forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
dir.c
2038 lines (1747 loc) · 47.3 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
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
* of the GNU General Public License version 2.
*/
/*
* Implements Extendible Hashing as described in:
* "Extendible Hashing" by Fagin, et al in
* __ACM Trans. on Database Systems__, Sept 1979.
*
*
* Here's the layout of dirents which is essentially the same as that of ext2
* within a single block. The field de_name_len is the number of bytes
* actually required for the name (no null terminator). The field de_rec_len
* is the number of bytes allocated to the dirent. The offset of the next
* dirent in the block is (dirent + dirent->de_rec_len). When a dirent is
* deleted, the preceding dirent inherits its allocated space, ie
* prev->de_rec_len += deleted->de_rec_len. Since the next dirent is obtained
* by adding de_rec_len to the current dirent, this essentially causes the
* deleted dirent to get jumped over when iterating through all the dirents.
*
* When deleting the first dirent in a block, there is no previous dirent so
* the field de_ino is set to zero to designate it as deleted. When allocating
* a dirent, gfs2_dirent_alloc iterates through the dirents in a block. If the
* first dirent has (de_ino == 0) and de_rec_len is large enough, this first
* dirent is allocated. Otherwise it must go through all the 'used' dirents
* searching for one in which the amount of total space minus the amount of
* used space will provide enough space for the new dirent.
*
* There are two types of blocks in which dirents reside. In a stuffed dinode,
* the dirents begin at offset sizeof(struct gfs2_dinode) from the beginning of
* the block. In leaves, they begin at offset sizeof(struct gfs2_leaf) from the
* beginning of the leaf block. The dirents reside in leaves when
*
* dip->i_diskflags & GFS2_DIF_EXHASH is true
*
* Otherwise, the dirents are "linear", within a single stuffed dinode block.
*
* When the dirents are in leaves, the actual contents of the directory file are
* used as an array of 64-bit block pointers pointing to the leaf blocks. The
* dirents are NOT in the directory file itself. There can be more than one
* block pointer in the array that points to the same leaf. In fact, when a
* directory is first converted from linear to exhash, all of the pointers
* point to the same leaf.
*
* When a leaf is completely full, the size of the hash table can be
* doubled unless it is already at the maximum size which is hard coded into
* GFS2_DIR_MAX_DEPTH. After that, leaves are chained together in a linked list,
* but never before the maximum hash table size has been reached.
*/
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/buffer_head.h>
#include <linux/sort.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/vmalloc.h>
#include "gfs2.h"
#include "incore.h"
#include "dir.h"
#include "glock.h"
#include "inode.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "trans.h"
#include "bmap.h"
#include "util.h"
#define IS_LEAF 1 /* Hashed (leaf) directory */
#define IS_DINODE 2 /* Linear (stuffed dinode block) directory */
#define MAX_RA_BLOCKS 32 /* max read-ahead blocks */
#define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1)
#define gfs2_dir_offset2hash(p) ((u32)(((u64)(p)) << 1))
struct qstr gfs2_qdot __read_mostly;
struct qstr gfs2_qdotdot __read_mostly;
typedef int (*gfs2_dscan_t)(const struct gfs2_dirent *dent,
const struct qstr *name, void *opaque);
