forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ctree.c
5929 lines (5246 loc) · 152 KB
/
ctree.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) 2007,2008 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/sched.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "print-tree.h"
#include "locking.h"
static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root
*root, struct btrfs_path *path, int level);
static int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root
*root, struct btrfs_key *ins_key,
struct btrfs_path *path, int data_size, int extend);
static int push_node_left(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *dst,
struct extent_buffer *src, int empty);
static int balance_node_right(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *dst_buf,
struct extent_buffer *src_buf);
static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
int level, int slot);
static int tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb);
struct btrfs_path *btrfs_alloc_path(void)
{
struct btrfs_path *path;
path = kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
return path;
}
/*
* set all locked nodes in the path to blocking locks. This should
* be done before scheduling
*/
noinline void btrfs_set_path_blocking(struct btrfs_path *p)
{
int i;
for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
if (!p->nodes[i] || !p->locks[i])
continue;
btrfs_set_lock_blocking_rw(p->nodes[i], p->locks[i]);
if (p->locks[i] == BTRFS_READ_LOCK)
p->locks[i] = BTRFS_READ_LOCK_BLOCKING;
else if (p->locks[i] == BTRFS_WRITE_LOCK)
p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING;
}
}
/*
* reset all the locked nodes in the patch to spinning locks.
*
* held is used to keep lockdep happy, when lockdep is enabled
* we set held to a blocking lock before we go around and
* retake all the spinlocks in the path. You can safely use NULL
* for held
*/
noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
struct extent_buffer *held, int held_rw)
{
int i;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/* lockdep really cares that we take all of these spinlocks
* in the right order. If any of the locks in the path are not
* currently blocking, it is going to complain. So, make really
* really sure by forcing the path to blocking before we clear
* the path blocking.
*/
if (held) {
btrfs_set_lock_blocking_rw(held, held_rw);
if (held_rw == BTRFS_WRITE_LOCK)
held_rw = BTRFS_WRITE_LOCK_BLOCKING;
else if (held_rw == BTRFS_READ_LOCK)
held_rw = BTRFS_READ_LOCK_BLOCKING;
}
btrfs_set_path_blocking(p);
#endif
for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) {
if (p->nodes[i] && p->locks[i]) {
btrfs_clear_lock_blocking_rw(p->nodes[i], p->locks[i]);
if (p->locks[i] == BTRFS_WRITE_LOCK_BLOCKING)
p->locks[i] = BTRFS_WRITE_LOCK;
else if (p->locks[i] == BTRFS_READ_LOCK_BLOCKING)
p->locks[i] = BTRFS_READ_LOCK;
}
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
if (held)
btrfs_clear_lock_blocking_rw(held, held_rw);
#endif
}
/* this also releases the path */
void btrfs_free_path(struct btrfs_path *p)
{
if (!p)
return;
btrfs_release_path(p);
kmem_cache_free(btrfs_path_cachep, p);
}
/*
* path release drops references on the extent buffers in the path
* and it drops any locks held by this path
*
* It is safe to call this on paths that no locks or extent buffers held.
*/
noinline void btrfs_release_path(struct btrfs_path *p)
{
int i;
for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
p->slots[i] = 0;
if (!p->nodes[i])
continue;
if (p->locks[i]) {
btrfs_tree_unlock_rw(p->nodes[i], p->locks[i]);
p->locks[i] = 0;
}
free_extent_buffer(p->nodes[i]);
p->nodes[i] = NULL;
}
}
/*
* safely gets a reference on the root node of a tree. A lock
* is not taken, so a concurrent writer may put a different node
* at the root of the tree. See btrfs_lock_root_node for the
* looping required.
*
* The extent buffer returned by this has a reference taken, so
* it won't disappear. It may stop being the root of the tree
* at any time because there are no locks held.
*/
struct extent_buffer *btrfs_root_node(struct btrfs_root *root)
{
struct extent_buffer *eb;
while (1) {
rcu_read_lock();
eb = rcu_dereference(root->node);
/*
* RCU really hurts here, we could free up the root node because
* it was cow'ed but we may not get the new root node yet so do
* the inc_not_zero dance and if it doesn't work then
* synchronize_rcu and try again.
