAL;

	/* Size cannot be smaller than the size supported by the device */
	if (size < bdev_logical_block_size(bdev))
		return -EINVAL;

	/* Don't change the size if it is same as current */
	if (bdev->bd_inode->i_blkbits != blksize_bits(size)) {
		sync_blockdev(bdev);
		bdev->bd_inode->i_blkbits = blksize_bits(size);
		kill_bdev(bdev);
	}
	return 0;
}

EXPORT_SYMBOL(set_blocksize);

int sb_set_blocksize(struct super_block *sb, int size)
{
	if (set_blocksize(sb->s_bdev, size))
		return 0;
	/* If we get here, we know size is power of two
	 * and it's value is between 512 and PAGE_SIZE */
	sb->s_blocksize = size;
	sb->s_blocksize_bits = blksize_bits(size);
	return sb->s_blocksize;
}

EXPORT_SYMBOL(sb_set_blocksize);

int sb_min_blocksize(struct super_block *sb, int size)
{
	int minsize = bdev_logical_block_size(sb->s_bdev);
	if (size < minsize)
		size = minsize;
	return sb_set_blocksize(sb, size);
}

EXPORT_SYMBOL(sb_min_blocksize);

int __sync_blockdev(struct block_device *bdev, int wait)
{
	if (!bdev)
		return 0;
	if (!wait)
		return filemap_flush(bdev->bd_inode->i_mapping);
	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
}

/*
 * Write out and wait upon all the dirty data associated with a block
 * device via its mapping.  Does not take the superblock lock.
 */
int sync_blockdev(struct block_device *bdev)
{
	return __sync_blockdev(bdev, 1);
}
EXPORT_SYMBOL(sync_blockdev);

/*
 * Write out and wait upon all dirty data associated with this
 * device.   Filesystem data as well as the underlying block
 * device.  Takes the superblock lock.
 */
int fsync_bdev(struct block_device *bdev)
{
	struct super_block *sb = get_super(bdev);
	if (sb) {
		int res = sync_filesystem(sb);
		drop_super(sb);
		return res;
	}
	return sync_blockdev(bdev);
}
EXPORT_SYMBOL(fsync_bdev);

/**
 * freeze_bdev  --  lock a filesystem and force it into a consistent state
 * @bdev:	blockdevice to lock
 *
 * If a superblock is found on this device, we take the s_umount semaphore
 * on it to make sure nobody unmounts until the snapshot creation is done.
 * The reference counter (bd_fsfreeze_count) guarantees that only the last
 * unfreeze process can unfreeze the frozen filesystem actually when multiple
 * freeze requests arrive simultaneously. It counts up in freeze_bdev() and
 * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
 * actually.
 */
int freeze_bdev(struct block_device *bdev)
{
	struct super_block *sb;
	int error = 0;

	mutex_lock(&bdev->bd_fsfreeze_mutex);
	if (++bdev->bd_fsfreeze_count > 1)
		goto done;

	sb = get_active_super(bdev);
	if (!sb)
		goto sync;
	if (sb->s_op->freeze_super)
		error = sb->s_op->freeze_super(sb);
	else
		error = freeze_super(sb);
	deactivate_super(sb);

	if (error) {
		bdev->bd_fsfreeze_count--;
		goto done;
	}
	bdev->bd_fsfreeze_sb = sb;

sync:
	sync_blockdev(bdev);
done:
	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	return error;
}
EXPORT_SYMBOL(freeze_bdev);

/**
 * thaw_bdev  -- unlock filesystem
 * @bdev:	blockdevice to unlock
 *
 * Unlocks the filesystem and marks it writeable again after freeze_bdev().
 */
int thaw_bdev(struct block_device *bdev)
{
	struct super_block *sb;
	int error = -EINVAL;

	mutex_lock(&bdev->bd_fsfreeze_mutex);
	if (!bdev->bd_fsfreeze_count)
		goto out;

	error = 0;
	if (--bdev->bd_fsfreeze_count > 0)
		goto out;

	sb = bdev->bd_fsfreeze_sb;
	if (!sb)
		goto out;

	if (sb->s_op->thaw_super)
		error = sb->s_op->thaw_super(sb);
	else
		error = thaw_super(sb);
	if (error)
		bdev->bd_fsfreeze_count++;
	else
		bdev->bd_fsfreeze_sb = NULL;
out:
	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	return error;
}
EXPORT_SYMBOL(thaw_bdev);

