summaryrefslogtreecommitdiff
path: root/fs/btrfs/file.c
blob: ce0cd29efa9eb4d8e917b312a84da6a2feb5d62d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mpage.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/slab.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "ioctl.h"
#include "print-tree.h"
#include "tree-log.h"
#include "locking.h"
#include "compat.h"


/* simple helper to fault in pages and copy.  This should go away
 * and be replaced with calls into generic code.
 */
static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
					 int write_bytes,
					 struct page **prepared_pages,
					 struct iov_iter *i)
{
	size_t copied;
	int pg = 0;
	int offset = pos & (PAGE_CACHE_SIZE - 1);

	while (write_bytes > 0) {
		size_t count = min_t(size_t,
				     PAGE_CACHE_SIZE - offset, write_bytes);
		struct page *page = prepared_pages[pg];
again:
		if (unlikely(iov_iter_fault_in_readable(i, count)))
			return -EFAULT;

		/* Copy data from userspace to the current page */
		copied = iov_iter_copy_from_user(page, i, offset, count);

		/* Flush processor's dcache for this page */
		flush_dcache_page(page);
		iov_iter_advance(i, copied);
		write_bytes -= copied;

		if (unlikely(copied == 0)) {
			count = min_t(size_t, PAGE_CACHE_SIZE - offset,
				      iov_iter_single_seg_count(i));
			goto again;
		}

		if (unlikely(copied < PAGE_CACHE_SIZE - offset)) {
			offset += copied;
		} else {
			pg++;
			offset = 0;
		}
	}
	return 0;
}

/*
 * unlocks pages after btrfs_file_write is done with them
 */
static noinline void btrfs_drop_pages(struct page **pages, size_t num_pages)
{
	size_t i;
	for (i = 0; i < num_pages; i++) {
		if (!pages[i])
			break;
		/* page checked is some magic around finding pages that
		 * have been modified without going through btrfs_set_page_dirty
		 * clear it here
		 */
		ClearPageChecked(pages[i]);
		unlock_page(pages[i]);
		mark_page_accessed(pages[i]);
		page_cache_release(pages[i]);
	}
}

/*
 * after copy_from_user, pages need to be dirtied and we need to make
 * sure holes are created between the current EOF and the start of
 * any next extents (if required).
 *
 * this also makes the decision about creating an inline extent vs
 * doing real data extents, marking pages dirty and delalloc as required.
 */
static noinline int dirty_and_release_pages(struct btrfs_trans_handle *trans,
				   struct btrfs_root *root,
				   struct file *file,
				   struct page **pages,
				   size_t num_pages,
				   loff_t pos,
				   size_t write_bytes)
{
	int err = 0;
	int i;
	struct inode *inode = fdentry(file)->d_inode;
	u64 num_bytes;
	u64 start_pos;
	u64 end_of_last_block;
	u64 end_pos = pos + write_bytes;
	loff_t isize = i_size_read(inode);

	start_pos = pos & ~((u64)root->sectorsize - 1);
	num_bytes = (write_bytes + pos - start_pos +
		    root->sectorsize - 1) & ~((u64)root->sectorsize - 1);

	end_of_last_block = start_pos + num_bytes - 1;
	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
					NULL);
	BUG_ON(err);

	for (i = 0; i < num_pages; i++) {
		struct page *p = pages[i];
		SetPageUptodate(p);
		ClearPageChecked(p);
		set_page_dirty(p);
	}
	if (end_pos > isize) {
		i_size_write(inode, end_pos);
		/* we've only changed i_size in ram, and we haven't updated
		 * the disk i_size.  There is no need to log the inode
		 * at this time.
		 */
	}
	return 0;
}

/*
 * this drops all the extents in the cache that intersect the range
 * [start, end].  Existing extents are split as required.
 */
int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
			    int skip_pinned)
{
	struct extent_map *em;
	struct extent_map *split = NULL;
	struct extent_map *split2 = NULL;
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	u64 len = end - start + 1;
	int ret;
	int testend = 1;
	unsigned long flags;
	int compressed = 0;

