forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
backref.c
2013 lines (1777 loc) · 52 KB
/
backref.c
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
/*
* Copyright (C) 2011 STRATO. 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/vmalloc.h>
#include "ctree.h"
#include "disk-io.h"
#include "backref.h"
#include "ulist.h"
#include "transaction.h"
#include "delayed-ref.h"
#include "locking.h"
/* Just an arbitrary number so we can be sure this happened */
#define BACKREF_FOUND_SHARED 6
struct extent_inode_elem {
u64 inum;
u64 offset;
struct extent_inode_elem *next;
};
static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb,
struct btrfs_file_extent_item *fi,
u64 extent_item_pos,
struct extent_inode_elem **eie)
{
u64 offset = 0;
struct extent_inode_elem *e;
if (!btrfs_file_extent_compression(eb, fi) &&
!btrfs_file_extent_encryption(eb, fi) &&
!btrfs_file_extent_other_encoding(eb, fi)) {
u64 data_offset;
u64 data_len;
data_offset = btrfs_file_extent_offset(eb, fi);
data_len = btrfs_file_extent_num_bytes(eb, fi);
if (extent_item_pos < data_offset ||
extent_item_pos >= data_offset + data_len)
return 1;
offset = extent_item_pos - data_offset;
}
e = kmalloc(sizeof(*e), GFP_NOFS);
if (!e)
return -ENOMEM;
e->next = *eie;
e->inum = key->objectid;
e->offset = key->offset + offset;
*eie = e;
return 0;
}
static void free_inode_elem_list(struct extent_inode_elem *eie)
{
struct extent_inode_elem *eie_next;
for (; eie; eie = eie_next) {
eie_next = eie->next;
kfree(eie);
}
}
static int find_extent_in_eb(struct extent_buffer *eb, u64 wanted_disk_byte,
u64 extent_item_pos,
struct extent_inode_elem **eie)
{
u64 disk_byte;
struct btrfs_key key;
struct btrfs_file_extent_item *fi;
int slot;
int nritems;
int extent_type;
int ret;
/*
* from the shared data ref, we only have the leaf but we need
* the key. thus, we must look into all items and see that we
* find one (some) with a reference to our extent item.
*/
nritems = btrfs_header_nritems(eb);
for (slot = 0; slot < nritems; ++slot) {
btrfs_item_key_to_cpu(eb, &key, slot);
if (key.type != BTRFS_EXTENT_DATA_KEY)
continue;
fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
extent_type = btrfs_file_extent_type(eb, fi);
if (extent_type == BTRFS_FILE_EXTENT_INLINE)
continue;
/* don't skip BTRFS_FILE_EXTENT_PREALLOC, we can handle that */
disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
if (disk_byte != wanted_disk_byte)
continue;
ret = check_extent_in_eb(&key, eb, fi, extent_item_pos, eie);
if (ret < 0)
return ret;
}
return 0;
}
/*
* this structure records all encountered refs on the way up to the root
*/
struct __prelim_ref {
struct list_head list;
u64 root_id;
struct btrfs_key key_for_search;
int level;
int count;
struct extent_inode_elem *inode_list;
u64 parent;
u64 wanted_disk_byte;
};
static struct kmem_cache *btrfs_prelim_ref_cache;
int __init btrfs_prelim_ref_init(void)
{
btrfs_prelim_ref_cache = kmem_cache_create("btrfs_prelim_ref",
sizeof(struct __prelim_ref),
0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
NULL);
if (!btrfs_prelim_ref_cache)
return -ENOMEM;
return 0;
}
void btrfs_prelim_ref_exit(void)
{
if (btrfs_prelim_ref_cache)
kmem_cache_destroy(btrfs_prelim_ref_cache);
}
/*
* the rules for all callers of this function are:
* - obtaining the parent is the goal
* - if you add a key, you must know that it is a correct key
* - if you cannot add the parent or a correct key, then we will look into the
* block later to set a correct key
*
* delayed refs
* ============
* backref type | shared | indirect | shared | indirect
* information | tree | tree | data | data
* --------------------+--------+----------+--------+----------
* parent logical | y | - | - | -
* key to resolve | - | y | y | y
* tree block logical | - | - | - | -
* root for resolving | y | y | y | y
*
* - column 1: we've the parent -> done
* - column 2, 3, 4: we use the key to find the parent
*
* on disk refs (inline or keyed)
* ==============================
* backref type | shared | indirect | shared | indirect
* information | tree | tree | data | data
* --------------------+--------+----------+--------+----------
* parent logical | y | - | y | -
* key to resolve | - | - | - | y
* tree block logical | y | y | y | y
* root for resolving | - | y | y | y
*
* - column 1, 3: we've the parent -> done
* - column 2: we take the first key from the block to find the parent
* (see __add_missing_keys)
* - column 4: we use the key to find the parent
*
* additional information that's available but not required to find the parent
* block might help in merging entries to gain some speed.