/**
 * bdev_read_page() - Start reading a page from a block device
 * @bdev: The device to read the page from
 * @sector: The offset on the device to read the page to (need not be aligned)
 * @page: The page to read
 *
 * On entry, the page should be locked.  It will be unlocked when the page
 * has been read.  If the block driver implements rw_page synchronously,
 * that will be true on exit from this function, but it need not be.
 *
 * Errors returned by this function are usually "soft", eg out of memory, or
 * queue full; callers should try a different route to read this page rather
 * than propagate an error back up the stack.
 *
 * Return: negative errno if an error occurs, 0 if submission was successful.
 */
int bdev_read_page(struct block_device *bdev, sector_t sector,
			struct page *page)
{
	const struct block_device_operations *ops = bdev->bd_disk->fops;
	int result = -EOPNOTSUPP;

	if (!ops->rw_page || bdev_get_integrity(bdev))
		return result;

	result = blk_queue_enter(bdev->bd_disk->queue, 0);
	if (result)
		return result;
	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
			      REQ_OP_READ);
	blk_queue_exit(bdev->bd_disk->queue);
	return result;
}

/**
 * bdev_write_page() - Start writing a page to a block device
 * @bdev: The device to write the page to
 * @sector: The offset on the device to write the page to (need not be aligned)
 * @page: The page to write
 * @wbc: The writeback_control for the write
 *
 * On entry, the page should be locked and not currently under writeback.
 * On exit, if the write started successfully, the page will be unlocked and
 * under writeback.  If the write failed already (eg the driver failed to
 * queue the page to the device), the page will still be locked.  If the
 * caller is a ->writepage implementation, it will need to unlock the page.
 *
 * Errors returned by this function are usually "soft", eg out of memory, or
 * queue full; callers should try a different route to write this page rather
 * than propagate an error back up the stack.
 *
 * Return: negative errno if an error occurs, 0 if submission was successful.
 */
int bdev_write_page(struct block_device *bdev, sector_t sector,
			struct page *page, struct writeback_control *wbc)
{
	int result;
	const struct block_device_operations *ops = bdev->bd_disk->fops;

	if (!ops->rw_page || bdev_get_integrity(bdev))
		return -EOPNOTSUPP;
	result = blk_queue_enter(bdev->bd_disk->queue, 0);
	if (result)
		return result;

	set_page_writeback(page);
	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
			      REQ_OP_WRITE);
	if (result) {
		end_page_writeback(page);
	} else {
		clean_page_buffers(page);
		unlock_page(page);
	}
	blk_queue_exit(bdev->bd_disk->queue);
	return result;
}

/*
 * pseudo-fs
 */

static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
static struct kmem_cache * bdev_cachep __read_mostly;

static struct inode *bdev_alloc_inode(struct super_block *sb)
{
	struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);

	if (!ei)
		return NULL;
	memset(&ei->bdev, 0, sizeof(ei->bdev));
	return &ei->vfs_inode;
}

static void bdev_free_inode(struct inode *inode)
{
	struct block_device *bdev = I_BDEV(inode);

	free_percpu(bdev->bd_stats);
	kfree(bdev->bd_meta_info);

	if (!bdev_is_partition(bdev)) {
		if (bdev->bd_disk && bdev->bd_disk->bdi)
			bdi_put(bdev->bd_disk->bdi);
		kfree(bdev->bd_disk);
	}

	if (MAJOR(bdev->bd_dev) == BLOCK_EXT_MAJOR)
		blk_free_ext_minor(MINOR(bdev->bd_dev));

	kmem_cache_free(bdev_cachep, BDEV_I(inode));
}

static void init_once(void *data)
{
	struct bdev_inode *ei = data;

	inode_init_once(&ei->vfs_inode);
}

static void bdev_evict_inode(struct inode *inode)
{
	truncate_inode_pages_final(&inode->i_data);
	invalidate_inode_buffers(inode); /* is it needed here? */
	clear_inode(inode);
}

static const struct super_operations bdev_sops = {
	.statfs = simple_statfs,
	.alloc_inode = bdev_alloc_inode,
	.free_inode = bdev_free_inode,
	.drop_inode = generic_delete_inode,
	.evict_inode = bdev_evict_inode,
};

static int bd_init_fs_context(struct fs_context *fc)
{
	struct pseudo_fs_context *ctx = init_pseudo(fc, BDEVFS_MAGIC);
	if (!ctx)
		return -ENOMEM;
	fc->s_iflags |= SB_I_CGROUPWB;
	ctx->ops = &bdev_sops;
	return 0;
}

static struct file_system_type bd_type = {
	.name		= "bdev",
	.init_fs_context = bd_init_fs_context,
	.kill_sb	= kill_anon_super,
};

struct super_block *blockdev_superblock __read_mostly;
EXPORT_SYMBOL_GPL(blockdev_superblock);

void __init bdev_cache_init(void)
{
	int err;
	static struct vfsmount *bd_mnt;

