summaryrefslogtreecommitdiff
path: root/block/fops.c
blob: 0cf8cf72cdfa108926ae8fc7f53bce05a3225058 (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
// 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/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/falloc.h>
#include <linux/suspend.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/module.h>
#include "blk.h"

static inline struct inode *bdev_file_inode(struct file *file)
{
	return file->f_mapping->host;
}

static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
{
	blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;

	/* avoid the need for a I/O completion work item */
	if (iocb_is_dsync(iocb))
		opf |= REQ_FUA;
	return opf;
}

static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
			      struct iov_iter *iter)
{
	return pos & (bdev_logical_block_size(bdev) - 1) ||
		!bdev_iter_is_aligned(bdev, iter);
}

#define DIO_INLINE_BIO_VECS 4

static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
		struct iov_iter *iter, unsigned int nr_pages)
{
	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
	struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
	loff_t pos = iocb->ki_pos;
	bool should_dirty = false;
	struct bio bio;
	ssize_t ret;

	if (blkdev_dio_unaligned(bdev, pos, iter))
		return -EINVAL;

	if (nr_pages <= DIO_INLINE_BIO_VECS)
		vecs = inline_vecs;
	else {
		vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec),
				     GFP_KERNEL);
		if (!vecs)
			return -ENOMEM;
	}

	if (iov_iter_rw(iter) == READ) {
		bio_init(&bio, bdev, vecs, nr_pages, REQ_OP_READ);
		if (user_backed_iter(iter))
			should_dirty = true;
	} else {
		bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb));
	}
	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
	bio.bi_ioprio = iocb->ki_ioprio;

	ret = bio_iov_iter_get_pages(&bio, iter);
	if (unlikely(ret))
		goto out;
	ret = bio.bi_iter.bi_size;

	if (iov_iter_rw(iter) == WRITE)
		task_io_account_write(ret);

	if (iocb->ki_flags & IOCB_NOWAIT)
		bio.bi_opf |= REQ_NOWAIT;

	submit_bio_wait(&bio);

	bio_release_pages(&bio, should_dirty);
	if (unlikely(bio.bi_status))
		ret = blk_status_to_errno(bio.bi_status);

out:
	if (vecs != inline_vecs)
		kfree(vecs);

	bio_uninit(&bio);

	return ret;
}

enum {
	DIO_SHOULD_DIRTY	= 1,
	DIO_IS_SYNC		= 2,
};

struct blkdev_dio {
	union {
		struct kiocb		*iocb;
		struct task_struct	*waiter;
	};
	size_t			size;
	atomic_t		ref;
	unsigned int		flags;
	struct bio		bio ____cacheline_aligned_in_smp;
};

static struct bio_set blkdev_dio_pool;

static void blkdev_bio_end_io(struct bio *bio)
{
	struct blkdev_dio *dio = bio->bi_private;
	bool should_dirty = dio->flags & DIO_SHOULD_DIRTY;

	if (bio->bi_status && !dio->bio.bi_status)
		dio->bio.bi_status = bio->bi_status;

	if (atomic_dec_and_test(&dio->ref)) {
		if (!(dio->flags & DIO_IS_SYNC)) {
			struct kiocb *iocb = dio->iocb;
			ssize_t ret;

			WRITE_ONCE(iocb->private, NULL);

			if (likely(!dio->bio.bi_status)) {
				ret = dio->size;
				iocb->ki_pos += ret;
			} else {
				ret = blk_status_to_errno(dio->bio.bi_status);
			}

			dio->iocb->ki_complete(iocb, ret);
			bio_put(&dio->bio);
		} else {
			struct task_struct *waiter = dio->waiter;

