forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtree-checker.c
1813 lines (1654 loc) · 54.1 KB
/
tree-checker.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
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) Qu Wenruo 2017. All rights reserved.
*/
/*
* The module is used to catch unexpected/corrupted tree block data.
* Such behavior can be caused either by a fuzzed image or bugs.
*
* The objective is to do leaf/node validation checks when tree block is read
* from disk, and check *every* possible member, so other code won't
* need to checking them again.
*
* Due to the potential and unwanted damage, every checker needs to be
* carefully reviewed otherwise so it does not prevent mount of valid images.
*/
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/error-injection.h>
#include "ctree.h"
#include "tree-checker.h"
#include "disk-io.h"
#include "compression.h"
#include "volumes.h"
#include "misc.h"
#include "btrfs_inode.h"
/*
* Error message should follow the following format:
* corrupt <type>: <identifier>, <reason>[, <bad_value>]
*
* @type: leaf or node
* @identifier: the necessary info to locate the leaf/node.
* It's recommended to decode key.objecitd/offset if it's
* meaningful.
* @reason: describe the error
* @bad_value: optional, it's recommended to output bad value and its
* expected value (range).
*
* Since comma is used to separate the components, only space is allowed
* inside each component.
*/
/*
* Append generic "corrupt leaf/node root=%llu block=%llu slot=%d: " to @fmt.
* Allows callers to customize the output.
*/
__printf(3, 4)
__cold
static void generic_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = eb->fs_info;
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(fs_info,
"corrupt %s: root=%llu block=%llu slot=%d, %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot, &vaf);
va_end(args);
}
/*
* Customized reporter for extent data item, since its key objectid and
* offset has its own meaning.
*/
__printf(3, 4)
__cold
static void file_extent_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_key key;
struct va_format vaf;
va_list args;
btrfs_item_key_to_cpu(eb, &key, slot);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(fs_info,
"corrupt %s: root=%llu block=%llu slot=%d ino=%llu file_offset=%llu, %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
key.objectid, key.offset, &vaf);
va_end(args);
}
/*
* Return 0 if the btrfs_file_extent_##name is aligned to @alignment
* Else return 1
*/
#define CHECK_FE_ALIGNED(leaf, slot, fi, name, alignment) \
({ \
if (unlikely(!IS_ALIGNED(btrfs_file_extent_##name((leaf), (fi)), \
(alignment)))) \
file_extent_err((leaf), (slot), \
"invalid %s for file extent, have %llu, should be aligned to %u", \
(#name), btrfs_file_extent_##name((leaf), (fi)), \
(alignment)); \
(!IS_ALIGNED(btrfs_file_extent_##name((leaf), (fi)), (alignment))); \
})
static u64 file_extent_end(struct extent_buffer *leaf,
struct btrfs_key *key,
struct btrfs_file_extent_item *extent)
{
u64 end;
u64 len;
if (btrfs_file_extent_type(leaf, extent) == BTRFS_FILE_EXTENT_INLINE) {
len = btrfs_file_extent_ram_bytes(leaf, extent);
end = ALIGN(key->offset + len, leaf->fs_info->sectorsize);
} else {
len = btrfs_file_extent_num_bytes(leaf, extent);
end = key->offset + len;
}
return end;
}
/*
* Customized report for dir_item, the only new important information is
* key->objectid, which represents inode number
*/
__printf(3, 4)
__cold
static void dir_item_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_key key;
struct va_format vaf;
va_list args;
btrfs_item_key_to_cpu(eb, &key, slot);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(fs_info,
"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
key.objectid, &vaf);
va_end(args);
}
/*
* This functions checks prev_key->objectid, to ensure current key and prev_key
* share the same objectid as inode number.
*
* This is to detect missing INODE_ITEM in subvolume trees.
*
* Return true if everything is OK or we don't need to check.
* Return false if anything is wrong.
