forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathdir.c
1757 lines (1529 loc) · 43 KB
/
dir.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
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* dir.c
*
* Creates, reads, walks and deletes directory-nodes
*
* Copyright (C) 2002, 2004 Oracle. All rights reserved.
*
* Portions of this code from linux/fs/ext3/dir.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card ([email protected])
* Laboratoire MASI - Institut Blaise pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/dir.c
*
* Copyright (C) 1991, 1992 Linux Torvalds
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* 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/fs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#define MLOG_MASK_PREFIX ML_NAMEI
#include <cluster/masklog.h>
#include "ocfs2.h"
#include "alloc.h"
#include "dir.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "file.h"
#include "inode.h"
#include "journal.h"
#include "namei.h"
#include "suballoc.h"
#include "super.h"
#include "uptodate.h"
#include "buffer_head_io.h"
#define NAMEI_RA_CHUNKS 2
#define NAMEI_RA_BLOCKS 4
#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b))
static unsigned char ocfs2_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
static int ocfs2_extend_dir(struct ocfs2_super *osb,
struct inode *dir,
struct buffer_head *parent_fe_bh,
unsigned int blocks_wanted,
struct buffer_head **new_de_bh);
static int ocfs2_do_extend_dir(struct super_block *sb,
handle_t *handle,
struct inode *dir,
struct buffer_head *parent_fe_bh,
struct ocfs2_alloc_context *data_ac,
struct ocfs2_alloc_context *meta_ac,
struct buffer_head **new_bh);
/*
* bh passed here can be an inode block or a dir data block, depending
* on the inode inline data flag.
*/
static int ocfs2_check_dir_entry(struct inode * dir,
struct ocfs2_dir_entry * de,
struct buffer_head * bh,
unsigned long offset)
{
const char *error_msg = NULL;
const int rlen = le16_to_cpu(de->rec_len);
if (rlen < OCFS2_DIR_REC_LEN(1))
error_msg = "rec_len is smaller than minimal";
else if (rlen % 4 != 0)
error_msg = "rec_len % 4 != 0";
else if (rlen < OCFS2_DIR_REC_LEN(de->name_len))
error_msg = "rec_len is too small for name_len";
else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)
error_msg = "directory entry across blocks";
if (error_msg != NULL)
mlog(ML_ERROR, "bad entry in directory #%llu: %s - "
"offset=%lu, inode=%llu, rec_len=%d, name_len=%d\n",
(unsigned long long)OCFS2_I(dir)->ip_blkno, error_msg,
offset, (unsigned long long)le64_to_cpu(de->inode), rlen,
de->name_len);
return error_msg == NULL ? 1 : 0;
}
static inline int ocfs2_match(int len,
const char * const name,
struct ocfs2_dir_entry *de)
{
if (len != de->name_len)
return 0;
if (!de->inode)
return 0;
return !memcmp(name, de->name, len);
}
/*
* Returns 0 if not found, -1 on failure, and 1 on success
*/
static int inline ocfs2_search_dirblock(struct buffer_head *bh,
struct inode *dir,
const char *name, int namelen,
unsigned long offset,
char *first_de,
unsigned int bytes,
struct ocfs2_dir_entry **res_dir)
{
struct ocfs2_dir_entry *de;
char *dlimit, *de_buf;
int de_len;
int ret = 0;
mlog_entry_void();
de_buf = first_de;
dlimit = de_buf + bytes;
while (de_buf < dlimit) {
/* this code is executed quadratically often */
/* do minimal checking `by hand' */
de = (struct ocfs2_dir_entry *) de_buf;
if (de_buf + namelen <= dlimit &&
ocfs2_match(namelen, name, de)) {
/* found a match - just to be sure, do a full check */
if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
ret = -1;
goto bail;
}
*res_dir = de;
ret = 1;
goto bail;
}
/* prevent looping on a bad block */
de_len = le16_to_cpu(de->rec_len);
if (de_len <= 0) {
ret = -1;
goto bail;
}
de_buf += de_len;
offset += de_len;
}
bail:
mlog_exit(ret);
return ret;
}
static struct buffer_head *ocfs2_find_entry_id(const char *name,
int namelen,
struct inode *dir,
struct ocfs2_dir_entry **res_dir)
{
int ret, found;
struct buffer_head *di_bh = NULL;
struct ocfs2_dinode *di;
struct ocfs2_inline_data *data;
ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno,
&di_bh, OCFS2_BH_CACHED, dir);
if (ret) {
mlog_errno(ret);
goto out;
}
di = (struct ocfs2_dinode *)di_bh->b_data;
data = &di->id2.i_data;
found = ocfs2_search_dirblock(di_bh, dir, name, namelen, 0,
data->id_data, i_size_read(dir), res_dir);
if (found == 1)
return di_bh;
brelse(di_bh);
out:
return NULL;
}
static struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen,
struct inode *dir,
struct ocfs2_dir_entry **res_dir)
{
struct super_block *sb;
struct buffer_head *bh_use[NAMEI_RA_SIZE];
struct buffer_head *bh, *ret = NULL;
unsigned long start, block, b;
int ra_max = 0; /* Number of bh's in the readahead
buffer, bh_use[] */
int ra_ptr = 0; /* Current index into readahead
buffer */
int num = 0;
int nblocks, i, err;
mlog_entry_void();
sb = dir->i_sb;
nblocks = i_size_read(dir) >> sb->s_blocksize_bits;
start = OCFS2_I(dir)->ip_dir_start_lookup;
if (start >= nblocks)
start = 0;
block = start;
restart:
do {
/*
* We deal with the read-ahead logic here.
