summaryrefslogtreecommitdiff
path: root/fs/btrfs/ordered-data.c
blob: 985a215584370efd95388dd41e8e150999d184bb (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include <linux/sched/mm.h>
#include "misc.h"
#include "ctree.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "extent_io.h"
#include "disk-io.h"
#include "compression.h"
#include "delalloc-space.h"
#include "qgroup.h"

static struct kmem_cache *btrfs_ordered_extent_cache;

static u64 entry_end(struct btrfs_ordered_extent *entry)
{
	if (entry->file_offset + entry->num_bytes < entry->file_offset)
		return (u64)-1;
	return entry->file_offset + entry->num_bytes;
}

/* returns NULL if the insertion worked, or it returns the node it did find
 * in the tree
 */
static struct rb_node *tree_insert(struct rb_root *root, u64 file_offset,
				   struct rb_node *node)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct btrfs_ordered_extent *entry;

	while (*p) {
		parent = *p;
		entry = rb_entry(parent, struct btrfs_ordered_extent, rb_node);

		if (file_offset < entry->file_offset)
			p = &(*p)->rb_left;
		else if (file_offset >= entry_end(entry))
			p = &(*p)->rb_right;
		else
			return parent;
	}

	rb_link_node(node, parent, p);
	rb_insert_color(node, root);
	return NULL;
}

/*
 * look for a given offset in the tree, and if it can't be found return the
 * first lesser offset
 */
static struct rb_node *__tree_search(struct rb_root *root, u64 file_offset,
				     struct rb_node **prev_ret)
{
	struct rb_node *n = root->rb_node;
	struct rb_node *prev = NULL;
	struct rb_node *test;
	struct btrfs_ordered_extent *entry;
	struct btrfs_ordered_extent *prev_entry = NULL;

	while (n) {
		entry = rb_entry(n, struct btrfs_ordered_extent, rb_node);
		prev = n;
		prev_entry = entry;

		if (file_offset < entry->file_offset)
			n = n->rb_left;
		else if (file_offset >= entry_end(entry))
			n = n->rb_right;
		else
			return n;
	}
	if (!prev_ret)
		return NULL;

	while (prev && file_offset >= entry_end(prev_entry)) {
		test = rb_next(prev);
		if (!test)
			break;
		prev_entry = rb_entry(test, struct btrfs_ordered_extent,
				      rb_node);
		if (file_offset < entry_end(prev_entry))
			break;

		prev = test;
	}
	if (prev)
		prev_entry = rb_entry(prev, struct btrfs_ordered_extent,
				      rb_node);
	while (prev && file_offset < entry_end(prev_entry)) {
		test = rb_prev(prev);
		if (!test)
			break;
		prev_entry = rb_entry(test, struct btrfs_ordered_extent,
				      rb_node);
		prev = test;
	}
	*prev_ret = prev;
	return NULL;
}

/*
 * helper to check if a given offset is inside a given entry
 */
static int offset_in_entry(struct btrfs_ordered_extent *entry, u64 file_offset)
{
	if (file_offset < entry->file_offset ||
	    entry->file_offset + entry->num_bytes <= file_offset)
		return 0;
	return 1;
}

static int range_overlaps(struct btrfs_ordered_extent *entry, u64 file_offset,
			  u64 len)
{
	if (file_offset + len <= entry->file_offset ||
	    entry->file_offset + entry->num_bytes <= file_offset)
		return 0;
	return 1;
}

/*
 * look find the first ordered struct that has this offset, otherwise
 * the first one less than this offset
 */
static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
					  u64 file_offset)
{
	struct rb_root *root = &tree->tree;
	struct rb_node *prev = NULL;
	struct rb_node *ret;
	struct btrfs_ordered_extent *entry;

	if (tree->last) {
		entry = rb_entry(tree->last, struct btrfs_ordered_extent,
				 rb_node);
		if (offset_in_entry(entry, file_offset))
			return tree->last;
	}
	ret = __tree_search(root, file_offset, &prev);
	if (!ret)
		ret = prev;
	if (ret)
		tree->last = ret;
	return ret;
}