	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
				SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC),
			init_once);
	err = register_filesystem(&bd_type);
	if (err)
		panic("Cannot register bdev pseudo-fs");
	bd_mnt = kern_mount(&bd_type);
	if (IS_ERR(bd_mnt))
		panic("Cannot create bdev pseudo-fs");
	blockdev_superblock = bd_mnt->mnt_sb;   /* For writeback */
}

struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
{
	struct block_device *bdev;
	struct inode *inode;

	inode = new_inode(blockdev_superblock);
	if (!inode)
		return NULL;
	inode->i_mode = S_IFBLK;
	inode->i_rdev = 0;
	inode->i_data.a_ops = &def_blk_aops;
	mapping_set_gfp_mask(&inode->i_data, GFP_USER);

	bdev = I_BDEV(inode);
	mutex_init(&bdev->bd_fsfreeze_mutex);
	spin_lock_init(&bdev->bd_size_lock);
	bdev->bd_partno = partno;
	bdev->bd_inode = inode;
	bdev->bd_stats = alloc_percpu(struct disk_stats);
	if (!bdev->bd_stats) {
		iput(inode);
		return NULL;
	}
	bdev->bd_disk = disk;
	return bdev;
}

void bdev_add(struct block_device *bdev, dev_t dev)
{
	bdev->bd_dev = dev;
	bdev->bd_inode->i_rdev = dev;
	bdev->bd_inode->i_ino = dev;
	insert_inode_hash(bdev->bd_inode);
}

long nr_blockdev_pages(void)
{
	struct inode *inode;
	long ret = 0;

	spin_lock(&blockdev_superblock->s_inode_list_lock);
	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list)
		ret += inode->i_mapping->nrpages;
	spin_unlock(&blockdev_superblock->s_inode_list_lock);

	return ret;
}

/**
 * bd_may_claim - test whether a block device can be claimed
 * @bdev: block device of interest
 * @whole: whole block device containing @bdev, may equal @bdev
 * @holder: holder trying to claim @bdev
 *
 * Test whether @bdev can be claimed by @holder.
 *
 * CONTEXT:
 * spin_lock(&bdev_lock).
 *
 * RETURNS:
 * %true if @bdev can be claimed, %false otherwise.
 */
static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
			 void *holder)
{
	if (bdev->bd_holder == holder)
		return true;	 /* already a holder */
	else if (bdev->bd_holder != NULL)
		return false; 	 /* held by someone else */
	else if (whole == bdev)
		return true;  	 /* is a whole device which isn't held */

	else if (whole->bd_holder == bd_may_claim)
		return true; 	 /* is a partition of a device that is being partitioned */
	else if (whole->bd_holder != NULL)
		return false;	 /* is a partition of a held device */
	else
		return true;	 /* is a partition of an un-held device */
}

/**
 * bd_prepare_to_claim - claim a block device
 * @bdev: block device of interest
 * @holder: holder trying to claim @bdev
 *
 * Claim @bdev.  This function fails if @bdev is already claimed by another
 * holder and waits if another claiming is in progress. return, the caller
 * has ownership of bd_claiming and bd_holder[s].
 *
 * RETURNS:
 * 0 if @bdev can be claimed, -EBUSY otherwise.
 */
int bd_prepare_to_claim(struct block_device *bdev, void *holder)
{
	struct block_device *whole = bdev_whole(bdev);

	if (WARN_ON_ONCE(!holder))
		return -EINVAL;
retry:
	spin_lock(&bdev_lock);
	/* if someone else claimed, fail */
	if (!bd_may_claim(bdev, whole, holder)) {
		spin_unlock(&bdev_lock);
		return -EBUSY;
	}

	/* if claiming is already in progress, wait for it to finish */
	if (whole->bd_claiming) {
		wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0);
		DEFINE_WAIT(wait);

