forked from kdave/btrfs-progs
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdisk-io.c
2435 lines (2123 loc) · 65.1 KB
/
disk-io.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 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 "kerncompat.h"
#include <sys/stat.h>
#include <linux/fs.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <fcntl.h>
#include <unistd.h>
#include <errno.h>
#include <uuid/uuid.h>
#include "kernel-lib/bitops.h"
#include "kernel-lib/list.h"
#include "kernel-lib/rbtree.h"
#include "kernel-lib/rbtree_types.h"
#include "kernel-shared/accessors.h"
#include "kernel-shared/extent-io-tree.h"
#include "kernel-shared/extent_io.h"
#include "kernel-shared/locking.h"
#include "kernel-shared/messages.h"
#include "kernel-shared/uapi/btrfs_tree.h"
#include "kernel-shared/ctree.h"
#include "kernel-shared/disk-io.h"
#include "kernel-shared/volumes.h"
#include "kernel-shared/transaction.h"
#include "kernel-shared/tree-checker.h"
#include "kernel-shared/zoned.h"
#include "crypto/hash.h"
#include "common/defs.h"
#include "common/extent-cache.h"
#include "common/messages.h"
#include "common/utils.h"
#include "common/rbtree-utils.h"
#include "common/device-scan.h"
#include "common/device-utils.h"
struct btrfs_fs_devices;
struct btrfs_key;
struct btrfs_super_block;
struct btrfs_trans_handle;
struct extent_buffer;
struct rb_node;
/* specified errno for check_tree_block */
#define BTRFS_BAD_BYTENR (-1)
#define BTRFS_BAD_FSID (-2)
#define BTRFS_BAD_LEVEL (-3)
#define BTRFS_BAD_NRITEMS (-4)
/* Calculate max possible nritems for a leaf/node */
static u32 max_nritems(u8 level, u32 nodesize)
{
if (level == 0)
return ((nodesize - sizeof(struct btrfs_header)) /
sizeof(struct btrfs_item));
return ((nodesize - sizeof(struct btrfs_header)) /
sizeof(struct btrfs_key_ptr));
}
static int check_tree_block(struct btrfs_fs_info *fs_info,
struct extent_buffer *buf)
{
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
u32 nodesize = fs_info->nodesize;
bool fsid_match = false;
int ret = BTRFS_BAD_FSID;
if (buf->start != btrfs_header_bytenr(buf))
return BTRFS_BAD_BYTENR;
if (btrfs_header_level(buf) >= BTRFS_MAX_LEVEL)
return BTRFS_BAD_LEVEL;
if (btrfs_header_nritems(buf) > max_nritems(btrfs_header_level(buf),
nodesize))
return BTRFS_BAD_NRITEMS;
/* Only leaf can be empty */
if (btrfs_header_nritems(buf) == 0 &&
btrfs_header_level(buf) != 0)
return BTRFS_BAD_NRITEMS;
while (fs_devices) {
/*
* Checking the incompat flag is only valid for the current
* fs. For seed devices it's forbidden to have their uuid
* changed so reading ->fsid in this case is fine
*/
if (fs_devices == fs_info->fs_devices &&
btrfs_fs_incompat(fs_info, METADATA_UUID))
fsid_match = !memcmp_extent_buffer(buf,
fs_devices->metadata_uuid,
btrfs_header_fsid(),
BTRFS_FSID_SIZE);
else
fsid_match = !memcmp_extent_buffer(buf,
fs_devices->fsid,
btrfs_header_fsid(),
BTRFS_FSID_SIZE);
if (fs_info->ignore_fsid_mismatch || fsid_match) {
ret = 0;
break;
}
fs_devices = fs_devices->seed;
}
return ret;
}
static void print_tree_block_error(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb,
int err)
{
char fs_uuid[BTRFS_UUID_UNPARSED_SIZE] = {'\0'};
char found_uuid[BTRFS_UUID_UNPARSED_SIZE] = {'\0'};
u8 buf[BTRFS_UUID_SIZE];
if (!err)
return;
fprintf(stderr, "bad tree block %llu, ", eb->start);
switch (err) {
case BTRFS_BAD_FSID:
read_extent_buffer(eb, buf, btrfs_header_fsid(),
BTRFS_UUID_SIZE);
uuid_unparse(buf, found_uuid);
uuid_unparse(fs_info->fs_devices->metadata_uuid, fs_uuid);
fprintf(stderr, "fsid mismatch, want=%s, have=%s\n",
fs_uuid, found_uuid);
break;
case BTRFS_BAD_BYTENR:
fprintf(stderr, "bytenr mismatch, want=%llu, have=%llu\n",
eb->start, btrfs_header_bytenr(eb));
break;
case BTRFS_BAD_LEVEL:
fprintf(stderr, "bad level, %u > %d\n",
btrfs_header_level(eb), BTRFS_MAX_LEVEL);
break;
case BTRFS_BAD_NRITEMS:
fprintf(stderr, "invalid nr_items: %u\n",
btrfs_header_nritems(eb));
break;
}
}
int btrfs_csum_data(struct btrfs_fs_info *fs_info, u16 csum_type, const u8 *data,
u8 *out, size_t len)
{
memset(out, 0, BTRFS_CSUM_SIZE);
switch (csum_type) {
case BTRFS_CSUM_TYPE_CRC32:
return hash_crc32c(data, len, out);
case BTRFS_CSUM_TYPE_XXHASH:
return hash_xxhash(data, len, out);
case BTRFS_CSUM_TYPE_SHA256:
return hash_sha256(data, len, out);
case BTRFS_CSUM_TYPE_BLAKE2:
return hash_blake2b(data, len, out);
default:
fprintf(stderr, "ERROR: unknown csum type: %d\n", csum_type);
ASSERT(0);
}
return -1;
}
static int __csum_tree_block_size(struct extent_buffer *buf, u16 csum_size,
int verify, int silent, u16 csum_type)
{
u8 result[BTRFS_CSUM_SIZE];
u32 len;
len = buf->len - BTRFS_CSUM_SIZE;
btrfs_csum_data(buf->fs_info, csum_type, (u8 *)buf->data + BTRFS_CSUM_SIZE,
result, len);
if (verify) {
if (buf->fs_info && buf->fs_info->skip_csum_check) {
/* printf("skip csum check for block %llu\n", buf->start); */
} else if (memcmp_extent_buffer(buf, result, 0, csum_size)) {
if (!silent) {
char found[BTRFS_CSUM_STRING_LEN];
char wanted[BTRFS_CSUM_STRING_LEN];
btrfs_format_csum(csum_type, result, found);
btrfs_format_csum(csum_type, (u8 *)buf->data, wanted);
printk(
"checksum verify failed on %llu wanted %s found %s\n",
(unsigned long long)buf->start,
wanted, found);
}
return 1;
}
} else {
write_extent_buffer(buf, result, 0, csum_size);
}
return 0;
}
int csum_tree_block_size(struct extent_buffer *buf, u16 csum_size, int verify,
u16 csum_type)
{
return __csum_tree_block_size(buf, csum_size, verify, 0, csum_type);
}
int verify_tree_block_csum_silent(struct extent_buffer *buf, u16 csum_size,
u16 csum_type)
{
return __csum_tree_block_size(buf, csum_size, 1, 1, csum_type);
}
static int csum_tree_block(struct btrfs_fs_info *fs_info,
struct extent_buffer *buf, int verify)
{
u16 csum_size = fs_info->csum_size;
u16 csum_type = fs_info->csum_type;
if (verify && fs_info->suppress_check_block_errors)
return verify_tree_block_csum_silent(buf, csum_size, csum_type);
return csum_tree_block_size(buf, csum_size, verify, csum_type);
}
struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info,
u64 bytenr, u32 blocksize)
{
return find_extent_buffer(fs_info, bytenr);
}
struct extent_buffer* btrfs_find_create_tree_block(
struct btrfs_fs_info *fs_info, u64 bytenr)
{
return alloc_extent_buffer(fs_info, bytenr, fs_info->nodesize);
}
void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
u64 parent_transid)
{
struct extent_buffer *eb;
u64 length;
struct btrfs_multi_bio *multi = NULL;
struct btrfs_device *device;
eb = btrfs_find_tree_block(fs_info, bytenr, fs_info->nodesize);
if (!(eb && btrfs_buffer_uptodate(eb, parent_transid, 0)) &&
!btrfs_map_block(fs_info, READ, bytenr, &length, &multi, 0,
NULL)) {
device = multi->stripes[0].dev;
device->total_ios++;
readahead(device->fd, multi->stripes[0].physical,
fs_info->nodesize);
}
free_extent_buffer(eb);
kfree(multi);
}
static int verify_parent_transid(struct extent_buffer *eb, u64 parent_transid,
int ignore)
{
int ret;
if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
return 0;
if (extent_buffer_uptodate(eb) &&
btrfs_header_generation(eb) == parent_transid) {
ret = 0;
goto out;
}
printk("parent transid verify failed on %llu wanted %llu found %llu\n",
(unsigned long long)eb->start,
(unsigned long long)parent_transid,
(unsigned long long)btrfs_header_generation(eb));
if (ignore) {
eb->flags |= EXTENT_BUFFER_BAD_TRANSID;
printk("Ignoring transid failure\n");
return 0;
}
ret = 1;
out:
clear_extent_buffer_uptodate(eb);
return ret;
}
static int read_on_restore(struct extent_buffer *eb)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_device *device;
int ret;
/*
* For on_restoring mode, there should be only one device, and logical
* address is mapped 1:1 to device physical offset.