	WARN_ON(end < start);
	if (end == (u64)-1) {
		len = (u64)-1;
		testend = 0;
	}
	while (1) {
		if (!split)
			split = alloc_extent_map(GFP_NOFS);
		if (!split2)
			split2 = alloc_extent_map(GFP_NOFS);

		write_lock(&em_tree->lock);
		em = lookup_extent_mapping(em_tree, start, len);
		if (!em) {
			write_unlock(&em_tree->lock);
			break;
		}
		flags = em->flags;
		if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) {
			if (testend && em->start + em->len >= start + len) {
				free_extent_map(em);
				write_unlock(&em_tree->lock);
				break;
			}
			start = em->start + em->len;
			if (testend)
				len = start + len - (em->start + em->len);
			free_extent_map(em);
			write_unlock(&em_tree->lock);
			continue;
		}
		compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
		clear_bit(EXTENT_FLAG_PINNED, &em->flags);
		remove_extent_mapping(em_tree, em);

		if (em->block_start < EXTENT_MAP_LAST_BYTE &&
		    em->start < start) {
			split->start = em->start;
			split->len = start - em->start;
			split->orig_start = em->orig_start;
			split->block_start = em->block_start;

			if (compressed)
				split->block_len = em->block_len;
			else
				split->block_len = split->len;

			split->bdev = em->bdev;
			split->flags = flags;
			ret = add_extent_mapping(em_tree, split);
			BUG_ON(ret);
			free_extent_map(split);
			split = split2;
			split2 = NULL;
		}
		if (em->block_start < EXTENT_MAP_LAST_BYTE &&
		    testend && em->start + em->len > start + len) {
			u64 diff = start + len - em->start;

			split->start = start + len;
			split->len = em->start + em->len - (start + len);
			split->bdev = em->bdev;
			split->flags = flags;

			if (compressed) {
				split->block_len = em->block_len;
				split->block_start = em->block_start;
				split->orig_start = em->orig_start;
			} else {
				split->block_len = split->len;
				split->block_start = em->block_start + diff;
				split->orig_start = split->start;
			}

			ret = add_extent_mapping(em_tree, split);
			BUG_ON(ret);
			free_extent_map(split);
			split = NULL;
		}
		write_unlock(&em_tree->lock);

		/* once for us */
		free_extent_map(em);
		/* once for the tree*/
		free_extent_map(em);
	}
	if (split)
		free_extent_map(split);
	if (split2)
		free_extent_map(split2);
	return 0;
}

/*
 * this is very complex, but the basic idea is to drop all extents
 * in the range start - end.  hint_block is filled in with a block number
 * that would be a good hint to the block allocator for this file.
 *
 * If an extent intersects the range but is not entirely inside the range
 * it is either truncated or split.  Anything entirely inside the range
 * is deleted from the tree.
 */
int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
		       u64 start, u64 end, u64 *hint_byte, int drop_cache)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_buffer *leaf;
	struct btrfs_file_extent_item *fi;
	struct btrfs_path *path;
	struct btrfs_key key;
	struct btrfs_key new_key;
	u64 search_start = start;
	u64 disk_bytenr = 0;
	u64 num_bytes = 0;
	u64 extent_offset = 0;
	u64 extent_end = 0;
	int del_nr = 0;
	int del_slot = 0;
	int extent_type;
	int recow;
	int ret;

	if (drop_cache)
		btrfs_drop_extent_cache(inode, start, end - 1, 0);

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	while (1) {
		recow = 0;
		ret = btrfs_lookup_file_extent(trans, root, path, inode->i_ino,
					       search_start, -1);
		if (ret < 0)
			break;
		if (ret > 0 && path->slots[0] > 0 && search_start == start) {
			leaf = path->nodes[0];
			btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1);
			if (key.objectid == inode->i_ino &&
			    key.type == BTRFS_EXTENT_DATA_KEY)
				path->slots[0]--;
		}
		ret = 0;
next_slot:
		leaf = path->nodes[0];
		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
			BUG_ON(del_nr > 0);
			ret = btrfs_next_leaf(root, path);
			if (ret < 0)
				break;
			if (ret > 0) {
				ret = 0;
				break;
			}
			leaf = path->nodes[0];
			recow = 1;
		}