*/
if (ra_ptr >= ra_max) {
/* Refill the readahead buffer */
ra_ptr = 0;
b = block;
for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) {
/*
* Terminate if we reach the end of the
* directory and must wrap, or if our
* search has finished at this block.
*/
if (b >= nblocks || (num && block == start)) {
bh_use[ra_max] = NULL;
break;
}
num++;
bh = ocfs2_bread(dir, b++, &err, 1);
bh_use[ra_max] = bh;
}
}
if ((bh = bh_use[ra_ptr++]) == NULL)
goto next;
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
/* read error, skip block & hope for the best */
ocfs2_error(dir->i_sb, "reading directory %llu, "
"offset %lu\n",
(unsigned long long)OCFS2_I(dir)->ip_blkno,
block);
brelse(bh);
goto next;
}
i = ocfs2_search_dirblock(bh, dir, name, namelen,
block << sb->s_blocksize_bits,
bh->b_data, sb->s_blocksize,
res_dir);
if (i == 1) {
OCFS2_I(dir)->ip_dir_start_lookup = block;
ret = bh;
goto cleanup_and_exit;
} else {
brelse(bh);
if (i < 0)
goto cleanup_and_exit;
}
next:
if (++block >= nblocks)
block = 0;
} while (block != start);
/*
* If the directory has grown while we were searching, then
* search the last part of the directory before giving up.
*/
block = nblocks;
nblocks = i_size_read(dir) >> sb->s_blocksize_bits;
if (block < nblocks) {
start = 0;
goto restart;
}
cleanup_and_exit:
/* Clean up the read-ahead blocks */
for (; ra_ptr < ra_max; ra_ptr++)
brelse(bh_use[ra_ptr]);
mlog_exit_ptr(ret);
return ret;
}
/*
* Try to find an entry of the provided name within 'dir'.
*
* If nothing was found, NULL is returned. Otherwise, a buffer_head
* and pointer to the dir entry are passed back.
*
* Caller can NOT assume anything about the contents of the
* buffer_head - it is passed back only so that it can be passed into
* any one of the manipulation functions (add entry, delete entry,
* etc). As an example, bh in the extent directory case is a data
* block, in the inline-data case it actually points to an inode.
*/
struct buffer_head *ocfs2_find_entry(const char *name, int namelen,
struct inode *dir,
struct ocfs2_dir_entry **res_dir)
{
*res_dir = NULL;
if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
return ocfs2_find_entry_id(name, namelen, dir, res_dir);
return ocfs2_find_entry_el(name, namelen, dir, res_dir);
}
/*
* Update inode number and type of a previously found directory entry.
*/
int ocfs2_update_entry(struct inode *dir, handle_t *handle,
struct buffer_head *de_bh, struct ocfs2_dir_entry *de,
struct inode *new_entry_inode)
{
int ret;
/*
* The same code works fine for both inline-data and extent
* based directories, so no need to split this up.