int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
struct buffer_head **bhp)
{
struct buffer_head *bh;
bh = gfs2_meta_new(ip->i_gl, block);
gfs2_trans_add_meta(ip->i_gl, bh);
gfs2_metatype_set(bh, GFS2_METATYPE_JD, GFS2_FORMAT_JD);
gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
*bhp = bh;
return 0;
}
static int gfs2_dir_get_existing_buffer(struct gfs2_inode *ip, u64 block,
struct buffer_head **bhp)
{
struct buffer_head *bh;
int error;
error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, &bh);
if (error)
return error;
if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), bh, GFS2_METATYPE_JD)) {
brelse(bh);
return -EIO;
}
*bhp = bh;
return 0;
}
static int gfs2_dir_write_stuffed(struct gfs2_inode *ip, const char *buf,
unsigned int offset, unsigned int size)
{
struct buffer_head *dibh;
int error;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
return error;
gfs2_trans_add_meta(ip->i_gl, dibh);
memcpy(dibh->b_data + offset + sizeof(struct gfs2_dinode), buf, size);
if (ip->i_inode.i_size < offset + size)
i_size_write(&ip->i_inode, offset + size);
ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
return size;
}
/**
* gfs2_dir_write_data - Write directory information to the inode
* @ip: The GFS2 inode
* @buf: The buffer containing information to be written
* @offset: The file offset to start writing at
* @size: The amount of data to write
*
* Returns: The number of bytes correctly written or error code
*/
static int gfs2_dir_write_data(struct gfs2_inode *ip, const char *buf,
u64 offset, unsigned int size)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct buffer_head *dibh;
u64 lblock, dblock;
u32 extlen = 0;
unsigned int o;
int copied = 0;
int error = 0;
int new = 0;
if (!size)
return 0;
if (gfs2_is_stuffed(ip) &&
offset + size <= sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode))
return gfs2_dir_write_stuffed(ip, buf, (unsigned int)offset,
size);
if (gfs2_assert_warn(sdp, gfs2_is_jdata(ip)))
return -EINVAL;
if (gfs2_is_stuffed(ip)) {
error = gfs2_unstuff_dinode(ip, NULL);
if (error)
return error;
}
lblock = offset;
o = do_div(lblock, sdp->sd_jbsize) + sizeof(struct gfs2_meta_header);
while (copied < size) {
unsigned int amount;
struct buffer_head *bh;
amount = size - copied;
if (amount > sdp->sd_sb.sb_bsize - o)
amount = sdp->sd_sb.sb_bsize - o;
if (!extlen) {
new = 1;
error = gfs2_extent_map(&ip->i_inode, lblock, &new,
&dblock, &extlen);
if (error)
goto fail;
error = -EIO;
if (gfs2_assert_withdraw(sdp, dblock))
goto fail;
}
if (amount == sdp->sd_jbsize || new)
error = gfs2_dir_get_new_buffer(ip, dblock, &bh);
else
error = gfs2_dir_get_existing_buffer(ip, dblock, &bh);
if (error)
goto fail;
gfs2_trans_add_meta(ip->i_gl, bh);
memcpy(bh->b_data + o, buf, amount);
brelse(bh);
buf += amount;
copied += amount;
lblock++;
dblock++;
extlen--;
o = sizeof(struct gfs2_meta_header);
}
out:
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
return error;
if (ip->i_inode.i_size < offset + copied)
i_size_write(&ip->i_inode, offset + copied);
ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
return copied;
fail:
if (copied)
goto out;
return error;
}
static int gfs2_dir_read_stuffed(struct gfs2_inode *ip, __be64 *buf,
unsigned int size)
{
struct buffer_head *dibh;
int error;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (!error) {
memcpy(buf, dibh->b_data + sizeof(struct gfs2_dinode), size);
brelse(dibh);
}
return (error) ? error : size;
}
/**
* gfs2_dir_read_data - Read a data from a directory inode