		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
		if (key.objectid > inode->i_ino ||
		    key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end)
			break;

		fi = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_file_extent_item);
		extent_type = btrfs_file_extent_type(leaf, fi);

		if (extent_type == BTRFS_FILE_EXTENT_REG ||
		    extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
			disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
			num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
			extent_offset = btrfs_file_extent_offset(leaf, fi);
			extent_end = key.offset +
				btrfs_file_extent_num_bytes(leaf, fi);
		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
			extent_end = key.offset +
				btrfs_file_extent_inline_len(leaf, fi);
		} else {
			WARN_ON(1);
			extent_end = search_start;
		}

		if (extent_end <= search_start) {
			path->slots[0]++;
			goto next_slot;
		}

		search_start = max(key.offset, start);
		if (recow) {
			btrfs_release_path(root, path);
			continue;
		}

		/*
		 *     | - range to drop - |
		 *  | -------- extent -------- |
		 */
		if (start > key.offset && end < extent_end) {
			BUG_ON(del_nr > 0);
			BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);

			memcpy(&new_key, &key, sizeof(new_key));
			new_key.offset = start;
			ret = btrfs_duplicate_item(trans, root, path,
						   &new_key);
			if (ret == -EAGAIN) {
				btrfs_release_path(root, path);
				continue;
			}
			if (ret < 0)
				break;

			leaf = path->nodes[0];
			fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							start - key.offset);

			fi = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_file_extent_item);

			extent_offset += start - key.offset;
			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							extent_end - start);
			btrfs_mark_buffer_dirty(leaf);

			if (disk_bytenr > 0) {
				ret = btrfs_inc_extent_ref(trans, root,
						disk_bytenr, num_bytes, 0,
						root->root_key.objectid,
						new_key.objectid,
						start - extent_offset);
				BUG_ON(ret);
				*hint_byte = disk_bytenr;
			}
			key.offset = start;
		}
		/*
		 *  | ---- range to drop ----- |
		 *      | -------- extent -------- |
		 */
		if (start <= key.offset && end < extent_end) {
			BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);

			memcpy(&new_key, &key, sizeof(new_key));
			new_key.offset = end;
			btrfs_set_item_key_safe(trans, root, path, &new_key);

			extent_offset += end - key.offset;
			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							extent_end - end);
			btrfs_mark_buffer_dirty(leaf);
			if (disk_bytenr > 0) {
				inode_sub_bytes(inode, end - key.offset);
				*hint_byte = disk_bytenr;
			}
			break;
		}

		search_start = extent_end;
		/*
		 *       | ---- range to drop ----- |
		 *  | -------- extent -------- |
		 */
		if (start > key.offset && end >= extent_end) {
			BUG_ON(del_nr > 0);
			BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);

			btrfs_set_file_extent_num_bytes(leaf, fi,
							start - key.offset);
			btrfs_mark_buffer_dirty(leaf);
			if (disk_bytenr > 0) {
				inode_sub_bytes(inode, extent_end - start);
				*hint_byte = disk_bytenr;
			}
			if (end == extent_end)
				break;

			path->slots[0]++;
			goto next_slot;
		}

		/*
		 *  | ---- range to drop ----- |
		 *    | ------ extent ------ |
		 */
		if (start <= key.offset && end >= extent_end) {
			if (del_nr == 0) {
				del_slot = path->slots[0];
				del_nr = 1;
			} else {
				BUG_ON(del_slot + del_nr != path->slots[0]);
				del_nr++;
			}

			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
				inode_sub_bytes(inode,
						extent_end - key.offset);
				extent_end = ALIGN(extent_end,
						   root->sectorsize);
			} else if (disk_bytenr > 0) {
				ret = btrfs_free_extent(trans, root,
						disk_bytenr, num_bytes, 0,
						root->root_key.objectid,
						key.objectid, key.offset -
						extent_offset);
				BUG_ON(ret);
				inode_sub_bytes(inode,
						extent_end - key.offset);
				*hint_byte = disk_bytenr;
			}

			if (end == extent_end)
				break;

			if (path->slots[0] + 1 < btrfs_header_nritems(leaf)) {
				path->slots[0]++;
				goto next_slot;
			}

			ret = btrfs_del_items(trans, root, path, del_slot,
					      del_nr);
			BUG_ON(ret);

			del_nr = 0;
			del_slot = 0;