		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
		spin_unlock(&bdev_lock);
		schedule();
		finish_wait(wq, &wait);
		goto retry;
	}

	/* yay, all mine */
	whole->bd_claiming = holder;
	spin_unlock(&bdev_lock);
	return 0;
}
EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */

static void bd_clear_claiming(struct block_device *whole, void *holder)
{
	lockdep_assert_held(&bdev_lock);
	/* tell others that we're done */
	BUG_ON(whole->bd_claiming != holder);
	whole->bd_claiming = NULL;
	wake_up_bit(&whole->bd_claiming, 0);
}

/**
 * bd_finish_claiming - finish claiming of a block device
 * @bdev: block device of interest
 * @holder: holder that has claimed @bdev
 *
 * Finish exclusive open of a block device. Mark the device as exlusively
 * open by the holder and wake up all waiters for exclusive open to finish.
 */
static void bd_finish_claiming(struct block_device *bdev, void *holder)
{
	struct block_device *whole = bdev_whole(bdev);

	spin_lock(&bdev_lock);
	BUG_ON(!bd_may_claim(bdev, whole, holder));
	/*
	 * Note that for a whole device bd_holders will be incremented twice,
	 * and bd_holder will be set to bd_may_claim before being set to holder
	 */
	whole->bd_holders++;
	whole->bd_holder = bd_may_claim;
	bdev->bd_holders++;
	bdev->bd_holder = holder;
	bd_clear_claiming(whole, holder);
	spin_unlock(&bdev_lock);
}

/**
 * bd_abort_claiming - abort claiming of a block device
 * @bdev: block device of interest
 * @holder: holder that has claimed @bdev
 *
 * Abort claiming of a block device when the exclusive open failed. This can be
 * also used when exclusive open is not actually desired and we just needed
 * to block other exclusive openers for a while.
 */
void bd_abort_claiming(struct block_device *bdev, void *holder)
{
	spin_lock(&bdev_lock);
	bd_clear_claiming(bdev_whole(bdev), holder);
	spin_unlock(&bdev_lock);
}
EXPORT_SYMBOL(bd_abort_claiming);

static void blkdev_flush_mapping(struct block_device *bdev)
{
	WARN_ON_ONCE(bdev->bd_holders);
	sync_blockdev(bdev);
	kill_bdev(bdev);
	bdev_write_inode(bdev);
}

static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
{
	struct gendisk *disk = bdev->bd_disk;
	int ret = 0;

	if (disk->fops->open) {
		ret = disk->fops->open(bdev, mode);
		if (ret) {
			/* avoid ghost partitions on a removed medium */
			if (ret == -ENOMEDIUM &&
			     test_bit(GD_NEED_PART_SCAN, &disk->state))
				bdev_disk_changed(disk, true);
			return ret;
		}
	}

	if (!bdev->bd_openers)
		set_init_blocksize(bdev);
	if (test_bit(GD_NEED_PART_SCAN, &disk->state))
		bdev_disk_changed(disk, false);
	bdev->bd_openers++;
	return 0;;
}

static void blkdev_put_whole(struct block_device *bdev, fmode_t mode)
{
	if (!--bdev->bd_openers)
		blkdev_flush_mapping(bdev);
	if (bdev->bd_disk->fops->release)
		bdev->bd_disk->fops->release(bdev->bd_disk, mode);
}

static int blkdev_get_part(struct block_device *part, fmode_t mode)
{
	struct gendisk *disk = part->bd_disk;
	int ret;

	if (part->bd_openers)
		goto done;

	ret = blkdev_get_whole(bdev_whole(part), mode);
	if (ret)
		return ret;

	ret = -ENXIO;
	if (!bdev_nr_sectors(part))
		goto out_blkdev_put;

	disk->open_partitions++;
	set_init_blocksize(part);
done:
	part->bd_openers++;
	return 0;

out_blkdev_put:
	blkdev_put_whole(bdev_whole(part), mode);
	return ret;
}

static void blkdev_put_part(struct block_device *part, fmode_t mode)
{
	struct block_device *whole = bdev_whole(part);

	if (--part->bd_openers)
		return;
	blkdev_flush_mapping(part);
	whole->bd_disk->open_partitions--;
	blkdev_put_whole(whole, mode);
}

struct block_device *blkdev_get_no_open(dev_t dev)
{
	struct block_device *bdev;
	struct inode *inode;

	inode = ilookup(blockdev_superblock, dev);
	if (!inode) {
		blk_request_module(dev);
		inode = ilookup(blockdev_superblock, dev);
		if (!inode)
			return NULL;
	}