*/
static bool check_prev_ino(struct extent_buffer *leaf,
struct btrfs_key *key, int slot,
struct btrfs_key *prev_key)
{
/* No prev key, skip check */
if (slot == 0)
return true;
/* Only these key->types needs to be checked */
ASSERT(key->type == BTRFS_XATTR_ITEM_KEY ||
key->type == BTRFS_INODE_REF_KEY ||
key->type == BTRFS_DIR_INDEX_KEY ||
key->type == BTRFS_DIR_ITEM_KEY ||
key->type == BTRFS_EXTENT_DATA_KEY);
/*
* Only subvolume trees along with their reloc trees need this check.
* Things like log tree doesn't follow this ino requirement.
*/
if (!is_fstree(btrfs_header_owner(leaf)))
return true;
if (key->objectid == prev_key->objectid)
return true;
/* Error found */
dir_item_err(leaf, slot,
"invalid previous key objectid, have %llu expect %llu",
prev_key->objectid, key->objectid);
return false;
}
static int check_extent_data_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot,
struct btrfs_key *prev_key)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_file_extent_item *fi;
u32 sectorsize = fs_info->sectorsize;
u32 item_size = btrfs_item_size_nr(leaf, slot);
u64 extent_end;
if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) {
file_extent_err(leaf, slot,
"unaligned file_offset for file extent, have %llu should be aligned to %u",
key->offset, sectorsize);
return -EUCLEAN;
}
/*
* Previous key must have the same key->objectid (ino).
* It can be XATTR_ITEM, INODE_ITEM or just another EXTENT_DATA.
* But if objectids mismatch, it means we have a missing
* INODE_ITEM.
*/
if (unlikely(!check_prev_ino(leaf, key, slot, prev_key)))
return -EUCLEAN;
fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
/*
* Make sure the item contains at least inline header, so the file
* extent type is not some garbage.
*/
if (unlikely(item_size < BTRFS_FILE_EXTENT_INLINE_DATA_START)) {
file_extent_err(leaf, slot,
"invalid item size, have %u expect [%zu, %u)",
item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START,
SZ_4K);
return -EUCLEAN;
}
if (unlikely(btrfs_file_extent_type(leaf, fi) >=
BTRFS_NR_FILE_EXTENT_TYPES)) {
file_extent_err(leaf, slot,
"invalid type for file extent, have %u expect range [0, %u]",
btrfs_file_extent_type(leaf, fi),
BTRFS_NR_FILE_EXTENT_TYPES - 1);
return -EUCLEAN;
}
/*
* Support for new compression/encryption must introduce incompat flag,
* and must be caught in open_ctree().
*/
if (unlikely(btrfs_file_extent_compression(leaf, fi) >=
BTRFS_NR_COMPRESS_TYPES)) {
file_extent_err(leaf, slot,
"invalid compression for file extent, have %u expect range [0, %u]",
btrfs_file_extent_compression(leaf, fi),
BTRFS_NR_COMPRESS_TYPES - 1);
return -EUCLEAN;
}
if (unlikely(btrfs_file_extent_encryption(leaf, fi))) {
file_extent_err(leaf, slot,
"invalid encryption for file extent, have %u expect 0",
btrfs_file_extent_encryption(leaf, fi));
return -EUCLEAN;
}
if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) {
/* Inline extent must have 0 as key offset */
if (unlikely(key->offset)) {
file_extent_err(leaf, slot,
