summaryrefslogtreecommitdiff
path: root/fs/ext4/file.c
blob: 0d624250a62bfdfaef0cf0710ef22f139e65d076 (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/ext4/file.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/file.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  ext4 fs regular file handling primitives
 *
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 *	(jj@sunsite.ms.mff.cuni.cz)
 */

#include <linux/time.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/mount.h>
#include <linux/path.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/pagevec.h>
#include <linux/uio.h>
#include <linux/mman.h>
#include <linux/backing-dev.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "truncate.h"

static bool ext4_dio_supported(struct inode *inode)
{
	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
		return false;
	if (fsverity_active(inode))
		return false;
	if (ext4_should_journal_data(inode))
		return false;
	if (ext4_has_inline_data(inode))
		return false;
	return true;
}

static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	ssize_t ret;
	struct inode *inode = file_inode(iocb->ki_filp);

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!inode_trylock_shared(inode))
			return -EAGAIN;
	} else {
		inode_lock_shared(inode);
	}

	if (!ext4_dio_supported(inode)) {
		inode_unlock_shared(inode);
		/*
		 * Fallback to buffered I/O if the operation being performed on
		 * the inode is not supported by direct I/O. The IOCB_DIRECT
		 * flag needs to be cleared here in order to ensure that the
		 * direct I/O path within generic_file_read_iter() is not
		 * taken.
		 */
		iocb->ki_flags &= ~IOCB_DIRECT;
		return generic_file_read_iter(iocb, to);
	}

	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL,
			   is_sync_kiocb(iocb));
	inode_unlock_shared(inode);

	file_accessed(iocb->ki_filp);
	return ret;
}

#ifdef CONFIG_FS_DAX
static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!inode_trylock_shared(inode))
			return -EAGAIN;
	} else {
		inode_lock_shared(inode);
	}
	/*
	 * Recheck under inode lock - at this point we are sure it cannot
	 * change anymore
	 */
	if (!IS_DAX(inode)) {
		inode_unlock_shared(inode);
		/* Fallback to buffered IO in case we cannot support DAX */
		return generic_file_read_iter(iocb, to);
	}
	ret = dax_iomap_rw(iocb, to, &ext4_iomap_ops);
	inode_unlock_shared(inode);

	file_accessed(iocb->ki_filp);
	return ret;
}
#endif

static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = file_inode(iocb->ki_filp);

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

	if (!iov_iter_count(to))
		return 0; /* skip atime */

#ifdef CONFIG_FS_DAX
	if (IS_DAX(inode))
		return ext4_dax_read_iter(iocb, to);
#endif
	if (iocb->ki_flags & IOCB_DIRECT)
		return ext4_dio_read_iter(iocb, to);

	return generic_file_read_iter(iocb, to);
}

/*
 * Called when an inode is released. Note that this is different
 * from ext4_file_open: open gets called at every open, but release
 * gets called only when /all/ the files are closed.
 */
static int ext4_release_file(struct inode *inode, struct file *filp)
{
	if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
		ext4_alloc_da_blocks(inode);
		ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
	}
	/* if we are the last writer on the inode, drop the block reservation */
	if ((filp->f_mode & FMODE_WRITE) &&
			(atomic_read(&inode->i_writecount) == 1) &&
		        !EXT4_I(inode)->i_reserved_data_blocks)
	{
		down_write(&EXT4_I(inode)->i_data_sem);
		ext4_discard_preallocations(inode);
		up_write(&EXT4_I(inode)->i_data_sem);
	}
	if (is_dx(inode) && filp->private_data)
		ext4_htree_free_dir_info(filp->private_data);

	return 0;
}

/*
 * This tests whether the IO in question is block-aligned or not.
 * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
 * are converted to written only after the IO is complete.  Until they are
 * mapped, these blocks appear as holes, so dio_zero_block() will assume that
 * it needs to zero out portions of the start and/or end block.  If 2 AIO
 * threads are at work on the same unwritten block, they must be synchronized
 * or one thread will zero the other's data, causing corruption.
 */
static bool
ext4_unaligned_io(struct inode *inode, struct iov_iter *from, loff_t pos)
{
	struct super_block *sb = inode->i_sb;
	unsigned long blockmask = sb->s_blocksize - 1;

	if ((pos | iov_iter_alignment(from)) & blockmask)
		return true;

	return false;
}

static bool
ext4_extending_io(struct inode *inode, loff_t offset, size_t len)
{
	if (offset + len > i_size_read(inode) ||
	    offset + len > EXT4_I(inode)->i_disksize)
		return true;
	return false;
}