			WRITE_ONCE(dio->waiter, NULL);
			blk_wake_io_task(waiter);
		}
	}

	if (should_dirty) {
		bio_check_pages_dirty(bio);
	} else {
		bio_release_pages(bio, false);
		bio_put(bio);
	}
}

static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
		unsigned int nr_pages)
{
	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
	struct blk_plug plug;
	struct blkdev_dio *dio;
	struct bio *bio;
	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
	loff_t pos = iocb->ki_pos;
	int ret = 0;

	if (blkdev_dio_unaligned(bdev, pos, iter))
		return -EINVAL;

	if (iocb->ki_flags & IOCB_ALLOC_CACHE)
		opf |= REQ_ALLOC_CACHE;
	bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
			       &blkdev_dio_pool);
	dio = container_of(bio, struct blkdev_dio, bio);
	atomic_set(&dio->ref, 1);
	/*
	 * Grab an extra reference to ensure the dio structure which is embedded
	 * into the first bio stays around.
	 */
	bio_get(bio);

	is_sync = is_sync_kiocb(iocb);
	if (is_sync) {
		dio->flags = DIO_IS_SYNC;
		dio->waiter = current;
	} else {
		dio->flags = 0;
		dio->iocb = iocb;
	}

	dio->size = 0;
	if (is_read && user_backed_iter(iter))
		dio->flags |= DIO_SHOULD_DIRTY;

	blk_start_plug(&plug);

	for (;;) {
		bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
		bio->bi_private = dio;
		bio->bi_end_io = blkdev_bio_end_io;
		bio->bi_ioprio = iocb->ki_ioprio;

		ret = bio_iov_iter_get_pages(bio, iter);
		if (unlikely(ret)) {
			bio->bi_status = BLK_STS_IOERR;
			bio_endio(bio);
			break;
		}
		if (iocb->ki_flags & IOCB_NOWAIT) {
			/*
			 * This is nonblocking IO, and we need to allocate
			 * another bio if we have data left to map. As we
			 * cannot guarantee that one of the sub bios will not
			 * fail getting issued FOR NOWAIT and as error results
			 * are coalesced across all of them, be safe and ask for
			 * a retry of this from blocking context.
			 */
			if (unlikely(iov_iter_count(iter))) {
				bio_release_pages(bio, false);
				bio_clear_flag(bio, BIO_REFFED);
				bio_put(bio);
				blk_finish_plug(&plug);
				return -EAGAIN;
			}
			bio->bi_opf |= REQ_NOWAIT;
		}

		if (is_read) {
			if (dio->flags & DIO_SHOULD_DIRTY)
				bio_set_pages_dirty(bio);
		} else {
			task_io_account_write(bio->bi_iter.bi_size);
		}
		dio->size += bio->bi_iter.bi_size;
		pos += bio->bi_iter.bi_size;

		nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
		if (!nr_pages) {
			submit_bio(bio);
			break;
		}
		atomic_inc(&dio->ref);
		submit_bio(bio);
		bio = bio_alloc(bdev, nr_pages, opf, GFP_KERNEL);
	}

	blk_finish_plug(&plug);

	if (!is_sync)
		return -EIOCBQUEUED;

	for (;;) {
		set_current_state(TASK_UNINTERRUPTIBLE);
		if (!READ_ONCE(dio->waiter))
			break;
		blk_io_schedule();
	}
	__set_current_state(TASK_RUNNING);

	if (!ret)
		ret = blk_status_to_errno(dio->bio.bi_status);
	if (likely(!ret))
		ret = dio->size;

	bio_put(&dio->bio);
	return ret;
}

static void blkdev_bio_end_io_async(struct bio *bio)
{
	struct blkdev_dio *dio = container_of(bio, struct blkdev_dio, bio);
	struct kiocb *iocb = dio->iocb;
	ssize_t ret;

	WRITE_ONCE(iocb->private, NULL);

	if (likely(!bio->bi_status)) {
		ret = dio->size;
		iocb->ki_pos += ret;
	} else {
		ret = blk_status_to_errno(bio->bi_status);
	}

	iocb->ki_complete(iocb, ret);

	if (dio->flags & DIO_SHOULD_DIRTY) {
		bio_check_pages_dirty(bio);
	} else {
		bio_release_pages(bio, false);
		bio_put(bio);
	}
}

static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
					struct iov_iter *iter,
					unsigned int nr_pages)
{
	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
	bool is_read = iov_iter_rw(iter) == READ;
	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
	struct blkdev_dio *dio;
	struct bio *bio;
	loff_t pos = iocb->ki_pos;
	int ret = 0;