	/* switch from the inode reference to a device mode one: */
	bdev = &BDEV_I(inode)->bdev;
	if (!kobject_get_unless_zero(&bdev->bd_device.kobj))
		bdev = NULL;
	iput(inode);

	if (!bdev)
		return NULL;
	if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN) ||
	    !try_module_get(bdev->bd_disk->fops->owner)) {
		put_device(&bdev->bd_device);
		return NULL;
	}

	return bdev;
}

void blkdev_put_no_open(struct block_device *bdev)
{
	module_put(bdev->bd_disk->fops->owner);
	put_device(&bdev->bd_device);
}

/**
 * blkdev_get_by_dev - open a block device by device number
 * @dev: device number of block device to open
 * @mode: FMODE_* mask
 * @holder: exclusive holder identifier
 *
 * Open the block device described by device number @dev. If @mode includes
 * %FMODE_EXCL, the block device is opened with exclusive access.  Specifying
 * %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may nest for
 * the same @holder.
 *
 * Use this interface ONLY if you really do not have anything better - i.e. when
 * you are behind a truly sucky interface and all you are given is a device
 * number.  Everything else should use blkdev_get_by_path().
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * Reference to the block_device on success, ERR_PTR(-errno) on failure.
 */
struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
{
	bool unblock_events = true;
	struct block_device *bdev;
	struct gendisk *disk;
	int ret;

	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
			MAJOR(dev), MINOR(dev),
			((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) |
			((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0));
	if (ret)
		return ERR_PTR(ret);

	bdev = blkdev_get_no_open(dev);
	if (!bdev)
		return ERR_PTR(-ENXIO);
	disk = bdev->bd_disk;

	if (mode & FMODE_EXCL) {
		ret = bd_prepare_to_claim(bdev, holder);
		if (ret)
			goto put_blkdev;
	}

	disk_block_events(disk);

	mutex_lock(&disk->open_mutex);
	ret = -ENXIO;
	if (!disk_live(disk))
		goto abort_claiming;
	if (bdev_is_partition(bdev))
		ret = blkdev_get_part(bdev, mode);
	else
		ret = blkdev_get_whole(bdev, mode);
	if (ret)
		goto abort_claiming;
	if (mode & FMODE_EXCL) {
		bd_finish_claiming(bdev, holder);

		/*
		 * Block event polling for write claims if requested.  Any write
		 * holder makes the write_holder state stick until all are
		 * released.  This is good enough and tracking individual
		 * writeable reference is too fragile given the way @mode is
		 * used in blkdev_get/put().
		 */
		if ((mode & FMODE_WRITE) && !bdev->bd_write_holder &&
		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
			bdev->bd_write_holder = true;
			unblock_events = false;
		}
	}
	mutex_unlock(&disk->open_mutex);

	if (unblock_events)
		disk_unblock_events(disk);
	return bdev;

abort_claiming:
	if (mode & FMODE_EXCL)
		bd_abort_claiming(bdev, holder);
	mutex_unlock(&disk->open_mutex);
	disk_unblock_events(disk);
put_blkdev:
	blkdev_put_no_open(bdev);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL(blkdev_get_by_dev);

/**
 * blkdev_get_by_path - open a block device by name
 * @path: path to the block device to open
 * @mode: FMODE_* mask
 * @holder: exclusive holder identifier
 *
 * Open the block device described by the device file at @path.  If @mode
 * includes %FMODE_EXCL, the block device is opened with exclusive access.
 * Specifying %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may
 * nest for the same @holder.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * Reference to the block_device on success, ERR_PTR(-errno) on failure.
 */
struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
					void *holder)
{
	struct block_device *bdev;
	dev_t dev;
	int error;

	error = lookup_bdev(path, &dev);
	if (error)
		return ERR_PTR(error);

	bdev = blkdev_get_by_dev(dev, mode, holder);
	if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
		blkdev_put(bdev, mode);
		return ERR_PTR(-EACCES);
	}

	return bdev;
}
EXPORT_SYMBOL(blkdev_get_by_path);

void blkdev_put(struct block_device *bdev, fmode_t mode)
{
	struct gendisk *disk = bdev->bd_disk;

