summaryrefslogtreecommitdiffstats
path: root/fs/zonefs/file.c
blob: 617e4f9db42eab769674230b12dc85595f12322b (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Simple file system for zoned block devices exposing zones as files.
 *
 * Copyright (C) 2022 Western Digital Corporation or its affiliates.
 */
#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/iomap.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/statfs.h>
#include <linux/writeback.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
#include <linux/parser.h>
#include <linux/uio.h>
#include <linux/mman.h>
#include <linux/sched/mm.h>
#include <linux/task_io_accounting_ops.h>

#include "zonefs.h"

#include "trace.h"

static int zonefs_read_iomap_begin(struct inode *inode, loff_t offset,
				   loff_t length, unsigned int flags,
				   struct iomap *iomap, struct iomap *srcmap)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	struct super_block *sb = inode->i_sb;
	loff_t isize;

	/*
	 * All blocks are always mapped below EOF. If reading past EOF,
	 * act as if there is a hole up to the file maximum size.
	 */
	mutex_lock(&zi->i_truncate_mutex);
	iomap->bdev = inode->i_sb->s_bdev;
	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
	isize = i_size_read(inode);
	if (iomap->offset >= isize) {
		iomap->type = IOMAP_HOLE;
		iomap->addr = IOMAP_NULL_ADDR;
		iomap->length = length;
	} else {
		iomap->type = IOMAP_MAPPED;
		iomap->addr = (z->z_sector << SECTOR_SHIFT) + iomap->offset;
		iomap->length = isize - iomap->offset;
	}
	mutex_unlock(&zi->i_truncate_mutex);

	trace_zonefs_iomap_begin(inode, iomap);

	return 0;
}

static const struct iomap_ops zonefs_read_iomap_ops = {
	.iomap_begin	= zonefs_read_iomap_begin,
};

static int zonefs_write_iomap_begin(struct inode *inode, loff_t offset,
				    loff_t length, unsigned int flags,
				    struct iomap *iomap, struct iomap *srcmap)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	struct super_block *sb = inode->i_sb;
	loff_t isize;

	/* All write I/Os should always be within the file maximum size */
	if (WARN_ON_ONCE(offset + length > z->z_capacity))
		return -EIO;

	/*
	 * Sequential zones can only accept direct writes. This is already
	 * checked when writes are issued, so warn if we see a page writeback
	 * operation.
	 */
	if (WARN_ON_ONCE(zonefs_zone_is_seq(z) && !(flags & IOMAP_DIRECT)))
		return -EIO;

	/*
	 * For conventional zones, all blocks are always mapped. For sequential
	 * zones, all blocks after always mapped below the inode size (zone
	 * write pointer) and unwriten beyond.
	 */
	mutex_lock(&zi->i_truncate_mutex);
	iomap->bdev = inode->i_sb->s_bdev;
	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
	iomap->addr = (z->z_sector << SECTOR_SHIFT) + iomap->offset;
	isize = i_size_read(inode);
	if (iomap->offset >= isize) {
		iomap->type = IOMAP_UNWRITTEN;
		iomap->length = z->z_capacity - iomap->offset;
	} else {
		iomap->type = IOMAP_MAPPED;
		iomap->length = isize - iomap->offset;
	}
	mutex_unlock(&zi->i_truncate_mutex);

	trace_zonefs_iomap_begin(inode, iomap);

	return 0;
}

static const struct iomap_ops zonefs_write_iomap_ops = {
	.iomap_begin	= zonefs_write_iomap_begin,
};

static int zonefs_read_folio(struct file *unused, struct folio *folio)
{
	return iomap_read_folio(folio, &zonefs_read_iomap_ops);
}

static void zonefs_readahead(struct readahead_control *rac)
{
	iomap_readahead(rac, &zonefs_read_iomap_ops);
}

