summaryrefslogtreecommitdiff
path: root/fs/btrfs/file-item.c
blob: 84a46a42d26269b94fbb0a823e1fec43439d5e69 (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
/*
 * 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/bio.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "volumes.h"
#include "print-tree.h"

#define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \
				   sizeof(struct btrfs_item) * 2) / \
				  size) - 1))

#define MAX_CSUM_ITEMS(r, size) (min_t(u32, __MAX_CSUM_ITEMS(r, size), \
				       PAGE_CACHE_SIZE))

#define MAX_ORDERED_SUM_BYTES(r) ((PAGE_SIZE - \
				   sizeof(struct btrfs_ordered_sum)) / \
				   sizeof(u32) * (r)->sectorsize)

int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root,
			     u64 objectid, u64 pos,
			     u64 disk_offset, u64 disk_num_bytes,
			     u64 num_bytes, u64 offset, u64 ram_bytes,
			     u8 compression, u8 encryption, u16 other_encoding)
{
	int ret = 0;
	struct btrfs_file_extent_item *item;
	struct btrfs_key file_key;
	struct btrfs_path *path;
	struct extent_buffer *leaf;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
	file_key.objectid = objectid;
	file_key.offset = pos;
	btrfs_set_key_type(&file_key, BTRFS_EXTENT_DATA_KEY);

	path->leave_spinning = 1;
	ret = btrfs_insert_empty_item(trans, root, path, &file_key,
				      sizeof(*item));
	if (ret < 0)
		goto out;
	BUG_ON(ret); /* Can't happen */
	leaf = path->nodes[0];
	item = btrfs_item_ptr(leaf, path->slots[0],
			      struct btrfs_file_extent_item);
	btrfs_set_file_extent_disk_bytenr(leaf, item, disk_offset);
	btrfs_set_file_extent_disk_num_bytes(leaf, item, disk_num_bytes);
	btrfs_set_file_extent_offset(leaf, item, offset);
	btrfs_set_file_extent_num_bytes(leaf, item, num_bytes);
	btrfs_set_file_extent_ram_bytes(leaf, item, ram_bytes);
	btrfs_set_file_extent_generation(leaf, item, trans->transid);
	btrfs_set_file_extent_type(leaf, item, BTRFS_FILE_EXTENT_REG);
	btrfs_set_file_extent_compression(leaf, item, compression);
	btrfs_set_file_extent_encryption(leaf, item, encryption);
	btrfs_set_file_extent_other_encoding(leaf, item, other_encoding);

	btrfs_mark_buffer_dirty(leaf);
out:
	btrfs_free_path(path);
	return ret;
}

static struct btrfs_csum_item *
btrfs_lookup_csum(struct btrfs_trans_handle *trans,
		  struct btrfs_root *root,
		  struct btrfs_path *path,
		  u64 bytenr, int cow)
{
	int ret;
	struct btrfs_key file_key;
	struct btrfs_key found_key;
	struct btrfs_csum_item *item;
	struct extent_buffer *leaf;
	u64 csum_offset = 0;
	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
	int csums_in_item;

	file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
	file_key.offset = bytenr;
	btrfs_set_key_type(&file_key, BTRFS_EXTENT_CSUM_KEY);
	ret = btrfs_search_slot(trans, root, &file_key, path, 0, cow);
	if (ret < 0)
		goto fail;
	leaf = path->nodes[0];
	if (ret > 0) {
		ret = 1;
		if (path->slots[0] == 0)
			goto fail;
		path->slots[0]--;
		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
		if (btrfs_key_type(&found_key) != BTRFS_EXTENT_CSUM_KEY)
			goto fail;

		csum_offset = (bytenr - found_key.offset) >>
				root->fs_info->sb->s_blocksize_bits;
		csums_in_item = btrfs_item_size_nr(leaf, path->slots[0]);
		csums_in_item /= csum_size;

		if (csum_offset == csums_in_item) {
			ret = -EFBIG;
			goto fail;
		} else if (csum_offset > csums_in_item) {
			goto fail;
		}
	}
	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item);
	item = (struct btrfs_csum_item *)((unsigned char *)item +
					  csum_offset * csum_size);
	return item;
fail:
	if (ret > 0)
		ret = -ENOENT;
	return ERR_PTR(ret);
}

int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root,
			     struct btrfs_path *path, u64 objectid,
			     u64 offset, int mod)
{
	int ret;
	struct btrfs_key file_key;
	int ins_len = mod < 0 ? -1 : 0;
	int cow = mod != 0;