"invalid file_offset for inline file extent, have %llu expect 0",
key->offset);
return -EUCLEAN;
}
/* Compressed inline extent has no on-disk size, skip it */
if (btrfs_file_extent_compression(leaf, fi) !=
BTRFS_COMPRESS_NONE)
return 0;
/* Uncompressed inline extent size must match item size */
if (unlikely(item_size != BTRFS_FILE_EXTENT_INLINE_DATA_START +
btrfs_file_extent_ram_bytes(leaf, fi))) {
file_extent_err(leaf, slot,
"invalid ram_bytes for uncompressed inline extent, have %u expect %llu",
item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START +
btrfs_file_extent_ram_bytes(leaf, fi));
return -EUCLEAN;
}
return 0;
}
/* Regular or preallocated extent has fixed item size */
if (unlikely(item_size != sizeof(*fi))) {
file_extent_err(leaf, slot,
"invalid item size for reg/prealloc file extent, have %u expect %zu",
item_size, sizeof(*fi));
return -EUCLEAN;
}
if (unlikely(CHECK_FE_ALIGNED(leaf, slot, fi, ram_bytes, sectorsize) ||
CHECK_FE_ALIGNED(leaf, slot, fi, disk_bytenr, sectorsize) ||
CHECK_FE_ALIGNED(leaf, slot, fi, disk_num_bytes, sectorsize) ||
CHECK_FE_ALIGNED(leaf, slot, fi, offset, sectorsize) ||
CHECK_FE_ALIGNED(leaf, slot, fi, num_bytes, sectorsize)))
return -EUCLEAN;
/* Catch extent end overflow */
if (unlikely(check_add_overflow(btrfs_file_extent_num_bytes(leaf, fi),
key->offset, &extent_end))) {
file_extent_err(leaf, slot,
"extent end overflow, have file offset %llu extent num bytes %llu",
key->offset,
btrfs_file_extent_num_bytes(leaf, fi));
return -EUCLEAN;
}
/*
* Check that no two consecutive file extent items, in the same leaf,
* present ranges that overlap each other.
*/
if (slot > 0 &&
prev_key->objectid == key->objectid &&
prev_key->type == BTRFS_EXTENT_DATA_KEY) {
struct btrfs_file_extent_item *prev_fi;
u64 prev_end;
prev_fi = btrfs_item_ptr(leaf, slot - 1,
struct btrfs_file_extent_item);
prev_end = file_extent_end(leaf, prev_key, prev_fi);
if (unlikely(prev_end > key->offset)) {
file_extent_err(leaf, slot - 1,
"file extent end range (%llu) goes beyond start offset (%llu) of the next file extent",
prev_end, key->offset);
return -EUCLEAN;
}
}
return 0;
}
static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key,
int slot, struct btrfs_key *prev_key)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
u32 sectorsize = fs_info->sectorsize;
const u32 csumsize = fs_info->csum_size;
if (unlikely(key->objectid != BTRFS_EXTENT_CSUM_OBJECTID)) {
generic_err(leaf, slot,
"invalid key objectid for csum item, have %llu expect %llu",
key->objectid, BTRFS_EXTENT_CSUM_OBJECTID);
return -EUCLEAN;
}
if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) {
generic_err(leaf, slot,
"unaligned key offset for csum item, have %llu should be aligned to %u",
key->offset, sectorsize);
return -EUCLEAN;
}
if (unlikely(!IS_ALIGNED(btrfs_item_size_nr(leaf, slot), csumsize))) {
generic_err(leaf, slot,
"unaligned item size for csum item, have %u should be aligned to %u",
btrfs_item_size_nr(leaf, slot), csumsize);
return -EUCLEAN;
}