/*
 * Map blocks for page writeback. This is used only on conventional zone files,
 * which implies that the page range can only be within the fixed inode size.
 */
static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
				   struct inode *inode, loff_t offset)
{
	struct zonefs_zone *z = zonefs_inode_zone(inode);

	if (WARN_ON_ONCE(zonefs_zone_is_seq(z)))
		return -EIO;
	if (WARN_ON_ONCE(offset >= i_size_read(inode)))
		return -EIO;

	/* If the mapping is already OK, nothing needs to be done */
	if (offset >= wpc->iomap.offset &&
	    offset < wpc->iomap.offset + wpc->iomap.length)
		return 0;

	return zonefs_write_iomap_begin(inode, offset,
					z->z_capacity - offset,
					IOMAP_WRITE, &wpc->iomap, NULL);
}

static const struct iomap_writeback_ops zonefs_writeback_ops = {
	.map_blocks		= zonefs_write_map_blocks,
};

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

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

static int zonefs_swap_activate(struct swap_info_struct *sis,
				struct file *swap_file, sector_t *span)
{
	struct inode *inode = file_inode(swap_file);

	if (zonefs_inode_is_seq(inode)) {
		zonefs_err(inode->i_sb,
			   "swap file: not a conventional zone file\n");
		return -EINVAL;
	}

	return iomap_swapfile_activate(sis, swap_file, span,
				       &zonefs_read_iomap_ops);
}

const struct address_space_operations zonefs_file_aops = {
	.read_folio		= zonefs_read_folio,
	.readahead		= zonefs_readahead,
	.writepages		= zonefs_writepages,
	.dirty_folio		= filemap_dirty_folio,
	.release_folio		= iomap_release_folio,
	.invalidate_folio	= iomap_invalidate_folio,
	.migrate_folio		= filemap_migrate_folio,
	.is_partially_uptodate	= iomap_is_partially_uptodate,
	.error_remove_page	= generic_error_remove_page,
	.direct_IO		= noop_direct_IO,
	.swap_activate		= zonefs_swap_activate,
};

int zonefs_file_truncate(struct inode *inode, loff_t isize)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	loff_t old_isize;
	enum req_op op;
	int ret = 0;

	/*
	 * Only sequential zone files can be truncated and truncation is allowed
	 * only down to a 0 size, which is equivalent to a zone reset, and to
	 * the maximum file size, which is equivalent to a zone finish.
	 */
	if (!zonefs_zone_is_seq(z))
		return -EPERM;

	if (!isize)
		op = REQ_OP_ZONE_RESET;
	else if (isize == z->z_capacity)
		op = REQ_OP_ZONE_FINISH;
	else
		return -EPERM;

	inode_dio_wait(inode);

	/* Serialize against page faults */
	filemap_invalidate_lock(inode->i_mapping);

	/* Serialize against zonefs_iomap_begin() */
	mutex_lock(&zi->i_truncate_mutex);

	old_isize = i_size_read(inode);
	if (isize == old_isize)
		goto unlock;

	ret = zonefs_inode_zone_mgmt(inode, op);
	if (ret)
		goto unlock;

	/*
	 * If the mount option ZONEFS_MNTOPT_EXPLICIT_OPEN is set,
	 * take care of open zones.
	 */
	if (z->z_flags & ZONEFS_ZONE_OPEN) {
		/*
		 * Truncating a zone to EMPTY or FULL is the equivalent of
		 * closing the zone. For a truncation to 0, we need to
		 * re-open the zone to ensure new writes can be processed.
		 * For a truncation to the maximum file size, the zone is
		 * closed and writes cannot be accepted anymore, so clear
		 * the open flag.
		 */
		if (!isize)
			ret = zonefs_inode_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
		else
			z->z_flags &= ~ZONEFS_ZONE_OPEN;
	}

	zonefs_update_stats(inode, isize);
	truncate_setsize(inode, isize);
	z->z_wpoffset = isize;
	zonefs_inode_account_active(inode);

unlock:
	mutex_unlock(&zi->i_truncate_mutex);
	filemap_invalidate_unlock(inode->i_mapping);

	return ret;
}

static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end,
			     int datasync)
{
	struct inode *inode = file_inode(file);
	int ret = 0;