*/
list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
if (device->devid == 1)
break;
}
device->total_ios++;
ret = btrfs_pread(device->fd, eb->data, eb->len, eb->start,
eb->fs_info->zoned);
if (ret != eb->len)
ret = -EIO;
else
ret = 0;
return ret;
}
int read_whole_eb(struct btrfs_fs_info *info, struct extent_buffer *eb, int mirror)
{
unsigned long offset = 0;
int ret = 0;
unsigned long bytes_left = eb->len;
while (bytes_left) {
u64 read_len = bytes_left;
if (info->on_restoring)
return read_on_restore(eb);
ret = read_data_from_disk(info, eb->data + offset,
eb->start + offset, &read_len,
mirror);
if (ret < 0)
return ret;
offset += read_len;
bytes_left -= read_len;
}
return 0;
}
int btrfs_read_extent_buffer(struct extent_buffer *eb,
struct btrfs_tree_parent_check *check)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
int ret;
u64 best_transid = 0;
int mirror_num = 1;
int good_mirror = 0;
int candidate_mirror = 0;
int num_copies;
int ignore = 0;
num_copies = btrfs_num_copies(fs_info, eb->start, eb->len);
while (1) {
ret = read_whole_eb(fs_info, eb, mirror_num);
if (ret == 0 && csum_tree_block(fs_info, eb, 1) == 0 &&
check_tree_block(fs_info, eb) == 0 &&
verify_parent_transid(eb, check->transid, ignore) == 0) {
if (eb->flags & EXTENT_BUFFER_BAD_TRANSID &&
list_empty(&eb->recow)) {
list_add_tail(&eb->recow,
&fs_info->recow_ebs);
eb->refs++;
}
/*
* check_tree_block() is less strict to allow btrfs
* check to get raw eb with bad key order and fix it.
* But we still need to try to get a good copy if
* possible, or bad key order can go into tools like
* btrfs ins dump-tree.
*/
if (btrfs_header_level(eb))
ret = __btrfs_check_node(eb);
else
ret = __btrfs_check_leaf(eb);
if (!ret || candidate_mirror == mirror_num) {
btrfs_set_buffer_uptodate(eb);
return 0;
}
if (candidate_mirror <= 0)
candidate_mirror = mirror_num;
}
if (ignore) {
if (candidate_mirror > 0) {
mirror_num = candidate_mirror;
continue;
}
if (check_tree_block(fs_info, eb)) {
if (!fs_info->suppress_check_block_errors)
print_tree_block_error(fs_info, eb,
check_tree_block(fs_info, eb));
} else {
if (!fs_info->suppress_check_block_errors)
fprintf(stderr, "Csum didn't match\n");
}
ret = -EIO;
break;
}
if (num_copies == 1 && fs_info->allow_transid_mismatch) {
ignore = 1;
continue;
}
if (btrfs_header_generation(eb) > best_transid) {
best_transid = btrfs_header_generation(eb);
good_mirror = mirror_num;
}
mirror_num++;
if (mirror_num > num_copies) {
if (!fs_info->allow_transid_mismatch) {
ret = -EIO;
break;
}
if (candidate_mirror > 0)
mirror_num = candidate_mirror;
else
mirror_num = good_mirror;
ignore = 1;
continue;
}
}
return ret;
}
struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
struct btrfs_tree_parent_check *check)
{
int ret;
struct extent_buffer *eb;
u32 sectorsize = fs_info->sectorsize;
/*
* Don't even try to create tree block for unaligned tree block
* bytenr.