/* Is IO overwriting allocated and initialized blocks? */
static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
{
	struct ext4_map_blocks map;
	unsigned int blkbits = inode->i_blkbits;
	int err, blklen;

	if (pos + len > i_size_read(inode))
		return false;

	map.m_lblk = pos >> blkbits;
	map.m_len = EXT4_MAX_BLOCKS(len, pos, blkbits);
	blklen = map.m_len;

	err = ext4_map_blocks(NULL, inode, &map, 0);
	/*
	 * 'err==len' means that all of the blocks have been preallocated,
	 * regardless of whether they have been initialized or not. To exclude
	 * unwritten extents, we need to check m_flags.
	 */
	return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
}

static ssize_t ext4_generic_write_checks(struct kiocb *iocb,
					 struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

	if (unlikely(IS_IMMUTABLE(inode)))
		return -EPERM;

	ret = generic_write_checks(iocb, from);
	if (ret <= 0)
		return ret;

	/*
	 * If we have encountered a bitmap-format file, the size limit
	 * is smaller than s_maxbytes, which is for extent-mapped files.
	 */
	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);

		if (iocb->ki_pos >= sbi->s_bitmap_maxbytes)
			return -EFBIG;
		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
	}

	return iov_iter_count(from);
}

static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
	ssize_t ret, count;

	count = ext4_generic_write_checks(iocb, from);
	if (count <= 0)
		return count;

	ret = file_modified(iocb->ki_filp);
	if (ret)
		return ret;
	return count;
}

static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
					struct iov_iter *from)
{
	ssize_t ret;
	struct inode *inode = file_inode(iocb->ki_filp);

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

	inode_lock(inode);
	ret = ext4_write_checks(iocb, from);
	if (ret <= 0)
		goto out;

	current->backing_dev_info = inode_to_bdi(inode);
	ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos);
	current->backing_dev_info = NULL;

out:
	inode_unlock(inode);
	if (likely(ret > 0)) {
		iocb->ki_pos += ret;
		ret = generic_write_sync(iocb, ret);
	}

	return ret;
}

static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
					   ssize_t written, size_t count)
{
	handle_t *handle;
	bool truncate = false;
	u8 blkbits = inode->i_blkbits;
	ext4_lblk_t written_blk, end_blk;

	/*
	 * Note that EXT4_I(inode)->i_disksize can get extended up to
	 * inode->i_size while the I/O was running due to writeback of delalloc
	 * blocks. But, the code in ext4_iomap_alloc() is careful to use
	 * zeroed/unwritten extents if this is possible; thus we won't leave
	 * uninitialized blocks in a file even if we didn't succeed in writing
	 * as much as we intended.
	 */
	WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize);
	if (offset + count <= EXT4_I(inode)->i_disksize) {
		/*
		 * We need to ensure that the inode is removed from the orphan
		 * list if it has been added prematurely, due to writeback of
		 * delalloc blocks.
		 */
		if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
			handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);

			if (IS_ERR(handle)) {
				ext4_orphan_del(NULL, inode);
				return PTR_ERR(handle);
			}

			ext4_orphan_del(handle, inode);
			ext4_journal_stop(handle);
		}

		return written;
	}

	if (written < 0)
		goto truncate;

	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
	if (IS_ERR(handle)) {
		written = PTR_ERR(handle);
		goto truncate;
	}

	if (ext4_update_inode_size(inode, offset + written))
		ext4_mark_inode_dirty(handle, inode);

	/*
	 * We may need to truncate allocated but not written blocks beyond EOF.
	 */
	written_blk = ALIGN(offset + written, 1 << blkbits);
	end_blk = ALIGN(offset + count, 1 << blkbits);
	if (written_blk < end_blk && ext4_can_truncate(inode))
		truncate = true;

	/*
	 * Remove the inode from the orphan list if it has been extended and
	 * everything went OK.
	 */
	if (!truncate && inode->i_nlink)
		ext4_orphan_del(handle, inode);
	ext4_journal_stop(handle);

	if (truncate) {
truncate:
		ext4_truncate_failed_write(inode);
		/*
		 * If the truncate operation failed early, then the inode may
		 * still be on the orphan list. In that case, we need to try
		 * remove the inode from the in-memory linked list.
		 */
		if (inode->i_nlink)
			ext4_orphan_del(NULL, inode);
	}

	return written;
}

static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
				 int error, unsigned int flags)
{
	loff_t offset = iocb->ki_pos;
	struct inode *inode = file_inode(iocb->ki_filp);

	if (error)
		return error;

	if (size && flags & IOMAP_DIO_UNWRITTEN)
		return ext4_convert_unwritten_extents(NULL, inode,
						      offset, size);

	return 0;
}

static const struct iomap_dio_ops ext4_dio_write_ops = {
	.end_io = ext4_dio_write_end_io,
};