*/
ret = ocfs2_journal_access(handle, dir, de_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
de->inode = cpu_to_le64(OCFS2_I(new_entry_inode)->ip_blkno);
ocfs2_set_de_type(de, new_entry_inode->i_mode);
ocfs2_journal_dirty(handle, de_bh);
out:
return ret;
}
static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
struct ocfs2_dir_entry *de_del,
struct buffer_head *bh, char *first_de,
unsigned int bytes)
{
struct ocfs2_dir_entry *de, *pde;
int i, status = -ENOENT;
mlog_entry("(0x%p, 0x%p, 0x%p, 0x%p)\n", handle, dir, de_del, bh);
i = 0;
pde = NULL;
de = (struct ocfs2_dir_entry *) first_de;
while (i < bytes) {
if (!ocfs2_check_dir_entry(dir, de, bh, i)) {
status = -EIO;
mlog_errno(status);
goto bail;
}
if (de == de_del) {
status = ocfs2_journal_access(handle, dir, bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
status = -EIO;
mlog_errno(status);
goto bail;
}
if (pde)
le16_add_cpu(&pde->rec_len,
le16_to_cpu(de->rec_len));
else
de->inode = 0;
dir->i_version++;
status = ocfs2_journal_dirty(handle, bh);
goto bail;
}
i += le16_to_cpu(de->rec_len);
pde = de;
de = (struct ocfs2_dir_entry *)((char *)de + le16_to_cpu(de->rec_len));
}
bail:
mlog_exit(status);
return status;
}
static inline int ocfs2_delete_entry_id(handle_t *handle,
struct inode *dir,
struct ocfs2_dir_entry *de_del,
struct buffer_head *bh)
{
int ret;
struct buffer_head *di_bh = NULL;
struct ocfs2_dinode *di;
struct ocfs2_inline_data *data;
ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno,
&di_bh, OCFS2_BH_CACHED, dir);
if (ret) {
mlog_errno(ret);
goto out;
}
di = (struct ocfs2_dinode *)di_bh->b_data;
data = &di->id2.i_data;
ret = __ocfs2_delete_entry(handle, dir, de_del, bh, data->id_data,
i_size_read(dir));
brelse(di_bh);
out:
return ret;
}
static inline int ocfs2_delete_entry_el(handle_t *handle,
struct inode *dir,
struct ocfs2_dir_entry *de_del,
struct buffer_head *bh)
{
return __ocfs2_delete_entry(handle, dir, de_del, bh, bh->b_data,
bh->b_size);
}
/*
* ocfs2_delete_entry deletes a directory entry by merging it with the
* previous entry
*/
int ocfs2_delete_entry(handle_t *handle,
struct inode *dir,
struct ocfs2_dir_entry *de_del,
struct buffer_head *bh)
{
if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
return ocfs2_delete_entry_id(handle, dir, de_del, bh);
return ocfs2_delete_entry_el(handle, dir, de_del, bh);
}
/*
* Check whether 'de' has enough room to hold an entry of
* 'new_rec_len' bytes.
*/
static inline int ocfs2_dirent_would_fit(struct ocfs2_dir_entry *de,
unsigned int new_rec_len)
{
unsigned int de_really_used;
/* Check whether this is an empty record with enough space */
if (le64_to_cpu(de->inode) == 0 &&
le16_to_cpu(de->rec_len) >= new_rec_len)
return 1;
/*
* Record might have free space at the end which we can
* use.
*/
de_really_used = OCFS2_DIR_REC_LEN(de->name_len);
if (le16_to_cpu(de->rec_len) >= (de_really_used + new_rec_len))
return 1;
return 0;
}
/* we don't always have a dentry for what we want to add, so people
* like orphan dir can call this instead.
*
* If you pass me insert_bh, I'll skip the search of the other dir
* blocks and put the record in there.