* Such unaligned tree block will free overlapping extent buffer,
* causing use-after-free bugs for fuzzed images.
*/
if (bytenr < sectorsize || !IS_ALIGNED(bytenr, sectorsize)) {
error("tree block bytenr %llu is not aligned to sectorsize %u",
bytenr, sectorsize);
return ERR_PTR(-EIO);
}
eb = btrfs_find_create_tree_block(fs_info, bytenr);
if (!eb)
return ERR_PTR(-ENOMEM);
if (btrfs_buffer_uptodate(eb, check->transid, 0))
return eb;
ret = btrfs_read_extent_buffer(eb, check);
if (ret) {
/*
* We failed to read this tree block, it be should deleted right
* now to avoid stale cache populate the cache.
*/
free_extent_buffer_nocache(eb);
return ERR_PTR(ret);
}
return eb;
}
int write_tree_block(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct extent_buffer *eb)
{
if (check_tree_block(fs_info, eb)) {
print_tree_block_error(fs_info, eb,
check_tree_block(fs_info, eb));
BUG();
}
if (trans && !btrfs_buffer_uptodate(eb, trans->transid, 0))
BUG();
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
csum_tree_block(fs_info, eb, 0);
return write_data_to_disk(fs_info, eb->data, eb->start, eb->len);
}
void btrfs_setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
u64 objectid)
{
root->node = NULL;
root->commit_root = NULL;
root->state = 0;
root->fs_info = fs_info;
root->objectid = objectid;
root->last_trans = 0;
root->last_inode_alloc = 0;
INIT_LIST_HEAD(&root->dirty_list);
INIT_LIST_HEAD(&root->unaligned_extent_recs);
memset(&root->root_key, 0, sizeof(root->root_key));
memset(&root->root_item, 0, sizeof(root->root_item));
root->root_key.objectid = objectid;
}
static int read_root_node(struct btrfs_fs_info *fs_info,
struct btrfs_root *root, u64 bytenr, u64 gen,
int level)
{
struct btrfs_tree_parent_check check = {
.owner_root = btrfs_root_id(root),
.transid = gen,
.level = level,
};
root->node = read_tree_block(fs_info, bytenr, &check);
if (!extent_buffer_uptodate(root->node))
goto err;
if (btrfs_header_level(root->node) != level) {
error("root [%llu %llu] level %d does not match %d\n",
root->root_key.objectid, root->root_key.offset,
btrfs_header_level(root->node), level);
goto err;
}
return 0;
err:
free_extent_buffer(root->node);
root->node = NULL;
return -EIO;
}
int btrfs_find_and_setup_root(struct btrfs_root *tree_root,
struct btrfs_fs_info *fs_info,
u64 objectid, struct btrfs_root *root)
{
int ret;
btrfs_setup_root(root, fs_info, objectid);
ret = btrfs_find_last_root(tree_root, objectid,
&root->root_item, &root->root_key);
if (ret)
return ret;
return read_root_node(fs_info, root,
btrfs_root_bytenr(&root->root_item),
btrfs_root_generation(&root->root_item),
btrfs_root_level(&root->root_item));
}
static int find_and_setup_log_root(struct btrfs_root *tree_root,
struct btrfs_fs_info *fs_info,
struct btrfs_super_block *disk_super)
{
u64 blocknr = btrfs_super_log_root(disk_super);
struct btrfs_root *log_root = kmalloc(sizeof(struct btrfs_root), GFP_KERNEL);
int ret;
if (!log_root)
return -ENOMEM;
if (blocknr == 0) {
kfree(log_root);
return 0;
}
btrfs_setup_root(log_root, fs_info, BTRFS_TREE_LOG_OBJECTID);
ret = read_root_node(fs_info, log_root, blocknr,
btrfs_super_generation(disk_super) + 1,
btrfs_super_log_root_level(disk_super));
if (ret) {
kfree(log_root);
fs_info->log_root_tree = NULL;
return ret;
}
fs_info->log_root_tree = log_root;
return 0;
}
int btrfs_free_fs_root(struct btrfs_root *root)
{
if (root->node)
free_extent_buffer(root->node);
if (root->commit_root)
free_extent_buffer(root->commit_root);
kfree(root);
return 0;
}
static void __free_fs_root(struct rb_node *node)
{
struct btrfs_root *root;