*/
static int __add_prelim_ref(struct list_head *head, u64 root_id,
struct btrfs_key *key, int level,
u64 parent, u64 wanted_disk_byte, int count,
gfp_t gfp_mask)
{
struct __prelim_ref *ref;
if (root_id == BTRFS_DATA_RELOC_TREE_OBJECTID)
return 0;
ref = kmem_cache_alloc(btrfs_prelim_ref_cache, gfp_mask);
if (!ref)
return -ENOMEM;
ref->root_id = root_id;
if (key) {
ref->key_for_search = *key;
/*
* We can often find data backrefs with an offset that is too
* large (>= LLONG_MAX, maximum allowed file offset) due to
* underflows when subtracting a file's offset with the data
* offset of its corresponding extent data item. This can
* happen for example in the clone ioctl.
* So if we detect such case we set the search key's offset to
* zero to make sure we will find the matching file extent item
* at add_all_parents(), otherwise we will miss it because the
* offset taken form the backref is much larger then the offset
* of the file extent item. This can make us scan a very large
* number of file extent items, but at least it will not make
* us miss any.
* This is an ugly workaround for a behaviour that should have
* never existed, but it does and a fix for the clone ioctl
* would touch a lot of places, cause backwards incompatibility
* and would not fix the problem for extents cloned with older
* kernels.
*/
if (ref->key_for_search.type == BTRFS_EXTENT_DATA_KEY &&
ref->key_for_search.offset >= LLONG_MAX)
ref->key_for_search.offset = 0;
} else {
memset(&ref->key_for_search, 0, sizeof(ref->key_for_search));
}
ref->inode_list = NULL;
ref->level = level;
ref->count = count;
ref->parent = parent;
ref->wanted_disk_byte = wanted_disk_byte;
list_add_tail(&ref->list, head);
return 0;
}
static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
struct ulist *parents, struct __prelim_ref *ref,
int level, u64 time_seq, const u64 *extent_item_pos,
u64 total_refs)
{
int ret = 0;
int slot;
struct extent_buffer *eb;
struct btrfs_key key;
struct btrfs_key *key_for_search = &ref->key_for_search;
struct btrfs_file_extent_item *fi;
struct extent_inode_elem *eie = NULL, *old = NULL;
u64 disk_byte;
u64 wanted_disk_byte = ref->wanted_disk_byte;
u64 count = 0;
if (level != 0) {
eb = path->nodes[level];
ret = ulist_add(parents, eb->start, 0, GFP_NOFS);
if (ret < 0)
return ret;
return 0;
}
/*
* We normally enter this function with the path already pointing to
* the first item to check. But sometimes, we may enter it with
* slot==nritems. In that case, go to the next leaf before we continue.
