forked from skristiansson/linux
-
Notifications
You must be signed in to change notification settings - Fork 14
/
Copy pathxattr.c
1788 lines (1622 loc) · 48.2 KB
/
xattr.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
/*
* linux/fs/ext4/xattr.c
*
* Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
*
* Fix by Harrison Xing <harrison@mountainviewdata.com>.
* Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>.
* Extended attributes for symlinks and special files added per
* suggestion of Luka Renko <luka.renko@hermes.si>.
* xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>,
* Red Hat Inc.
* ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz
* and Andreas Gruenbacher <agruen@suse.de>.
*/
/*
* Extended attributes are stored directly in inodes (on file systems with
* inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl
* field contains the block number if an inode uses an additional block. All
* attributes must fit in the inode and one additional block. Blocks that
* contain the identical set of attributes may be shared among several inodes.
* Identical blocks are detected by keeping a cache of blocks that have
* recently been accessed.
*
* The attributes in inodes and on blocks have a different header; the entries
* are stored in the same format:
*
* +------------------+
* | header |
* | entry 1 | |
* | entry 2 | | growing downwards
* | entry 3 | v
* | four null bytes |
* | . . . |
* | value 1 | ^
* | value 3 | | growing upwards
* | value 2 | |
* +------------------+
*
* The header is followed by multiple entry descriptors. In disk blocks, the
* entry descriptors are kept sorted. In inodes, they are unsorted. The
* attribute values are aligned to the end of the block in no specific order.
*
* Locking strategy
* ----------------
* EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem.
* EA blocks are only changed if they are exclusive to an inode, so
* holding xattr_sem also means that nothing but the EA block's reference
* count can change. Multiple writers to the same block are synchronized
* by the buffer lock.
*/
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/mbcache.h>
#include <linux/quotaops.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include "xattr.h"
#include "acl.h"
#ifdef EXT4_XATTR_DEBUG
# define ea_idebug(inode, f...) do { \
printk(KERN_DEBUG "inode %s:%lu: ", \
inode->i_sb->s_id, inode->i_ino); \
printk(f); \
printk("\n"); \
} while (0)
# define ea_bdebug(bh, f...) do { \
printk(KERN_DEBUG "block %pg:%lu: ", \
bh->b_bdev, (unsigned long) bh->b_blocknr); \
printk(f); \
printk("\n"); \
} while (0)
#else
# define ea_idebug(inode, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
# define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
static struct buffer_head *ext4_xattr_cache_find(struct inode *,
struct ext4_xattr_header *,
struct mb_cache_entry **);
static void ext4_xattr_rehash(struct ext4_xattr_header *,
struct ext4_xattr_entry *);
static int ext4_xattr_list(struct dentry *dentry, char *buffer,
size_t buffer_size);
static const struct xattr_handler *ext4_xattr_handler_map[] = {
[EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler,
#ifdef CONFIG_EXT4_FS_POSIX_ACL
[EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler,
[EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
#endif
[EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4_FS_SECURITY
[EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler,
#endif
};
const struct xattr_handler *ext4_xattr_handlers[] = {
&ext4_xattr_user_handler,
&ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4_FS_POSIX_ACL
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
#ifdef CONFIG_EXT4_FS_SECURITY
&ext4_xattr_security_handler,
#endif
NULL
};
#define EXT4_GET_MB_CACHE(inode) (((struct ext4_sb_info *) \
inode->i_sb->s_fs_info)->s_mb_cache)
static __le32 ext4_xattr_block_csum(struct inode *inode,
sector_t block_nr,
struct ext4_xattr_header *hdr)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
__le64 dsk_block_nr = cpu_to_le64(block_nr);
__u32 dummy_csum = 0;
int offset = offsetof(struct ext4_xattr_header, h_checksum);
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr,
sizeof(dsk_block_nr));
csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset);
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
offset += sizeof(dummy_csum);
csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset,
EXT4_BLOCK_SIZE(inode->i_sb) - offset);
return cpu_to_le32(csum);
}
static int ext4_xattr_block_csum_verify(struct inode *inode,
sector_t block_nr,
struct ext4_xattr_header *hdr)
{
if (ext4_has_metadata_csum(inode->i_sb) &&
(hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr)))
return 0;
return 1;
}
static void ext4_xattr_block_csum_set(struct inode *inode,
sector_t block_nr,
struct ext4_xattr_header *hdr)
{
if (!ext4_has_metadata_csum(inode->i_sb))
return;
hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr);
}
static inline int ext4_handle_dirty_xattr_block(handle_t *handle,
struct inode *inode,
struct buffer_head *bh)
{
ext4_xattr_block_csum_set(inode, bh->b_blocknr, BHDR(bh));
return ext4_handle_dirty_metadata(handle, inode, bh);
}
static inline const struct xattr_handler *
ext4_xattr_handler(int name_index)
{
const struct xattr_handler *handler = NULL;
if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map))
handler = ext4_xattr_handler_map[name_index];
return handler;
}
/*
* Inode operation listxattr()
*
* d_inode(dentry)->i_mutex: don't care
*/
ssize_t
ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
return ext4_xattr_list(dentry, buffer, size);
}
static int
ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
void *value_start)
{
struct ext4_xattr_entry *e = entry;
while (!IS_LAST_ENTRY(e)) {
struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
if ((void *)next >= end)
return -EFSCORRUPTED;
e = next;
}
while (!IS_LAST_ENTRY(entry)) {
if (entry->e_value_size != 0 &&
(value_start + le16_to_cpu(entry->e_value_offs) <
(void *)e + sizeof(__u32) ||
value_start + le16_to_cpu(entry->e_value_offs) +
le32_to_cpu(entry->e_value_size) > end))
return -EFSCORRUPTED;
entry = EXT4_XATTR_NEXT(entry);
}
return 0;
}
static inline int
ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
{
int error;
if (buffer_verified(bh))
return 0;
if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
BHDR(bh)->h_blocks != cpu_to_le32(1))
return -EFSCORRUPTED;
if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh)))
return -EFSBADCRC;
error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size,
bh->b_data);
if (!error)
set_buffer_verified(bh);
return error;
}
static int
__xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
void *end, const char *function, unsigned int line)
{
struct ext4_xattr_entry *entry = IFIRST(header);
int error = -EFSCORRUPTED;
if (((void *) header >= end) ||
(header->h_magic != le32_to_cpu(EXT4_XATTR_MAGIC)))
goto errout;
error = ext4_xattr_check_names(entry, end, entry);
errout:
if (error)
__ext4_error_inode(inode, function, line, 0,
"corrupted in-inode xattr");
return error;
}
#define xattr_check_inode(inode, header, end) \
__xattr_check_inode((inode), (header), (end), __func__, __LINE__)
static inline int
ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size)
{
size_t value_size = le32_to_cpu(entry->e_value_size);
if (entry->e_value_block != 0 || value_size > size ||
le16_to_cpu(entry->e_value_offs) + value_size > size)
return -EFSCORRUPTED;
return 0;
}
static int
ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index,
const char *name, size_t size, int sorted)
{
struct ext4_xattr_entry *entry;
size_t name_len;
int cmp = 1;
if (name == NULL)
return -EINVAL;
name_len = strlen(name);
entry = *pentry;
for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
cmp = name_index - entry->e_name_index;
if (!cmp)
cmp = name_len - entry->e_name_len;
if (!cmp)
cmp = memcmp(name, entry->e_name, name_len);
if (cmp <= 0 && (sorted || cmp == 0))
break;
}
*pentry = entry;
if (!cmp && ext4_xattr_check_entry(entry, size))
return -EFSCORRUPTED;
return cmp ? -ENODATA : 0;
}
static int
ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
void *buffer, size_t buffer_size)
{
struct buffer_head *bh = NULL;
struct ext4_xattr_entry *entry;
size_t size;
int error;
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
name_index, name, buffer, (long)buffer_size);
error = -ENODATA;
if (!EXT4_I(inode)->i_file_acl)
goto cleanup;
ea_idebug(inode, "reading block %llu",
(unsigned long long)EXT4_I(inode)->i_file_acl);
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
if (!bh)
goto cleanup;
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
if (ext4_xattr_check_block(inode, bh)) {