root = container_of(node, struct btrfs_root, rb_node);
btrfs_free_fs_root(root);
}
FREE_RB_BASED_TREE(fs_roots, __free_fs_root);
struct btrfs_root *btrfs_read_fs_root_no_cache(struct btrfs_fs_info *fs_info,
struct btrfs_key *location)
{
struct btrfs_root *root;
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_path *path;
struct extent_buffer *l;
u64 generation;
int ret = 0;
root = calloc(1, sizeof(*root));
if (!root)
return ERR_PTR(-ENOMEM);
if (location->offset == (u64)-1) {
ret = btrfs_find_and_setup_root(tree_root, fs_info,
location->objectid, root);
if (ret) {
kfree(root);
return ERR_PTR(ret);
}
goto insert;
}
btrfs_setup_root(root, fs_info,
location->objectid);
path = btrfs_alloc_path();
if (!path) {
kfree(root);
return ERR_PTR(-ENOMEM);
}
ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0);
if (ret != 0) {
if (ret > 0)
ret = -ENOENT;
goto out;
}
l = path->nodes[0];
read_extent_buffer(l, &root->root_item,
btrfs_item_ptr_offset(l, path->slots[0]),
sizeof(root->root_item));
memcpy(&root->root_key, location, sizeof(*location));
ret = 0;
out:
btrfs_free_path(path);
if (ret) {
kfree(root);
return ERR_PTR(ret);
}
generation = btrfs_root_generation(&root->root_item);
ret = read_root_node(fs_info, root,
btrfs_root_bytenr(&root->root_item), generation,
btrfs_root_level(&root->root_item));
if (ret) {
kfree(root);
return ERR_PTR(-EIO);
}
insert:
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
if (is_fstree(root->root_key.objectid))
set_bit(BTRFS_ROOT_SHAREABLE, &root->state);
return root;
}
static int btrfs_global_roots_compare_keys(const struct rb_node *node,
const void *data)
{
const struct btrfs_key *key = (struct btrfs_key *)data;
const struct btrfs_root *root;
root = rb_entry(node, struct btrfs_root, rb_node);
return btrfs_comp_cpu_keys(key, &root->root_key);
}
static int btrfs_global_roots_compare(const struct rb_node *node1,
const struct rb_node *node2)
{
const struct btrfs_root *root = rb_entry(node2, struct btrfs_root, rb_node);
return btrfs_global_roots_compare_keys(node1, &root->root_key);
}
static int btrfs_fs_roots_compare_objectids(const struct rb_node *node,
const void *data)
{
u64 objectid = *((const u64 *)data);
const struct btrfs_root *root;
root = rb_entry(node, struct btrfs_root, rb_node);
if (objectid > root->objectid)
return 1;
else if (objectid < root->objectid)
return -1;
else
return 0;
}
int btrfs_fs_roots_compare_roots(const struct rb_node *node1, const struct rb_node *node2)
{
const struct btrfs_root *root;
root = rb_entry(node2, struct btrfs_root, rb_node);
return btrfs_fs_roots_compare_objectids(node1, &root->objectid);
}
int btrfs_global_root_insert(struct btrfs_fs_info *fs_info,
struct btrfs_root *root)
{
return rb_insert(&fs_info->global_roots_tree, &root->rb_node,
btrfs_global_roots_compare);
}
struct btrfs_root *btrfs_global_root(struct btrfs_fs_info *fs_info,
struct btrfs_key *key)
{
struct rb_node *node;
/*
* Some callers use the key->offset = (u64)-1 convention for looking up
* roots, so set this to 0 if we ended up here from that.
*/
if (key->offset == (u64)-1)
key->offset = 0;
node = rb_search(&fs_info->global_roots_tree, (void *)key,
btrfs_global_roots_compare_keys, NULL);
if (node)
return rb_entry(node, struct btrfs_root, rb_node);
return NULL;
}
u64 btrfs_global_root_id(struct btrfs_fs_info *fs_info, u64 bytenr)
{
struct btrfs_block_group *block_group;
u64 ret = 0;
if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
return ret;
/*
* We use this because we won't have this many global roots, and -1 is
* special, so we need something that'll not be found if we have any
* errors from here on.