*/
int __ocfs2_add_entry(handle_t *handle,
struct inode *dir,
const char *name, int namelen,
struct inode *inode, u64 blkno,
struct buffer_head *parent_fe_bh,
struct buffer_head *insert_bh)
{
unsigned long offset;
unsigned short rec_len;
struct ocfs2_dir_entry *de, *de1;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)parent_fe_bh->b_data;
struct super_block *sb = dir->i_sb;
int retval, status;
unsigned int size = sb->s_blocksize;
char *data_start = insert_bh->b_data;
mlog_entry_void();
if (!namelen)
return -EINVAL;
if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
data_start = di->id2.i_data.id_data;
size = i_size_read(dir);
BUG_ON(insert_bh != parent_fe_bh);
}
rec_len = OCFS2_DIR_REC_LEN(namelen);
offset = 0;
de = (struct ocfs2_dir_entry *) data_start;
while (1) {
BUG_ON((char *)de >= (size + data_start));
/* These checks should've already been passed by the
* prepare function, but I guess we can leave them
* here anyway. */
if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) {
retval = -ENOENT;
goto bail;
}
if (ocfs2_match(namelen, name, de)) {
retval = -EEXIST;
goto bail;
}
if (ocfs2_dirent_would_fit(de, rec_len)) {
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh);
if (retval < 0) {
mlog_errno(retval);
goto bail;
}
status = ocfs2_journal_access(handle, dir, insert_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
/* By now the buffer is marked for journaling */
offset += le16_to_cpu(de->rec_len);
if (le64_to_cpu(de->inode)) {
de1 = (struct ocfs2_dir_entry *)((char *) de +
OCFS2_DIR_REC_LEN(de->name_len));
de1->rec_len =
cpu_to_le16(le16_to_cpu(de->rec_len) -
OCFS2_DIR_REC_LEN(de->name_len));
de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len));
de = de1;
}
de->file_type = OCFS2_FT_UNKNOWN;
if (blkno) {
de->inode = cpu_to_le64(blkno);
ocfs2_set_de_type(de, inode->i_mode);
} else
de->inode = 0;
de->name_len = namelen;
memcpy(de->name, name, namelen);
dir->i_version++;
status = ocfs2_journal_dirty(handle, insert_bh);
retval = 0;
goto bail;
}
offset += le16_to_cpu(de->rec_len);
de = (struct ocfs2_dir_entry *) ((char *) de + le16_to_cpu(de->rec_len));
}
/* when you think about it, the assert above should prevent us
* from ever getting here. */
retval = -ENOSPC;
bail:
mlog_exit(retval);
return retval;
}
static int ocfs2_dir_foreach_blk_id(struct inode *inode,
u64 *f_version,
loff_t *f_pos, void *priv,
filldir_t filldir, int *filldir_err)
{
int ret, i, filldir_ret;
unsigned long offset = *f_pos;
struct buffer_head *di_bh = NULL;
struct ocfs2_dinode *di;
struct ocfs2_inline_data *data;
struct ocfs2_dir_entry *de;
ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno,
&di_bh, OCFS2_BH_CACHED, inode);
if (ret) {
mlog(ML_ERROR, "Unable to read inode block for dir %llu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
goto out;
}
di = (struct ocfs2_dinode *)di_bh->b_data;
data = &di->id2.i_data;
while (*f_pos < i_size_read(inode)) {
revalidate:
/* If the dir block has changed since the last call to
* readdir(2), then we might be pointing to an invalid
* dirent right now. Scan from the start of the block
* to make sure. */
if (*f_version != inode->i_version) {
for (i = 0; i < i_size_read(inode) && i < offset; ) {
de = (struct ocfs2_dir_entry *)
(data->id_data + i);
/* It's too expensive to do a full
* dirent test each time round this
* loop, but we do have to test at
* least that it is non-zero. A
* failure will be detected in the
* dirent test below. */
if (le16_to_cpu(de->rec_len) <
OCFS2_DIR_REC_LEN(1))
break;
i += le16_to_cpu(de->rec_len);
}
*f_pos = offset = i;
*f_version = inode->i_version;
}
de = (struct ocfs2_dir_entry *) (data->id_data + *f_pos);
if (!ocfs2_check_dir_entry(inode, de, di_bh, *f_pos)) {
/* On error, skip the f_pos to the end. */
*f_pos = i_size_read(inode);
goto out;
}
offset += le16_to_cpu(de->rec_len);
if (le64_to_cpu(de->inode)) {
/* We might block in the next section
* if the data destination is
* currently swapped out. So, use a
* version stamp to detect whether or
* not the directory has been modified
* during the copy operation.