*/
if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
if (time_seq == (u64)-1)
ret = btrfs_next_leaf(root, path);
else
ret = btrfs_next_old_leaf(root, path, time_seq);
}
while (!ret && count < total_refs) {
eb = path->nodes[0];
slot = path->slots[0];
btrfs_item_key_to_cpu(eb, &key, slot);
if (key.objectid != key_for_search->objectid ||
key.type != BTRFS_EXTENT_DATA_KEY)
break;
fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
if (disk_byte == wanted_disk_byte) {
eie = NULL;
old = NULL;
count++;
if (extent_item_pos) {
ret = check_extent_in_eb(&key, eb, fi,
*extent_item_pos,
&eie);
if (ret < 0)
break;
}
if (ret > 0)
goto next;
ret = ulist_add_merge_ptr(parents, eb->start,
eie, (void **)&old, GFP_NOFS);
if (ret < 0)
break;
if (!ret && extent_item_pos) {
while (old->next)
old = old->next;
old->next = eie;
}
eie = NULL;
}
next:
if (time_seq == (u64)-1)
ret = btrfs_next_item(root, path);
else
ret = btrfs_next_old_item(root, path, time_seq);
}
if (ret > 0)
ret = 0;
else if (ret < 0)
free_inode_elem_list(eie);
return ret;
}
/*
* resolve an indirect backref in the form (root_id, key, level)
* to a logical address
*/
static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
struct btrfs_path *path, u64 time_seq,
struct __prelim_ref *ref,
struct ulist *parents,
const u64 *extent_item_pos, u64 total_refs)
{
struct btrfs_root *root;
struct btrfs_key root_key;
struct extent_buffer *eb;
int ret = 0;
int root_level;
int level = ref->level;
int index;
root_key.objectid = ref->root_id;
root_key.type = BTRFS_ROOT_ITEM_KEY;
root_key.offset = (u64)-1;
index = srcu_read_lock(&fs_info->subvol_srcu);
root = btrfs_get_fs_root(fs_info, &root_key, false);
if (IS_ERR(root)) {
srcu_read_unlock(&fs_info->subvol_srcu, index);
ret = PTR_ERR(root);
goto out;
}
if (btrfs_test_is_dummy_root(root)) {
srcu_read_unlock(&fs_info->subvol_srcu, index);
ret = -ENOENT;
goto out;
}
if (path->search_commit_root)
root_level = btrfs_header_level(root->commit_root);
else if (time_seq == (u64)-1)
root_level = btrfs_header_level(root->node);
else
root_level = btrfs_old_root_level(root, time_seq);
if (root_level + 1 == level) {
srcu_read_unlock(&fs_info->subvol_srcu, index);
goto out;
}
path->lowest_level = level;
if (time_seq == (u64)-1)
ret = btrfs_search_slot(NULL, root, &ref->key_for_search, path,
0, 0);
else
ret = btrfs_search_old_slot(root, &ref->key_for_search, path,
time_seq);
/* root node has been locked, we can release @subvol_srcu safely here */
srcu_read_unlock(&fs_info->subvol_srcu, index);
pr_debug("search slot in root %llu (level %d, ref count %d) returned "
"%d for key (%llu %u %llu)\n",
ref->root_id, level, ref->count, ret,
ref->key_for_search.objectid, ref->key_for_search.type,
ref->key_for_search.offset);
if (ret < 0)
goto out;
eb = path->nodes[level];
while (!eb) {
if (WARN_ON(!level)) {
ret = 1;
goto out;
}
level--;
eb = path->nodes[level];
}
ret = add_all_parents(root, path, parents, ref, level, time_seq,
extent_item_pos, total_refs);
out:
path->lowest_level = 0;
btrfs_release_path(path);
return ret;
}
/*
* resolve all indirect backrefs from the list
*/
static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
struct btrfs_path *path, u64 time_seq,
struct list_head *head,
const u64 *extent_item_pos, u64 total_refs,
u64 root_objectid)
{
int err;
int ret = 0;
struct __prelim_ref *ref;
struct __prelim_ref *ref_safe;
struct __prelim_ref *new_ref;
struct ulist *parents;
struct ulist_node *node;
struct ulist_iterator uiter;
parents = ulist_alloc(GFP_NOFS);
if (!parents)
return -ENOMEM;
/*
* _safe allows us to insert directly after the current item without
* iterating over the newly inserted items.
* we're also allowed to re-assign ref during iteration.