*/
ret = BTRFS_LAST_FREE_OBJECTID;
block_group = btrfs_lookup_first_block_group(fs_info, bytenr);
if (block_group)
ret = block_group->global_root_id;
return ret;
}
struct btrfs_root *btrfs_csum_root(struct btrfs_fs_info *fs_info,
u64 bytenr)
{
struct btrfs_key key = {
.objectid = BTRFS_CSUM_TREE_OBJECTID,
.type = BTRFS_ROOT_ITEM_KEY,
.offset = btrfs_global_root_id(fs_info, bytenr),
};
return btrfs_global_root(fs_info, &key);
}
struct btrfs_root *btrfs_extent_root(struct btrfs_fs_info *fs_info,
u64 bytenr)
{
struct btrfs_key key = {
.objectid = BTRFS_EXTENT_TREE_OBJECTID,
.type = BTRFS_ROOT_ITEM_KEY,
.offset = btrfs_global_root_id(fs_info, bytenr),
};
return btrfs_global_root(fs_info, &key);
}
struct btrfs_root *btrfs_read_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_key *location)
{
struct btrfs_root *root;
struct rb_node *node;
int ret;
u64 objectid = location->objectid;
if (location->objectid == BTRFS_ROOT_TREE_OBJECTID)
return fs_info->tree_root;
if (location->objectid == BTRFS_EXTENT_TREE_OBJECTID)
return btrfs_global_root(fs_info, location);
if (location->objectid == BTRFS_CHUNK_TREE_OBJECTID)
return fs_info->chunk_root;
if (location->objectid == BTRFS_DEV_TREE_OBJECTID)
return fs_info->dev_root;
if (location->objectid == BTRFS_CSUM_TREE_OBJECTID)
return btrfs_global_root(fs_info, location);
if (location->objectid == BTRFS_UUID_TREE_OBJECTID)
return fs_info->uuid_root ? fs_info->uuid_root : ERR_PTR(-ENOENT);
if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID)
return fs_info->quota_enabled ? fs_info->quota_root :
ERR_PTR(-ENOENT);
if (location->objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) {
root = btrfs_global_root(fs_info, location);
return root ? root : ERR_PTR(-ENOENT);
}
if (location->objectid == BTRFS_BLOCK_GROUP_TREE_OBJECTID)
return fs_info->block_group_root ? fs_info->block_group_root :
ERR_PTR(-ENOENT);
if (location->objectid == BTRFS_RAID_STRIPE_TREE_OBJECTID)
return fs_info->stripe_root ? fs_info->stripe_root : ERR_PTR(-ENOENT);
BUG_ON(location->objectid == BTRFS_TREE_RELOC_OBJECTID);
node = rb_search(&fs_info->fs_root_tree, (void *)&objectid,
btrfs_fs_roots_compare_objectids, NULL);
if (node)
return container_of(node, struct btrfs_root, rb_node);
root = btrfs_read_fs_root_no_cache(fs_info, location);
if (IS_ERR(root))
return root;
ret = rb_insert(&fs_info->fs_root_tree, &root->rb_node,
btrfs_fs_roots_compare_roots);
BUG_ON(ret);
return root;
}
static void __free_global_root(struct rb_node *node)
{
struct btrfs_root *root;
root = rb_entry(node, struct btrfs_root, rb_node);
kfree(root);
}
FREE_RB_BASED_TREE(global_roots, __free_global_root);
void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
{
if (fs_info->quota_root)
kfree(fs_info->quota_root);
if (fs_info->stripe_root)
kfree(fs_info->stripe_root);
free_global_roots_tree(&fs_info->global_roots_tree);
kfree(fs_info->tree_root);
kfree(fs_info->chunk_root);
kfree(fs_info->dev_root);
kfree(fs_info->uuid_root);
kfree(fs_info->block_group_root);
kfree(fs_info->super_copy);
kfree(fs_info->log_root_tree);
kfree(fs_info);
}
struct btrfs_fs_info *btrfs_new_fs_info(int writable, u64 sb_bytenr)
{
struct btrfs_fs_info *fs_info;
fs_info = calloc(1, sizeof(struct btrfs_fs_info));
if (!fs_info)
return NULL;
fs_info->tree_root = calloc(1, sizeof(struct btrfs_root));
fs_info->chunk_root = calloc(1, sizeof(struct btrfs_root));
fs_info->dev_root = calloc(1, sizeof(struct btrfs_root));
fs_info->quota_root = calloc(1, sizeof(struct btrfs_root));