/*
 * The intention here is to start with shared lock acquired then see if any
 * condition requires an exclusive inode lock. If yes, then we restart the
 * whole operation by releasing the shared lock and acquiring exclusive lock.
 *
 * - For unaligned_io we never take shared lock as it may cause data corruption
 *   when two unaligned IO tries to modify the same block e.g. while zeroing.
 *
 * - For extending writes case we don't take the shared lock, since it requires
 *   updating inode i_disksize and/or orphan handling with exclusive lock.
 *
 * - shared locking will only be true mostly with overwrites. Otherwise we will
 *   switch to exclusive i_rwsem lock.
 */
static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
				     bool *ilock_shared, bool *extend)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	loff_t offset;
	size_t count;
	ssize_t ret;

restart:
	ret = ext4_generic_write_checks(iocb, from);
	if (ret <= 0)
		goto out;

	offset = iocb->ki_pos;
	count = ret;
	if (ext4_extending_io(inode, offset, count))
		*extend = true;
	/*
	 * Determine whether the IO operation will overwrite allocated
	 * and initialized blocks.
	 * We need exclusive i_rwsem for changing security info
	 * in file_modified().
	 */
	if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
	     !ext4_overwrite_io(inode, offset, count))) {
		inode_unlock_shared(inode);
		*ilock_shared = false;
		inode_lock(inode);
		goto restart;
	}

	ret = file_modified(file);
	if (ret < 0)
		goto out;

	return count;
out:
	if (*ilock_shared)
		inode_unlock_shared(inode);
	else
		inode_unlock(inode);
	return ret;
}

static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	ssize_t ret;
	handle_t *handle;
	struct inode *inode = file_inode(iocb->ki_filp);
	loff_t offset = iocb->ki_pos;
	size_t count = iov_iter_count(from);
	const struct iomap_ops *iomap_ops = &ext4_iomap_ops;
	bool extend = false, unaligned_io = false;
	bool ilock_shared = true;

	/*
	 * We initially start with shared inode lock unless it is
	 * unaligned IO which needs exclusive lock anyways.
	 */
	if (ext4_unaligned_io(inode, from, offset)) {
		unaligned_io = true;
		ilock_shared = false;
	}
	/*
	 * Quick check here without any i_rwsem lock to see if it is extending
	 * IO. A more reliable check is done in ext4_dio_write_checks() with
	 * proper locking in place.
	 */
	if (offset + count > i_size_read(inode))
		ilock_shared = false;

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (ilock_shared) {
			if (!inode_trylock_shared(inode))
				return -EAGAIN;
		} else {
			if (!inode_trylock(inode))
				return -EAGAIN;
		}
	} else {
		if (ilock_shared)
			inode_lock_shared(inode);
		else
			inode_lock(inode);
	}

	/* Fallback to buffered I/O if the inode does not support direct I/O. */
	if (!ext4_dio_supported(inode)) {
		if (ilock_shared)
			inode_unlock_shared(inode);
		else
			inode_unlock(inode);
		return ext4_buffered_write_iter(iocb, from);
	}

	ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend);
	if (ret <= 0)
		return ret;

	offset = iocb->ki_pos;
	count = ret;

	/*
	 * Unaligned direct IO must be serialized among each other as zeroing
	 * of partial blocks of two competing unaligned IOs can result in data
	 * corruption.
	 *
	 * So we make sure we don't allow any unaligned IO in flight.
	 * For IOs where we need not wait (like unaligned non-AIO DIO),
	 * below inode_dio_wait() may anyway become a no-op, since we start
	 * with exclusive lock.
	 */
	if (unaligned_io)
		inode_dio_wait(inode);

	if (extend) {
		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
		if (IS_ERR(handle)) {
			ret = PTR_ERR(handle);
			goto out;
		}

		ret = ext4_orphan_add(handle, inode);
		if (ret) {
			ext4_journal_stop(handle);
			goto out;
		}

		ext4_journal_stop(handle);
	}

	if (ilock_shared)
		iomap_ops = &ext4_iomap_overwrite_ops;
	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
			   is_sync_kiocb(iocb) || unaligned_io || extend);

	if (extend)
		ret = ext4_handle_inode_extension(inode, offset, ret, count);

out:
	if (ilock_shared)
		inode_unlock_shared(inode);
	else
		inode_unlock(inode);

	if (ret >= 0 && iov_iter_count(from)) {
		ssize_t err;
		loff_t endbyte;

		offset = iocb->ki_pos;
		err = ext4_buffered_write_iter(iocb, from);
		if (err < 0)
			return err;