	file_key.objectid = objectid;
	file_key.offset = offset;
	btrfs_set_key_type(&file_key, BTRFS_EXTENT_DATA_KEY);
	ret = btrfs_search_slot(trans, root, &file_key, path, ins_len, cow);
	return ret;
}

static void btrfs_io_bio_endio_readpage(struct btrfs_io_bio *bio, int err)
{
	kfree(bio->csum_allocated);
}

static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
				   struct inode *inode, struct bio *bio,
				   u64 logical_offset, u32 *dst, int dio)
{
	struct bio_vec *bvec = bio->bi_io_vec;
	struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio);
	struct btrfs_csum_item *item = NULL;
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct btrfs_path *path;
	u8 *csum;
	u64 offset = 0;
	u64 item_start_offset = 0;
	u64 item_last_offset = 0;
	u64 disk_bytenr;
	u32 diff;
	int nblocks;
	int bio_index = 0;
	int count;
	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);

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

	nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits;
	if (!dst) {
		if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) {
			btrfs_bio->csum_allocated = kmalloc(nblocks * csum_size,
							    GFP_NOFS);
			if (!btrfs_bio->csum_allocated) {
				btrfs_free_path(path);
				return -ENOMEM;
			}
			btrfs_bio->csum = btrfs_bio->csum_allocated;
			btrfs_bio->end_io = btrfs_io_bio_endio_readpage;
		} else {
			btrfs_bio->csum = btrfs_bio->csum_inline;
		}
		csum = btrfs_bio->csum;
	} else {
		csum = (u8 *)dst;
	}

	if (bio->bi_iter.bi_size > PAGE_CACHE_SIZE * 8)
		path->reada = 2;

	WARN_ON(bio->bi_vcnt <= 0);

	/*
	 * the free space stuff is only read when it hasn't been
	 * updated in the current transaction.  So, we can safely
	 * read from the commit root and sidestep a nasty deadlock
	 * between reading the free space cache and updating the csum tree.
	 */
	if (btrfs_is_free_space_inode(inode)) {
		path->search_commit_root = 1;
		path->skip_locking = 1;
	}

	disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
	if (dio)
		offset = logical_offset;
	while (bio_index < bio->bi_vcnt) {
		if (!dio)
			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
		count = btrfs_find_ordered_sum(inode, offset, disk_bytenr,
					       (u32 *)csum, nblocks);
		if (count)
			goto found;

		if (!item || disk_bytenr < item_start_offset ||
		    disk_bytenr >= item_last_offset) {
			struct btrfs_key found_key;
			u32 item_size;

			if (item)
				btrfs_release_path(path);
			item = btrfs_lookup_csum(NULL, root->fs_info->csum_root,
						 path, disk_bytenr, 0);
			if (IS_ERR(item)) {
				count = 1;
				memset(csum, 0, csum_size);
				if (BTRFS_I(inode)->root->root_key.objectid ==
				    BTRFS_DATA_RELOC_TREE_OBJECTID) {
					set_extent_bits(io_tree, offset,
						offset + bvec->bv_len - 1,
						EXTENT_NODATASUM, GFP_NOFS);
				} else {
					printk(KERN_INFO "btrfs no csum found "
					       "for inode %llu start %llu\n",
					       btrfs_ino(inode), offset);
				}
				item = NULL;
				btrfs_release_path(path);
				goto found;
			}
			btrfs_item_key_to_cpu(path->nodes[0], &found_key,
					      path->slots[0]);

			item_start_offset = found_key.offset;
			item_size = btrfs_item_size_nr(path->nodes[0],
						       path->slots[0]);
			item_last_offset = item_start_offset +
				(item_size / csum_size) *
				root->sectorsize;
			item = btrfs_item_ptr(path->nodes[0], path->slots[0],
					      struct btrfs_csum_item);
		}
		/*
		 * this byte range must be able to fit inside
		 * a single leaf so it will also fit inside a u32
		 */
		diff = disk_bytenr - item_start_offset;
		diff = diff / root->sectorsize;
		diff = diff * csum_size;
		count = min_t(int, nblocks, (item_last_offset - disk_bytenr) >>
					    inode->i_sb->s_blocksize_bits);
		read_extent_buffer(path->nodes[0], csum,
				   ((unsigned long)item) + diff,
				   csum_size * count);
found:
		csum += count * csum_size;
		nblocks -= count;
		while (count--) {
			disk_bytenr += bvec->bv_len;
			offset += bvec->bv_len;
			bio_index++;
			bvec++;
		}
	}
	btrfs_free_path(path);
	return 0;
}