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

	/*
	 * Since only direct writes are allowed in sequential files, page cache
	 * flush is needed only for conventional zone files.
	 */
	if (zonefs_inode_is_cnv(inode))
		ret = file_write_and_wait_range(file, start, end);
	if (!ret)
		ret = blkdev_issue_flush(inode->i_sb->s_bdev);

	if (ret)
		zonefs_io_error(inode, true);

	return ret;
}

static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
{
	struct inode *inode = file_inode(vmf->vma->vm_file);
	vm_fault_t ret;

	if (unlikely(IS_IMMUTABLE(inode)))
		return VM_FAULT_SIGBUS;

	/*
	 * Sanity check: only conventional zone files can have shared
	 * writeable mappings.
	 */
	if (zonefs_inode_is_seq(inode))
		return VM_FAULT_NOPAGE;

	sb_start_pagefault(inode->i_sb);
	file_update_time(vmf->vma->vm_file);

	/* Serialize against truncates */
	filemap_invalidate_lock_shared(inode->i_mapping);
	ret = iomap_page_mkwrite(vmf, &zonefs_write_iomap_ops);
	filemap_invalidate_unlock_shared(inode->i_mapping);

	sb_end_pagefault(inode->i_sb);
	return ret;
}

static const struct vm_operations_struct zonefs_file_vm_ops = {
	.fault		= filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= zonefs_filemap_page_mkwrite,
};

static int zonefs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	/*
	 * Conventional zones accept random writes, so their files can support
	 * shared writable mappings. For sequential zone files, only read
	 * mappings are possible since there are no guarantees for write
	 * ordering between msync() and page cache writeback.
	 */
	if (zonefs_inode_is_seq(file_inode(file)) &&
	    (vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
		return -EINVAL;

	file_accessed(file);
	vma->vm_ops = &zonefs_file_vm_ops;

	return 0;
}

static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence)
{
	loff_t isize = i_size_read(file_inode(file));

	/*
	 * Seeks are limited to below the zone size for conventional zones
	 * and below the zone write pointer for sequential zones. In both
	 * cases, this limit is the inode size.
	 */
	return generic_file_llseek_size(file, offset, whence, isize, isize);
}

static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
					int error, unsigned int flags)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	if (error) {
		zonefs_io_error(inode, true);
		return error;
	}

	if (size && zonefs_inode_is_seq(inode)) {
		/*
		 * Note that we may be seeing completions out of order,
		 * but that is not a problem since a write completed
		 * successfully necessarily means that all preceding writes
		 * were also successful. So we can safely increase the inode
		 * size to the write end location.
		 */
		mutex_lock(&zi->i_truncate_mutex);
		if (i_size_read(inode) < iocb->ki_pos + size) {
			zonefs_update_stats(inode, iocb->ki_pos + size);
			zonefs_i_size_write(inode, iocb->ki_pos + size);
		}
		mutex_unlock(&zi->i_truncate_mutex);
	}

	return 0;
}

static const struct iomap_dio_ops zonefs_write_dio_ops = {
	.end_io			= zonefs_file_write_dio_end_io,
};

static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	struct block_device *bdev = inode->i_sb->s_bdev;
	unsigned int max = bdev_max_zone_append_sectors(bdev);
	struct bio *bio;
	ssize_t size = 0;
	int nr_pages;
	ssize_t ret;

	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
	iov_iter_truncate(from, max);

	nr_pages = iov_iter_npages(from, BIO_MAX_VECS);
	if (!nr_pages)
		return 0;

	bio = bio_alloc(bdev, nr_pages,
			REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE, GFP_NOFS);
	bio->bi_iter.bi_sector = z->z_sector;
	bio->bi_ioprio = iocb->ki_ioprio;
	if (iocb_is_dsync(iocb))
		bio->bi_opf |= REQ_FUA;

	ret = bio_iov_iter_get_pages(bio, from);
	if (unlikely(ret))
		goto out_release;

	size = bio->bi_iter.bi_size;
	task_io_account_write(size);

	if (iocb->ki_flags & IOCB_HIPRI)
		bio_set_polled(bio, iocb);

	ret = submit_bio_wait(bio);