			btrfs_release_path(root, path);
			continue;
		}

		BUG_ON(1);
	}

	if (del_nr > 0) {
		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
		BUG_ON(ret);
	}

	btrfs_free_path(path);
	return ret;
}

static int extent_mergeable(struct extent_buffer *leaf, int slot,
			    u64 objectid, u64 bytenr, u64 orig_offset,
			    u64 *start, u64 *end)
{
	struct btrfs_file_extent_item *fi;
	struct btrfs_key key;
	u64 extent_end;

	if (slot < 0 || slot >= btrfs_header_nritems(leaf))
		return 0;

	btrfs_item_key_to_cpu(leaf, &key, slot);
	if (key.objectid != objectid || key.type != BTRFS_EXTENT_DATA_KEY)
		return 0;

	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
	if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG ||
	    btrfs_file_extent_disk_bytenr(leaf, fi) != bytenr ||
	    btrfs_file_extent_offset(leaf, fi) != key.offset - orig_offset ||
	    btrfs_file_extent_compression(leaf, fi) ||
	    btrfs_file_extent_encryption(leaf, fi) ||
	    btrfs_file_extent_other_encoding(leaf, fi))
		return 0;

	extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
	if ((*start && *start != key.offset) || (*end && *end != extent_end))
		return 0;

	*start = key.offset;
	*end = extent_end;
	return 1;
}

/*
 * Mark extent in the range start - end as written.
 *
 * This changes extent type from 'pre-allocated' to 'regular'. If only
 * part of extent is marked as written, the extent will be split into
 * two or three.
 */
int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
			      struct inode *inode, u64 start, u64 end)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_buffer *leaf;
	struct btrfs_path *path;
	struct btrfs_file_extent_item *fi;
	struct btrfs_key key;
	struct btrfs_key new_key;
	u64 bytenr;
	u64 num_bytes;
	u64 extent_end;
	u64 orig_offset;
	u64 other_start;
	u64 other_end;
	u64 split;
	int del_nr = 0;
	int del_slot = 0;
	int recow;
	int ret;

	btrfs_drop_extent_cache(inode, start, end - 1, 0);

	path = btrfs_alloc_path();
	BUG_ON(!path);
again:
	recow = 0;
	split = start;
	key.objectid = inode->i_ino;
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = split;

	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
	if (ret > 0 && path->slots[0] > 0)
		path->slots[0]--;

	leaf = path->nodes[0];
	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
	BUG_ON(key.objectid != inode->i_ino ||
	       key.type != BTRFS_EXTENT_DATA_KEY);
	fi = btrfs_item_ptr(leaf, path->slots[0],
			    struct btrfs_file_extent_item);
	BUG_ON(btrfs_file_extent_type(leaf, fi) !=
	       BTRFS_FILE_EXTENT_PREALLOC);
	extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
	BUG_ON(key.offset > start || extent_end < end);

	bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
	num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
	orig_offset = key.offset - btrfs_file_extent_offset(leaf, fi);
	memcpy(&new_key, &key, sizeof(new_key));

	if (start == key.offset && end < extent_end) {
		other_start = 0;
		other_end = start;
		if (extent_mergeable(leaf, path->slots[0] - 1,
				     inode->i_ino, bytenr, orig_offset,
				     &other_start, &other_end)) {
			new_key.offset = end;
			btrfs_set_item_key_safe(trans, root, path, &new_key);
			fi = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							extent_end - end);
			btrfs_set_file_extent_offset(leaf, fi,
						     end - orig_offset);
			fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							end - other_start);
			btrfs_mark_buffer_dirty(leaf);
			goto out;
		}
	}

	if (start > key.offset && end == extent_end) {
		other_start = end;
		other_end = 0;
		if (extent_mergeable(leaf, path->slots[0] + 1,
				     inode->i_ino, bytenr, orig_offset,
				     &other_start, &other_end)) {
			fi = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							start - key.offset);
			path->slots[0]++;
			new_key.offset = start;
			btrfs_set_item_key_safe(trans, root, path, &new_key);

			fi = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							other_end - start);
			btrfs_set_file_extent_offset(leaf, fi,
						     start - orig_offset);
			btrfs_mark_buffer_dirty(leaf);
			goto out;
		}
	}

	while (start > key.offset || end < extent_end) {
		if (key.offset == start)
			split = end;