if (slot > 0 && prev_key->type == BTRFS_EXTENT_CSUM_KEY) {
u64 prev_csum_end;
u32 prev_item_size;
prev_item_size = btrfs_item_size_nr(leaf, slot - 1);
prev_csum_end = (prev_item_size / csumsize) * sectorsize;
prev_csum_end += prev_key->offset;
if (unlikely(prev_csum_end > key->offset)) {
generic_err(leaf, slot - 1,
"csum end range (%llu) goes beyond the start range (%llu) of the next csum item",
prev_csum_end, key->offset);
return -EUCLEAN;
}
}
return 0;
}
/* Inode item error output has the same format as dir_item_err() */
#define inode_item_err(eb, slot, fmt, ...) \
dir_item_err(eb, slot, fmt, __VA_ARGS__)
static int check_inode_key(struct extent_buffer *leaf, struct btrfs_key *key,
int slot)
{
struct btrfs_key item_key;
bool is_inode_item;
btrfs_item_key_to_cpu(leaf, &item_key, slot);
is_inode_item = (item_key.type == BTRFS_INODE_ITEM_KEY);
/* For XATTR_ITEM, location key should be all 0 */
if (item_key.type == BTRFS_XATTR_ITEM_KEY) {
if (unlikely(key->objectid != 0 || key->type != 0 ||
key->offset != 0))
return -EUCLEAN;
return 0;
}
if (unlikely((key->objectid < BTRFS_FIRST_FREE_OBJECTID ||
key->objectid > BTRFS_LAST_FREE_OBJECTID) &&
key->objectid != BTRFS_ROOT_TREE_DIR_OBJECTID &&
key->objectid != BTRFS_FREE_INO_OBJECTID)) {
if (is_inode_item) {
generic_err(leaf, slot,
"invalid key objectid: has %llu expect %llu or [%llu, %llu] or %llu",
key->objectid, BTRFS_ROOT_TREE_DIR_OBJECTID,
BTRFS_FIRST_FREE_OBJECTID,
BTRFS_LAST_FREE_OBJECTID,
BTRFS_FREE_INO_OBJECTID);
} else {
dir_item_err(leaf, slot,
"invalid location key objectid: has %llu expect %llu or [%llu, %llu] or %llu",
key->objectid, BTRFS_ROOT_TREE_DIR_OBJECTID,
BTRFS_FIRST_FREE_OBJECTID,
BTRFS_LAST_FREE_OBJECTID,
BTRFS_FREE_INO_OBJECTID);
}
return -EUCLEAN;
}
if (unlikely(key->offset != 0)) {
if (is_inode_item)
inode_item_err(leaf, slot,
"invalid key offset: has %llu expect 0",
key->offset);
else
dir_item_err(leaf, slot,
"invalid location key offset:has %llu expect 0",
key->offset);
return -EUCLEAN;
}
return 0;
}
static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key,
int slot)
{
struct btrfs_key item_key;
bool is_root_item;
btrfs_item_key_to_cpu(leaf, &item_key, slot);
is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY);
/* No such tree id */
if (unlikely(key->objectid == 0)) {
if (is_root_item)
generic_err(leaf, slot, "invalid root id 0");
else
dir_item_err(leaf, slot,
"invalid location key root id 0");
return -EUCLEAN;
}
/* DIR_ITEM/INDEX/INODE_REF is not allowed to point to non-fs trees */
if (unlikely(!is_fstree(key->objectid) && !is_root_item)) {
dir_item_err(leaf, slot,
"invalid location key objectid, have %llu expect [%llu, %llu]",
key->objectid, BTRFS_FIRST_FREE_OBJECTID,
BTRFS_LAST_FREE_OBJECTID);
return -EUCLEAN;
}
/*
* ROOT_ITEM with non-zero offset means this is a snapshot, created at
* @offset transid.
* Furthermore, for location key in DIR_ITEM, its offset is always -1.
*
* So here we only check offset for reloc tree whose key->offset must
* be a valid tree.