/*
 * Allocate and add a new ordered_extent into the per-inode tree.
 *
 * The tree is given a single reference on the ordered extent that was
 * inserted.
 */
static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,
				      u64 disk_bytenr, u64 num_bytes,
				      u64 disk_num_bytes, int type, int dio,
				      int compress_type)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;
	struct rb_node *node;
	struct btrfs_ordered_extent *entry;
	int ret;

	if (type == BTRFS_ORDERED_NOCOW || type == BTRFS_ORDERED_PREALLOC) {
		/* For nocow write, we can release the qgroup rsv right now */
		ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes);
		if (ret < 0)
			return ret;
		ret = 0;
	} else {
		/*
		 * The ordered extent has reserved qgroup space, release now
		 * and pass the reserved number for qgroup_record to free.
		 */
		ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes);
		if (ret < 0)
			return ret;
	}
	entry = kmem_cache_zalloc(btrfs_ordered_extent_cache, GFP_NOFS);
	if (!entry)
		return -ENOMEM;

	entry->file_offset = file_offset;
	entry->disk_bytenr = disk_bytenr;
	entry->num_bytes = num_bytes;
	entry->disk_num_bytes = disk_num_bytes;
	entry->bytes_left = num_bytes;
	entry->inode = igrab(&inode->vfs_inode);
	entry->compress_type = compress_type;
	entry->truncated_len = (u64)-1;
	entry->qgroup_rsv = ret;
	entry->physical = (u64)-1;
	entry->disk = NULL;
	entry->partno = (u8)-1;

	ASSERT(type == BTRFS_ORDERED_REGULAR ||
	       type == BTRFS_ORDERED_NOCOW ||
	       type == BTRFS_ORDERED_PREALLOC ||
	       type == BTRFS_ORDERED_COMPRESSED);
	set_bit(type, &entry->flags);

	percpu_counter_add_batch(&fs_info->ordered_bytes, num_bytes,
				 fs_info->delalloc_batch);

	if (dio)
		set_bit(BTRFS_ORDERED_DIRECT, &entry->flags);

	/* one ref for the tree */
	refcount_set(&entry->refs, 1);
	init_waitqueue_head(&entry->wait);
	INIT_LIST_HEAD(&entry->list);
	INIT_LIST_HEAD(&entry->log_list);
	INIT_LIST_HEAD(&entry->root_extent_list);
	INIT_LIST_HEAD(&entry->work_list);
	init_completion(&entry->completion);

	trace_btrfs_ordered_extent_add(inode, entry);

	spin_lock_irq(&tree->lock);
	node = tree_insert(&tree->tree, file_offset,
			   &entry->rb_node);
	if (node)
		btrfs_panic(fs_info, -EEXIST,
				"inconsistency in ordered tree at offset %llu",
				file_offset);
	spin_unlock_irq(&tree->lock);

	spin_lock(&root->ordered_extent_lock);
	list_add_tail(&entry->root_extent_list,
		      &root->ordered_extents);
	root->nr_ordered_extents++;
	if (root->nr_ordered_extents == 1) {
		spin_lock(&fs_info->ordered_root_lock);
		BUG_ON(!list_empty(&root->ordered_root));
		list_add_tail(&root->ordered_root, &fs_info->ordered_roots);
		spin_unlock(&fs_info->ordered_root_lock);
	}
	spin_unlock(&root->ordered_extent_lock);