		/*
		 * We need to ensure that the pages within the page cache for
		 * the range covered by this I/O are written to disk and
		 * invalidated. This is in attempt to preserve the expected
		 * direct I/O semantics in the case we fallback to buffered I/O
		 * to complete off the I/O request.
		 */
		ret += err;
		endbyte = offset + err - 1;
		err = filemap_write_and_wait_range(iocb->ki_filp->f_mapping,
						   offset, endbyte);
		if (!err)
			invalidate_mapping_pages(iocb->ki_filp->f_mapping,
						 offset >> PAGE_SHIFT,
						 endbyte >> PAGE_SHIFT);
	}

	return ret;
}

#ifdef CONFIG_FS_DAX
static ssize_t
ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	ssize_t ret;
	size_t count;
	loff_t offset;
	handle_t *handle;
	bool extend = false;
	struct inode *inode = file_inode(iocb->ki_filp);

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!inode_trylock(inode))
			return -EAGAIN;
	} else {
		inode_lock(inode);
	}

	ret = ext4_write_checks(iocb, from);
	if (ret <= 0)
		goto out;

	offset = iocb->ki_pos;
	count = iov_iter_count(from);

	if (offset + count > EXT4_I(inode)->i_disksize) {
		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
		if (IS_ERR(handle)) {
			ret = PTR_ERR(handle);
			goto out;
		}

		ret = ext4_orphan_add(handle, inode);
		if (ret) {
			ext4_journal_stop(handle);
			goto out;
		}

		extend = true;
		ext4_journal_stop(handle);
	}

	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);

	if (extend)
		ret = ext4_handle_inode_extension(inode, offset, ret, count);
out:
	inode_unlock(inode);
	if (ret > 0)
		ret = generic_write_sync(iocb, ret);
	return ret;
}
#endif

static ssize_t
ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

#ifdef CONFIG_FS_DAX
	if (IS_DAX(inode))
		return ext4_dax_write_iter(iocb, from);
#endif
	if (iocb->ki_flags & IOCB_DIRECT)
		return ext4_dio_write_iter(iocb, from);

	return ext4_buffered_write_iter(iocb, from);
}

#ifdef CONFIG_FS_DAX
static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
		enum page_entry_size pe_size)
{
	int error = 0;
	vm_fault_t result;
	int retries = 0;
	handle_t *handle = NULL;
	struct inode *inode = file_inode(vmf->vma->vm_file);
	struct super_block *sb = inode->i_sb;

	/*
	 * We have to distinguish real writes from writes which will result in a
	 * COW page; COW writes should *not* poke the journal (the file will not
	 * be changed). Doing so would cause unintended failures when mounted
	 * read-only.
	 *
	 * We check for VM_SHARED rather than vmf->cow_page since the latter is
	 * unset for pe_size != PE_SIZE_PTE (i.e. only in do_cow_fault); for
	 * other sizes, dax_iomap_fault will handle splitting / fallback so that
	 * we eventually come back with a COW page.
	 */
	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
		(vmf->vma->vm_flags & VM_SHARED);
	pfn_t pfn;

	if (write) {
		sb_start_pagefault(sb);
		file_update_time(vmf->vma->vm_file);
		down_read(&EXT4_I(inode)->i_mmap_sem);
retry:
		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
					       EXT4_DATA_TRANS_BLOCKS(sb));
		if (IS_ERR(handle)) {
			up_read(&EXT4_I(inode)->i_mmap_sem);
			sb_end_pagefault(sb);
			return VM_FAULT_SIGBUS;
		}
	} else {
		down_read(&EXT4_I(inode)->i_mmap_sem);
	}
	result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops);
	if (write) {
		ext4_journal_stop(handle);

		if ((result & VM_FAULT_ERROR) && error == -ENOSPC &&
		    ext4_should_retry_alloc(sb, &retries))
			goto retry;
		/* Handling synchronous page fault? */
		if (result & VM_FAULT_NEEDDSYNC)
			result = dax_finish_sync_fault(vmf, pe_size, pfn);
		up_read(&EXT4_I(inode)->i_mmap_sem);
		sb_end_pagefault(sb);
	} else {
		up_read(&EXT4_I(inode)->i_mmap_sem);
	}

	return result;
}

static vm_fault_t ext4_dax_fault(struct vm_fault *vmf)
{
	return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
}

static const struct vm_operations_struct ext4_dax_vm_ops = {
	.fault		= ext4_dax_fault,
	.huge_fault	= ext4_dax_huge_fault,
	.page_mkwrite	= ext4_dax_fault,
	.pfn_mkwrite	= ext4_dax_fault,
};
#else
#define ext4_dax_vm_ops	ext4_file_vm_ops
#endif

static const struct vm_operations_struct ext4_file_vm_ops = {
	.fault		= ext4_filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite   = ext4_page_mkwrite,
};

static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *inode = file->f_mapping->host;
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
	struct dax_device *dax_dev = sbi->s_daxdev;

	if (unlikely(ext4_forced_shutdown(sbi)))
		return -EIO;