* @ip: The GFS2 Inode
* @buf: The buffer to place result into
* @size: Amount of data to transfer
*
* Returns: The amount of data actually copied or the error
*/
static int gfs2_dir_read_data(struct gfs2_inode *ip, __be64 *buf,
unsigned int size)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
u64 lblock, dblock;
u32 extlen = 0;
unsigned int o;
int copied = 0;
int error = 0;
if (gfs2_is_stuffed(ip))
return gfs2_dir_read_stuffed(ip, buf, size);
if (gfs2_assert_warn(sdp, gfs2_is_jdata(ip)))
return -EINVAL;
lblock = 0;
o = do_div(lblock, sdp->sd_jbsize) + sizeof(struct gfs2_meta_header);
while (copied < size) {
unsigned int amount;
struct buffer_head *bh;
int new;
amount = size - copied;
if (amount > sdp->sd_sb.sb_bsize - o)
amount = sdp->sd_sb.sb_bsize - o;
if (!extlen) {
new = 0;
error = gfs2_extent_map(&ip->i_inode, lblock, &new,
&dblock, &extlen);
if (error || !dblock)
goto fail;
BUG_ON(extlen < 1);
bh = gfs2_meta_ra(ip->i_gl, dblock, extlen);
} else {
error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, &bh);
if (error)
goto fail;
}
error = gfs2_metatype_check(sdp, bh, GFS2_METATYPE_JD);
if (error) {
brelse(bh);
goto fail;
}
dblock++;
extlen--;
memcpy(buf, bh->b_data + o, amount);
brelse(bh);
buf += (amount/sizeof(__be64));
copied += amount;
lblock++;
o = sizeof(struct gfs2_meta_header);
}
return copied;
fail:
return (copied) ? copied : error;
}
/**
* gfs2_dir_get_hash_table - Get pointer to the dir hash table
* @ip: The inode in question
*
* Returns: The hash table or an error
*/
static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip)
{
struct inode *inode = &ip->i_inode;
int ret;
u32 hsize;
__be64 *hc;
BUG_ON(!(ip->i_diskflags & GFS2_DIF_EXHASH));
hc = ip->i_hash_cache;
if (hc)
return hc;
hsize = 1 << ip->i_depth;
hsize *= sizeof(__be64);
if (hsize != i_size_read(&ip->i_inode)) {
gfs2_consist_inode(ip);
return ERR_PTR(-EIO);
}
hc = kmalloc(hsize, GFP_NOFS | __GFP_NOWARN);
if (hc == NULL)
hc = __vmalloc(hsize, GFP_NOFS, PAGE_KERNEL);
if (hc == NULL)
return ERR_PTR(-ENOMEM);
ret = gfs2_dir_read_data(ip, hc, hsize);
if (ret < 0) {
if (is_vmalloc_addr(hc))
vfree(hc);
else
kfree(hc);
return ERR_PTR(ret);
}
spin_lock(&inode->i_lock);
if (ip->i_hash_cache) {
if (is_vmalloc_addr(hc))
vfree(hc);
else
kfree(hc);
} else {
ip->i_hash_cache = hc;
}
spin_unlock(&inode->i_lock);
return ip->i_hash_cache;
}
/**
* gfs2_dir_hash_inval - Invalidate dir hash
* @ip: The directory inode
*
* Must be called with an exclusive glock, or during glock invalidation.
*/
void gfs2_dir_hash_inval(struct gfs2_inode *ip)
{
__be64 *hc = ip->i_hash_cache;
ip->i_hash_cache = NULL;
if (is_vmalloc_addr(hc))
vfree(hc);
else
kfree(hc);
}
static inline int gfs2_dirent_sentinel(const struct gfs2_dirent *dent)
{
return dent->de_inum.no_addr == 0 || dent->de_inum.no_formal_ino == 0;
}
static inline int __gfs2_dirent_find(const struct gfs2_dirent *dent,
const struct qstr *name, int ret)
{
if (!gfs2_dirent_sentinel(dent) &&
be32_to_cpu(dent->de_hash) == name->hash &&
be16_to_cpu(dent->de_name_len) == name->len &&
memcmp(dent+1, name->name, name->len) == 0)
return ret;
return 0;
}
static int gfs2_dirent_find(const struct gfs2_dirent *dent,
const struct qstr *name,
void *opaque)
{
return __gfs2_dirent_find(dent, name, 1);
}
static int gfs2_dirent_prev(const struct gfs2_dirent *dent,
const struct qstr *name,
void *opaque)
{
return __gfs2_dirent_find(dent, name, 2);
}
/*
* name->name holds ptr to start of block.
* name->len holds size of block.
