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
|
/*
* linux/fs/ext2/ialloc.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* BSD ufs-inspired inode and directory allocation by
* Stephen Tweedie (sct@dcs.ed.ac.uk), 1993
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller (davem@caip.rutgers.edu), 1995
*/
#include <linux/quotaops.h>
#include <linux/sched.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/random.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
/*
* ialloc.c contains the inodes allocation and deallocation routines
*/
/*
* The free inodes are managed by bitmaps. A file system contains several
* blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap
* block for inodes, N blocks for the inode table and data blocks.
*
* The file system contains group descriptors which are located after the
* super block. Each descriptor contains the number of the bitmap block and
* the free blocks count in the block.
*/
/*
* Read the inode allocation bitmap for a given block_group, reading
* into the specified slot in the superblock's bitmap cache.
*
* Return buffer_head of bitmap on success or NULL.
*/
static struct buffer_head *
read_inode_bitmap(struct super_block * sb, unsigned long block_group)
{
struct ext2_group_desc *desc;
struct buffer_head *bh = NULL;
desc = ext2_get_group_desc(sb, block_group, NULL);
if (!desc)
goto error_out;
bh = sb_bread(sb, le32_to_cpu(desc->bg_inode_bitmap));
if (!bh)
ext2_error(sb, "read_inode_bitmap",
"Cannot read inode bitmap - "
"block_group = %lu, inode_bitmap = %u",
block_group, le32_to_cpu(desc->bg_inode_bitmap));
error_out:
return bh;
}
static void ext2_release_inode(struct super_block *sb, int group, int dir)
{
struct ext2_group_desc * desc;
struct buffer_head *bh;
desc = ext2_get_group_desc(sb, group, &bh);
if (!desc) {
ext2_error(sb, "ext2_release_inode",
"can't get descriptor for group %d", group);
return;
}
spin_lock(sb_bgl_lock(EXT2_SB(sb), group));
le16_add_cpu(&desc->bg_free_inodes_count, 1);
if (dir)
le16_add_cpu(&desc->bg_used_dirs_count, -1);
spin_unlock(sb_bgl_lock(EXT2_SB(sb), group));
if (dir)
percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter);
sb->s_dirt = 1;
mark_buffer_dirty(bh);
}
/*
* NOTE! When we get the inode, we're the only people
* that have access to it, and as such there are no
* race conditions we have to worry about. The inode
* is not on the hash-lists, and it cannot be reached
* through the filesystem because the directory entry
* has been deleted earlier.
*
* HOWEVER: we must make sure that we get no aliases,
* which means that we have to call "clear_inode()"
* _before_ we mark the inode not in use in the inode
* bitmaps. Otherwise a newly created file might use
* the same inode number (not actually the same pointer
* though), and then we'd have two inodes sharing the
* same inode number and space on the harddisk.
*/
void ext2_free_inode (struct inode * inode)
{
struct super_block * sb = inode->i_sb;
int is_directory;
unsigned long ino;
struct buffer_head *bitmap_bh = NULL;
unsigned long block_group;
unsigned long bit;
struct ext2_super_block * es;
ino = inode->i_ino;
ext2_debug ("freeing inode %lu\n", ino);
/*
* Note: we must free any quota before locking the superblock,
* as writing the quota to disk may need the lock as well.
*/
if (!is_bad_inode(inode)) {
/* Quota is already initialized in iput() */
ext2_xattr_delete_inode(inode);
dquot_free_inode(inode);
dquot_drop(inode);
}
es = EXT2_SB(sb)->s_es;
is_directory = S_ISDIR(inode->i_mode);
/* Do this BEFORE marking the inode not in use or returning an error */
clear_inode (inode);
if (ino < EXT2_FIRST_INO(sb) ||
ino > le32_to_cpu(es->s_inodes_count)) {
ext2_error (sb, "ext2_free_inode",
"reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT2_INODES_PER_GROUP(sb);
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
/* Ok, now we can actually update the inode bitmaps.. */
if (!ext2_clear_bit_atomic(sb_bgl_lock(EXT2_SB(sb), block_group),
bit, (void *) bitmap_bh->b_data))
ext2_error (sb, "ext2_free_inode",
"bit already cleared for inode %lu", ino);
else
ext2_release_inode(sb, block_group, is_directory);
mark_buffer_dirty(bitmap_bh);
if (sb->s_flags & MS_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
error_return:
brelse(bitmap_bh);
}
/*
* We perform asynchronous prereading of the new inode's inode block when
* we create the inode, in the expectation that the inode will be written
* back soon. There are two reasons:
*
* - When creating a large number of files, the async prereads will be
* nicely merged into large reads
* - When writing out a large number of inodes, we don't need to keep on
* stalling the writes while we read the inode block.
*
* FIXME: ext2_get_group_desc() needs to be simplified.
*/
static void ext2_preread_inode(struct inode *inode)
{
unsigned long block_group;
unsigned long offset;
unsigned long block;
struct ext2_group_desc * gdp;
struct backing_dev_info *bdi;
bdi = inode->i_mapping->backing_dev_info;
if (bdi_read_congested(bdi))
return;
if (bdi_write_congested(bdi))
return;
block_group = (inode->i_ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb);
gdp = ext2_get_group_desc(inode->i_sb, block_group, NULL);
if (gdp == NULL)
return;
/*
* Figure out the offset within the block group inode table
*/
offset = ((inode->i_ino - 1) % EXT2_INODES_PER_GROUP(inode->i_sb)) *
EXT2_INODE_SIZE(inode->i_sb);
block = le32_to_cpu(gdp->bg_inode_table) +
(offset >> EXT2_BLOCK_SIZE_BITS(inode->i_sb));
sb_breadahead(inode->i_sb, block);
}
/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
* the groups with above-average free space, that group with the fewest
* directories already is chosen.
*
* For other inodes, search forward from the parent directory\'s block
* group to find a free inode.
*/
static int find_group_dir(struct super_block *sb, struct inode *parent)
{
int ngroups = EXT2_SB(sb)->s_groups_count;
int avefreei = ext2_count_free_inodes(sb) / ngroups;
struct ext2_group_desc *desc, *best_desc = NULL;
int group, best_group = -1;
for (group = 0; group < ngroups; group++) {
desc = ext2_get_group_desc (sb, group, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
continue;
if (!best_desc ||
(le16_to_cpu(desc->bg_free_blocks_count) >
le16_to_cpu(best_desc->bg_free_blocks_count))) {
|