*/
u64 version = *f_version;
unsigned char d_type = DT_UNKNOWN;
if (de->file_type < OCFS2_FT_MAX)
d_type = ocfs2_filetype_table[de->file_type];
filldir_ret = filldir(priv, de->name,
de->name_len,
*f_pos,
le64_to_cpu(de->inode),
d_type);
if (filldir_ret) {
if (filldir_err)
*filldir_err = filldir_ret;
break;
}
if (version != *f_version)
goto revalidate;
}
*f_pos += le16_to_cpu(de->rec_len);
}
out:
brelse(di_bh);
return 0;
}
static int ocfs2_dir_foreach_blk_el(struct inode *inode,
u64 *f_version,
loff_t *f_pos, void *priv,
filldir_t filldir, int *filldir_err)
{
int error = 0;
unsigned long offset, blk, last_ra_blk = 0;
int i, stored;
struct buffer_head * bh, * tmp;
struct ocfs2_dir_entry * de;
int err;
struct super_block * sb = inode->i_sb;
unsigned int ra_sectors = 16;
stored = 0;
bh = NULL;
offset = (*f_pos) & (sb->s_blocksize - 1);
while (!error && !stored && *f_pos < i_size_read(inode)) {
blk = (*f_pos) >> sb->s_blocksize_bits;
bh = ocfs2_bread(inode, blk, &err, 0);
if (!bh) {
mlog(ML_ERROR,
"directory #%llu contains a hole at offset %lld\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
*f_pos);
*f_pos += sb->s_blocksize - offset;
continue;
}
/* The idea here is to begin with 8k read-ahead and to stay
* 4k ahead of our current position.
*
* TODO: Use the pagecache for this. We just need to
* make sure it's cluster-safe... */
if (!last_ra_blk
|| (((last_ra_blk - blk) << 9) <= (ra_sectors / 2))) {
for (i = ra_sectors >> (sb->s_blocksize_bits - 9);
i > 0; i--) {
tmp = ocfs2_bread(inode, ++blk, &err, 1);
if (tmp)
brelse(tmp);
}
last_ra_blk = blk;
ra_sectors = 8;
}
revalidate:
/* If the dir block has changed since the last call to
* readdir(2), then we might be pointing to an invalid
* dirent right now. Scan from the start of the block
* to make sure. */
if (*f_version != inode->i_version) {
for (i = 0; i < sb->s_blocksize && i < offset; ) {
de = (struct ocfs2_dir_entry *) (bh->b_data + i);
/* It's too expensive to do a full
* dirent test each time round this
* loop, but we do have to test at
* least that it is non-zero. A
* failure will be detected in the
* dirent test below. */
if (le16_to_cpu(de->rec_len) <
OCFS2_DIR_REC_LEN(1))
break;
i += le16_to_cpu(de->rec_len);
}
offset = i;
*f_pos = ((*f_pos) & ~(sb->s_blocksize - 1))
| offset;
*f_version = inode->i_version;
}
while (!error && *f_pos < i_size_read(inode)
&& offset < sb->s_blocksize) {
de = (struct ocfs2_dir_entry *) (bh->b_data + offset);
if (!ocfs2_check_dir_entry(inode, de, bh, offset)) {
/* On error, skip the f_pos to the
next block. */
*f_pos = ((*f_pos) | (sb->s_blocksize - 1)) + 1;
brelse(bh);
goto out;
}
offset += le16_to_cpu(de->rec_len);
if (le64_to_cpu(de->inode)) {
/* We might block in the next section
* if the data destination is
* currently swapped out. So, use a
* version stamp to detect whether or
* not the directory has been modified
* during the copy operation.
*/
unsigned long version = *f_version;
unsigned char d_type = DT_UNKNOWN;
if (de->file_type < OCFS2_FT_MAX)
d_type = ocfs2_filetype_table[de->file_type];
error = filldir(priv, de->name,
de->name_len,
*f_pos,
le64_to_cpu(de->inode),
d_type);
if (error) {
if (filldir_err)
*filldir_err = error;
break;
}
if (version != *f_version)
goto revalidate;
stored ++;
}
*f_pos += le16_to_cpu(de->rec_len);
}
offset = 0;
brelse(bh);
}
stored = 0;
out:
return stored;
}
static int ocfs2_dir_foreach_blk(struct inode *inode, u64 *f_version,
loff_t *f_pos, void *priv, filldir_t filldir,
int *filldir_err)
{
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
return ocfs2_dir_foreach_blk_id(inode, f_version, f_pos, priv,
filldir, filldir_err);
return ocfs2_dir_foreach_blk_el(inode, f_version, f_pos, priv, filldir,
filldir_err);
}
/*
* This is intended to be called from inside other kernel functions,
* so we fake some arguments.