*/
static int gfs2_dirent_last(const struct gfs2_dirent *dent,
const struct qstr *name,
void *opaque)
{
const char *start = name->name;
const char *end = (const char *)dent + be16_to_cpu(dent->de_rec_len);
if (name->len == (end - start))
return 1;
return 0;
}
static int gfs2_dirent_find_space(const struct gfs2_dirent *dent,
const struct qstr *name,
void *opaque)
{
unsigned required = GFS2_DIRENT_SIZE(name->len);
unsigned actual = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
unsigned totlen = be16_to_cpu(dent->de_rec_len);
if (gfs2_dirent_sentinel(dent))
actual = 0;
if (totlen - actual >= required)
return 1;
return 0;
}
struct dirent_gather {
const struct gfs2_dirent **pdent;
unsigned offset;
};
static int gfs2_dirent_gather(const struct gfs2_dirent *dent,
const struct qstr *name,
void *opaque)
{
struct dirent_gather *g = opaque;
if (!gfs2_dirent_sentinel(dent)) {
g->pdent[g->offset++] = dent;
}
return 0;
}
/*
* Other possible things to check:
* - Inode located within filesystem size (and on valid block)
* - Valid directory entry type
* Not sure how heavy-weight we want to make this... could also check
* hash is correct for example, but that would take a lot of extra time.
* For now the most important thing is to check that the various sizes
* are correct.
*/
static int gfs2_check_dirent(struct gfs2_dirent *dent, unsigned int offset,
unsigned int size, unsigned int len, int first)
{
const char *msg = "gfs2_dirent too small";
if (unlikely(size < sizeof(struct gfs2_dirent)))
goto error;
msg = "gfs2_dirent misaligned";
if (unlikely(offset & 0x7))
goto error;
msg = "gfs2_dirent points beyond end of block";
if (unlikely(offset + size > len))
goto error;
msg = "zero inode number";
if (unlikely(!first && gfs2_dirent_sentinel(dent)))
goto error;
msg = "name length is greater than space in dirent";
if (!gfs2_dirent_sentinel(dent) &&
unlikely(sizeof(struct gfs2_dirent)+be16_to_cpu(dent->de_name_len) >
size))
goto error;
return 0;
error:
printk(KERN_WARNING "gfs2_check_dirent: %s (%s)\n", msg,
first ? "first in block" : "not first in block");
return -EIO;
}
static int gfs2_dirent_offset(const void *buf)
{
const struct gfs2_meta_header *h = buf;
int offset;
BUG_ON(buf == NULL);
switch(be32_to_cpu(h->mh_type)) {
case GFS2_METATYPE_LF:
offset = sizeof(struct gfs2_leaf);
break;
case GFS2_METATYPE_DI:
offset = sizeof(struct gfs2_dinode);
break;
default:
goto wrong_type;
}
return offset;
wrong_type:
printk(KERN_WARNING "gfs2_scan_dirent: wrong block type %u\n",
be32_to_cpu(h->mh_type));
return -1;
}
static struct gfs2_dirent *gfs2_dirent_scan(struct inode *inode, void *buf,
unsigned int len, gfs2_dscan_t scan,
const struct qstr *name,
void *opaque)
{
struct gfs2_dirent *dent, *prev;
unsigned offset;
unsigned size;
int ret = 0;
ret = gfs2_dirent_offset(buf);