bad_block:
EXT4_ERROR_INODE(inode, "bad block %llu",
EXT4_I(inode)->i_file_acl);
error = -EFSCORRUPTED;
goto cleanup;
}
ext4_xattr_cache_insert(ext4_mb_cache, bh);
entry = BFIRST(bh);
error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1);
if (error == -EFSCORRUPTED)
goto bad_block;
if (error)
goto cleanup;
size = le32_to_cpu(entry->e_value_size);
if (buffer) {
error = -ERANGE;
if (size > buffer_size)
goto cleanup;
memcpy(buffer, bh->b_data + le16_to_cpu(entry->e_value_offs),
size);
}
error = size;
cleanup:
brelse(bh);
return error;
}
int
ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
void *buffer, size_t buffer_size)
{
struct ext4_xattr_ibody_header *header;
struct ext4_xattr_entry *entry;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
size_t size;
void *end;
int error;
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return -ENODATA;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
entry = IFIRST(header);
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
error = xattr_check_inode(inode, header, end);
if (error)
goto cleanup;
error = ext4_xattr_find_entry(&entry, name_index, name,
end - (void *)entry, 0);
if (error)
goto cleanup;
size = le32_to_cpu(entry->e_value_size);
if (buffer) {
error = -ERANGE;
if (size > buffer_size)
goto cleanup;
memcpy(buffer, (void *)IFIRST(header) +
le16_to_cpu(entry->e_value_offs), size);
}
error = size;
cleanup:
brelse(iloc.bh);
return error;
}
/*
* ext4_xattr_get()
*
* Copy an extended attribute into the buffer
* provided, or compute the buffer size required.
* Buffer is NULL to compute the size of the buffer required.
*
* Returns a negative error number on failure, or the number of bytes
* used / required on success.
*/
int
ext4_xattr_get(struct inode *inode, int name_index, const char *name,
void *buffer, size_t buffer_size)
{
int error;
if (strlen(name) > 255)
return -ERANGE;
down_read(&EXT4_I(inode)->xattr_sem);
error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
buffer_size);
if (error == -ENODATA)
error = ext4_xattr_block_get(inode, name_index, name, buffer,
buffer_size);
up_read(&EXT4_I(inode)->xattr_sem);
return error;
}
static int
ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry,
char *buffer, size_t buffer_size)
{
size_t rest = buffer_size;
for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
const struct xattr_handler *handler =
ext4_xattr_handler(entry->e_name_index);
if (handler && (!handler->list || handler->list(dentry))) {
const char *prefix = handler->prefix ?: handler->name;
size_t prefix_len = strlen(prefix);
size_t size = prefix_len + entry->e_name_len + 1;
if (buffer) {
if (size > rest)
return -ERANGE;
memcpy(buffer, prefix, prefix_len);
buffer += prefix_len;
memcpy(buffer, entry->e_name, entry->e_name_len);
buffer += entry->e_name_len;
*buffer++ = 0;
}
rest -= size;
}
}
return buffer_size - rest; /* total size */
}
static int
ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
struct inode *inode = d_inode(dentry);
struct buffer_head *bh = NULL;
int error;
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ea_idebug(inode, "buffer=%p, buffer_size=%ld",
buffer, (long)buffer_size);
error = 0;
if (!EXT4_I(inode)->i_file_acl)
goto cleanup;
ea_idebug(inode, "reading block %llu",
(unsigned long long)EXT4_I(inode)->i_file_acl);
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
error = -EIO;
if (!bh)
goto cleanup;
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
if (ext4_xattr_check_block(inode, bh)) {
EXT4_ERROR_INODE(inode, "bad block %llu",
EXT4_I(inode)->i_file_acl);
error = -EFSCORRUPTED;
goto cleanup;
}
ext4_xattr_cache_insert(ext4_mb_cache, bh);
error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
cleanup:
brelse(bh);
return error;
}
static int
ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
struct inode *inode = d_inode(dentry);
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
void *end;
int error;
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return 0;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
error = xattr_check_inode(inode, header, end);
if (error)
goto cleanup;
error = ext4_xattr_list_entries(dentry, IFIRST(header),
buffer, buffer_size);
cleanup:
brelse(iloc.bh);
return error;
}
/*
* ext4_xattr_list()
*
* Copy a list of attribute names into the buffer
* provided, or compute the buffer size required.