int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode,
			  struct bio *bio, u32 *dst)
{
	return __btrfs_lookup_bio_sums(root, inode, bio, 0, dst, 0);
}

int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode,
			      struct btrfs_dio_private *dip, struct bio *bio,
			      u64 offset)
{
	int len = (bio->bi_iter.bi_sector << 9) - dip->disk_bytenr;
	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
	int ret;

	len >>= inode->i_sb->s_blocksize_bits;
	len *= csum_size;

	ret = __btrfs_lookup_bio_sums(root, inode, bio, offset,
				      (u32 *)(dip->csum + len), 1);
	return ret;
}

int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
			     struct list_head *list, int search_commit)
{
	struct btrfs_key key;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_ordered_sum *sums;
	struct btrfs_csum_item *item;
	LIST_HEAD(tmplist);
	unsigned long offset;
	int ret;
	size_t size;
	u64 csum_end;
	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);

	ASSERT(start == ALIGN(start, root->sectorsize) &&
	       (end + 1) == ALIGN(end + 1, root->sectorsize));

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

	if (search_commit) {
		path->skip_locking = 1;
		path->reada = 2;
		path->search_commit_root = 1;
	}

	key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
	key.offset = start;
	key.type = BTRFS_EXTENT_CSUM_KEY;

	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (ret < 0)
		goto fail;
	if (ret > 0 && path->slots[0] > 0) {
		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1);
		if (key.objectid == BTRFS_EXTENT_CSUM_OBJECTID &&
		    key.type == BTRFS_EXTENT_CSUM_KEY) {
			offset = (start - key.offset) >>
				 root->fs_info->sb->s_blocksize_bits;
			if (offset * csum_size <
			    btrfs_item_size_nr(leaf, path->slots[0] - 1))
				path->slots[0]--;
		}
	}

	while (start <= end) {
		leaf = path->nodes[0];
		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(root, path);
			if (ret < 0)
				goto fail;
			if (ret > 0)
				break;
			leaf = path->nodes[0];
		}

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

		if (key.offset > start)
			start = key.offset;

		size = btrfs_item_size_nr(leaf, path->slots[0]);
		csum_end = key.offset + (size / csum_size) * root->sectorsize;
		if (csum_end <= start) {
			path->slots[0]++;
			continue;
		}

		csum_end = min(csum_end, end + 1);
		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
				      struct btrfs_csum_item);
		while (start < csum_end) {
			size = min_t(size_t, csum_end - start,
				     MAX_ORDERED_SUM_BYTES(root));
			sums = kzalloc(btrfs_ordered_sum_size(root, size),
				       GFP_NOFS);
			if (!sums) {
				ret = -ENOMEM;
				goto fail;
			}

			sums->bytenr = start;
			sums->len = (int)size;

			offset = (start - key.offset) >>
				root->fs_info->sb->s_blocksize_bits;
			offset *= csum_size;
			size >>= root->fs_info->sb->s_blocksize_bits;

			read_extent_buffer(path->nodes[0],
					   sums->sums,
					   ((unsigned long)item) + offset,
					   csum_size * size);

			start += root->sectorsize * size;
			list_add_tail(&sums->list, &tmplist);
		}
		path->slots[0]++;
	}
	ret = 0;
fail:
	while (ret < 0 && !list_empty(&tmplist)) {
		sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
		list_del(&sums->list);
		kfree(sums);
	}
	list_splice_tail(&tmplist, list);

	btrfs_free_path(path);
	return ret;
}

int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
		       struct bio *bio, u64 file_start, int contig)
{
	struct btrfs_ordered_sum *sums;
	struct btrfs_ordered_extent *ordered;
	char *data;
	struct bio_vec *bvec = bio->bi_io_vec;
	int bio_index = 0;
	int index;
	unsigned long total_bytes = 0;
	unsigned long this_sum_bytes = 0;
	u64 offset;