		new_key.offset = split;
		ret = btrfs_duplicate_item(trans, root, path, &new_key);
		if (ret == -EAGAIN) {
			btrfs_release_path(root, path);
			goto again;
		}
		BUG_ON(ret < 0);

		leaf = path->nodes[0];
		fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
				    struct btrfs_file_extent_item);
		btrfs_set_file_extent_num_bytes(leaf, fi,
						split - key.offset);

		fi = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_file_extent_item);

		btrfs_set_file_extent_offset(leaf, fi, split - orig_offset);
		btrfs_set_file_extent_num_bytes(leaf, fi,
						extent_end - split);
		btrfs_mark_buffer_dirty(leaf);

		ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
					   root->root_key.objectid,
					   inode->i_ino, orig_offset);
		BUG_ON(ret);

		if (split == start) {
			key.offset = start;
		} else {
			BUG_ON(start != key.offset);
			path->slots[0]--;
			extent_end = end;
		}
		recow = 1;
	}

	other_start = end;
	other_end = 0;
	if (extent_mergeable(leaf, path->slots[0] + 1,
			     inode->i_ino, bytenr, orig_offset,
			     &other_start, &other_end)) {
		if (recow) {
			btrfs_release_path(root, path);
			goto again;
		}
		extent_end = other_end;
		del_slot = path->slots[0] + 1;
		del_nr++;
		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
					0, root->root_key.objectid,
					inode->i_ino, orig_offset);
		BUG_ON(ret);
	}
	other_start = 0;
	other_end = start;
	if (extent_mergeable(leaf, path->slots[0] - 1,
			     inode->i_ino, bytenr, orig_offset,
			     &other_start, &other_end)) {
		if (recow) {
			btrfs_release_path(root, path);
			goto again;
		}
		key.offset = other_start;
		del_slot = path->slots[0];
		del_nr++;
		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
					0, root->root_key.objectid,
					inode->i_ino, orig_offset);
		BUG_ON(ret);
	}
	if (del_nr == 0) {
		fi = btrfs_item_ptr(leaf, path->slots[0],
			   struct btrfs_file_extent_item);
		btrfs_set_file_extent_type(leaf, fi,
					   BTRFS_FILE_EXTENT_REG);
		btrfs_mark_buffer_dirty(leaf);
	} else {
		fi = btrfs_item_ptr(leaf, del_slot - 1,
			   struct btrfs_file_extent_item);
		btrfs_set_file_extent_type(leaf, fi,
					   BTRFS_FILE_EXTENT_REG);
		btrfs_set_file_extent_num_bytes(leaf, fi,
						extent_end - key.offset);
		btrfs_mark_buffer_dirty(leaf);

		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
		BUG_ON(ret);
	}
out:
	btrfs_free_path(path);
	return 0;
}

/*
 * this gets pages into the page cache and locks them down, it also properly
 * waits for data=ordered extents to finish before allowing the pages to be
 * modified.
 */
static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
			 struct page **pages, size_t num_pages,
			 loff_t pos, unsigned long first_index,
			 unsigned long last_index, size_t write_bytes)
{
	struct extent_state *cached_state = NULL;
	int i;
	unsigned long index = pos >> PAGE_CACHE_SHIFT;
	struct inode *inode = fdentry(file)->d_inode;
	int err = 0;
	u64 start_pos;
	u64 last_pos;

	start_pos = pos & ~((u64)root->sectorsize - 1);
	last_pos = ((u64)index + num_pages) << PAGE_CACHE_SHIFT;

	if (start_pos > inode->i_size) {
		err = btrfs_cont_expand(inode, start_pos);
		if (err)
			return err;
	}