* Buffer is NULL to compute the size of the buffer required.
*
* Returns a negative error number on failure, or the number of bytes
* used / required on success.
*/
static int
ext4_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
int ret, ret2;
down_read(&EXT4_I(d_inode(dentry))->xattr_sem);
ret = ret2 = ext4_xattr_ibody_list(dentry, buffer, buffer_size);
if (ret < 0)
goto errout;
if (buffer) {
buffer += ret;
buffer_size -= ret;
}
ret = ext4_xattr_block_list(dentry, buffer, buffer_size);
if (ret < 0)
goto errout;
ret += ret2;
errout:
up_read(&EXT4_I(d_inode(dentry))->xattr_sem);
return ret;
}
/*
* If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is
* not set, set it.
*/
static void ext4_xattr_update_super_block(handle_t *handle,
struct super_block *sb)
{
if (ext4_has_feature_xattr(sb))
return;
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
ext4_set_feature_xattr(sb);
ext4_handle_dirty_super(handle, sb);
}
}
/*
* Release the xattr block BH: If the reference count is > 1, decrement it;
* otherwise free the block.
*/
static void
ext4_xattr_release_block(handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
u32 hash, ref;
int error = 0;
BUFFER_TRACE(bh, "get_write_access");
error = ext4_journal_get_write_access(handle, bh);
if (error)
goto out;
lock_buffer(bh);
hash = le32_to_cpu(BHDR(bh)->h_hash);
ref = le32_to_cpu(BHDR(bh)->h_refcount);
if (ref == 1) {
ea_bdebug(bh, "refcount now=0; freeing");
/*
* This must happen under buffer lock for
* ext4_xattr_block_set() to reliably detect freed block
*/
mb_cache_entry_delete_block(ext4_mb_cache, hash, bh->b_blocknr);
get_bh(bh);
unlock_buffer(bh);
ext4_free_blocks(handle, inode, bh, 0, 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
} else {
ref--;
BHDR(bh)->h_refcount = cpu_to_le32(ref);
if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) {
struct mb_cache_entry *ce;
ce = mb_cache_entry_get(ext4_mb_cache, hash,
bh->b_blocknr);
if (ce) {
ce->e_reusable = 1;
mb_cache_entry_put(ext4_mb_cache, ce);
}
}
/*
* Beware of this ugliness: Releasing of xattr block references
* from different inodes can race and so we have to protect
* from a race where someone else frees the block (and releases
* its journal_head) before we are done dirtying the buffer. In
* nojournal mode this race is harmless and we actually cannot
* call ext4_handle_dirty_xattr_block() with locked buffer as
* that function can call sync_dirty_buffer() so for that case
* we handle the dirtying after unlocking the buffer.