	/*
	 * We don't need the count_max_extents here, we can assume that all of
	 * that work has been done at higher layers, so this is truly the
	 * smallest the extent is going to get.
	 */
	spin_lock(&inode->lock);
	btrfs_mod_outstanding_extents(inode, 1);
	spin_unlock(&inode->lock);

	return 0;
}

int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,
			     u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes,
			     int type)
{
	ASSERT(type == BTRFS_ORDERED_REGULAR ||
	       type == BTRFS_ORDERED_NOCOW ||
	       type == BTRFS_ORDERED_PREALLOC);
	return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,
					  num_bytes, disk_num_bytes, type, 0,
					  BTRFS_COMPRESS_NONE);
}

int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset,
				 u64 disk_bytenr, u64 num_bytes,
				 u64 disk_num_bytes, int type)
{
	ASSERT(type == BTRFS_ORDERED_REGULAR ||
	       type == BTRFS_ORDERED_NOCOW ||
	       type == BTRFS_ORDERED_PREALLOC);
	return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,
					  num_bytes, disk_num_bytes, type, 1,
					  BTRFS_COMPRESS_NONE);
}

int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset,
				      u64 disk_bytenr, u64 num_bytes,
				      u64 disk_num_bytes, int compress_type)
{
	ASSERT(compress_type != BTRFS_COMPRESS_NONE);
	return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,
					  num_bytes, disk_num_bytes,
					  BTRFS_ORDERED_COMPRESSED, 0,
					  compress_type);
}

/*
 * Add a struct btrfs_ordered_sum into the list of checksums to be inserted
 * when an ordered extent is finished.  If the list covers more than one
 * ordered extent, it is split across multiples.
 */
void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
			   struct btrfs_ordered_sum *sum)
{
	struct btrfs_ordered_inode_tree *tree;

	tree = &BTRFS_I(entry->inode)->ordered_tree;
	spin_lock_irq(&tree->lock);
	list_add_tail(&sum->list, &entry->list);
	spin_unlock_irq(&tree->lock);
}

/*
 * Finish IO for one ordered extent across a given range.  The range can
 * contain several ordered extents.
 *
 * @found_ret:	 Return the finished ordered extent
 * @file_offset: File offset for the finished IO
 * 		 Will also be updated to one byte past the range that is
 * 		 recordered as finished. This allows caller to walk forward.
 * @io_size:	 Length of the finish IO range
 * @uptodate:	 If the IO finished without problem
 *
 * Return true if any ordered extent is finished in the range, and update
 * @found_ret and @file_offset.
 * Return false otherwise.
 *
 * NOTE: Although The range can cross multiple ordered extents, only one
 * ordered extent will be updated during one call. The caller is responsible to
 * iterate all ordered extents in the range.
 */
bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,
				   struct btrfs_ordered_extent **finished_ret,
				   u64 *file_offset, u64 io_size, int uptodate)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;
	struct rb_node *node;
	struct btrfs_ordered_extent *entry = NULL;
	bool finished = false;
	unsigned long flags;
	u64 dec_end;
	u64 dec_start;
	u64 to_dec;

	spin_lock_irqsave(&tree->lock, flags);
	node = tree_search(tree, *file_offset);
	if (!node)
		goto out;

	entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
	if (!offset_in_entry(entry, *file_offset))
		goto out;

	dec_start = max(*file_offset, entry->file_offset);
	dec_end = min(*file_offset + io_size,
		      entry->file_offset + entry->num_bytes);
	*file_offset = dec_end;
	if (dec_start > dec_end) {
		btrfs_crit(fs_info, "bad ordering dec_start %llu end %llu",
			   dec_start, dec_end);
	}
	to_dec = dec_end - dec_start;
	if (to_dec > entry->bytes_left) {
		btrfs_crit(fs_info,
			   "bad ordered accounting left %llu size %llu",
			   entry->bytes_left, to_dec);
	}
	entry->bytes_left -= to_dec;
	if (!uptodate)
		set_bit(BTRFS_ORDERED_IOERR, &entry->flags);

	if (entry->bytes_left == 0) {
		/*
		 * Ensure only one caller can set the flag and finished_ret
		 * accordingly
		 */
		finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
		/* test_and_set_bit implies a barrier */
		cond_wake_up_nomb(&entry->wait);
	}
out:
	if (finished && finished_ret && entry) {
		*finished_ret = entry;
		refcount_inc(&entry->refs);
	}
	spin_unlock_irqrestore(&tree->lock, flags);
	return finished;
}