	/*
	 * If the file zone was written underneath the file system, the zone
	 * write pointer may not be where we expect it to be, but the zone
	 * append write can still succeed. So check manually that we wrote where
	 * we intended to, that is, at zi->i_wpoffset.
	 */
	if (!ret) {
		sector_t wpsector =
			z->z_sector + (z->z_wpoffset >> SECTOR_SHIFT);

		if (bio->bi_iter.bi_sector != wpsector) {
			zonefs_warn(inode->i_sb,
				"Corrupted write pointer %llu for zone at %llu\n",
				bio->bi_iter.bi_sector, z->z_sector);
			ret = -EIO;
		}
	}

	zonefs_file_write_dio_end_io(iocb, size, ret, 0);
	trace_zonefs_file_dio_append(inode, size, ret);

out_release:
	bio_release_pages(bio, false);
	bio_put(bio);

	if (ret >= 0) {
		iocb->ki_pos += size;
		return size;
	}

	return ret;
}

/*
 * Do not exceed the LFS limits nor the file zone size. If pos is under the
 * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
 */
static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
					loff_t count)
{
	struct inode *inode = file_inode(file);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	loff_t limit = rlimit(RLIMIT_FSIZE);
	loff_t max_size = z->z_capacity;

	if (limit != RLIM_INFINITY) {
		if (pos >= limit) {
			send_sig(SIGXFSZ, current, 0);
			return -EFBIG;
		}
		count = min(count, limit - pos);
	}

	if (!(file->f_flags & O_LARGEFILE))
		max_size = min_t(loff_t, MAX_NON_LFS, max_size);

	if (unlikely(pos >= max_size))
		return -EFBIG;

	return min(count, max_size - pos);
}

static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	loff_t count;

	if (IS_SWAPFILE(inode))
		return -ETXTBSY;

	if (!iov_iter_count(from))
		return 0;

	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
		return -EINVAL;

	if (iocb->ki_flags & IOCB_APPEND) {
		if (zonefs_zone_is_cnv(z))
			return -EINVAL;
		mutex_lock(&zi->i_truncate_mutex);
		iocb->ki_pos = z->z_wpoffset;
		mutex_unlock(&zi->i_truncate_mutex);
	}

	count = zonefs_write_check_limits(file, iocb->ki_pos,
					  iov_iter_count(from));
	if (count < 0)
		return count;

	iov_iter_truncate(from, count);
	return iov_iter_count(from);
}

/*
 * Handle direct writes. For sequential zone files, this is the only possible
 * write path. For these files, check that the user is issuing writes
 * sequentially from the end of the file. This code assumes that the block layer
 * delivers write requests to the device in sequential order. This is always the
 * case if a block IO scheduler implementing the ELEVATOR_F_ZBD_SEQ_WRITE
 * elevator feature is being used (e.g. mq-deadline). The block layer always
 * automatically select such an elevator for zoned block devices during the
 * device initialization.
 */
static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	struct super_block *sb = inode->i_sb;
	bool sync = is_sync_kiocb(iocb);
	bool append = false;
	ssize_t ret, count;

	/*
	 * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
	 * as this can cause write reordering (e.g. the first aio gets EAGAIN
	 * on the inode lock but the second goes through but is now unaligned).
	 */
	if (zonefs_zone_is_seq(z) && !sync && (iocb->ki_flags & IOCB_NOWAIT))
		return -EOPNOTSUPP;

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

	count = zonefs_write_checks(iocb, from);
	if (count <= 0) {
		ret = count;
		goto inode_unlock;
	}

	if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
		ret = -EINVAL;
		goto inode_unlock;
	}