*/
if (atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
break;
}
rcu_read_unlock();
synchronize_rcu();
}
return eb;
}
/* loop around taking references on and locking the root node of the
* tree until you end up with a lock on the root. A locked buffer
* is returned, with a reference held.
*/
struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
{
struct extent_buffer *eb;
while (1) {
eb = btrfs_root_node(root);
btrfs_tree_lock(eb);
if (eb == root->node)
break;
btrfs_tree_unlock(eb);
free_extent_buffer(eb);
}
return eb;
}
/* loop around taking references on and locking the root node of the
* tree until you end up with a lock on the root. A locked buffer
* is returned, with a reference held.
*/
static struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
{
struct extent_buffer *eb;
while (1) {
eb = btrfs_root_node(root);
btrfs_tree_read_lock(eb);
if (eb == root->node)
break;
btrfs_tree_read_unlock(eb);
free_extent_buffer(eb);
}
return eb;
}
/* cowonly root (everything not a reference counted cow subvolume), just get
* put onto a simple dirty list. transaction.c walks this to make sure they
* get properly updated on disk.
*/
static void add_root_to_dirty_list(struct btrfs_root *root)
{
spin_lock(&root->fs_info->trans_lock);
if (test_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state) &&
list_empty(&root->dirty_list)) {
list_add(&root->dirty_list,
&root->fs_info->dirty_cowonly_roots);
}
spin_unlock(&root->fs_info->trans_lock);
}
/*
* used by snapshot creation to make a copy of a root for a tree with
* a given objectid. The buffer with the new root node is returned in
* cow_ret, and this func returns zero on success or a negative error code.
*/
int btrfs_copy_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf,
struct extent_buffer **cow_ret, u64 new_root_objectid)
{
struct extent_buffer *cow;
int ret = 0;
int level;
struct btrfs_disk_key disk_key;
WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
trans->transid != root->fs_info->running_transaction->transid);
WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
trans->transid != root->last_trans);
level = btrfs_header_level(buf);
if (level == 0)
btrfs_item_key(buf, &disk_key, 0);
else
btrfs_node_key(buf, &disk_key, 0);
cow = btrfs_alloc_free_block(trans, root, buf->len, 0,
new_root_objectid, &disk_key, level,
buf->start, 0);
if (IS_ERR(cow))
return PTR_ERR(cow);
copy_extent_buffer(cow, buf, 0, 0, cow->len);
btrfs_set_header_bytenr(cow, cow->start);
btrfs_set_header_generation(cow, trans->transid);
btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV);
btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN |
BTRFS_HEADER_FLAG_RELOC);
if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC);
else
btrfs_set_header_owner(cow, new_root_objectid);
write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(),
BTRFS_FSID_SIZE);
WARN_ON(btrfs_header_generation(buf) > trans->transid);
if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
ret = btrfs_inc_ref(trans, root, cow, 1, 1);
else
ret = btrfs_inc_ref(trans, root, cow, 0, 1);
if (ret)
return ret;
btrfs_mark_buffer_dirty(cow);
*cow_ret = cow;
return 0;
}
enum mod_log_op {
MOD_LOG_KEY_REPLACE,
MOD_LOG_KEY_ADD,
MOD_LOG_KEY_REMOVE,
MOD_LOG_KEY_REMOVE_WHILE_FREEING,
MOD_LOG_KEY_REMOVE_WHILE_MOVING,
MOD_LOG_MOVE_KEYS,
MOD_LOG_ROOT_REPLACE,
};
struct tree_mod_move {
int dst_slot;
int nr_items;
};
struct tree_mod_root {
u64 logical;
u8 level;
};
struct tree_mod_elem {
struct rb_node node;
u64 index; /* shifted logical */
u64 seq;
enum mod_log_op op;
/* this is used for MOD_LOG_KEY_* and MOD_LOG_MOVE_KEYS operations */
int slot;
/* this is used for MOD_LOG_KEY* and MOD_LOG_ROOT_REPLACE */
u64 generation;
/* those are used for op == MOD_LOG_KEY_{REPLACE,REMOVE} */
struct btrfs_disk_key key;
u64 blockptr;
/* this is used for op == MOD_LOG_MOVE_KEYS */
struct tree_mod_move move;
/* this is used for op == MOD_LOG_ROOT_REPLACE */
struct tree_mod_root old_root;
};
static inline void tree_mod_log_read_lock(struct btrfs_fs_info *fs_info)
{
read_lock(&fs_info->tree_mod_log_lock);
}
static inline void tree_mod_log_read_unlock(struct btrfs_fs_info *fs_info)
{
read_unlock(&fs_info->tree_mod_log_lock);
}
static inline void tree_mod_log_write_lock(struct btrfs_fs_info *fs_info)
{
write_lock(&fs_info->tree_mod_log_lock);
}
static inline void tree_mod_log_write_unlock(struct btrfs_fs_info *fs_info)
{
write_unlock(&fs_info->tree_mod_log_lock);
}
/*
* Pull a new tree mod seq number for our operation.