	if (blkdev_dio_unaligned(bdev, pos, iter))
		return -EINVAL;

	if (iocb->ki_flags & IOCB_ALLOC_CACHE)
		opf |= REQ_ALLOC_CACHE;
	bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
			       &blkdev_dio_pool);
	dio = container_of(bio, struct blkdev_dio, bio);
	dio->flags = 0;
	dio->iocb = iocb;
	bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
	bio->bi_end_io = blkdev_bio_end_io_async;
	bio->bi_ioprio = iocb->ki_ioprio;

	if (iov_iter_is_bvec(iter)) {
		/*
		 * Users don't rely on the iterator being in any particular
		 * state for async I/O returning -EIOCBQUEUED, hence we can
		 * avoid expensive iov_iter_advance(). Bypass
		 * bio_iov_iter_get_pages() and set the bvec directly.
		 */
		bio_iov_bvec_set(bio, iter);
	} else {
		ret = bio_iov_iter_get_pages(bio, iter);
		if (unlikely(ret)) {
			bio_put(bio);
			return ret;
		}
	}
	dio->size = bio->bi_iter.bi_size;

	if (is_read) {
		if (user_backed_iter(iter)) {
			dio->flags |= DIO_SHOULD_DIRTY;
			bio_set_pages_dirty(bio);
		}
	} else {
		task_io_account_write(bio->bi_iter.bi_size);
	}

	if (iocb->ki_flags & IOCB_NOWAIT)
		bio->bi_opf |= REQ_NOWAIT;

	if (iocb->ki_flags & IOCB_HIPRI) {
		bio->bi_opf |= REQ_POLLED;
		submit_bio(bio);
		WRITE_ONCE(iocb->private, bio);
	} else {
		submit_bio(bio);
	}
	return -EIOCBQUEUED;
}

static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
	unsigned int nr_pages;

	if (!iov_iter_count(iter))
		return 0;

	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
	if (likely(nr_pages <= BIO_MAX_VECS)) {
		if (is_sync_kiocb(iocb))
			return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
		return __blkdev_direct_IO_async(iocb, iter, nr_pages);
	}
	return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
}

static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
{
	struct block_device *bdev = I_BDEV(inode);
	loff_t isize = i_size_read(inode);

	iomap->bdev = bdev;
	iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev));
	if (iomap->offset >= isize)
		return -EIO;
	iomap->type = IOMAP_MAPPED;
	iomap->addr = iomap->offset;
	iomap->length = isize - iomap->offset;
	iomap->flags |= IOMAP_F_BUFFER_HEAD; /* noop for !CONFIG_BUFFER_HEAD */
	return 0;
}

static const struct iomap_ops blkdev_iomap_ops = {
	.iomap_begin		= blkdev_iomap_begin,
};

#ifdef CONFIG_BUFFER_HEAD
static int blkdev_get_block(struct inode *inode, sector_t iblock,
		struct buffer_head *bh, int create)
{
	bh->b_bdev = I_BDEV(inode);
	bh->b_blocknr = iblock;
	set_buffer_mapped(bh);
	return 0;
}

/*
 * We cannot call mpage_writepages() as it does not take the buffer lock.
 * We must use block_write_full_folio() directly which holds the buffer
 * lock.  The buffer lock provides the synchronisation with writeback
 * that filesystems rely on when they use the blockdev's mapping.
 */
static int blkdev_writepages(struct address_space *mapping,
		struct writeback_control *wbc)
{
	struct blk_plug plug;
	int err;

	blk_start_plug(&plug);
	err = write_cache_pages(mapping, wbc, block_write_full_folio,
			blkdev_get_block);
	blk_finish_plug(&plug);

	return err;
}

static int blkdev_read_folio(struct file *file, struct folio *folio)
{
	return block_read_full_folio(folio, blkdev_get_block);
}

static void blkdev_readahead(struct readahead_control *rac)
{
	mpage_readahead(rac, blkdev_get_block);
}