if (ret < 0)
goto consist_inode;
offset = ret;
prev = NULL;
dent = buf + offset;
size = be16_to_cpu(dent->de_rec_len);
if (gfs2_check_dirent(dent, offset, size, len, 1))
goto consist_inode;
do {
ret = scan(dent, name, opaque);
if (ret)
break;
offset += size;
if (offset == len)
break;
prev = dent;
dent = buf + offset;
size = be16_to_cpu(dent->de_rec_len);
if (gfs2_check_dirent(dent, offset, size, len, 0))
goto consist_inode;
} while(1);
switch(ret) {
case 0:
return NULL;
case 1:
return dent;
case 2:
return prev ? prev : dent;
default:
BUG_ON(ret > 0);
return ERR_PTR(ret);
}
consist_inode:
gfs2_consist_inode(GFS2_I(inode));
return ERR_PTR(-EIO);
}
static int dirent_check_reclen(struct gfs2_inode *dip,
const struct gfs2_dirent *d, const void *end_p)
{
const void *ptr = d;
u16 rec_len = be16_to_cpu(d->de_rec_len);
if (unlikely(rec_len < sizeof(struct gfs2_dirent)))
goto broken;
ptr += rec_len;
if (ptr < end_p)
return rec_len;
if (ptr == end_p)
return -ENOENT;
broken:
gfs2_consist_inode(dip);
return -EIO;
}
/**
* dirent_next - Next dirent
* @dip: the directory
* @bh: The buffer
* @dent: Pointer to list of dirents
*
* Returns: 0 on success, error code otherwise
*/
static int dirent_next(struct gfs2_inode *dip, struct buffer_head *bh,
struct gfs2_dirent **dent)
{
struct gfs2_dirent *cur = *dent, *tmp;
char *bh_end = bh->b_data + bh->b_size;
int ret;
ret = dirent_check_reclen(dip, cur, bh_end);
if (ret < 0)
return ret;
tmp = (void *)cur + ret;
ret = dirent_check_reclen(dip, tmp, bh_end);
if (ret == -EIO)
return ret;
/* Only the first dent could ever have de_inum.no_addr == 0 */
if (gfs2_dirent_sentinel(tmp)) {
gfs2_consist_inode(dip);
return -EIO;
}
*dent = tmp;
return 0;
}
/**
* dirent_del - Delete a dirent
* @dip: The GFS2 inode
* @bh: The buffer
* @prev: The previous dirent
* @cur: The current dirent
*
*/
static void dirent_del(struct gfs2_inode *dip, struct buffer_head *bh,
struct gfs2_dirent *prev, struct gfs2_dirent *cur)
{
u16 cur_rec_len, prev_rec_len;
if (gfs2_dirent_sentinel(cur)) {
gfs2_consist_inode(dip);
return;
}
gfs2_trans_add_meta(dip->i_gl, bh);
/* If there is no prev entry, this is the first entry in the block.
The de_rec_len is already as big as it needs to be. Just zero
out the inode number and return. */
if (!prev) {
cur->de_inum.no_addr = 0;
cur->de_inum.no_formal_ino = 0;
return;
}
/* Combine this dentry with the previous one. */
prev_rec_len = be16_to_cpu(prev->de_rec_len);
cur_rec_len = be16_to_cpu(cur->de_rec_len);
if ((char *)prev + prev_rec_len != (char *)cur)
gfs2_consist_inode(dip);
if ((char *)cur + cur_rec_len > bh->b_data + bh->b_size)
gfs2_consist_inode(dip);
prev_rec_len += cur_rec_len;
prev->de_rec_len = cpu_to_be16(prev_rec_len);
}
/*
* Takes a dent from which to grab space as an argument. Returns the
* newly created dent.