*/
if (ext4_handle_valid(handle))
error = ext4_handle_dirty_xattr_block(handle, inode,
bh);
unlock_buffer(bh);
if (!ext4_handle_valid(handle))
error = ext4_handle_dirty_xattr_block(handle, inode,
bh);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
ea_bdebug(bh, "refcount now=%d; releasing",
le32_to_cpu(BHDR(bh)->h_refcount));
}
out:
ext4_std_error(inode->i_sb, error);
return;
}
/*
* Find the available free space for EAs. This also returns the total number of
* bytes used by EA entries.
*/
static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
size_t *min_offs, void *base, int *total)
{
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
if (!last->e_value_block && last->e_value_size) {
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < *min_offs)
*min_offs = offs;
}
if (total)
*total += EXT4_XATTR_LEN(last->e_name_len);
}
return (*min_offs - ((void *)last - base) - sizeof(__u32));
}
static int
ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
{
struct ext4_xattr_entry *last;
size_t free, min_offs = s->end - s->base, name_len = strlen(i->name);
/* Compute min_offs and last. */
last = s->first;
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
if (!last->e_value_block && last->e_value_size) {
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < min_offs)
min_offs = offs;
}
}
free = min_offs - ((void *)last - s->base) - sizeof(__u32);
if (!s->not_found) {
if (!s->here->e_value_block && s->here->e_value_size) {
size_t size = le32_to_cpu(s->here->e_value_size);
free += EXT4_XATTR_SIZE(size);
}
free += EXT4_XATTR_LEN(name_len);
}
if (i->value) {
if (free < EXT4_XATTR_LEN(name_len) +
EXT4_XATTR_SIZE(i->value_len))
return -ENOSPC;
}
if (i->value && s->not_found) {
/* Insert the new name. */
size_t size = EXT4_XATTR_LEN(name_len);
size_t rest = (void *)last - (void *)s->here + sizeof(__u32);
memmove((void *)s->here + size, s->here, rest);
memset(s->here, 0, size);
s->here->e_name_index = i->name_index;
s->here->e_name_len = name_len;
memcpy(s->here->e_name, i->name, name_len);
} else {
if (!s->here->e_value_block && s->here->e_value_size) {
void *first_val = s->base + min_offs;
size_t offs = le16_to_cpu(s->here->e_value_offs);
void *val = s->base + offs;
size_t size = EXT4_XATTR_SIZE(
le32_to_cpu(s->here->e_value_size));
if (i->value && size == EXT4_XATTR_SIZE(i->value_len)) {
/* The old and the new value have the same
size. Just replace. */
s->here->e_value_size =
cpu_to_le32(i->value_len);
if (i->value == EXT4_ZERO_XATTR_VALUE) {
memset(val, 0, size);
} else {
/* Clear pad bytes first. */
memset(val + size - EXT4_XATTR_PAD, 0,
EXT4_XATTR_PAD);
memcpy(val, i->value, i->value_len);
}
return 0;
}
/* Remove the old value. */
memmove(first_val + size, first_val, val - first_val);
memset(first_val, 0, size);
s->here->e_value_size = 0;
s->here->e_value_offs = 0;
min_offs += size;
/* Adjust all value offsets. */
last = s->first;
while (!IS_LAST_ENTRY(last)) {
size_t o = le16_to_cpu(last->e_value_offs);
if (!last->e_value_block &&
last->e_value_size && o < offs)
last->e_value_offs =
cpu_to_le16(o + size);
last = EXT4_XATTR_NEXT(last);
}
}
if (!i->value) {
/* Remove the old name. */
size_t size = EXT4_XATTR_LEN(name_len);
last = ENTRY((void *)last - size);
memmove(s->here, (void *)s->here + size,