*/
if (unlikely(key->objectid == BTRFS_TREE_RELOC_OBJECTID &&
key->offset == 0)) {
generic_err(leaf, slot, "invalid root id 0 for reloc tree");
return -EUCLEAN;
}
return 0;
}
static int check_dir_item(struct extent_buffer *leaf,
struct btrfs_key *key, struct btrfs_key *prev_key,
int slot)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_dir_item *di;
u32 item_size = btrfs_item_size_nr(leaf, slot);
u32 cur = 0;
if (unlikely(!check_prev_ino(leaf, key, slot, prev_key)))
return -EUCLEAN;
di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
while (cur < item_size) {
struct btrfs_key location_key;
u32 name_len;
u32 data_len;
u32 max_name_len;
u32 total_size;
u32 name_hash;
u8 dir_type;
int ret;
/* header itself should not cross item boundary */
if (unlikely(cur + sizeof(*di) > item_size)) {
dir_item_err(leaf, slot,
"dir item header crosses item boundary, have %zu boundary %u",
cur + sizeof(*di), item_size);
return -EUCLEAN;
}
/* Location key check */
btrfs_dir_item_key_to_cpu(leaf, di, &location_key);
if (location_key.type == BTRFS_ROOT_ITEM_KEY) {
ret = check_root_key(leaf, &location_key, slot);
if (unlikely(ret < 0))
return ret;
} else if (location_key.type == BTRFS_INODE_ITEM_KEY ||
location_key.type == 0) {
ret = check_inode_key(leaf, &location_key, slot);
if (unlikely(ret < 0))
return ret;
} else {
dir_item_err(leaf, slot,
"invalid location key type, have %u, expect %u or %u",
location_key.type, BTRFS_ROOT_ITEM_KEY,
BTRFS_INODE_ITEM_KEY);
return -EUCLEAN;
}
/* dir type check */
dir_type = btrfs_dir_type(leaf, di);
if (unlikely(dir_type >= BTRFS_FT_MAX)) {
dir_item_err(leaf, slot,
"invalid dir item type, have %u expect [0, %u)",
dir_type, BTRFS_FT_MAX);
return -EUCLEAN;
}
if (unlikely(key->type == BTRFS_XATTR_ITEM_KEY &&
dir_type != BTRFS_FT_XATTR)) {
dir_item_err(leaf, slot,
"invalid dir item type for XATTR key, have %u expect %u",
dir_type, BTRFS_FT_XATTR);
return -EUCLEAN;
}
if (unlikely(dir_type == BTRFS_FT_XATTR &&
key->type != BTRFS_XATTR_ITEM_KEY)) {
dir_item_err(leaf, slot,
"xattr dir type found for non-XATTR key");
return -EUCLEAN;
}
if (dir_type == BTRFS_FT_XATTR)
max_name_len = XATTR_NAME_MAX;
else
max_name_len = BTRFS_NAME_LEN;
/* Name/data length check */
name_len = btrfs_dir_name_len(leaf, di);
data_len = btrfs_dir_data_len(leaf, di);
if (unlikely(name_len > max_name_len)) {
dir_item_err(leaf, slot,
"dir item name len too long, have %u max %u",
name_len, max_name_len);
return -EUCLEAN;
}
if (unlikely(name_len + data_len > BTRFS_MAX_XATTR_SIZE(fs_info))) {
dir_item_err(leaf, slot,
"dir item name and data len too long, have %u max %u",
name_len + data_len,
BTRFS_MAX_XATTR_SIZE(fs_info));
return -EUCLEAN;
}
if (unlikely(data_len && dir_type != BTRFS_FT_XATTR)) {
dir_item_err(leaf, slot,
"dir item with invalid data len, have %u expect 0",
data_len);
return -EUCLEAN;
}
total_size = sizeof(*di) + name_len + data_len;
/* header and name/data should not cross item boundary */
if (unlikely(cur + total_size > item_size)) {
dir_item_err(leaf, slot,
"dir item data crosses item boundary, have %u boundary %u",
cur + total_size, item_size);
return -EUCLEAN;
}
/*
* Special check for XATTR/DIR_ITEM, as key->offset is name
* hash, should match its name
*/
if (key->type == BTRFS_DIR_ITEM_KEY ||
key->type == BTRFS_XATTR_ITEM_KEY) {
char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
read_extent_buffer(leaf, namebuf,
(unsigned long)(di + 1), name_len);
name_hash = btrfs_name_hash(namebuf, name_len);
if (unlikely(key->offset != name_hash)) {
dir_item_err(leaf, slot,
"name hash mismatch with key, have 0x%016x expect 0x%016llx",
name_hash, key->offset);
return -EUCLEAN;
}
}
cur += total_size;
di = (struct btrfs_dir_item *)((void *)di + total_size);
}
return 0;
}
__printf(3, 4)
__cold
static void block_group_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_key key;
struct va_format vaf;
va_list args;
btrfs_item_key_to_cpu(eb, &key, slot);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(fs_info,
"corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
key.objectid, key.offset, &vaf);
va_end(args);
}
static int check_block_group_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
struct btrfs_block_group_item bgi;
u32 item_size = btrfs_item_size_nr(leaf, slot);
u64 flags;
u64 type;
/*
* Here we don't really care about alignment since extent allocator can
* handle it. We care more about the size.