static int blkdev_write_begin(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
{
	return block_write_begin(mapping, pos, len, pagep, blkdev_get_block);
}

static int blkdev_write_end(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, unsigned copied, struct page *page,
		void *fsdata)
{
	int ret;
	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);

	unlock_page(page);
	put_page(page);

	return ret;
}

const struct address_space_operations def_blk_aops = {
	.dirty_folio	= block_dirty_folio,
	.invalidate_folio = block_invalidate_folio,
	.read_folio	= blkdev_read_folio,
	.readahead	= blkdev_readahead,
	.writepages	= blkdev_writepages,
	.write_begin	= blkdev_write_begin,
	.write_end	= blkdev_write_end,
	.migrate_folio	= buffer_migrate_folio_norefs,
	.is_dirty_writeback = buffer_check_dirty_writeback,
};
#else /* CONFIG_BUFFER_HEAD */
static int blkdev_read_folio(struct file *file, struct folio *folio)
{
	return iomap_read_folio(folio, &blkdev_iomap_ops);
}

static void blkdev_readahead(struct readahead_control *rac)
{
	iomap_readahead(rac, &blkdev_iomap_ops);
}

static int blkdev_map_blocks(struct iomap_writepage_ctx *wpc,
		struct inode *inode, loff_t offset)
{
	loff_t isize = i_size_read(inode);

	if (WARN_ON_ONCE(offset >= isize))
		return -EIO;
	if (offset >= wpc->iomap.offset &&
	    offset < wpc->iomap.offset + wpc->iomap.length)
		return 0;
	return blkdev_iomap_begin(inode, offset, isize - offset,
				  IOMAP_WRITE, &wpc->iomap, NULL);
}

static const struct iomap_writeback_ops blkdev_writeback_ops = {
	.map_blocks		= blkdev_map_blocks,
};

static int blkdev_writepages(struct address_space *mapping,
		struct writeback_control *wbc)
{
	struct iomap_writepage_ctx wpc = { };

	return iomap_writepages(mapping, wbc, &wpc, &blkdev_writeback_ops);
}

const struct address_space_operations def_blk_aops = {
	.dirty_folio	= filemap_dirty_folio,
	.release_folio		= iomap_release_folio,
	.invalidate_folio	= iomap_invalidate_folio,
	.read_folio		= blkdev_read_folio,
	.readahead		= blkdev_readahead,
	.writepages		= blkdev_writepages,
	.is_partially_uptodate  = iomap_is_partially_uptodate,
	.error_remove_folio	= generic_error_remove_folio,
	.migrate_folio		= filemap_migrate_folio,
};
#endif /* CONFIG_BUFFER_HEAD */

/*
 * for a block special file file_inode(file)->i_size is zero
 * so we compute the size by hand (just as in block_read/write above)
 */
static loff_t blkdev_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *bd_inode = bdev_file_inode(file);
	loff_t retval;

	inode_lock(bd_inode);
	retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
	inode_unlock(bd_inode);
	return retval;
}

static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
		int datasync)
{
	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
	int error;

	error = file_write_and_wait_range(filp, start, end);
	if (error)
		return error;

	/*
	 * There is no need to serialise calls to blkdev_issue_flush with
	 * i_mutex and doing so causes performance issues with concurrent
	 * O_SYNC writers to a block device.
	 */
	error = blkdev_issue_flush(bdev);
	if (error == -EOPNOTSUPP)
		error = 0;

	return error;
}

/**
 * file_to_blk_mode - get block open flags from file flags
 * @file: file whose open flags should be converted
 *
 * Look at file open flags and generate corresponding block open flags from
 * them. The function works both for file just being open (e.g. during ->open
 * callback) and for file that is already open. This is actually non-trivial
 * (see comment in the function).
 */
blk_mode_t file_to_blk_mode(struct file *file)
{
	blk_mode_t mode = 0;
	struct bdev_handle *handle = file->private_data;

	if (file->f_mode & FMODE_READ)
		mode |= BLK_OPEN_READ;
	if (file->f_mode & FMODE_WRITE)
		mode |= BLK_OPEN_WRITE;
	/*
	 * do_dentry_open() clears O_EXCL from f_flags, use handle->mode to
	 * determine whether the open was exclusive for already open files.
	 */
	if (handle)
		mode |= handle->mode & BLK_OPEN_EXCL;
	else if (file->f_flags & O_EXCL)
		mode |= BLK_OPEN_EXCL;
	if (file->f_flags & O_NDELAY)
		mode |= BLK_OPEN_NDELAY;