*/
static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
{
return atomic64_inc_return(&fs_info->tree_mod_seq);
}
/*
* This adds a new blocker to the tree mod log's blocker list if the @elem
* passed does not already have a sequence number set. So when a caller expects
* to record tree modifications, it should ensure to set elem->seq to zero
* before calling btrfs_get_tree_mod_seq.
* Returns a fresh, unused tree log modification sequence number, even if no new
* blocker was added.
*/
u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
struct seq_list *elem)
{
tree_mod_log_write_lock(fs_info);
spin_lock(&fs_info->tree_mod_seq_lock);
if (!elem->seq) {
elem->seq = btrfs_inc_tree_mod_seq(fs_info);
list_add_tail(&elem->list, &fs_info->tree_mod_seq_list);
}
spin_unlock(&fs_info->tree_mod_seq_lock);
tree_mod_log_write_unlock(fs_info);
return elem->seq;
}
void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
struct seq_list *elem)
{
struct rb_root *tm_root;
struct rb_node *node;
struct rb_node *next;
struct seq_list *cur_elem;
struct tree_mod_elem *tm;
u64 min_seq = (u64)-1;
u64 seq_putting = elem->seq;
if (!seq_putting)
return;
spin_lock(&fs_info->tree_mod_seq_lock);
list_del(&elem->list);
elem->seq = 0;
list_for_each_entry(cur_elem, &fs_info->tree_mod_seq_list, list) {
if (cur_elem->seq < min_seq) {
if (seq_putting > cur_elem->seq) {
/*
* blocker with lower sequence number exists, we
* cannot remove anything from the log
*/
spin_unlock(&fs_info->tree_mod_seq_lock);
return;
}
min_seq = cur_elem->seq;
}
}
spin_unlock(&fs_info->tree_mod_seq_lock);
/*
* anything that's lower than the lowest existing (read: blocked)
* sequence number can be removed from the tree.
*/
tree_mod_log_write_lock(fs_info);
tm_root = &fs_info->tree_mod_log;
for (node = rb_first(tm_root); node; node = next) {
next = rb_next(node);
tm = container_of(node, struct tree_mod_elem, node);
if (tm->seq > min_seq)
continue;
rb_erase(node, tm_root);
kfree(tm);
}
tree_mod_log_write_unlock(fs_info);
}
/*
* key order of the log:
* index -> sequence
*
* the index is the shifted logical of the *new* root node for root replace
* operations, or the shifted logical of the affected block for all other
* operations.
*
* Note: must be called with write lock (tree_mod_log_write_lock).
*/
static noinline int
__tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
{
struct rb_root *tm_root;
struct rb_node **new;
struct rb_node *parent = NULL;
struct tree_mod_elem *cur;
BUG_ON(!tm);
tm->seq = btrfs_inc_tree_mod_seq(fs_info);
tm_root = &fs_info->tree_mod_log;
new = &tm_root->rb_node;
while (*new) {
cur = container_of(*new, struct tree_mod_elem, node);
parent = *new;
if (cur->index < tm->index)
new = &((*new)->rb_left);
else if (cur->index > tm->index)
new = &((*new)->rb_right);
else if (cur->seq < tm->seq)
new = &((*new)->rb_left);
else if (cur->seq > tm->seq)
new = &((*new)->rb_right);
else
return -EEXIST;
}
rb_link_node(&tm->node, parent, new);
rb_insert_color(&tm->node, tm_root);
return 0;
}
/*
* Determines if logging can be omitted. Returns 1 if it can. Otherwise, it
* returns zero with the tree_mod_log_lock acquired. The caller must hold
* this until all tree mod log insertions are recorded in the rb tree and then
* call tree_mod_log_write_unlock() to release.