/*
 * Finish IO for one ordered extent across a given range.  The range can only
 * contain one ordered extent.
 *
 * @cached:	 The cached ordered extent. If not NULL, we can skip the tree
 *               search and use the ordered extent directly.
 * 		 Will be also used to store the finished ordered extent.
 * @file_offset: File offset for the finished IO
 * @io_size:	 Length of the finish IO range
 * @uptodate:	 If the IO finishes without problem
 *
 * Return true if the ordered extent is finished in the range, and update
 * @cached.
 * Return false otherwise.
 *
 * NOTE: The range can NOT cross multiple ordered extents.
 * Thus caller should ensure the range doesn't cross ordered extents.
 */
bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode,
				    struct btrfs_ordered_extent **cached,
				    u64 file_offset, u64 io_size, int uptodate)
{
	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;
	struct rb_node *node;
	struct btrfs_ordered_extent *entry = NULL;
	unsigned long flags;
	bool finished = false;

	spin_lock_irqsave(&tree->lock, flags);
	if (cached && *cached) {
		entry = *cached;
		goto have_entry;
	}

	node = tree_search(tree, file_offset);
	if (!node)
		goto out;

	entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
have_entry:
	if (!offset_in_entry(entry, file_offset))
		goto out;

	if (io_size > entry->bytes_left)
		btrfs_crit(inode->root->fs_info,
			   "bad ordered accounting left %llu size %llu",
		       entry->bytes_left, io_size);

	entry->bytes_left -= io_size;
	if (!uptodate)
		set_bit(BTRFS_ORDERED_IOERR, &entry->flags);

	if (entry->bytes_left == 0) {
		/*
		 * Ensure only one caller can set the flag and finished_ret
		 * accordingly
		 */
		finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
		/* test_and_set_bit implies a barrier */
		cond_wake_up_nomb(&entry->wait);
	}
out:
	if (finished && cached && entry) {
		*cached = entry;
		refcount_inc(&entry->refs);
	}
	spin_unlock_irqrestore(&tree->lock, flags);
	return finished;
}

/*
 * used to drop a reference on an ordered extent.  This will free
 * the extent if the last reference is dropped
 */
void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
{
	struct list_head *cur;
	struct btrfs_ordered_sum *sum;

	trace_btrfs_ordered_extent_put(BTRFS_I(entry->inode), entry);

	if (refcount_dec_and_test(&entry->refs)) {
		ASSERT(list_empty(&entry->root_extent_list));
		ASSERT(list_empty(&entry->log_list));
		ASSERT(RB_EMPTY_NODE(&entry->rb_node));
		if (entry->inode)
			btrfs_add_delayed_iput(entry->inode);
		while (!list_empty(&entry->list)) {
			cur = entry->list.next;
			sum = list_entry(cur, struct btrfs_ordered_sum, list);
			list_del(&sum->list);
			kvfree(sum);
		}
		kmem_cache_free(btrfs_ordered_extent_cache, entry);
	}
}

/*
 * remove an ordered extent from the tree.  No references are dropped
 * and waiters are woken up.
 */
void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
				 struct btrfs_ordered_extent *entry)
{
	struct btrfs_ordered_inode_tree *tree;
	struct btrfs_root *root = btrfs_inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct rb_node *node;
	bool pending;

	/* This is paired with btrfs_add_ordered_extent. */
	spin_lock(&btrfs_inode->lock);
	btrfs_mod_outstanding_extents(btrfs_inode, -1);
	spin_unlock(&btrfs_inode->lock);
	if (root != fs_info->tree_root)
		btrfs_delalloc_release_metadata(btrfs_inode, entry->num_bytes,
						false);

	percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes,
				 fs_info->delalloc_batch);

	tree = &btrfs_inode->ordered_tree;
	spin_lock_irq(&tree->lock);
	node = &entry->rb_node;
	rb_erase(node, &tree->tree);
	RB_CLEAR_NODE(node);
	if (tree->last == node)
		tree->last = NULL;
	set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
	pending = test_and_clear_bit(BTRFS_ORDERED_PENDING, &entry->flags);
	spin_unlock_irq(&tree->lock);