	WARN_ON(bio->bi_vcnt <= 0);
	sums = kzalloc(btrfs_ordered_sum_size(root, bio->bi_iter.bi_size),
		       GFP_NOFS);
	if (!sums)
		return -ENOMEM;

	sums->len = bio->bi_iter.bi_size;
	INIT_LIST_HEAD(&sums->list);

	if (contig)
		offset = file_start;
	else
		offset = page_offset(bvec->bv_page) + bvec->bv_offset;

	ordered = btrfs_lookup_ordered_extent(inode, offset);
	BUG_ON(!ordered); /* Logic error */
	sums->bytenr = (u64)bio->bi_iter.bi_sector << 9;
	index = 0;

	while (bio_index < bio->bi_vcnt) {
		if (!contig)
			offset = page_offset(bvec->bv_page) + bvec->bv_offset;

		if (offset >= ordered->file_offset + ordered->len ||
		    offset < ordered->file_offset) {
			unsigned long bytes_left;
			sums->len = this_sum_bytes;
			this_sum_bytes = 0;
			btrfs_add_ordered_sum(inode, ordered, sums);
			btrfs_put_ordered_extent(ordered);

			bytes_left = bio->bi_iter.bi_size - total_bytes;

			sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
				       GFP_NOFS);
			BUG_ON(!sums); /* -ENOMEM */
			sums->len = bytes_left;
			ordered = btrfs_lookup_ordered_extent(inode, offset);
			BUG_ON(!ordered); /* Logic error */
			sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
				       total_bytes;
			index = 0;
		}

		data = kmap_atomic(bvec->bv_page);
		sums->sums[index] = ~(u32)0;
		sums->sums[index] = btrfs_csum_data(data + bvec->bv_offset,
						    sums->sums[index],
						    bvec->bv_len);
		kunmap_atomic(data);
		btrfs_csum_final(sums->sums[index],
				 (char *)(sums->sums + index));

		bio_index++;
		index++;
		total_bytes += bvec->bv_len;
		this_sum_bytes += bvec->bv_len;
		offset += bvec->bv_len;
		bvec++;
	}
	this_sum_bytes = 0;
	btrfs_add_ordered_sum(inode, ordered, sums);
	btrfs_put_ordered_extent(ordered);
	return 0;
}

/*
 * helper function for csum removal, this expects the
 * key to describe the csum pointed to by the path, and it expects
 * the csum to overlap the range [bytenr, len]
 *
 * The csum should not be entirely contained in the range and the
 * range should not be entirely contained in the csum.
 *
 * This calls btrfs_truncate_item with the correct args based on the
 * overlap, and fixes up the key as required.
 */
static noinline void truncate_one_csum(struct btrfs_root *root,
				       struct btrfs_path *path,
				       struct btrfs_key *key,
				       u64 bytenr, u64 len)
{
	struct extent_buffer *leaf;
	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
	u64 csum_end;
	u64 end_byte = bytenr + len;
	u32 blocksize_bits = root->fs_info->sb->s_blocksize_bits;

	leaf = path->nodes[0];
	csum_end = btrfs_item_size_nr(leaf, path->slots[0]) / csum_size;
	csum_end <<= root->fs_info->sb->s_blocksize_bits;
	csum_end += key->offset;

	if (key->offset < bytenr && csum_end <= end_byte) {
		/*
		 *         [ bytenr - len ]
		 *         [   ]
		 *   [csum     ]
		 *   A simple truncate off the end of the item
		 */
		u32 new_size = (bytenr - key->offset) >> blocksize_bits;
		new_size *= csum_size;
		btrfs_truncate_item(root, path, new_size, 1);
	} else if (key->offset >= bytenr && csum_end > end_byte &&
		   end_byte > key->offset) {
		/*
		 *         [ bytenr - len ]
		 *                 [ ]
		 *                 [csum     ]
		 * we need to truncate from the beginning of the csum
		 */
		u32 new_size = (csum_end - end_byte) >> blocksize_bits;
		new_size *= csum_size;

		btrfs_truncate_item(root, path, new_size, 0);

		key->offset = end_byte;
		btrfs_set_item_key_safe(root, path, key);
	} else {
		BUG();
	}
}

/*
 * deletes the csum items from the csum tree for a given
 * range of bytes.
 */
int btrfs_del_csums(struct btrfs_trans_handle *trans,
		    struct btrfs_root *root, u64 bytenr, u64 len)
{
	struct btrfs_path *path;
	struct btrfs_key key;
	u64 end_byte = bytenr + len;
	u64 csum_end;
	struct extent_buffer *leaf;
	int ret;
	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
	int blocksize_bits = root->fs_info->sb->s_blocksize_bits;

	root = root->fs_info->csum_root;