	memset(pages, 0, num_pages * sizeof(struct page *));
again:
	for (i = 0; i < num_pages; i++) {
		pages[i] = grab_cache_page(inode->i_mapping, index + i);
		if (!pages[i]) {
			err = -ENOMEM;
			BUG_ON(1);
		}
		wait_on_page_writeback(pages[i]);
	}
	if (start_pos < inode->i_size) {
		struct btrfs_ordered_extent *ordered;
		lock_extent_bits(&BTRFS_I(inode)->io_tree,
				 start_pos, last_pos - 1, 0, &cached_state,
				 GFP_NOFS);
		ordered = btrfs_lookup_first_ordered_extent(inode,
							    last_pos - 1);
		if (ordered &&
		    ordered->file_offset + ordered->len > start_pos &&
		    ordered->file_offset < last_pos) {
			btrfs_put_ordered_extent(ordered);
			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
					     start_pos, last_pos - 1,
					     &cached_state, GFP_NOFS);
			for (i = 0; i < num_pages; i++) {
				unlock_page(pages[i]);
				page_cache_release(pages[i]);
			}
			btrfs_wait_ordered_range(inode, start_pos,
						 last_pos - start_pos);
			goto again;
		}
		if (ordered)
			btrfs_put_ordered_extent(ordered);

		clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos,
				  last_pos - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
				  EXTENT_DO_ACCOUNTING, 0, 0, &cached_state,
				  GFP_NOFS);
		unlock_extent_cached(&BTRFS_I(inode)->io_tree,
				     start_pos, last_pos - 1, &cached_state,
				     GFP_NOFS);
	}
	for (i = 0; i < num_pages; i++) {
		clear_page_dirty_for_io(pages[i]);
		set_page_extent_mapped(pages[i]);
		WARN_ON(!PageLocked(pages[i]));
	}
	return 0;
}

static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
				    const struct iovec *iov,
				    unsigned long nr_segs, loff_t pos)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = fdentry(file)->d_inode;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct page *pinned[2];
	struct page **pages = NULL;
	struct iov_iter i;
	loff_t *ppos = &iocb->ki_pos;
	loff_t start_pos;
	ssize_t num_written = 0;
	ssize_t err = 0;
	size_t count;
	size_t ocount;
	int ret = 0;
	int nrptrs;
	unsigned long first_index;
	unsigned long last_index;
	int will_write;
	int buffered = 0;

	will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
		      (file->f_flags & O_DIRECT));

	pinned[0] = NULL;
	pinned[1] = NULL;

	start_pos = pos;

	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);

	mutex_lock(&inode->i_mutex);

	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
	if (err)
		goto out;
	count = ocount;

	current->backing_dev_info = inode->i_mapping->backing_dev_info;
	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
	if (err)
		goto out;

	if (count == 0)
		goto out;

	err = file_remove_suid(file);
	if (err)
		goto out;

	file_update_time(file);
	BTRFS_I(inode)->sequence++;

	if (unlikely(file->f_flags & O_DIRECT)) {
		num_written = generic_file_direct_write(iocb, iov, &nr_segs,
							pos, ppos, count,
							ocount);
		/*
		 * the generic O_DIRECT will update in-memory i_size after the
		 * DIOs are done.  But our endio handlers that update the on
		 * disk i_size never update past the in memory i_size.  So we
		 * need one more update here to catch any additions to the
		 * file
		 */
		if (inode->i_size != BTRFS_I(inode)->disk_i_size) {
			btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
			mark_inode_dirty(inode);
		}

		if (num_written < 0) {
			ret = num_written;
			num_written = 0;
			goto out;
		} else if (num_written == count) {
			/* pick up pos changes done by the generic code */
			pos = *ppos;
			goto out;
		}
		/*
		 * We are going to do buffered for the rest of the range, so we
		 * need to make sure to invalidate the buffered pages when we're
		 * done.
		 */
		buffered = 1;
		pos += num_written;
	}

	iov_iter_init(&i, iov, nr_segs, count, num_written);
	nrptrs = min((iov_iter_count(&i) + PAGE_CACHE_SIZE - 1) /
		     PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
		     (sizeof(struct page *)));
	pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);

	/* generic_write_checks can change our pos */
	start_pos = pos;

	first_index = pos >> PAGE_CACHE_SHIFT;
	last_index = (pos + iov_iter_count(&i)) >> PAGE_CACHE_SHIFT;