	/*
	 * The current running transaction is waiting on us, we need to let it
	 * know that we're complete and wake it up.
	 */
	if (pending) {
		struct btrfs_transaction *trans;

		/*
		 * The checks for trans are just a formality, it should be set,
		 * but if it isn't we don't want to deref/assert under the spin
		 * lock, so be nice and check if trans is set, but ASSERT() so
		 * if it isn't set a developer will notice.
		 */
		spin_lock(&fs_info->trans_lock);
		trans = fs_info->running_transaction;
		if (trans)
			refcount_inc(&trans->use_count);
		spin_unlock(&fs_info->trans_lock);

		ASSERT(trans);
		if (trans) {
			if (atomic_dec_and_test(&trans->pending_ordered))
				wake_up(&trans->pending_wait);
			btrfs_put_transaction(trans);
		}
	}

	spin_lock(&root->ordered_extent_lock);
	list_del_init(&entry->root_extent_list);
	root->nr_ordered_extents--;

	trace_btrfs_ordered_extent_remove(btrfs_inode, entry);

	if (!root->nr_ordered_extents) {
		spin_lock(&fs_info->ordered_root_lock);
		BUG_ON(list_empty(&root->ordered_root));
		list_del_init(&root->ordered_root);
		spin_unlock(&fs_info->ordered_root_lock);
	}
	spin_unlock(&root->ordered_extent_lock);
	wake_up(&entry->wait);
}

static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
{
	struct btrfs_ordered_extent *ordered;

	ordered = container_of(work, struct btrfs_ordered_extent, flush_work);
	btrfs_start_ordered_extent(ordered, 1);
	complete(&ordered->completion);
}

/*
 * wait for all the ordered extents in a root.  This is done when balancing
 * space between drives.
 */
u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
			       const u64 range_start, const u64 range_len)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	LIST_HEAD(splice);
	LIST_HEAD(skipped);
	LIST_HEAD(works);
	struct btrfs_ordered_extent *ordered, *next;
	u64 count = 0;
	const u64 range_end = range_start + range_len;

	mutex_lock(&root->ordered_extent_mutex);
	spin_lock(&root->ordered_extent_lock);
	list_splice_init(&root->ordered_extents, &splice);
	while (!list_empty(&splice) && nr) {
		ordered = list_first_entry(&splice, struct btrfs_ordered_extent,
					   root_extent_list);

		if (range_end <= ordered->disk_bytenr ||
		    ordered->disk_bytenr + ordered->disk_num_bytes <= range_start) {
			list_move_tail(&ordered->root_extent_list, &skipped);
			cond_resched_lock(&root->ordered_extent_lock);
			continue;
		}

		list_move_tail(&ordered->root_extent_list,
			       &root->ordered_extents);
		refcount_inc(&ordered->refs);
		spin_unlock(&root->ordered_extent_lock);

		btrfs_init_work(&ordered->flush_work,
				btrfs_run_ordered_extent_work, NULL, NULL);
		list_add_tail(&ordered->work_list, &works);
		btrfs_queue_work(fs_info->flush_workers, &ordered->flush_work);

		cond_resched();
		spin_lock(&root->ordered_extent_lock);
		if (nr != U64_MAX)
			nr--;
		count++;
	}
	list_splice_tail(&skipped, &root->ordered_extents);
	list_splice_tail(&splice, &root->ordered_extents);
	spin_unlock(&root->ordered_extent_lock);

	list_for_each_entry_safe(ordered, next, &works, work_list) {
		list_del_init(&ordered->work_list);
		wait_for_completion(&ordered->completion);
		btrfs_put_ordered_extent(ordered);
		cond_resched();
	}
	mutex_unlock(&root->ordered_extent_mutex);

	return count;
}

void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
			     const u64 range_start, const u64 range_len)
{
	struct btrfs_root *root;
	struct list_head splice;
	u64 done;