*/
list_for_each_entry_safe(ref, ref_safe, head, list) {
if (ref->parent) /* already direct */
continue;
if (ref->count == 0)
continue;
if (root_objectid && ref->root_id != root_objectid) {
ret = BACKREF_FOUND_SHARED;
goto out;
}
err = __resolve_indirect_ref(fs_info, path, time_seq, ref,
parents, extent_item_pos,
total_refs);
/*
* we can only tolerate ENOENT,otherwise,we should catch error
* and return directly.
*/
if (err == -ENOENT) {
continue;
} else if (err) {
ret = err;
goto out;
}
/* we put the first parent into the ref at hand */
ULIST_ITER_INIT(&uiter);
node = ulist_next(parents, &uiter);
ref->parent = node ? node->val : 0;
ref->inode_list = node ?
(struct extent_inode_elem *)(uintptr_t)node->aux : NULL;
/* additional parents require new refs being added here */
while ((node = ulist_next(parents, &uiter))) {
new_ref = kmem_cache_alloc(btrfs_prelim_ref_cache,
GFP_NOFS);
if (!new_ref) {
ret = -ENOMEM;
goto out;
}
memcpy(new_ref, ref, sizeof(*ref));
new_ref->parent = node->val;
new_ref->inode_list = (struct extent_inode_elem *)
(uintptr_t)node->aux;
list_add(&new_ref->list, &ref->list);
}
ulist_reinit(parents);
}
out:
ulist_free(parents);
return ret;
}
static inline int ref_for_same_block(struct __prelim_ref *ref1,
struct __prelim_ref *ref2)
{
if (ref1->level != ref2->level)
return 0;
if (ref1->root_id != ref2->root_id)
return 0;
if (ref1->key_for_search.type != ref2->key_for_search.type)
return 0;
if (ref1->key_for_search.objectid != ref2->key_for_search.objectid)
return 0;
if (ref1->key_for_search.offset != ref2->key_for_search.offset)
return 0;
if (ref1->parent != ref2->parent)
return 0;
return 1;
}
/*
* read tree blocks and add keys where required.
*/
static int __add_missing_keys(struct btrfs_fs_info *fs_info,
struct list_head *head)
{
struct __prelim_ref *ref;
struct extent_buffer *eb;
list_for_each_entry(ref, head, list) {
if (ref->parent)
continue;
if (ref->key_for_search.type)
continue;
BUG_ON(!ref->wanted_disk_byte);
eb = read_tree_block(fs_info->tree_root, ref->wanted_disk_byte,
0);
if (IS_ERR(eb)) {
return PTR_ERR(eb);
} else if (!extent_buffer_uptodate(eb)) {
free_extent_buffer(eb);
return -EIO;
}
btrfs_tree_read_lock(eb);
if (btrfs_header_level(eb) == 0)
btrfs_item_key_to_cpu(eb, &ref->key_for_search, 0);
else
btrfs_node_key_to_cpu(eb, &ref->key_for_search, 0);
btrfs_tree_read_unlock(eb);
free_extent_buffer(eb);
}
return 0;
}
/*
* merge backrefs and adjust counts accordingly
*
* mode = 1: merge identical keys, if key is set
* FIXME: if we add more keys in __add_prelim_ref, we can merge more here.
* additionally, we could even add a key range for the blocks we
* looked into to merge even more (-> replace unresolved refs by those
* having a parent).