	/* Enforce sequential writes (append only) in sequential zones */
	if (zonefs_zone_is_seq(z)) {
		mutex_lock(&zi->i_truncate_mutex);
		if (iocb->ki_pos != z->z_wpoffset) {
			mutex_unlock(&zi->i_truncate_mutex);
			ret = -EINVAL;
			goto inode_unlock;
		}
		mutex_unlock(&zi->i_truncate_mutex);
		append = sync;
	}

	if (append)
		ret = zonefs_file_dio_append(iocb, from);
	else
		ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
				   &zonefs_write_dio_ops, 0, NULL, 0);
	if (zonefs_zone_is_seq(z) &&
	    (ret > 0 || ret == -EIOCBQUEUED)) {
		if (ret > 0)
			count = ret;

		/*
		 * Update the zone write pointer offset assuming the write
		 * operation succeeded. If it did not, the error recovery path
		 * will correct it. Also do active seq file accounting.
		 */
		mutex_lock(&zi->i_truncate_mutex);
		z->z_wpoffset += count;
		zonefs_inode_account_active(inode);
		mutex_unlock(&zi->i_truncate_mutex);
	}

inode_unlock:
	inode_unlock(inode);

	return ret;
}

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

	/*
	 * Direct IO writes are mandatory for sequential zone files so that the
	 * write IO issuing order is preserved.
	 */
	if (zonefs_inode_is_seq(inode))
		return -EIO;

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

	ret = zonefs_write_checks(iocb, from);
	if (ret <= 0)
		goto inode_unlock;

	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops);
	if (ret > 0)
		iocb->ki_pos += ret;
	else if (ret == -EIO)
		zonefs_io_error(inode, true);

inode_unlock:
	inode_unlock(inode);
	if (ret > 0)
		ret = generic_write_sync(iocb, ret);

	return ret;
}

static ssize_t zonefs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_zone *z = zonefs_inode_zone(inode);

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

	if (sb_rdonly(inode->i_sb))
		return -EROFS;

	/* Write operations beyond the zone capacity are not allowed */
	if (iocb->ki_pos >= z->z_capacity)
		return -EFBIG;

	if (iocb->ki_flags & IOCB_DIRECT) {
		ssize_t ret = zonefs_file_dio_write(iocb, from);

		if (ret != -ENOTBLK)
			return ret;
	}

	return zonefs_file_buffered_write(iocb, from);
}

static int zonefs_file_read_dio_end_io(struct kiocb *iocb, ssize_t size,
				       int error, unsigned int flags)
{
	if (error) {
		zonefs_io_error(file_inode(iocb->ki_filp), false);
		return error;
	}

	return 0;
}

static const struct iomap_dio_ops zonefs_read_dio_ops = {
	.end_io			= zonefs_file_read_dio_end_io,
};

static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	struct super_block *sb = inode->i_sb;
	loff_t isize;
	ssize_t ret;

	/* Offline zones cannot be read */
	if (unlikely(IS_IMMUTABLE(inode) && !(inode->i_mode & 0777)))
		return -EPERM;

	if (iocb->ki_pos >= z->z_capacity)
		return 0;

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

	/* Limit read operations to written data */
	mutex_lock(&zi->i_truncate_mutex);
	isize = i_size_read(inode);
	if (iocb->ki_pos >= isize) {
		mutex_unlock(&zi->i_truncate_mutex);
		ret = 0;
		goto inode_unlock;
	}
	iov_iter_truncate(to, isize - iocb->ki_pos);
	mutex_unlock(&zi->i_truncate_mutex);

	if (iocb->ki_flags & IOCB_DIRECT) {
		size_t count = iov_iter_count(to);

		if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
			ret = -EINVAL;
			goto inode_unlock;
		}
		file_accessed(iocb->ki_filp);
		ret = iomap_dio_rw(iocb, to, &zonefs_read_iomap_ops,
				   &zonefs_read_dio_ops, 0, NULL, 0);
	} else {
		ret = generic_file_read_iter(iocb, to);
		if (ret == -EIO)
			zonefs_io_error(inode, false);
	}