	INIT_LIST_HEAD(&splice);

	mutex_lock(&fs_info->ordered_operations_mutex);
	spin_lock(&fs_info->ordered_root_lock);
	list_splice_init(&fs_info->ordered_roots, &splice);
	while (!list_empty(&splice) && nr) {
		root = list_first_entry(&splice, struct btrfs_root,
					ordered_root);
		root = btrfs_grab_root(root);
		BUG_ON(!root);
		list_move_tail(&root->ordered_root,
			       &fs_info->ordered_roots);
		spin_unlock(&fs_info->ordered_root_lock);

		done = btrfs_wait_ordered_extents(root, nr,
						  range_start, range_len);
		btrfs_put_root(root);

		spin_lock(&fs_info->ordered_root_lock);
		if (nr != U64_MAX) {
			nr -= done;
		}
	}
	list_splice_tail(&splice, &fs_info->ordered_roots);
	spin_unlock(&fs_info->ordered_root_lock);
	mutex_unlock(&fs_info->ordered_operations_mutex);
}

/*
 * Used to start IO or wait for a given ordered extent to finish.
 *
 * If wait is one, this effectively waits on page writeback for all the pages
 * in the extent, and it waits on the io completion code to insert
 * metadata into the btree corresponding to the extent
 */
void btrfs_start_ordered_extent(struct btrfs_ordered_extent *entry, int wait)
{
	u64 start = entry->file_offset;
	u64 end = start + entry->num_bytes - 1;
	struct btrfs_inode *inode = BTRFS_I(entry->inode);

	trace_btrfs_ordered_extent_start(inode, entry);

	/*
	 * pages in the range can be dirty, clean or writeback.  We
	 * start IO on any dirty ones so the wait doesn't stall waiting
	 * for the flusher thread to find them
	 */
	if (!test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
		filemap_fdatawrite_range(inode->vfs_inode.i_mapping, start, end);
	if (wait) {
		wait_event(entry->wait, test_bit(BTRFS_ORDERED_COMPLETE,
						 &entry->flags));
	}
}

/*
 * Used to wait on ordered extents across a large range of bytes.
 */
int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
{
	int ret = 0;
	int ret_wb = 0;
	u64 end;
	u64 orig_end;
	struct btrfs_ordered_extent *ordered;

	if (start + len < start) {
		orig_end = INT_LIMIT(loff_t);
	} else {
		orig_end = start + len - 1;
		if (orig_end > INT_LIMIT(loff_t))
			orig_end = INT_LIMIT(loff_t);
	}

	/* start IO across the range first to instantiate any delalloc
	 * extents
	 */
	ret = btrfs_fdatawrite_range(inode, start, orig_end);
	if (ret)
		return ret;

	/*
	 * If we have a writeback error don't return immediately. Wait first
	 * for any ordered extents that haven't completed yet. This is to make
	 * sure no one can dirty the same page ranges and call writepages()
	 * before the ordered extents complete - to avoid failures (-EEXIST)
	 * when adding the new ordered extents to the ordered tree.
	 */
	ret_wb = filemap_fdatawait_range(inode->i_mapping, start, orig_end);

	end = orig_end;
	while (1) {
		ordered = btrfs_lookup_first_ordered_extent(BTRFS_I(inode), end);
		if (!ordered)
			break;
		if (ordered->file_offset > orig_end) {
			btrfs_put_ordered_extent(ordered);
			break;
		}
		if (ordered->file_offset + ordered->num_bytes <= start) {
			btrfs_put_ordered_extent(ordered);
			break;
		}
		btrfs_start_ordered_extent(ordered, 1);
		end = ordered->file_offset;
		/*
		 * If the ordered extent had an error save the error but don't
		 * exit without waiting first for all other ordered extents in
		 * the range to complete.
		 */
		if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags))
			ret = -EIO;
		btrfs_put_ordered_extent(ordered);
		if (end == 0 || end == start)
			break;
		end--;
	}
	return ret_wb ? ret_wb : ret;
}