*/
if (unlikely(key->offset == 0)) {
block_group_err(leaf, slot,
"invalid block group size 0");
return -EUCLEAN;
}
if (unlikely(item_size != sizeof(bgi))) {
block_group_err(leaf, slot,
"invalid item size, have %u expect %zu",
item_size, sizeof(bgi));
return -EUCLEAN;
}
read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
sizeof(bgi));
if (unlikely(btrfs_stack_block_group_chunk_objectid(&bgi) !=
BTRFS_FIRST_CHUNK_TREE_OBJECTID)) {
block_group_err(leaf, slot,
"invalid block group chunk objectid, have %llu expect %llu",
btrfs_stack_block_group_chunk_objectid(&bgi),
BTRFS_FIRST_CHUNK_TREE_OBJECTID);
return -EUCLEAN;
}
if (unlikely(btrfs_stack_block_group_used(&bgi) > key->offset)) {
block_group_err(leaf, slot,
"invalid block group used, have %llu expect [0, %llu)",
btrfs_stack_block_group_used(&bgi), key->offset);
return -EUCLEAN;
}
flags = btrfs_stack_block_group_flags(&bgi);
if (unlikely(hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1)) {
block_group_err(leaf, slot,
"invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
flags & BTRFS_BLOCK_GROUP_PROFILE_MASK,
hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK));
return -EUCLEAN;
}
type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
if (unlikely(type != BTRFS_BLOCK_GROUP_DATA &&
type != BTRFS_BLOCK_GROUP_METADATA &&
type != BTRFS_BLOCK_GROUP_SYSTEM &&
type != (BTRFS_BLOCK_GROUP_METADATA |
BTRFS_BLOCK_GROUP_DATA))) {
block_group_err(leaf, slot,
"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx",
type, hweight64(type),
BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA,
BTRFS_BLOCK_GROUP_SYSTEM,
BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA);
return -EUCLEAN;
}
return 0;
}
__printf(4, 5)
__cold
static void chunk_err(const struct extent_buffer *leaf,
const struct btrfs_chunk *chunk, u64 logical,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = leaf->fs_info;
bool is_sb;
struct va_format vaf;
va_list args;
int i;
int slot = -1;
/* Only superblock eb is able to have such small offset */
is_sb = (leaf->start == BTRFS_SUPER_INFO_OFFSET);
if (!is_sb) {
/*
* Get the slot number by iterating through all slots, this
* would provide better readability.
*/
for (i = 0; i < btrfs_header_nritems(leaf); i++) {
if (btrfs_item_ptr_offset(leaf, i) ==
(unsigned long)chunk) {
slot = i;
break;
}
}
}
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (is_sb)
btrfs_crit(fs_info,
"corrupt superblock syschunk array: chunk_start=%llu, %pV",
logical, &vaf);
else
btrfs_crit(fs_info,
"corrupt leaf: root=%llu block=%llu slot=%d chunk_start=%llu, %pV",
BTRFS_CHUNK_TREE_OBJECTID, leaf->start, slot,
logical, &vaf);
va_end(args);
}
/*
* The common chunk check which could also work on super block sys chunk array.
*
* Return -EUCLEAN if anything is corrupted.
* Return 0 if everything is OK.