*/
static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb) {
smp_mb();
if (list_empty(&(fs_info)->tree_mod_seq_list))
return 1;
if (eb && btrfs_header_level(eb) == 0)
return 1;
tree_mod_log_write_lock(fs_info);
if (list_empty(&(fs_info)->tree_mod_seq_list)) {
tree_mod_log_write_unlock(fs_info);
return 1;
}
return 0;
}
/* Similar to tree_mod_dont_log, but doesn't acquire any locks. */
static inline int tree_mod_need_log(const struct btrfs_fs_info *fs_info,
struct extent_buffer *eb)
{
smp_mb();
if (list_empty(&(fs_info)->tree_mod_seq_list))
return 0;
if (eb && btrfs_header_level(eb) == 0)
return 0;
return 1;
}
static struct tree_mod_elem *
alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
enum mod_log_op op, gfp_t flags)
{
struct tree_mod_elem *tm;
tm = kzalloc(sizeof(*tm), flags);
if (!tm)
return NULL;
tm->index = eb->start >> PAGE_CACHE_SHIFT;
if (op != MOD_LOG_KEY_ADD) {
btrfs_node_key(eb, &tm->key, slot);
tm->blockptr = btrfs_node_blockptr(eb, slot);
}
tm->op = op;
tm->slot = slot;
tm->generation = btrfs_node_ptr_generation(eb, slot);
RB_CLEAR_NODE(&tm->node);
return tm;
}
static noinline int
tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int slot,
enum mod_log_op op, gfp_t flags)
{
struct tree_mod_elem *tm;
int ret;
if (!tree_mod_need_log(fs_info, eb))
return 0;
tm = alloc_tree_mod_elem(eb, slot, op, flags);
if (!tm)
return -ENOMEM;
if (tree_mod_dont_log(fs_info, eb)) {
kfree(tm);
return 0;
}
ret = __tree_mod_log_insert(fs_info, tm);
tree_mod_log_write_unlock(fs_info);
if (ret)
kfree(tm);
return ret;
}
static noinline int
tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int dst_slot, int src_slot,
int nr_items, gfp_t flags)
{
struct tree_mod_elem *tm = NULL;
struct tree_mod_elem **tm_list = NULL;
int ret = 0;
int i;
int locked = 0;
if (!tree_mod_need_log(fs_info, eb))
return 0;
tm_list = kzalloc(nr_items * sizeof(struct tree_mod_elem *), flags);
if (!tm_list)
return -ENOMEM;
tm = kzalloc(sizeof(*tm), flags);
if (!tm) {
ret = -ENOMEM;
goto free_tms;
}
tm->index = eb->start >> PAGE_CACHE_SHIFT;
tm->slot = src_slot;
tm->move.dst_slot = dst_slot;
tm->move.nr_items = nr_items;
tm->op = MOD_LOG_MOVE_KEYS;
for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
tm_list[i] = alloc_tree_mod_elem(eb, i + dst_slot,
MOD_LOG_KEY_REMOVE_WHILE_MOVING, flags);
if (!tm_list[i]) {
ret = -ENOMEM;
goto free_tms;
}
}
if (tree_mod_dont_log(fs_info, eb))
goto free_tms;
locked = 1;
/*
* When we override something during the move, we log these removals.
* This can only happen when we move towards the beginning of the
* buffer, i.e. dst_slot < src_slot.