/*
 * find an ordered extent corresponding to file_offset.  return NULL if
 * nothing is found, otherwise take a reference on the extent and return it
 */
struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode,
							 u64 file_offset)
{
	struct btrfs_ordered_inode_tree *tree;
	struct rb_node *node;
	struct btrfs_ordered_extent *entry = NULL;
	unsigned long flags;

	tree = &inode->ordered_tree;
	spin_lock_irqsave(&tree->lock, flags);
	node = tree_search(tree, file_offset);
	if (!node)
		goto out;

	entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
	if (!offset_in_entry(entry, file_offset))
		entry = NULL;
	if (entry)
		refcount_inc(&entry->refs);
out:
	spin_unlock_irqrestore(&tree->lock, flags);
	return entry;
}

/* Since the DIO code tries to lock a wide area we need to look for any ordered
 * extents that exist in the range, rather than just the start of the range.
 */
struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
		struct btrfs_inode *inode, u64 file_offset, u64 len)
{
	struct btrfs_ordered_inode_tree *tree;
	struct rb_node *node;
	struct btrfs_ordered_extent *entry = NULL;

	tree = &inode->ordered_tree;
	spin_lock_irq(&tree->lock);
	node = tree_search(tree, file_offset);
	if (!node) {
		node = tree_search(tree, file_offset + len);
		if (!node)
			goto out;
	}

	while (1) {
		entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
		if (range_overlaps(entry, file_offset, len))
			break;

		if (entry->file_offset >= file_offset + len) {
			entry = NULL;
			break;
		}
		entry = NULL;
		node = rb_next(node);
		if (!node)
			break;
	}
out:
	if (entry)
		refcount_inc(&entry->refs);
	spin_unlock_irq(&tree->lock);
	return entry;
}

/*
 * Adds all ordered extents to the given list. The list ends up sorted by the
 * file_offset of the ordered extents.
 */
void btrfs_get_ordered_extents_for_logging(struct btrfs_inode *inode,
					   struct list_head *list)
{
	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;
	struct rb_node *n;

	ASSERT(inode_is_locked(&inode->vfs_inode));

	spin_lock_irq(&tree->lock);
	for (n = rb_first(&tree->tree); n; n = rb_next(n)) {
		struct btrfs_ordered_extent *ordered;

		ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);

		if (test_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
			continue;

		ASSERT(list_empty(&ordered->log_list));
		list_add_tail(&ordered->log_list, list);
		refcount_inc(&ordered->refs);
	}
	spin_unlock_irq(&tree->lock);
}

/*
 * lookup and return any extent before 'file_offset'.  NULL is returned
 * if none is found
 */
struct btrfs_ordered_extent *
btrfs_lookup_first_ordered_extent(struct btrfs_inode *inode, u64 file_offset)
{
	struct btrfs_ordered_inode_tree *tree;
	struct rb_node *node;
	struct btrfs_ordered_extent *entry = NULL;

	tree = &inode->ordered_tree;
	spin_lock_irq(&tree->lock);
	node = tree_search(tree, file_offset);
	if (!node)
		goto out;

	entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
	refcount_inc(&entry->refs);
out:
	spin_unlock_irq(&tree->lock);
	return entry;
}