*/
int btrfs_check_chunk_valid(struct extent_buffer *leaf,
struct btrfs_chunk *chunk, u64 logical)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
u64 length;
u64 chunk_end;
u64 stripe_len;
u16 num_stripes;
u16 sub_stripes;
u64 type;
u64 features;
bool mixed = false;
int raid_index;
int nparity;
int ncopies;
length = btrfs_chunk_length(leaf, chunk);
stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
type = btrfs_chunk_type(leaf, chunk);
raid_index = btrfs_bg_flags_to_raid_index(type);
ncopies = btrfs_raid_array[raid_index].ncopies;
nparity = btrfs_raid_array[raid_index].nparity;
if (unlikely(!num_stripes)) {
chunk_err(leaf, chunk, logical,
"invalid chunk num_stripes, have %u", num_stripes);
return -EUCLEAN;
}
if (unlikely(num_stripes < ncopies)) {
chunk_err(leaf, chunk, logical,
"invalid chunk num_stripes < ncopies, have %u < %d",
num_stripes, ncopies);
return -EUCLEAN;
}
if (unlikely(nparity && num_stripes == nparity)) {
chunk_err(leaf, chunk, logical,
"invalid chunk num_stripes == nparity, have %u == %d",
num_stripes, nparity);
return -EUCLEAN;
}
if (unlikely(!IS_ALIGNED(logical, fs_info->sectorsize))) {
chunk_err(leaf, chunk, logical,
"invalid chunk logical, have %llu should aligned to %u",
logical, fs_info->sectorsize);
return -EUCLEAN;
}
if (unlikely(btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize)) {
chunk_err(leaf, chunk, logical,
"invalid chunk sectorsize, have %u expect %u",
btrfs_chunk_sector_size(leaf, chunk),
fs_info->sectorsize);
return -EUCLEAN;
}
if (unlikely(!length || !IS_ALIGNED(length, fs_info->sectorsize))) {
chunk_err(leaf, chunk, logical,
"invalid chunk length, have %llu", length);
return -EUCLEAN;
}
if (unlikely(check_add_overflow(logical, length, &chunk_end))) {
chunk_err(leaf, chunk, logical,
"invalid chunk logical start and length, have logical start %llu length %llu",
logical, length);
return -EUCLEAN;
}
if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) {
chunk_err(leaf, chunk, logical,
"invalid chunk stripe length: %llu",
stripe_len);
return -EUCLEAN;
}
if (unlikely(type & ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
BTRFS_BLOCK_GROUP_PROFILE_MASK))) {
chunk_err(leaf, chunk, logical,
"unrecognized chunk type: 0x%llx",
~(BTRFS_BLOCK_GROUP_TYPE_MASK |
BTRFS_BLOCK_GROUP_PROFILE_MASK) &
btrfs_chunk_type(leaf, chunk));
return -EUCLEAN;
}
if (unlikely(!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0)) {
chunk_err(leaf, chunk, logical,
"invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set",
type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
return -EUCLEAN;
}
if (unlikely((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0)) {
chunk_err(leaf, chunk, logical,
"missing chunk type flag, have 0x%llx one bit must be set in 0x%llx",
type, BTRFS_BLOCK_GROUP_TYPE_MASK);
return -EUCLEAN;
}
if (unlikely((type & BTRFS_BLOCK_GROUP_SYSTEM) &&
(type & (BTRFS_BLOCK_GROUP_METADATA |
BTRFS_BLOCK_GROUP_DATA)))) {
chunk_err(leaf, chunk, logical,
"system chunk with data or metadata type: 0x%llx",
type);
return -EUCLEAN;
}
features = btrfs_super_incompat_flags(fs_info->super_copy);
if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
mixed = true;
if (!mixed) {
if (unlikely((type & BTRFS_BLOCK_GROUP_METADATA) &&
(type & BTRFS_BLOCK_GROUP_DATA))) {
chunk_err(leaf, chunk, logical,
"mixed chunk type in non-mixed mode: 0x%llx", type);
return -EUCLEAN;
}
}
if (unlikely((type & BTRFS_BLOCK_GROUP_RAID10 &&
sub_stripes != btrfs_raid_array[BTRFS_RAID_RAID10].sub_stripes) ||
(type & BTRFS_BLOCK_GROUP_RAID1 &&
num_stripes != btrfs_raid_array[BTRFS_RAID_RAID1].devs_min) ||
(type & BTRFS_BLOCK_GROUP_RAID1C3 &&
num_stripes != btrfs_raid_array[BTRFS_RAID_RAID1C3].devs_min) ||
(type & BTRFS_BLOCK_GROUP_RAID1C4 &&
num_stripes != btrfs_raid_array[BTRFS_RAID_RAID1C4].devs_min) ||
(type & BTRFS_BLOCK_GROUP_RAID5 &&
num_stripes < btrfs_raid_array[BTRFS_RAID_RAID5].devs_min) ||
(type & BTRFS_BLOCK_GROUP_RAID6 &&
num_stripes < btrfs_raid_array[BTRFS_RAID_RAID6].devs_min) ||
(type & BTRFS_BLOCK_GROUP_DUP &&
num_stripes != btrfs_raid_array[BTRFS_RAID_DUP].dev_stripes) ||
((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 &&
num_stripes != btrfs_raid_array[BTRFS_RAID_SINGLE].dev_stripes))) {
chunk_err(leaf, chunk, logical,
"invalid num_stripes:sub_stripes %u:%u for profile %llu",
num_stripes, sub_stripes,
type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
return -EUCLEAN;
}
return 0;
}
/*
* Enhanced version of chunk item checker.