* mode = 2: merge identical parents
*/
static void __merge_refs(struct list_head *head, int mode)
{
struct __prelim_ref *pos1;
list_for_each_entry(pos1, head, list) {
struct __prelim_ref *pos2 = pos1, *tmp;
list_for_each_entry_safe_continue(pos2, tmp, head, list) {
struct __prelim_ref *xchg, *ref1 = pos1, *ref2 = pos2;
struct extent_inode_elem *eie;
if (!ref_for_same_block(ref1, ref2))
continue;
if (mode == 1) {
if (!ref1->parent && ref2->parent) {
xchg = ref1;
ref1 = ref2;
ref2 = xchg;
}
} else {
if (ref1->parent != ref2->parent)
continue;
}
eie = ref1->inode_list;
while (eie && eie->next)
eie = eie->next;
if (eie)
eie->next = ref2->inode_list;
else
ref1->inode_list = ref2->inode_list;
ref1->count += ref2->count;
list_del(&ref2->list);
kmem_cache_free(btrfs_prelim_ref_cache, ref2);
}
}
}
/*
* add all currently queued delayed refs from this head whose seq nr is
* smaller or equal that seq to the list
*/
static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
struct list_head *prefs, u64 *total_refs,
u64 inum)
{
struct btrfs_delayed_ref_node *node;
struct btrfs_delayed_extent_op *extent_op = head->extent_op;
struct btrfs_key key;
struct btrfs_key op_key = {0};
int sgn;
int ret = 0;
if (extent_op && extent_op->update_key)
btrfs_disk_key_to_cpu(&op_key, &extent_op->key);
spin_lock(&head->lock);
list_for_each_entry(node, &head->ref_list, list) {
if (node->seq > seq)
continue;
switch (node->action) {
case BTRFS_ADD_DELAYED_EXTENT:
case BTRFS_UPDATE_DELAYED_HEAD:
WARN_ON(1);
continue;
case BTRFS_ADD_DELAYED_REF:
sgn = 1;
break;
case BTRFS_DROP_DELAYED_REF:
sgn = -1;
break;
default:
BUG_ON(1);
}
*total_refs += (node->ref_mod * sgn);
switch (node->type) {
case BTRFS_TREE_BLOCK_REF_KEY: {
struct btrfs_delayed_tree_ref *ref;
ref = btrfs_delayed_node_to_tree_ref(node);
ret = __add_prelim_ref(prefs, ref->root, &op_key,
ref->level + 1, 0, node->bytenr,
node->ref_mod * sgn, GFP_ATOMIC);
break;
}
case BTRFS_SHARED_BLOCK_REF_KEY: {
struct btrfs_delayed_tree_ref *ref;
ref = btrfs_delayed_node_to_tree_ref(node);
ret = __add_prelim_ref(prefs, 0, NULL,
ref->level + 1, ref->parent,
node->bytenr,
node->ref_mod * sgn, GFP_ATOMIC);
break;
}
case BTRFS_EXTENT_DATA_REF_KEY: {
struct btrfs_delayed_data_ref *ref;
ref = btrfs_delayed_node_to_data_ref(node);
key.objectid = ref->objectid;
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = ref->offset;
/*
* Found a inum that doesn't match our known inum, we
* know it's shared.
*/
if (inum && ref->objectid != inum) {
ret = BACKREF_FOUND_SHARED;
break;
}
ret = __add_prelim_ref(prefs, ref->root, &key, 0, 0,
node->bytenr,
node->ref_mod * sgn, GFP_ATOMIC);
break;
}
case BTRFS_SHARED_DATA_REF_KEY: {
struct btrfs_delayed_data_ref *ref;
ref = btrfs_delayed_node_to_data_ref(node);
ret = __add_prelim_ref(prefs, 0, NULL, 0,
ref->parent, node->bytenr,
node->ref_mod * sgn, GFP_ATOMIC);
break;
}
default:
WARN_ON(1);
}
if (ret)
break;
}
spin_unlock(&head->lock);
return ret;
}
/*
* add all inline backrefs for bytenr to the list
*/
static int __add_inline_refs(struct btrfs_fs_info *fs_info,
struct btrfs_path *path, u64 bytenr,
int *info_level, struct list_head *prefs,
u64 *total_refs, u64 inum)
{
int ret = 0;
int slot;
struct extent_buffer *leaf;
struct btrfs_key key;
struct btrfs_key found_key;
unsigned long ptr;
unsigned long end;
struct btrfs_extent_item *ei;