*/
static struct gfs2_dirent *gfs2_init_dirent(struct inode *inode,
struct gfs2_dirent *dent,
const struct qstr *name,
struct buffer_head *bh)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_dirent *ndent;
unsigned offset = 0, totlen;
if (!gfs2_dirent_sentinel(dent))
offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
totlen = be16_to_cpu(dent->de_rec_len);
BUG_ON(offset + name->len > totlen);
gfs2_trans_add_meta(ip->i_gl, bh);
ndent = (struct gfs2_dirent *)((char *)dent + offset);
dent->de_rec_len = cpu_to_be16(offset);
gfs2_qstr2dirent(name, totlen - offset, ndent);
return ndent;
}
static struct gfs2_dirent *gfs2_dirent_alloc(struct inode *inode,
struct buffer_head *bh,
const struct qstr *name)
{
struct gfs2_dirent *dent;
dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
gfs2_dirent_find_space, name, NULL);
if (!dent || IS_ERR(dent))
return dent;
return gfs2_init_dirent(inode, dent, name, bh);
}
static int get_leaf(struct gfs2_inode *dip, u64 leaf_no,
struct buffer_head **bhp)
{
int error;
error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, bhp);
if (!error && gfs2_metatype_check(GFS2_SB(&dip->i_inode), *bhp, GFS2_METATYPE_LF)) {
/* printk(KERN_INFO "block num=%llu\n", leaf_no); */
error = -EIO;
}
return error;
}
/**
* get_leaf_nr - Get a leaf number associated with the index
* @dip: The GFS2 inode
* @index:
* @leaf_out:
*
* Returns: 0 on success, error code otherwise
*/
static int get_leaf_nr(struct gfs2_inode *dip, u32 index,
u64 *leaf_out)
{
__be64 *hash;
hash = gfs2_dir_get_hash_table(dip);
if (IS_ERR(hash))
return PTR_ERR(hash);
*leaf_out = be64_to_cpu(*(hash + index));
return 0;
}
static int get_first_leaf(struct gfs2_inode *dip, u32 index,
struct buffer_head **bh_out)
{
u64 leaf_no;
int error;
error = get_leaf_nr(dip, index, &leaf_no);
if (!error)
error = get_leaf(dip, leaf_no, bh_out);
return error;
}
static struct gfs2_dirent *gfs2_dirent_search(struct inode *inode,
const struct qstr *name,
gfs2_dscan_t scan,
struct buffer_head **pbh)
{
struct buffer_head *bh;
struct gfs2_dirent *dent;
struct gfs2_inode *ip = GFS2_I(inode);
int error;
if (ip->i_diskflags & GFS2_DIF_EXHASH) {
struct gfs2_leaf *leaf;
unsigned hsize = 1 << ip->i_depth;
unsigned index;
u64 ln;
if (hsize * sizeof(u64) != i_size_read(inode)) {
gfs2_consist_inode(ip);
return ERR_PTR(-EIO);
}
index = name->hash >> (32 - ip->i_depth);
error = get_first_leaf(ip, index, &bh);
if (error)
return ERR_PTR(error);
do {
dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
scan, name, NULL);
if (dent)
goto got_dent;
leaf = (struct gfs2_leaf *)bh->b_data;
ln = be64_to_cpu(leaf->lf_next);
brelse(bh);
if (!ln)
break;
error = get_leaf(ip, ln, &bh);
} while(!error);
return error ? ERR_PTR(error) : NULL;
}
error = gfs2_meta_inode_buffer(ip, &bh);
if (error)
return ERR_PTR(error);
dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, scan, name, NULL);
got_dent:
if (unlikely(dent == NULL || IS_ERR(dent))) {
brelse(bh);
bh = NULL;
}
*pbh = bh;
return dent;
}
static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, u16 depth)
{
struct gfs2_inode *ip = GFS2_I(inode);
unsigned int n = 1;
u64 bn;
int error;
struct buffer_head *bh;
struct gfs2_leaf *leaf;
struct gfs2_dirent *dent;
struct qstr name = { .name = "" };
error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
if (error)
return NULL;
bh = gfs2_meta_new(ip->i_gl, bn);
if (!bh)
return NULL;
gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1);