(void *)last - (void *)s->here + sizeof(__u32));
memset(last, 0, size);
}
}
if (i->value) {
/* Insert the new value. */
s->here->e_value_size = cpu_to_le32(i->value_len);
if (i->value_len) {
size_t size = EXT4_XATTR_SIZE(i->value_len);
void *val = s->base + min_offs - size;
s->here->e_value_offs = cpu_to_le16(min_offs - size);
if (i->value == EXT4_ZERO_XATTR_VALUE) {
memset(val, 0, size);
} else {
/* Clear the pad bytes first. */
memset(val + size - EXT4_XATTR_PAD, 0,
EXT4_XATTR_PAD);
memcpy(val, i->value, i->value_len);
}
}
}
return 0;
}
struct ext4_xattr_block_find {
struct ext4_xattr_search s;
struct buffer_head *bh;
};
static int
ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
struct ext4_xattr_block_find *bs)
{
struct super_block *sb = inode->i_sb;
int error;
ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld",
i->name_index, i->name, i->value, (long)i->value_len);
if (EXT4_I(inode)->i_file_acl) {
/* The inode already has an extended attribute block. */
bs->bh = sb_bread(sb, EXT4_I(inode)->i_file_acl);
error = -EIO;
if (!bs->bh)
goto cleanup;
ea_bdebug(bs->bh, "b_count=%d, refcount=%d",
atomic_read(&(bs->bh->b_count)),
le32_to_cpu(BHDR(bs->bh)->h_refcount));
if (ext4_xattr_check_block(inode, bs->bh)) {
EXT4_ERROR_INODE(inode, "bad block %llu",
EXT4_I(inode)->i_file_acl);
error = -EFSCORRUPTED;
goto cleanup;
}
/* Find the named attribute. */
bs->s.base = BHDR(bs->bh);
bs->s.first = BFIRST(bs->bh);
bs->s.end = bs->bh->b_data + bs->bh->b_size;
bs->s.here = bs->s.first;
error = ext4_xattr_find_entry(&bs->s.here, i->name_index,
i->name, bs->bh->b_size, 1);
if (error && error != -ENODATA)
goto cleanup;
bs->s.not_found = error;
}
error = 0;
cleanup:
return error;
}
static int
ext4_xattr_block_set(handle_t *handle, struct inode *inode,
struct ext4_xattr_info *i,
struct ext4_xattr_block_find *bs)
{
struct super_block *sb = inode->i_sb;
struct buffer_head *new_bh = NULL;
struct ext4_xattr_search *s = &bs->s;
struct mb_cache_entry *ce = NULL;
int error = 0;
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
#define header(x) ((struct ext4_xattr_header *)(x))
if (i->value && i->value_len > sb->s_blocksize)
return -ENOSPC;
if (s->base) {
BUFFER_TRACE(bs->bh, "get_write_access");
error = ext4_journal_get_write_access(handle, bs->bh);
if (error)
goto cleanup;
lock_buffer(bs->bh);
if (header(s->base)->h_refcount == cpu_to_le32(1)) {
__u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash);
/*
* This must happen under buffer lock for
* ext4_xattr_block_set() to reliably detect modified
* block
*/
mb_cache_entry_delete_block(ext4_mb_cache, hash,
bs->bh->b_blocknr);
ea_bdebug(bs->bh, "modifying in-place");
error = ext4_xattr_set_entry(i, s);
if (!error) {
if (!IS_LAST_ENTRY(s->first))
ext4_xattr_rehash(header(s->base),
s->here);
ext4_xattr_cache_insert(ext4_mb_cache,
bs->bh);
}
unlock_buffer(bs->bh);
if (error == -EFSCORRUPTED)
goto bad_block;
if (!error)
error = ext4_handle_dirty_xattr_block(handle,
inode,
bs->bh);
if (error)
goto cleanup;
goto inserted;
} else {
int offset = (char *)s->here - bs->bh->b_data;
unlock_buffer(bs->bh);
ea_bdebug(bs->bh, "cloning");
s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
error = -ENOMEM;
if (s->base == NULL)
goto cleanup;
memcpy(s->base, BHDR(bs->bh), bs->bh->b_size);