u64 flags;
u64 item_size;
/*
* enumerate all inline refs
*/
leaf = path->nodes[0];
slot = path->slots[0];
item_size = btrfs_item_size_nr(leaf, slot);
BUG_ON(item_size < sizeof(*ei));
ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
flags = btrfs_extent_flags(leaf, ei);
*total_refs += btrfs_extent_refs(leaf, ei);
btrfs_item_key_to_cpu(leaf, &found_key, slot);
ptr = (unsigned long)(ei + 1);
end = (unsigned long)ei + item_size;
if (found_key.type == BTRFS_EXTENT_ITEM_KEY &&
flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
struct btrfs_tree_block_info *info;
info = (struct btrfs_tree_block_info *)ptr;
*info_level = btrfs_tree_block_level(leaf, info);
ptr += sizeof(struct btrfs_tree_block_info);
BUG_ON(ptr > end);
} else if (found_key.type == BTRFS_METADATA_ITEM_KEY) {
*info_level = found_key.offset;
} else {
BUG_ON(!(flags & BTRFS_EXTENT_FLAG_DATA));
}
while (ptr < end) {
struct btrfs_extent_inline_ref *iref;
u64 offset;
int type;
iref = (struct btrfs_extent_inline_ref *)ptr;
type = btrfs_extent_inline_ref_type(leaf, iref);
offset = btrfs_extent_inline_ref_offset(leaf, iref);
switch (type) {
case BTRFS_SHARED_BLOCK_REF_KEY:
ret = __add_prelim_ref(prefs, 0, NULL,
*info_level + 1, offset,
bytenr, 1, GFP_NOFS);
break;
case BTRFS_SHARED_DATA_REF_KEY: {
struct btrfs_shared_data_ref *sdref;
int count;
sdref = (struct btrfs_shared_data_ref *)(iref + 1);
count = btrfs_shared_data_ref_count(leaf, sdref);
ret = __add_prelim_ref(prefs, 0, NULL, 0, offset,
bytenr, count, GFP_NOFS);
break;
}
case BTRFS_TREE_BLOCK_REF_KEY:
ret = __add_prelim_ref(prefs, offset, NULL,
*info_level + 1, 0,
bytenr, 1, GFP_NOFS);
break;
case BTRFS_EXTENT_DATA_REF_KEY: {
struct btrfs_extent_data_ref *dref;
int count;
u64 root;
dref = (struct btrfs_extent_data_ref *)(&iref->offset);
count = btrfs_extent_data_ref_count(leaf, dref);
key.objectid = btrfs_extent_data_ref_objectid(leaf,
dref);
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = btrfs_extent_data_ref_offset(leaf, dref);
if (inum && key.objectid != inum) {
ret = BACKREF_FOUND_SHARED;
break;
}
root = btrfs_extent_data_ref_root(leaf, dref);
ret = __add_prelim_ref(prefs, root, &key, 0, 0,
bytenr, count, GFP_NOFS);
break;
}
default:
WARN_ON(1);
}
if (ret)
return ret;
ptr += btrfs_extent_inline_ref_size(type);
}
return 0;
}
/*
* add all non-inline backrefs for bytenr to the list
*/
static int __add_keyed_refs(struct btrfs_fs_info *fs_info,
struct btrfs_path *path, u64 bytenr,
int info_level, struct list_head *prefs, u64 inum)
{
struct btrfs_root *extent_root = fs_info->extent_root;
int ret;
int slot;
struct extent_buffer *leaf;
struct btrfs_key key;
while (1) {
ret = btrfs_next_item(extent_root, path);
if (ret < 0)
break;
if (ret) {
ret = 0;
break;
}
slot = path->slots[0];
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &key, slot);
if (key.objectid != bytenr)
break;
if (key.type < BTRFS_TREE_BLOCK_REF_KEY)
continue;
if (key.type > BTRFS_SHARED_DATA_REF_KEY)
break;
switch (key.type) {
case BTRFS_SHARED_BLOCK_REF_KEY:
ret = __add_prelim_ref(prefs, 0, NULL,
info_level + 1, key.offset,
bytenr, 1, GFP_NOFS);
break;
case BTRFS_SHARED_DATA_REF_KEY: {
struct btrfs_shared_data_ref *sdref;
int count;
sdref = btrfs_item_ptr(leaf, slot,
struct btrfs_shared_data_ref);
count = btrfs_shared_data_ref_count(leaf, sdref);
ret = __add_prelim_ref(prefs, 0, NULL, 0, key.offset,