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

	while (1) {
		key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
		key.offset = end_byte - 1;
		key.type = BTRFS_EXTENT_CSUM_KEY;

		path->leave_spinning = 1;
		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
		if (ret > 0) {
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		} else if (ret < 0) {
			break;
		}

		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);

		if (key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
		    key.type != BTRFS_EXTENT_CSUM_KEY) {
			break;
		}

		if (key.offset >= end_byte)
			break;

		csum_end = btrfs_item_size_nr(leaf, path->slots[0]) / csum_size;
		csum_end <<= blocksize_bits;
		csum_end += key.offset;

		/* this csum ends before we start, we're done */
		if (csum_end <= bytenr)
			break;

		/* delete the entire item, it is inside our range */
		if (key.offset >= bytenr && csum_end <= end_byte) {
			ret = btrfs_del_item(trans, root, path);
			if (ret)
				goto out;
			if (key.offset == bytenr)
				break;
		} else if (key.offset < bytenr && csum_end > end_byte) {
			unsigned long offset;
			unsigned long shift_len;
			unsigned long item_offset;
			/*
			 *        [ bytenr - len ]
			 *     [csum                ]
			 *
			 * Our bytes are in the middle of the csum,
			 * we need to split this item and insert a new one.
			 *
			 * But we can't drop the path because the
			 * csum could change, get removed, extended etc.
			 *
			 * The trick here is the max size of a csum item leaves
			 * enough room in the tree block for a single
			 * item header.  So, we split the item in place,
			 * adding a new header pointing to the existing
			 * bytes.  Then we loop around again and we have
			 * a nicely formed csum item that we can neatly
			 * truncate.
			 */
			offset = (bytenr - key.offset) >> blocksize_bits;
			offset *= csum_size;

			shift_len = (len >> blocksize_bits) * csum_size;

			item_offset = btrfs_item_ptr_offset(leaf,
							    path->slots[0]);

			memset_extent_buffer(leaf, 0, item_offset + offset,
					     shift_len);
			key.offset = bytenr;

			/*
			 * btrfs_split_item returns -EAGAIN when the
			 * item changed size or key
			 */
			ret = btrfs_split_item(trans, root, path, &key, offset);
			if (ret && ret != -EAGAIN) {
				btrfs_abort_transaction(trans, root, ret);
				goto out;
			}

			key.offset = end_byte - 1;
		} else {
			truncate_one_csum(root, path, &key, bytenr, len);
			if (key.offset < bytenr)
				break;
		}
		btrfs_release_path(path);
	}
	ret = 0;
out:
	btrfs_free_path(path);
	return ret;
}

int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root,
			   struct btrfs_ordered_sum *sums)
{
	struct btrfs_key file_key;
	struct btrfs_key found_key;
	struct btrfs_path *path;
	struct btrfs_csum_item *item;
	struct btrfs_csum_item *item_end;
	struct extent_buffer *leaf = NULL;
	u64 next_offset;
	u64 total_bytes = 0;
	u64 csum_offset;
	u64 bytenr;
	u32 nritems;
	u32 ins_size;
	int index = 0;
	int found_next;
	int ret;
	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
again:
	next_offset = (u64)-1;
	found_next = 0;
	bytenr = sums->bytenr + total_bytes;
	file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
	file_key.offset = bytenr;
	btrfs_set_key_type(&file_key, BTRFS_EXTENT_CSUM_KEY);

	item = btrfs_lookup_csum(trans, root, path, bytenr, 1);
	if (!IS_ERR(item)) {
		ret = 0;
		leaf = path->nodes[0];
		item_end = btrfs_item_ptr(leaf, path->slots[0],
					  struct btrfs_csum_item);
		item_end = (struct btrfs_csum_item *)((char *)item_end +
			   btrfs_item_size_nr(leaf, path->slots[0]));
		goto found;
	}
	ret = PTR_ERR(item);
	if (ret != -EFBIG && ret != -ENOENT)
		goto fail_unlock;

	if (ret == -EFBIG) {
		u32 item_size;
		/* we found one, but it isn't big enough yet */
		leaf = path->nodes[0];
		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
		if ((item_size / csum_size) >=
		    MAX_CSUM_ITEMS(root, csum_size)) {
			/* already at max size, make a new one */
			goto insert;
		}
	} else {
		int slot = path->slots[0] + 1;
		/* we didn't find a csum item, insert one */
		nritems = btrfs_header_nritems(path->nodes[0]);
		if (path->slots[0] >= nritems - 1) {
			ret = btrfs_next_leaf(root, path);
			if (ret == 1)
				found_next = 1;
			if (ret != 0)
				goto insert;
			slot = 0;
		}
		btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
		if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
		    found_key.type != BTRFS_EXTENT_CSUM_KEY) {
			found_next = 1;
			goto insert;
		}
		next_offset = found_key.offset;
		found_next = 1;
		goto insert;
	}