/*
 * btrfs_flush_ordered_range - Lock the passed range and ensures all pending
 * ordered extents in it are run to completion.
 *
 * @inode:        Inode whose ordered tree is to be searched
 * @start:        Beginning of range to flush
 * @end:          Last byte of range to lock
 * @cached_state: If passed, will return the extent state responsible for the
 * locked range. It's the caller's responsibility to free the cached state.
 *
 * This function always returns with the given range locked, ensuring after it's
 * called no order extent can be pending.
 */
void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
					u64 end,
					struct extent_state **cached_state)
{
	struct btrfs_ordered_extent *ordered;
	struct extent_state *cache = NULL;
	struct extent_state **cachedp = &cache;

	if (cached_state)
		cachedp = cached_state;

	while (1) {
		lock_extent_bits(&inode->io_tree, start, end, cachedp);
		ordered = btrfs_lookup_ordered_range(inode, start,
						     end - start + 1);
		if (!ordered) {
			/*
			 * If no external cached_state has been passed then
			 * decrement the extra ref taken for cachedp since we
			 * aren't exposing it outside of this function
			 */
			if (!cached_state)
				refcount_dec(&cache->refs);
			break;
		}
		unlock_extent_cached(&inode->io_tree, start, end, cachedp);
		btrfs_start_ordered_extent(ordered, 1);
		btrfs_put_ordered_extent(ordered);
	}
}

static int clone_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pos,
				u64 len)
{
	struct inode *inode = ordered->inode;
	u64 file_offset = ordered->file_offset + pos;
	u64 disk_bytenr = ordered->disk_bytenr + pos;
	u64 num_bytes = len;
	u64 disk_num_bytes = len;
	int type;
	unsigned long flags_masked = ordered->flags & ~(1 << BTRFS_ORDERED_DIRECT);
	int compress_type = ordered->compress_type;
	unsigned long weight;
	int ret;

	weight = hweight_long(flags_masked);
	WARN_ON_ONCE(weight > 1);
	if (!weight)
		type = 0;
	else
		type = __ffs(flags_masked);

	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags)) {
		WARN_ON_ONCE(1);
		ret = btrfs_add_ordered_extent_compress(BTRFS_I(inode),
				file_offset, disk_bytenr, num_bytes,
				disk_num_bytes, compress_type);
	} else if (test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
		ret = btrfs_add_ordered_extent_dio(BTRFS_I(inode), file_offset,
				disk_bytenr, num_bytes, disk_num_bytes, type);
	} else {
		ret = btrfs_add_ordered_extent(BTRFS_I(inode), file_offset,
				disk_bytenr, num_bytes, disk_num_bytes, type);
	}

	return ret;
}

int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre,
				u64 post)
{
	struct inode *inode = ordered->inode;
	struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree;
	struct rb_node *node;
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	int ret = 0;

	spin_lock_irq(&tree->lock);
	/* Remove from tree once */
	node = &ordered->rb_node;
	rb_erase(node, &tree->tree);
	RB_CLEAR_NODE(node);
	if (tree->last == node)
		tree->last = NULL;

	ordered->file_offset += pre;
	ordered->disk_bytenr += pre;
	ordered->num_bytes -= (pre + post);
	ordered->disk_num_bytes -= (pre + post);
	ordered->bytes_left -= (pre + post);

	/* Re-insert the node */
	node = tree_insert(&tree->tree, ordered->file_offset, &ordered->rb_node);
	if (node)
		btrfs_panic(fs_info, -EEXIST,
			"zoned: inconsistency in ordered tree at offset %llu",
			    ordered->file_offset);

	spin_unlock_irq(&tree->lock);

	if (pre)
		ret = clone_ordered_extent(ordered, 0, pre);
	if (post)
		ret = clone_ordered_extent(ordered, pre + ordered->disk_num_bytes,
					   post);

	return ret;
}

int __init ordered_data_init(void)
{
	btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent",
				     sizeof(struct btrfs_ordered_extent), 0,
				     SLAB_MEM_SPREAD,
				     NULL);
	if (!btrfs_ordered_extent_cache)
		return -ENOMEM;

	return 0;
}

void __cold ordered_data_exit(void)
{
	kmem_cache_destroy(btrfs_ordered_extent_cache);
}