	/*
	 * there are lots of better ways to do this, but this code
	 * makes sure the first and last page in the file range are
	 * up to date and ready for cow
	 */
	if ((pos & (PAGE_CACHE_SIZE - 1))) {
		pinned[0] = grab_cache_page(inode->i_mapping, first_index);
		if (!PageUptodate(pinned[0])) {
			ret = btrfs_readpage(NULL, pinned[0]);
			BUG_ON(ret);
			wait_on_page_locked(pinned[0]);
		} else {
			unlock_page(pinned[0]);
		}
	}
	if ((pos + iov_iter_count(&i)) & (PAGE_CACHE_SIZE - 1)) {
		pinned[1] = grab_cache_page(inode->i_mapping, last_index);
		if (!PageUptodate(pinned[1])) {
			ret = btrfs_readpage(NULL, pinned[1]);
			BUG_ON(ret);
			wait_on_page_locked(pinned[1]);
		} else {
			unlock_page(pinned[1]);
		}
	}

	while (iov_iter_count(&i) > 0) {
		size_t offset = pos & (PAGE_CACHE_SIZE - 1);
		size_t write_bytes = min(iov_iter_count(&i),
					 nrptrs * (size_t)PAGE_CACHE_SIZE -
					 offset);
		size_t num_pages = (write_bytes + PAGE_CACHE_SIZE - 1) >>
					PAGE_CACHE_SHIFT;

		WARN_ON(num_pages > nrptrs);
		memset(pages, 0, sizeof(struct page *) * nrptrs);

		ret = btrfs_delalloc_reserve_space(inode, write_bytes);
		if (ret)
			goto out;

		ret = prepare_pages(root, file, pages, num_pages,
				    pos, first_index, last_index,
				    write_bytes);
		if (ret) {
			btrfs_delalloc_release_space(inode, write_bytes);
			goto out;
		}

		ret = btrfs_copy_from_user(pos, num_pages,
					   write_bytes, pages, &i);
		if (ret == 0) {
			dirty_and_release_pages(NULL, root, file, pages,
						num_pages, pos, write_bytes);
		}

		btrfs_drop_pages(pages, num_pages);
		if (ret) {
			btrfs_delalloc_release_space(inode, write_bytes);
			goto out;
		}

		if (will_write) {
			filemap_fdatawrite_range(inode->i_mapping, pos,
						 pos + write_bytes - 1);
		} else {
			balance_dirty_pages_ratelimited_nr(inode->i_mapping,
							   num_pages);
			if (num_pages <
			    (root->leafsize >> PAGE_CACHE_SHIFT) + 1)
				btrfs_btree_balance_dirty(root, 1);
			btrfs_throttle(root);
		}

		pos += write_bytes;
		num_written += write_bytes;

		cond_resched();
	}
out:
	mutex_unlock(&inode->i_mutex);
	if (ret)
		err = ret;

	kfree(pages);
	if (pinned[0])
		page_cache_release(pinned[0]);
	if (pinned[1])
		page_cache_release(pinned[1]);
	*ppos = pos;

	/*
	 * we want to make sure fsync finds this change
	 * but we haven't joined a transaction running right now.
	 *
	 * Later on, someone is sure to update the inode and get the
	 * real transid recorded.
	 *
	 * We set last_trans now to the fs_info generation + 1,
	 * this will either be one more than the running transaction
	 * or the generation used for the next transaction if there isn't
	 * one running right now.
	 */
	BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;

	if (num_written > 0 && will_write) {
		struct btrfs_trans_handle *trans;

		err = btrfs_wait_ordered_range(inode, start_pos, num_written);
		if (err)
			num_written = err;

		if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
			trans = btrfs_start_transaction(root, 0);
			ret = btrfs_log_dentry_safe(trans, root,
						    file->f_dentry);
			if (ret == 0) {
				ret = btrfs_sync_log(trans, root);
				if (ret == 0)
					btrfs_end_transaction(trans, root);
				else
					btrfs_commit_transaction(trans, root);
			} else if (ret != BTRFS_NO_LOG_SYNC) {
				btrfs_commit_transaction(trans, root);
			} else {
				btrfs_end_transaction(trans, root);
			}
		}
		if (file->f_flags & O_DIRECT && buffered) {
			invalidate_mapping_pages(inode->i_mapping,
			      start_pos >> PAGE_CACHE_SHIFT,
			     (start_pos + num_written - 1) >> PAGE_CACHE_SHIFT);
		}
	}
	current->backing_dev_info = NULL;
	return num_written ? num_written : err;
}

int btrfs_release_file(struct inode *inode, struct file *filp)
{
	/*
	 * ordered_data_close is set by settattr when we are about to truncate
	 * a file from a non-zero size to a zero size.  This tries to
	 * flush down new bytes that may have been written if the
	 * application were using truncate to replace a file in place.
	 */
	if (BTRFS_I(inode)->ordered_data_close) {
		BTRFS_I(inode)->ordered_data_close = 0;
		btrfs_add_ordered_operation(NULL, BTRFS_I(inode)->root, inode);
		if (inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT)
			filemap_flush(inode->i_mapping);
	}
	if (filp->private_data)
		btrfs_ioctl_trans_end(filp);
	return 0;
}