	/*
	 * If all bits in O_ACCMODE set (aka O_RDWR | O_WRONLY), the floppy
	 * driver has historically allowed ioctls as if the file was opened for
	 * writing, but does not allow and actual reads or writes.
	 */
	if ((file->f_flags & O_ACCMODE) == (O_RDWR | O_WRONLY))
		mode |= BLK_OPEN_WRITE_IOCTL;

	return mode;
}

static int blkdev_open(struct inode *inode, struct file *filp)
{
	struct bdev_handle *handle;
	blk_mode_t mode;

	/*
	 * Preserve backwards compatibility and allow large file access
	 * even if userspace doesn't ask for it explicitly. Some mkfs
	 * binary needs it. We might want to drop this workaround
	 * during an unstable branch.
	 */
	filp->f_flags |= O_LARGEFILE;
	filp->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;

	mode = file_to_blk_mode(filp);
	handle = bdev_open_by_dev(inode->i_rdev, mode,
			mode & BLK_OPEN_EXCL ? filp : NULL, NULL);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	if (bdev_nowait(handle->bdev))
		filp->f_mode |= FMODE_NOWAIT;

	filp->f_mapping = handle->bdev->bd_inode->i_mapping;
	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
	filp->private_data = handle;
	return 0;
}

static int blkdev_release(struct inode *inode, struct file *filp)
{
	bdev_release(filp->private_data);
	return 0;
}

static ssize_t
blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
	size_t count = iov_iter_count(from);
	ssize_t written;

	written = kiocb_invalidate_pages(iocb, count);
	if (written) {
		if (written == -EBUSY)
			return 0;
		return written;
	}

	written = blkdev_direct_IO(iocb, from);
	if (written > 0) {
		kiocb_invalidate_post_direct_write(iocb, count);
		iocb->ki_pos += written;
		count -= written;
	}
	if (written != -EIOCBQUEUED)
		iov_iter_revert(from, count - iov_iter_count(from));
	return written;
}

static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from)
{
	return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops);
}

/*
 * Write data to the block device.  Only intended for the block device itself
 * and the raw driver which basically is a fake block device.
 *
 * Does not take i_mutex for the write and thus is not for general purpose
 * use.
 */
static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct block_device *bdev = I_BDEV(file->f_mapping->host);
	struct inode *bd_inode = bdev->bd_inode;
	loff_t size = bdev_nr_bytes(bdev);
	size_t shorted = 0;
	ssize_t ret;

	if (bdev_read_only(bdev))
		return -EPERM;

	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
		return -ETXTBSY;

	if (!iov_iter_count(from))
		return 0;

	if (iocb->ki_pos >= size)
		return -ENOSPC;

	if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
		return -EOPNOTSUPP;

	size -= iocb->ki_pos;
	if (iov_iter_count(from) > size) {
		shorted = iov_iter_count(from) - size;
		iov_iter_truncate(from, size);
	}

	ret = file_update_time(file);
	if (ret)
		return ret;

	if (iocb->ki_flags & IOCB_DIRECT) {
		ret = blkdev_direct_write(iocb, from);
		if (ret >= 0 && iov_iter_count(from))
			ret = direct_write_fallback(iocb, from, ret,
					blkdev_buffered_write(iocb, from));
	} else {
		ret = blkdev_buffered_write(iocb, from);
	}

	if (ret > 0)
		ret = generic_write_sync(iocb, ret);
	iov_iter_reexpand(from, iov_iter_count(from) + shorted);
	return ret;
}

static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
	loff_t size = bdev_nr_bytes(bdev);
	loff_t pos = iocb->ki_pos;
	size_t shorted = 0;
	ssize_t ret = 0;
	size_t count;