	/*
	 * at this point, we know the tree has an item, but it isn't big
	 * enough yet to put our csum in.  Grow it
	 */
	btrfs_release_path(path);
	ret = btrfs_search_slot(trans, root, &file_key, path,
				csum_size, 1);
	if (ret < 0)
		goto fail_unlock;

	if (ret > 0) {
		if (path->slots[0] == 0)
			goto insert;
		path->slots[0]--;
	}

	leaf = path->nodes[0];
	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
	csum_offset = (bytenr - found_key.offset) >>
			root->fs_info->sb->s_blocksize_bits;

	if (btrfs_key_type(&found_key) != BTRFS_EXTENT_CSUM_KEY ||
	    found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
	    csum_offset >= MAX_CSUM_ITEMS(root, csum_size)) {
		goto insert;
	}

	if (csum_offset == btrfs_item_size_nr(leaf, path->slots[0]) /
	    csum_size) {
		int extend_nr;
		u64 tmp;
		u32 diff;
		u32 free_space;

		if (btrfs_leaf_free_space(root, leaf) <
				 sizeof(struct btrfs_item) + csum_size * 2)
			goto insert;

		free_space = btrfs_leaf_free_space(root, leaf) -
					 sizeof(struct btrfs_item) - csum_size;
		tmp = sums->len - total_bytes;
		tmp >>= root->fs_info->sb->s_blocksize_bits;
		WARN_ON(tmp < 1);

		extend_nr = max_t(int, 1, (int)tmp);
		diff = (csum_offset + extend_nr) * csum_size;
		diff = min(diff, MAX_CSUM_ITEMS(root, csum_size) * csum_size);

		diff = diff - btrfs_item_size_nr(leaf, path->slots[0]);
		diff = min(free_space, diff);
		diff /= csum_size;
		diff *= csum_size;

		btrfs_extend_item(root, path, diff);
		ret = 0;
		goto csum;
	}

insert:
	btrfs_release_path(path);
	csum_offset = 0;
	if (found_next) {
		u64 tmp;

		tmp = sums->len - total_bytes;
		tmp >>= root->fs_info->sb->s_blocksize_bits;
		tmp = min(tmp, (next_offset - file_key.offset) >>
					 root->fs_info->sb->s_blocksize_bits);

		tmp = max((u64)1, tmp);
		tmp = min(tmp, (u64)MAX_CSUM_ITEMS(root, csum_size));
		ins_size = csum_size * tmp;
	} else {
		ins_size = csum_size;
	}
	path->leave_spinning = 1;
	ret = btrfs_insert_empty_item(trans, root, path, &file_key,
				      ins_size);
	path->leave_spinning = 0;
	if (ret < 0)
		goto fail_unlock;
	if (WARN_ON(ret != 0))
		goto fail_unlock;
	leaf = path->nodes[0];
csum:
	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item);
	item_end = (struct btrfs_csum_item *)((unsigned char *)item +
				      btrfs_item_size_nr(leaf, path->slots[0]));
	item = (struct btrfs_csum_item *)((unsigned char *)item +
					  csum_offset * csum_size);
found:
	ins_size = (u32)(sums->len - total_bytes) >>
		   root->fs_info->sb->s_blocksize_bits;
	ins_size *= csum_size;
	ins_size = min_t(u32, (unsigned long)item_end - (unsigned long)item,
			      ins_size);
	write_extent_buffer(leaf, sums->sums + index, (unsigned long)item,
			    ins_size);

	ins_size /= csum_size;
	total_bytes += ins_size * root->sectorsize;
	index += ins_size;

	btrfs_mark_buffer_dirty(path->nodes[0]);
	if (total_bytes < sums->len) {
		btrfs_release_path(path);
		cond_resched();
		goto again;
	}
out:
	btrfs_free_path(path);
	return ret;

fail_unlock:
	goto out;
}