*/
for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
ret = __tree_mod_log_insert(fs_info, tm_list[i]);
if (ret)
goto free_tms;
}
ret = __tree_mod_log_insert(fs_info, tm);
if (ret)
goto free_tms;
tree_mod_log_write_unlock(fs_info);
kfree(tm_list);
return 0;
free_tms:
for (i = 0; i < nr_items; i++) {
if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node))
rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log);
kfree(tm_list[i]);
}
if (locked)
tree_mod_log_write_unlock(fs_info);
kfree(tm_list);
kfree(tm);
return ret;
}
static inline int
__tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
struct tree_mod_elem **tm_list,
int nritems)
{
int i, j;
int ret;
for (i = nritems - 1; i >= 0; i--) {
ret = __tree_mod_log_insert(fs_info, tm_list[i]);
if (ret) {
for (j = nritems - 1; j > i; j--)
rb_erase(&tm_list[j]->node,
&fs_info->tree_mod_log);
return ret;
}
}
return 0;
}
static noinline int
tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
struct extent_buffer *old_root,
struct extent_buffer *new_root, gfp_t flags,
int log_removal)
{
struct tree_mod_elem *tm = NULL;
struct tree_mod_elem **tm_list = NULL;
int nritems = 0;
int ret = 0;
int i;
if (!tree_mod_need_log(fs_info, NULL))
return 0;
if (log_removal && btrfs_header_level(old_root) > 0) {
nritems = btrfs_header_nritems(old_root);
tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *),
flags);
if (!tm_list) {
ret = -ENOMEM;
goto free_tms;
}
for (i = 0; i < nritems; i++) {
tm_list[i] = alloc_tree_mod_elem(old_root, i,
MOD_LOG_KEY_REMOVE_WHILE_FREEING, flags);
if (!tm_list[i]) {
ret = -ENOMEM;
goto free_tms;
}
}
}
tm = kzalloc(sizeof(*tm), flags);
if (!tm) {
ret = -ENOMEM;
goto free_tms;
}
tm->index = new_root->start >> PAGE_CACHE_SHIFT;
tm->old_root.logical = old_root->start;
tm->old_root.level = btrfs_header_level(old_root);
tm->generation = btrfs_header_generation(old_root);
tm->op = MOD_LOG_ROOT_REPLACE;
if (tree_mod_dont_log(fs_info, NULL))
goto free_tms;
if (tm_list)
ret = __tree_mod_log_free_eb(fs_info, tm_list, nritems);
if (!ret)
ret = __tree_mod_log_insert(fs_info, tm);
tree_mod_log_write_unlock(fs_info);
if (ret)
goto free_tms;
kfree(tm_list);
return ret;
free_tms:
if (tm_list) {
for (i = 0; i < nritems; i++)
kfree(tm_list[i]);
kfree(tm_list);
}
kfree(tm);
return ret;
}
static struct tree_mod_elem *
__tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
int smallest)
{
struct rb_root *tm_root;
struct rb_node *node;
struct tree_mod_elem *cur = NULL;
struct tree_mod_elem *found = NULL;
u64 index = start >> PAGE_CACHE_SHIFT;
tree_mod_log_read_lock(fs_info);
tm_root = &fs_info->tree_mod_log;
node = tm_root->rb_node;
while (node) {
cur = container_of(node, struct tree_mod_elem, node);
if (cur->index < index) {
node = node->rb_left;
} else if (cur->index > index) {
node = node->rb_right;
} else if (cur->seq < min_seq) {
node = node->rb_left;
} else if (!smallest) {
/* we want the node with the highest seq */
if (found)
BUG_ON(found->seq > cur->seq);
found = cur;
node = node->rb_left;
} else if (cur->seq > min_seq) {
/* we want the node with the smallest seq */
if (found)
BUG_ON(found->seq < cur->seq);
found = cur;
node = node->rb_right;
} else {
found = cur;
break;
}
}
tree_mod_log_read_unlock(fs_info);
return found;
}
/*
* this returns the element from the log with the smallest time sequence
* value that's in the log (the oldest log item). any element with a time
* sequence lower than min_seq will be ignored.
*/
static struct tree_mod_elem *
tree_mod_log_search_oldest(struct btrfs_fs_info *fs_info, u64 start,
u64 min_seq)
{
return __tree_mod_log_search(fs_info, start, min_seq, 1);
}
/*
* this returns the element from the log with the largest time sequence
* value that's in the log (the most recent log item). any element with
* a time sequence lower than min_seq will be ignored.