bytenr, count, GFP_NOFS);
break;
}
case BTRFS_TREE_BLOCK_REF_KEY:
ret = __add_prelim_ref(prefs, key.offset, NULL,
info_level + 1, 0,
bytenr, 1, GFP_NOFS);
break;
case BTRFS_EXTENT_DATA_REF_KEY: {
struct btrfs_extent_data_ref *dref;
int count;
u64 root;
dref = btrfs_item_ptr(leaf, slot,
struct btrfs_extent_data_ref);
count = btrfs_extent_data_ref_count(leaf, dref);
key.objectid = btrfs_extent_data_ref_objectid(leaf,
dref);
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = btrfs_extent_data_ref_offset(leaf, dref);
if (inum && key.objectid != inum) {
ret = BACKREF_FOUND_SHARED;
break;
}
root = btrfs_extent_data_ref_root(leaf, dref);
ret = __add_prelim_ref(prefs, root, &key, 0, 0,
bytenr, count, GFP_NOFS);
break;
}
default:
WARN_ON(1);
}
if (ret)
return ret;
}
return ret;
}
/*
* this adds all existing backrefs (inline backrefs, backrefs and delayed
* refs) for the given bytenr to the refs list, merges duplicates and resolves
* indirect refs to their parent bytenr.
* When roots are found, they're added to the roots list
*
* NOTE: This can return values > 0
*
* If time_seq is set to (u64)-1, it will not search delayed_refs, and behave
* much like trans == NULL case, the difference only lies in it will not
* commit root.
* The special case is for qgroup to search roots in commit_transaction().
*
* FIXME some caching might speed things up
*/
static int find_parent_nodes(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
u64 time_seq, struct ulist *refs,
struct ulist *roots, const u64 *extent_item_pos,
u64 root_objectid, u64 inum)
{
struct btrfs_key key;
struct btrfs_path *path;
struct btrfs_delayed_ref_root *delayed_refs = NULL;
struct btrfs_delayed_ref_head *head;
int info_level = 0;
int ret;
struct list_head prefs_delayed;
struct list_head prefs;
struct __prelim_ref *ref;
struct extent_inode_elem *eie = NULL;
u64 total_refs = 0;
INIT_LIST_HEAD(&prefs);
INIT_LIST_HEAD(&prefs_delayed);
key.objectid = bytenr;
key.offset = (u64)-1;
if (btrfs_fs_incompat(fs_info, SKINNY_METADATA))
key.type = BTRFS_METADATA_ITEM_KEY;
else
key.type = BTRFS_EXTENT_ITEM_KEY;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
if (!trans) {
path->search_commit_root = 1;
path->skip_locking = 1;
}
if (time_seq == (u64)-1)
path->skip_locking = 1;
/*
* grab both a lock on the path and a lock on the delayed ref head.
* We need both to get a consistent picture of how the refs look
* at a specified point in time
*/
again:
head = NULL;
ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 0);
if (ret < 0)
goto out;
BUG_ON(ret == 0);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
if (trans && likely(trans->type != __TRANS_DUMMY) &&
time_seq != (u64)-1) {
#else
if (trans && time_seq != (u64)-1) {
#endif
/*
* look if there are updates for this ref queued and lock the
* head
*/
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
head = btrfs_find_delayed_ref_head(trans, bytenr);
if (head) {
if (!mutex_trylock(&head->mutex)) {
atomic_inc(&head->node.refs);
spin_unlock(&delayed_refs->lock);
btrfs_release_path(path);
/*
* Mutex was contended, block until it's
* released and try again
*/
mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
btrfs_put_delayed_ref(&head->node);
goto again;
}
spin_unlock(&delayed_refs->lock);
ret = __add_delayed_refs(head, time_seq,
&prefs_delayed, &total_refs,