*
* The common btrfs_check_chunk_valid() doesn't check item size since it needs
* to work on super block sys_chunk_array which doesn't have full item ptr.
*/
static int check_leaf_chunk_item(struct extent_buffer *leaf,
struct btrfs_chunk *chunk,
struct btrfs_key *key, int slot)
{
int num_stripes;
if (unlikely(btrfs_item_size_nr(leaf, slot) < sizeof(struct btrfs_chunk))) {
chunk_err(leaf, chunk, key->offset,
"invalid chunk item size: have %u expect [%zu, %u)",
btrfs_item_size_nr(leaf, slot),
sizeof(struct btrfs_chunk),
BTRFS_LEAF_DATA_SIZE(leaf->fs_info));
return -EUCLEAN;
}
num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
/* Let btrfs_check_chunk_valid() handle this error type */
if (num_stripes == 0)
goto out;
if (unlikely(btrfs_chunk_item_size(num_stripes) !=
btrfs_item_size_nr(leaf, slot))) {
chunk_err(leaf, chunk, key->offset,
"invalid chunk item size: have %u expect %lu",
btrfs_item_size_nr(leaf, slot),
btrfs_chunk_item_size(num_stripes));
return -EUCLEAN;
}
out:
return btrfs_check_chunk_valid(leaf, chunk, key->offset);
}
__printf(3, 4)
__cold
static void dev_item_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
struct btrfs_key key;
struct va_format vaf;
va_list args;
btrfs_item_key_to_cpu(eb, &key, slot);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(eb->fs_info,
"corrupt %s: root=%llu block=%llu slot=%d devid=%llu %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
key.objectid, &vaf);
va_end(args);
}
static int check_dev_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
struct btrfs_dev_item *ditem;
if (unlikely(key->objectid != BTRFS_DEV_ITEMS_OBJECTID)) {
dev_item_err(leaf, slot,
"invalid objectid: has=%llu expect=%llu",
key->objectid, BTRFS_DEV_ITEMS_OBJECTID);
return -EUCLEAN;
}
ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item);
if (unlikely(btrfs_device_id(leaf, ditem) != key->offset)) {
dev_item_err(leaf, slot,
"devid mismatch: key has=%llu item has=%llu",
key->offset, btrfs_device_id(leaf, ditem));
return -EUCLEAN;
}
/*
* For device total_bytes, we don't have reliable way to check it, as
* it can be 0 for device removal. Device size check can only be done
* by dev extents check.
*/
if (unlikely(btrfs_device_bytes_used(leaf, ditem) >
btrfs_device_total_bytes(leaf, ditem))) {
dev_item_err(leaf, slot,
"invalid bytes used: have %llu expect [0, %llu]",
btrfs_device_bytes_used(leaf, ditem),
btrfs_device_total_bytes(leaf, ditem));
return -EUCLEAN;
}
/*
* Remaining members like io_align/type/gen/dev_group aren't really
* utilized. Skip them to make later usage of them easier.
*/
return 0;