gfs2_trans_add_meta(ip->i_gl, bh);
gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF);
leaf = (struct gfs2_leaf *)bh->b_data;
leaf->lf_depth = cpu_to_be16(depth);
leaf->lf_entries = 0;
leaf->lf_dirent_format = cpu_to_be32(GFS2_FORMAT_DE);
leaf->lf_next = 0;
memset(leaf->lf_reserved, 0, sizeof(leaf->lf_reserved));
dent = (struct gfs2_dirent *)(leaf+1);
gfs2_qstr2dirent(&name, bh->b_size - sizeof(struct gfs2_leaf), dent);
*pbh = bh;
return leaf;
}
/**
* dir_make_exhash - Convert a stuffed directory into an ExHash directory
* @dip: The GFS2 inode
*
* Returns: 0 on success, error code otherwise
*/
static int dir_make_exhash(struct inode *inode)
{
struct gfs2_inode *dip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_dirent *dent;
struct qstr args;
struct buffer_head *bh, *dibh;
struct gfs2_leaf *leaf;
int y;
u32 x;
__be64 *lp;
u64 bn;
int error;
error = gfs2_meta_inode_buffer(dip, &dibh);
if (error)
return error;
/* Turn over a new leaf */
leaf = new_leaf(inode, &bh, 0);
if (!leaf)
return -ENOSPC;
bn = bh->b_blocknr;
gfs2_assert(sdp, dip->i_entries < (1 << 16));
leaf->lf_entries = cpu_to_be16(dip->i_entries);
/* Copy dirents */
gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_leaf), dibh,
sizeof(struct gfs2_dinode));
/* Find last entry */
x = 0;
args.len = bh->b_size - sizeof(struct gfs2_dinode) +
sizeof(struct gfs2_leaf);
args.name = bh->b_data;
dent = gfs2_dirent_scan(&dip->i_inode, bh->b_data, bh->b_size,
gfs2_dirent_last, &args, NULL);
if (!dent) {
brelse(bh);
brelse(dibh);
return -EIO;
}
if (IS_ERR(dent)) {
brelse(bh);
brelse(dibh);
return PTR_ERR(dent);
}
/* Adjust the last dirent's record length
(Remember that dent still points to the last entry.) */
dent->de_rec_len = cpu_to_be16(be16_to_cpu(dent->de_rec_len) +
sizeof(struct gfs2_dinode) -
sizeof(struct gfs2_leaf));
brelse(bh);
/* We're done with the new leaf block, now setup the new
hash table. */
gfs2_trans_add_meta(dip->i_gl, dibh);
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
lp = (__be64 *)(dibh->b_data + sizeof(struct gfs2_dinode));
for (x = sdp->sd_hash_ptrs; x--; lp++)
*lp = cpu_to_be64(bn);
i_size_write(inode, sdp->sd_sb.sb_bsize / 2);
gfs2_add_inode_blocks(&dip->i_inode, 1);
dip->i_diskflags |= GFS2_DIF_EXHASH;
for (x = sdp->sd_hash_ptrs, y = -1; x; x >>= 1, y++) ;
dip->i_depth = y;
gfs2_dinode_out(dip, dibh->b_data);
brelse(dibh);
return 0;
}
/**
* dir_split_leaf - Split a leaf block into two
* @dip: The GFS2 inode
* @index:
* @leaf_no:
*
* Returns: 0 on success, error code on failure
*/
static int dir_split_leaf(struct inode *inode, const struct qstr *name)
{
struct gfs2_inode *dip = GFS2_I(inode);
struct buffer_head *nbh, *obh, *dibh;
struct gfs2_leaf *nleaf, *oleaf;
struct gfs2_dirent *dent = NULL, *prev = NULL, *next = NULL, *new;
u32 start, len, half_len, divider;
u64 bn, leaf_no;
__be64 *lp;
u32 index;
int x, moved = 0;
int error;
index = name->hash >> (32 - dip->i_depth);
error = get_leaf_nr(dip, index, &leaf_no);
if (error)
return error;
/* Get the old leaf block */
error = get_leaf(dip, leaf_no, &obh);
if (error)
return error;
oleaf = (struct gfs2_leaf *)obh->b_data;
if (dip->i_depth == be16_to_cpu(oleaf->lf_depth)) {
brelse(obh);
return 1; /* can't split */
}
gfs2_trans_add_meta(dip->i_gl, obh);
nleaf = new_leaf(inode, &nbh, be16_to_cpu(oleaf->lf_depth) + 1);
if (!nleaf) {
brelse(obh);
return -ENOSPC;
}
bn = nbh->b_blocknr;
/* Compute the start and len of leaf pointers in the hash table. */