s->first = ENTRY(header(s->base)+1);
header(s->base)->h_refcount = cpu_to_le32(1);
s->here = ENTRY(s->base + offset);
s->end = s->base + bs->bh->b_size;
}
} else {
/* Allocate a buffer where we construct the new block. */
s->base = kzalloc(sb->s_blocksize, GFP_NOFS);
/* assert(header == s->base) */
error = -ENOMEM;
if (s->base == NULL)
goto cleanup;
header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
header(s->base)->h_blocks = cpu_to_le32(1);
header(s->base)->h_refcount = cpu_to_le32(1);
s->first = ENTRY(header(s->base)+1);
s->here = ENTRY(header(s->base)+1);
s->end = s->base + sb->s_blocksize;
}
error = ext4_xattr_set_entry(i, s);
if (error == -EFSCORRUPTED)
goto bad_block;
if (error)
goto cleanup;
if (!IS_LAST_ENTRY(s->first))
ext4_xattr_rehash(header(s->base), s->here);
inserted:
if (!IS_LAST_ENTRY(s->first)) {
new_bh = ext4_xattr_cache_find(inode, header(s->base), &ce);
if (new_bh) {
/* We found an identical block in the cache. */
if (new_bh == bs->bh)
ea_bdebug(new_bh, "keeping");
else {
u32 ref;
/* The old block is released after updating
the inode. */
error = dquot_alloc_block(inode,
EXT4_C2B(EXT4_SB(sb), 1));
if (error)
goto cleanup;
BUFFER_TRACE(new_bh, "get_write_access");
error = ext4_journal_get_write_access(handle,
new_bh);
if (error)
goto cleanup_dquot;
lock_buffer(new_bh);
/*
* We have to be careful about races with
* freeing, rehashing or adding references to
* xattr block. Once we hold buffer lock xattr
* block's state is stable so we can check
* whether the block got freed / rehashed or
* not. Since we unhash mbcache entry under
* buffer lock when freeing / rehashing xattr
* block, checking whether entry is still
* hashed is reliable. Same rules hold for
* e_reusable handling.
*/
if (hlist_bl_unhashed(&ce->e_hash_list) ||
!ce->e_reusable) {
/*
* Undo everything and check mbcache
* again.
*/
unlock_buffer(new_bh);
dquot_free_block(inode,
EXT4_C2B(EXT4_SB(sb),
1));
brelse(new_bh);
mb_cache_entry_put(ext4_mb_cache, ce);
ce = NULL;
new_bh = NULL;
goto inserted;
}
ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
BHDR(new_bh)->h_refcount = cpu_to_le32(ref);
if (ref >= EXT4_XATTR_REFCOUNT_MAX)
ce->e_reusable = 0;
ea_bdebug(new_bh, "reusing; refcount now=%d",
ref);
unlock_buffer(new_bh);
error = ext4_handle_dirty_xattr_block(handle,
inode,
new_bh);
if (error)
goto cleanup_dquot;
}
mb_cache_entry_touch(ext4_mb_cache, ce);
mb_cache_entry_put(ext4_mb_cache, ce);
ce = NULL;
} else if (bs->bh && s->base == bs->bh->b_data) {
/* We were modifying this block in-place. */
ea_bdebug(bs->bh, "keeping this block");
new_bh = bs->bh;
get_bh(new_bh);
} else {
/* We need to allocate a new block */
ext4_fsblk_t goal, block;
goal = ext4_group_first_block_no(sb,
EXT4_I(inode)->i_block_group);
/* non-extent files can't have physical blocks past 2^32 */
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
block = ext4_new_meta_blocks(handle, inode, goal, 0,
NULL, &error);
if (error)
goto cleanup;
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
ea_idebug(inode, "creating block %llu",
(unsigned long long)block);
new_bh = sb_getblk(sb, block);
if (unlikely(!new_bh)) {
error = -ENOMEM;
getblk_failed:
ext4_free_blocks(handle, inode, NULL, block, 1,
EXT4_FREE_BLOCKS_METADATA);