	/*
	 * We don't support synchronous mappings for non-DAX files and
	 * for DAX files if underneath dax_device is not synchronous.
	 */
	if (!daxdev_mapping_supported(vma, dax_dev))
		return -EOPNOTSUPP;

	file_accessed(file);
	if (IS_DAX(file_inode(file))) {
		vma->vm_ops = &ext4_dax_vm_ops;
		vma->vm_flags |= VM_HUGEPAGE;
	} else {
		vma->vm_ops = &ext4_file_vm_ops;
	}
	return 0;
}

static int ext4_sample_last_mounted(struct super_block *sb,
				    struct vfsmount *mnt)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct path path;
	char buf[64], *cp;
	handle_t *handle;
	int err;

	if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
		return 0;

	if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
		return 0;

	sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
	/*
	 * Sample where the filesystem has been mounted and
	 * store it in the superblock for sysadmin convenience
	 * when trying to sort through large numbers of block
	 * devices or filesystem images.
	 */
	memset(buf, 0, sizeof(buf));
	path.mnt = mnt;
	path.dentry = mnt->mnt_root;
	cp = d_path(&path, buf, sizeof(buf));
	err = 0;
	if (IS_ERR(cp))
		goto out;

	handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
	err = PTR_ERR(handle);
	if (IS_ERR(handle))
		goto out;
	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
	if (err)
		goto out_journal;
	strlcpy(sbi->s_es->s_last_mounted, cp,
		sizeof(sbi->s_es->s_last_mounted));
	ext4_handle_dirty_super(handle, sb);
out_journal:
	ext4_journal_stop(handle);
out:
	sb_end_intwrite(sb);
	return err;
}

static int ext4_file_open(struct inode * inode, struct file * filp)
{
	int ret;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

	ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt);
	if (ret)
		return ret;

	ret = fscrypt_file_open(inode, filp);
	if (ret)
		return ret;

	ret = fsverity_file_open(inode, filp);
	if (ret)
		return ret;

	/*
	 * Set up the jbd2_inode if we are opening the inode for
	 * writing and the journal is present
	 */
	if (filp->f_mode & FMODE_WRITE) {
		ret = ext4_inode_attach_jinode(inode);
		if (ret < 0)
			return ret;
	}

	filp->f_mode |= FMODE_NOWAIT;
	return dquot_file_open(inode, filp);
}

/*
 * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
 * by calling generic_file_llseek_size() with the appropriate maxbytes
 * value for each.
 */
loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	loff_t maxbytes;

	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
		maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
	else
		maxbytes = inode->i_sb->s_maxbytes;

	switch (whence) {
	default:
		return generic_file_llseek_size(file, offset, whence,
						maxbytes, i_size_read(inode));
	case SEEK_HOLE:
		inode_lock_shared(inode);
		offset = iomap_seek_hole(inode, offset,
					 &ext4_iomap_report_ops);
		inode_unlock_shared(inode);
		break;
	case SEEK_DATA:
		inode_lock_shared(inode);
		offset = iomap_seek_data(inode, offset,
					 &ext4_iomap_report_ops);
		inode_unlock_shared(inode);
		break;
	}

	if (offset < 0)
		return offset;
	return vfs_setpos(file, offset, maxbytes);
}

const struct file_operations ext4_file_operations = {
	.llseek		= ext4_llseek,
	.read_iter	= ext4_file_read_iter,
	.write_iter	= ext4_file_write_iter,
	.iopoll		= iomap_dio_iopoll,
	.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= ext4_compat_ioctl,
#endif
	.mmap		= ext4_file_mmap,
	.mmap_supported_flags = MAP_SYNC,
	.open		= ext4_file_open,
	.release	= ext4_release_file,
	.fsync		= ext4_sync_file,
	.get_unmapped_area = thp_get_unmapped_area,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.fallocate	= ext4_fallocate,
};

const struct inode_operations ext4_file_inode_operations = {
	.setattr	= ext4_setattr,
	.getattr	= ext4_file_getattr,
	.listxattr	= ext4_listxattr,
	.get_acl	= ext4_get_acl,
	.set_acl	= ext4_set_acl,
	.fiemap		= ext4_fiemap,
};