fs_info->uuid_root = calloc(1, sizeof(struct btrfs_root));
fs_info->stripe_root = calloc(1, sizeof(struct btrfs_root));
fs_info->block_group_root = calloc(1, sizeof(struct btrfs_root));
fs_info->super_copy = calloc(1, BTRFS_SUPER_INFO_SIZE);
if (!fs_info->tree_root || !fs_info->chunk_root || !fs_info->dev_root ||
!fs_info->quota_root || !fs_info->uuid_root ||
!fs_info->block_group_root || !fs_info->super_copy ||
!fs_info->stripe_root)
goto free_all;
extent_buffer_init_cache(fs_info);
extent_io_tree_init(fs_info, &fs_info->dirty_buffers, 0);
extent_io_tree_init(fs_info, &fs_info->free_space_cache, 0);
extent_io_tree_init(fs_info, &fs_info->pinned_extents, 0);
extent_io_tree_init(fs_info, &fs_info->extent_ins, 0);
fs_info->block_group_cache_tree = RB_ROOT;
fs_info->excluded_extents = NULL;
fs_info->fs_root_tree = RB_ROOT;
cache_tree_init(&fs_info->mapping_tree.cache_tree);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
INIT_LIST_HEAD(&fs_info->recow_ebs);
spin_lock_init(&fs_info->trans_lock);
init_rwsem(&fs_info->commit_root_sem);
if (!writable)
fs_info->readonly = 1;
fs_info->super_bytenr = sb_bytenr;
fs_info->data_alloc_profile = (u64)-1;
fs_info->metadata_alloc_profile = (u64)-1;
fs_info->system_alloc_profile = fs_info->metadata_alloc_profile;
fs_info->nr_global_roots = 1;
fs_info->initial_fd = -1;
return fs_info;
free_all:
btrfs_free_fs_info(fs_info);
return NULL;
}
int btrfs_check_fs_compatibility(struct btrfs_super_block *sb,
unsigned int flags)
{
u64 features;
features = btrfs_super_incompat_flags(sb) &
~BTRFS_FEATURE_INCOMPAT_SUPP;
if (features) {
printk("couldn't open because of unsupported "
"option features (%llx).\n",
(unsigned long long)features);
return -ENOTSUP;
}
features = btrfs_super_incompat_flags(sb);
if (!(features & BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF)) {
features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
btrfs_set_super_incompat_flags(sb, features);
}
features = btrfs_super_compat_ro_flags(sb);
if (flags & OPEN_CTREE_WRITES) {
if (flags & OPEN_CTREE_INVALIDATE_FST) {
/* Clear the FREE_SPACE_TREE_VALID bit on disk... */
features &= ~BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID;
btrfs_set_super_compat_ro_flags(sb, features);
/* ... and ignore the free space tree bit. */
features &= ~BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE;
}
if (features & ~BTRFS_FEATURE_COMPAT_RO_SUPP) {
printk("couldn't open RDWR because of unsupported "
"option features (0x%llx)\n",
(unsigned long long)features);
return -ENOTSUP;
}
}
return 0;
}
static int find_best_backup_root(struct btrfs_super_block *super)
{
struct btrfs_root_backup *backup;
u64 orig_gen = btrfs_super_generation(super);
u64 gen = 0;
int best_index = 0;
int i;
for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
backup = super->super_roots + i;
if (btrfs_backup_tree_root_gen(backup) != orig_gen &&
btrfs_backup_tree_root_gen(backup) > gen) {
best_index = i;
gen = btrfs_backup_tree_root_gen(backup);
}
}
return best_index;
}
static int read_root_or_create_block(struct btrfs_fs_info *fs_info,
struct btrfs_root *root, u64 bytenr,
u64 gen, int level, unsigned flags,
char *str)
{
int ret;
ret = read_root_node(fs_info, root, bytenr, gen, level);
if (ret) {
if (!(flags & OPEN_CTREE_PARTIAL)) {
error("could not setup %s tree", str);
return -EIO;
}
warning("could not setup %s tree, skipping it", str);
/*
* Need a blank node here just so we don't screw up in the
* million of places that assume a root has a valid ->node