	if (unlikely(pos + iov_iter_count(to) > size)) {
		if (pos >= size)
			return 0;
		size -= pos;
		shorted = iov_iter_count(to) - size;
		iov_iter_truncate(to, size);
	}

	count = iov_iter_count(to);
	if (!count)
		goto reexpand; /* skip atime */

	if (iocb->ki_flags & IOCB_DIRECT) {
		ret = kiocb_write_and_wait(iocb, count);
		if (ret < 0)
			goto reexpand;
		file_accessed(iocb->ki_filp);

		ret = blkdev_direct_IO(iocb, to);
		if (ret >= 0) {
			iocb->ki_pos += ret;
			count -= ret;
		}
		iov_iter_revert(to, count - iov_iter_count(to));
		if (ret < 0 || !count)
			goto reexpand;
	}

	ret = filemap_read(iocb, to, ret);

reexpand:
	if (unlikely(shorted))
		iov_iter_reexpand(to, iov_iter_count(to) + shorted);
	return ret;
}

#define	BLKDEV_FALLOC_FL_SUPPORTED					\
		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)

static long blkdev_fallocate(struct file *file, int mode, loff_t start,
			     loff_t len)
{
	struct inode *inode = bdev_file_inode(file);
	struct block_device *bdev = I_BDEV(inode);
	loff_t end = start + len - 1;
	loff_t isize;
	int error;

	/* Fail if we don't recognize the flags. */
	if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
		return -EOPNOTSUPP;

	/* Don't go off the end of the device. */
	isize = bdev_nr_bytes(bdev);
	if (start >= isize)
		return -EINVAL;
	if (end >= isize) {
		if (mode & FALLOC_FL_KEEP_SIZE) {
			len = isize - start;
			end = start + len - 1;
		} else
			return -EINVAL;
	}

	/*
	 * Don't allow IO that isn't aligned to logical block size.
	 */
	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
		return -EINVAL;

	filemap_invalidate_lock(inode->i_mapping);

	/*
	 * Invalidate the page cache, including dirty pages, for valid
	 * de-allocate mode calls to fallocate().
	 */
	switch (mode) {
	case FALLOC_FL_ZERO_RANGE:
	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
		error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
		if (error)
			goto fail;

		error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
					     len >> SECTOR_SHIFT, GFP_KERNEL,
					     BLKDEV_ZERO_NOUNMAP);
		break;
	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
		error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
		if (error)
			goto fail;

		error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
					     len >> SECTOR_SHIFT, GFP_KERNEL,
					     BLKDEV_ZERO_NOFALLBACK);
		break;
	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
		error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
		if (error)
			goto fail;

		error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT,
					     len >> SECTOR_SHIFT, GFP_KERNEL);
		break;
	default:
		error = -EOPNOTSUPP;
	}

 fail:
	filemap_invalidate_unlock(inode->i_mapping);
	return error;
}

static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *bd_inode = bdev_file_inode(file);

	if (bdev_read_only(I_BDEV(bd_inode)))
		return generic_file_readonly_mmap(file, vma);

	return generic_file_mmap(file, vma);
}

const struct file_operations def_blk_fops = {
	.open		= blkdev_open,
	.release	= blkdev_release,
	.llseek		= blkdev_llseek,
	.read_iter	= blkdev_read_iter,
	.write_iter	= blkdev_write_iter,
	.iopoll		= iocb_bio_iopoll,
	.mmap		= blkdev_mmap,
	.fsync		= blkdev_fsync,
	.unlocked_ioctl	= blkdev_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= compat_blkdev_ioctl,
#endif
	.splice_read	= filemap_splice_read,
	.splice_write	= iter_file_splice_write,
	.fallocate	= blkdev_fallocate,
};

static __init int blkdev_init(void)
{
	return bioset_init(&blkdev_dio_pool, 4,
				offsetof(struct blkdev_dio, bio),
				BIOSET_NEED_BVECS|BIOSET_PERCPU_CACHE);
}
module_init(blkdev_init);