*/
static struct tree_mod_elem *
tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq)
{
return __tree_mod_log_search(fs_info, start, min_seq, 0);
}
static noinline int
tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
struct extent_buffer *src, unsigned long dst_offset,
unsigned long src_offset, int nr_items)
{
int ret = 0;
struct tree_mod_elem **tm_list = NULL;
struct tree_mod_elem **tm_list_add, **tm_list_rem;
int i;
int locked = 0;
if (!tree_mod_need_log(fs_info, NULL))
return 0;
if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0)
return 0;
tm_list = kzalloc(nr_items * 2 * sizeof(struct tree_mod_elem *),
GFP_NOFS);
if (!tm_list)
return -ENOMEM;
tm_list_add = tm_list;
tm_list_rem = tm_list + nr_items;
for (i = 0; i < nr_items; i++) {
tm_list_rem[i] = alloc_tree_mod_elem(src, i + src_offset,
MOD_LOG_KEY_REMOVE, GFP_NOFS);
if (!tm_list_rem[i]) {
ret = -ENOMEM;
goto free_tms;
}
tm_list_add[i] = alloc_tree_mod_elem(dst, i + dst_offset,
MOD_LOG_KEY_ADD, GFP_NOFS);
if (!tm_list_add[i]) {
ret = -ENOMEM;
goto free_tms;
}
}
if (tree_mod_dont_log(fs_info, NULL))
goto free_tms;
locked = 1;
for (i = 0; i < nr_items; i++) {
ret = __tree_mod_log_insert(fs_info, tm_list_rem[i]);
if (ret)
goto free_tms;
ret = __tree_mod_log_insert(fs_info, tm_list_add[i]);
if (ret)
goto free_tms;
}
tree_mod_log_write_unlock(fs_info);
kfree(tm_list);
return 0;
free_tms:
for (i = 0; i < nr_items * 2; i++) {
if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node))
rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log);
kfree(tm_list[i]);
}
if (locked)
tree_mod_log_write_unlock(fs_info);
kfree(tm_list);
return ret;
}
static inline void
tree_mod_log_eb_move(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
int dst_offset, int src_offset, int nr_items)
{
int ret;
ret = tree_mod_log_insert_move(fs_info, dst, dst_offset, src_offset,
nr_items, GFP_NOFS);
BUG_ON(ret < 0);
}
static noinline void
tree_mod_log_set_node_key(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int slot, int atomic)
{
int ret;
ret = tree_mod_log_insert_key(fs_info, eb, slot,
MOD_LOG_KEY_REPLACE,
atomic ? GFP_ATOMIC : GFP_NOFS);
BUG_ON(ret < 0);
}
static noinline int
tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb)
{
struct tree_mod_elem **tm_list = NULL;
int nritems = 0;
int i;
int ret = 0;
if (btrfs_header_level(eb) == 0)
return 0;
if (!tree_mod_need_log(fs_info, NULL))
return 0;
nritems = btrfs_header_nritems(eb);
tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *),
GFP_NOFS);
if (!tm_list)
return -ENOMEM;
for (i = 0; i < nritems; i++) {
tm_list[i] = alloc_tree_mod_elem(eb, i,
MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
if (!tm_list[i]) {
ret = -ENOMEM;
goto free_tms;
}
}
if (tree_mod_dont_log(fs_info, eb))
goto free_tms;
ret = __tree_mod_log_free_eb(fs_info, tm_list, nritems);
tree_mod_log_write_unlock(fs_info);
if (ret)
goto free_tms;
kfree(tm_list);
return 0;
free_tms:
for (i = 0; i < nritems; i++)
kfree(tm_list[i]);
kfree(tm_list);
return ret;
}
static noinline void
tree_mod_log_set_root_pointer(struct btrfs_root *root,
struct extent_buffer *new_root_node,
int log_removal)
{
int ret;
ret = tree_mod_log_insert_root(root->fs_info, root->node,
new_root_node, GFP_NOFS, log_removal);
BUG_ON(ret < 0);
}
/*
* check if the tree block can be shared by multiple trees
*/
int btrfs_block_can_be_shared(struct btrfs_root *root,
struct extent_buffer *buf)
{
/*
* Tree blocks not in refernece counted trees and tree roots
* are never shared. If a block was allocated after the last
* snapshot and the block was not allocated by tree relocation,
* we know the block is not shared.
*/
if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
buf != root->node && buf != root->commit_root &&
(btrfs_header_generation(buf) <=
btrfs_root_last_snapshot(&root->root_item) ||
btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
return 1;
#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
return 1;
#endif
return 0;
}
static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf,
struct extent_buffer *cow,
int *last_ref)
{
u64 refs;
u64 owner;
u64 flags;
u64 new_flags = 0;
int ret;
/*
* Backrefs update rules:
*
* Always use full backrefs for extent pointers in tree block
* allocated by tree relocation.
*
* If a shared tree block is no longer referenced by its owner
* tree (btrfs_header_owner(buf) == root->root_key.objectid),