*/
int ocfs2_dir_foreach(struct inode *inode, loff_t *f_pos, void *priv,
filldir_t filldir)
{
int ret = 0, filldir_err = 0;
u64 version = inode->i_version;
while (*f_pos < i_size_read(inode)) {
ret = ocfs2_dir_foreach_blk(inode, &version, f_pos, priv,
filldir, &filldir_err);
if (ret || filldir_err)
break;
}
if (ret > 0)
ret = -EIO;
return 0;
}
/*
* ocfs2_readdir()
*
*/
int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
int error = 0;
struct inode *inode = filp->f_path.dentry->d_inode;
int lock_level = 0;
mlog_entry("dirino=%llu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
error = ocfs2_inode_lock_atime(inode, filp->f_vfsmnt, &lock_level);
if (lock_level && error >= 0) {
/* We release EX lock which used to update atime
* and get PR lock again to reduce contention
* on commonly accessed directories. */
ocfs2_inode_unlock(inode, 1);
lock_level = 0;
error = ocfs2_inode_lock(inode, NULL, 0);
}
if (error < 0) {
if (error != -ENOENT)
mlog_errno(error);
/* we haven't got any yet, so propagate the error. */
goto bail_nolock;
}
error = ocfs2_dir_foreach_blk(inode, &filp->f_version, &filp->f_pos,
dirent, filldir, NULL);
ocfs2_inode_unlock(inode, lock_level);
bail_nolock:
mlog_exit(error);
return error;
}
/*
* NOTE: this should always be called with parent dir i_mutex taken.
*/
int ocfs2_find_files_on_disk(const char *name,
int namelen,
u64 *blkno,
struct inode *inode,
struct buffer_head **dirent_bh,
struct ocfs2_dir_entry **dirent)
{
int status = -ENOENT;
mlog_entry("(name=%.*s, blkno=%p, inode=%p, dirent_bh=%p, dirent=%p)\n",
namelen, name, blkno, inode, dirent_bh, dirent);
*dirent_bh = ocfs2_find_entry(name, namelen, inode, dirent);
if (!*dirent_bh || !*dirent) {
status = -ENOENT;
goto leave;
}
*blkno = le64_to_cpu((*dirent)->inode);
status = 0;
leave:
if (status < 0) {
*dirent = NULL;
if (*dirent_bh) {
brelse(*dirent_bh);
*dirent_bh = NULL;
}
}
mlog_exit(status);
return status;
}
/*
* Convenience function for callers which just want the block number
* mapped to a name and don't require the full dirent info, etc.
*/
int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name,
int namelen, u64 *blkno)
{
int ret;
struct buffer_head *bh = NULL;
struct ocfs2_dir_entry *dirent = NULL;
ret = ocfs2_find_files_on_disk(name, namelen, blkno, dir, &bh, &dirent);
brelse(bh);
return ret;
}
/* Check for a name within a directory.
*
* Return 0 if the name does not exist
* Return -EEXIST if the directory contains the name
*
* Callers should have i_mutex + a cluster lock on dir
*/
int ocfs2_check_dir_for_entry(struct inode *dir,
const char *name,
int namelen)
{
int ret;
struct buffer_head *dirent_bh = NULL;
struct ocfs2_dir_entry *dirent = NULL;
mlog_entry("dir %llu, name '%.*s'\n",
(unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name);
ret = -EEXIST;
dirent_bh = ocfs2_find_entry(name, namelen, dir, &dirent);
if (dirent_bh)
goto bail;
ret = 0;
bail:
if (dirent_bh)
brelse(dirent_bh);
mlog_exit(ret);
return ret;
}
struct ocfs2_empty_dir_priv {
unsigned seen_dot;
unsigned seen_dot_dot;
unsigned seen_other;
};
static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len,
loff_t pos, u64 ino, unsigned type)
{
struct ocfs2_empty_dir_priv *p = priv;
/*
* Check the positions of "." and ".." records to be sure
* they're in the correct place.
*/
if (name_len == 1 && !strncmp(".", name, 1) && pos == 0) {
p->seen_dot = 1;
return 0;
}
if (name_len == 2 && !strncmp("..", name, 2) &&
pos == OCFS2_DIR_REC_LEN(1)) {
p->seen_dot_dot = 1;
return 0;
}
p->seen_other = 1;
return 1;
}
/*
* routine to check that the specified directory is empty (for rmdir)
*
* Returns 1 if dir is empty, zero otherwise.
*/
int ocfs2_empty_dir(struct inode *inode)
{
int ret;
loff_t start = 0;
struct ocfs2_empty_dir_priv priv;
memset(&priv, 0, sizeof(priv));