	/*
	 * Sync early if it looks like we're the last one.  If someone else
	 * opens the block device between now and the decrement of bd_openers
	 * then we did a sync that we didn't need to, but that's not the end
	 * of the world and we want to avoid long (could be several minute)
	 * syncs while holding the mutex.
	 */
	if (bdev->bd_openers == 1)
		sync_blockdev(bdev);

	mutex_lock(&disk->open_mutex);
	if (mode & FMODE_EXCL) {
		struct block_device *whole = bdev_whole(bdev);
		bool bdev_free;

		/*
		 * Release a claim on the device.  The holder fields
		 * are protected with bdev_lock.  open_mutex is to
		 * synchronize disk_holder unlinking.
		 */
		spin_lock(&bdev_lock);

		WARN_ON_ONCE(--bdev->bd_holders < 0);
		WARN_ON_ONCE(--whole->bd_holders < 0);

		if ((bdev_free = !bdev->bd_holders))
			bdev->bd_holder = NULL;
		if (!whole->bd_holders)
			whole->bd_holder = NULL;

		spin_unlock(&bdev_lock);

		/*
		 * If this was the last claim, remove holder link and
		 * unblock evpoll if it was a write holder.
		 */
		if (bdev_free && bdev->bd_write_holder) {
			disk_unblock_events(disk);
			bdev->bd_write_holder = false;
		}
	}

	/*
	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
	 * event.  This is to ensure detection of media removal commanded
	 * from userland - e.g. eject(1).
	 */
	disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE);

	if (bdev_is_partition(bdev))
		blkdev_put_part(bdev, mode);
	else
		blkdev_put_whole(bdev, mode);
	mutex_unlock(&disk->open_mutex);

	blkdev_put_no_open(bdev);
}
EXPORT_SYMBOL(blkdev_put);

/**
 * lookup_bdev  - lookup a struct block_device by name
 * @pathname:	special file representing the block device
 * @dev:	return value of the block device's dev_t
 *
 * Get a reference to the blockdevice at @pathname in the current
 * namespace if possible and return it.  Return ERR_PTR(error)
 * otherwise.
 */
int lookup_bdev(const char *pathname, dev_t *dev)
{
	struct inode *inode;
	struct path path;
	int error;

	if (!pathname || !*pathname)
		return -EINVAL;

	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
	if (error)
		return error;

	inode = d_backing_inode(path.dentry);
	error = -ENOTBLK;
	if (!S_ISBLK(inode->i_mode))
		goto out_path_put;
	error = -EACCES;
	if (!may_open_dev(&path))
		goto out_path_put;

	*dev = inode->i_rdev;
	error = 0;
out_path_put:
	path_put(&path);
	return error;
}
EXPORT_SYMBOL(lookup_bdev);

int __invalidate_device(struct block_device *bdev, bool kill_dirty)
{
	struct super_block *sb = get_super(bdev);
	int res = 0;

	if (sb) {
		/*
		 * no need to lock the super, get_super holds the
		 * read mutex so the filesystem cannot go away
		 * under us (->put_super runs with the write lock
		 * hold).
		 */
		shrink_dcache_sb(sb);
		res = invalidate_inodes(sb, kill_dirty);
		drop_super(sb);
	}
	invalidate_bdev(bdev);
	return res;
}
EXPORT_SYMBOL(__invalidate_device);

void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
{
	struct inode *inode, *old_inode = NULL;

	spin_lock(&blockdev_superblock->s_inode_list_lock);
	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
		struct address_space *mapping = inode->i_mapping;
		struct block_device *bdev;

		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
		    mapping->nrpages == 0) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(&blockdev_superblock->s_inode_list_lock);
		/*
		 * We hold a reference to 'inode' so it couldn't have been
		 * removed from s_inodes list while we dropped the
		 * s_inode_list_lock  We cannot iput the inode now as we can
		 * be holding the last reference and we cannot iput it under
		 * s_inode_list_lock. So we keep the reference and iput it
		 * later.
		 */
		iput(old_inode);
		old_inode = inode;
		bdev = I_BDEV(inode);

		mutex_lock(&bdev->bd_disk->open_mutex);
		if (bdev->bd_openers)
			func(bdev, arg);
		mutex_unlock(&bdev->bd_disk->open_mutex);

		spin_lock(&blockdev_superblock->s_inode_list_lock);
	}
	spin_unlock(&blockdev_superblock->s_inode_list_lock);
	iput(old_inode);
}