inode_unlock:
	inode_unlock_shared(inode);

	return ret;
}

/*
 * Write open accounting is done only for sequential files.
 */
static inline bool zonefs_seq_file_need_wro(struct inode *inode,
					    struct file *file)
{
	if (zonefs_inode_is_cnv(inode))
		return false;

	if (!(file->f_mode & FMODE_WRITE))
		return false;

	return true;
}

static int zonefs_seq_file_write_open(struct inode *inode)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	int ret = 0;

	mutex_lock(&zi->i_truncate_mutex);

	if (!zi->i_wr_refcnt) {
		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
		unsigned int wro = atomic_inc_return(&sbi->s_wro_seq_files);

		if (sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {

			if (sbi->s_max_wro_seq_files
			    && wro > sbi->s_max_wro_seq_files) {
				atomic_dec(&sbi->s_wro_seq_files);
				ret = -EBUSY;
				goto unlock;
			}

			if (i_size_read(inode) < z->z_capacity) {
				ret = zonefs_inode_zone_mgmt(inode,
							     REQ_OP_ZONE_OPEN);
				if (ret) {
					atomic_dec(&sbi->s_wro_seq_files);
					goto unlock;
				}
				z->z_flags |= ZONEFS_ZONE_OPEN;
				zonefs_inode_account_active(inode);
			}
		}
	}

	zi->i_wr_refcnt++;

unlock:
	mutex_unlock(&zi->i_truncate_mutex);

	return ret;
}

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

	ret = generic_file_open(inode, file);
	if (ret)
		return ret;

	if (zonefs_seq_file_need_wro(inode, file))
		return zonefs_seq_file_write_open(inode);

	return 0;
}

static void zonefs_seq_file_write_close(struct inode *inode)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	int ret = 0;

	mutex_lock(&zi->i_truncate_mutex);

	zi->i_wr_refcnt--;
	if (zi->i_wr_refcnt)
		goto unlock;

	/*
	 * The file zone may not be open anymore (e.g. the file was truncated to
	 * its maximum size or it was fully written). For this case, we only
	 * need to decrement the write open count.
	 */
	if (z->z_flags & ZONEFS_ZONE_OPEN) {
		ret = zonefs_inode_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
		if (ret) {
			__zonefs_io_error(inode, false);
			/*
			 * Leaving zones explicitly open may lead to a state
			 * where most zones cannot be written (zone resources
			 * exhausted). So take preventive action by remounting
			 * read-only.
			 */
			if (z->z_flags & ZONEFS_ZONE_OPEN &&
			    !(sb->s_flags & SB_RDONLY)) {
				zonefs_warn(sb,
					"closing zone at %llu failed %d\n",
					z->z_sector, ret);
				zonefs_warn(sb,
					"remounting filesystem read-only\n");
				sb->s_flags |= SB_RDONLY;
			}
			goto unlock;
		}

		z->z_flags &= ~ZONEFS_ZONE_OPEN;
		zonefs_inode_account_active(inode);
	}

	atomic_dec(&sbi->s_wro_seq_files);

unlock:
	mutex_unlock(&zi->i_truncate_mutex);
}

static int zonefs_file_release(struct inode *inode, struct file *file)
{
	/*
	 * If we explicitly open a zone we must close it again as well, but the
	 * zone management operation can fail (either due to an IO error or as
	 * the zone has gone offline or read-only). Make sure we don't fail the
	 * close(2) for user-space.
	 */
	if (zonefs_seq_file_need_wro(inode, file))
		zonefs_seq_file_write_close(inode);

	return 0;
}

const struct file_operations zonefs_file_operations = {
	.open		= zonefs_file_open,
	.release	= zonefs_file_release,
	.fsync		= zonefs_file_fsync,
	.mmap		= zonefs_file_mmap,
	.llseek		= zonefs_file_llseek,
	.read_iter	= zonefs_file_read_iter,
	.write_iter	= zonefs_file_write_iter,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.iopoll		= iocb_bio_iopoll,
};