/*
 * fsync call for both files and directories.  This logs the inode into
 * the tree log instead of forcing full commits whenever possible.
 *
 * It needs to call filemap_fdatawait so that all ordered extent updates are
 * in the metadata btree are up to date for copying to the log.
 *
 * It drops the inode mutex before doing the tree log commit.  This is an
 * important optimization for directories because holding the mutex prevents
 * new operations on the dir while we write to disk.
 */
int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
	struct inode *inode = dentry->d_inode;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	int ret = 0;
	struct btrfs_trans_handle *trans;


	/* we wait first, since the writeback may change the inode */
	root->log_batch++;
	/* the VFS called filemap_fdatawrite for us */
	btrfs_wait_ordered_range(inode, 0, (u64)-1);
	root->log_batch++;

	/*
	 * check the transaction that last modified this inode
	 * and see if its already been committed
	 */
	if (!BTRFS_I(inode)->last_trans)
		goto out;

	/*
	 * if the last transaction that changed this file was before
	 * the current transaction, we can bail out now without any
	 * syncing
	 */
	mutex_lock(&root->fs_info->trans_mutex);
	if (BTRFS_I(inode)->last_trans <=
	    root->fs_info->last_trans_committed) {
		BTRFS_I(inode)->last_trans = 0;
		mutex_unlock(&root->fs_info->trans_mutex);
		goto out;
	}
	mutex_unlock(&root->fs_info->trans_mutex);

	/*
	 * ok we haven't committed the transaction yet, lets do a commit
	 */
	if (file && file->private_data)
		btrfs_ioctl_trans_end(file);

	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto out;
	}

	ret = btrfs_log_dentry_safe(trans, root, dentry);
	if (ret < 0)
		goto out;

	/* we've logged all the items and now have a consistent
	 * version of the file in the log.  It is possible that
	 * someone will come in and modify the file, but that's
	 * fine because the log is consistent on disk, and we
	 * have references to all of the file's extents
	 *
	 * It is possible that someone will come in and log the
	 * file again, but that will end up using the synchronization
	 * inside btrfs_sync_log to keep things safe.
	 */
	mutex_unlock(&dentry->d_inode->i_mutex);

	if (ret != BTRFS_NO_LOG_SYNC) {
		if (ret > 0) {
			ret = btrfs_commit_transaction(trans, root);
		} else {
			ret = btrfs_sync_log(trans, root);
			if (ret == 0)
				ret = btrfs_end_transaction(trans, root);
			else
				ret = btrfs_commit_transaction(trans, root);
		}
	} else {
		ret = btrfs_end_transaction(trans, root);
	}
	mutex_lock(&dentry->d_inode->i_mutex);
out:
	return ret > 0 ? -EIO : ret;
}

static const struct vm_operations_struct btrfs_file_vm_ops = {
	.fault		= filemap_fault,
	.page_mkwrite	= btrfs_page_mkwrite,
};

static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
{
	struct address_space *mapping = filp->f_mapping;

	if (!mapping->a_ops->readpage)
		return -ENOEXEC;

	file_accessed(filp);
	vma->vm_ops = &btrfs_file_vm_ops;
	vma->vm_flags |= VM_CAN_NONLINEAR;

	return 0;
}

const struct file_operations btrfs_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read       = generic_file_aio_read,
	.splice_read	= generic_file_splice_read,
	.aio_write	= btrfs_file_aio_write,
	.mmap		= btrfs_file_mmap,
	.open		= generic_file_open,
	.release	= btrfs_release_file,
	.fsync		= btrfs_sync_file,
	.unlocked_ioctl	= btrfs_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= btrfs_ioctl,
#endif
};