forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
ialloc.c
1623 lines (1451 loc) · 44.6 KB
/
ialloc.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext4/ialloc.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card ([email protected])
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* BSD ufs-inspired inode and directory allocation by
* Stephen Tweedie ([email protected]), 1993
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller ([email protected]), 1995
*/
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/random.h>
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <linux/cred.h>
#include <asm/byteorder.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include <trace/events/ext4.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.
*/
/*
* To avoid calling the atomic setbit hundreds or thousands of times, we only
* need to use it within a single byte (to ensure we get endianness right).
* We can use memset for the rest of the bitmap as there are no other users.
*/
void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
{
int i;
if (start_bit >= end_bit)
return;
ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
ext4_set_bit(i, bitmap);
if (i < end_bit)
memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
}
void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate)
{
if (uptodate) {
set_buffer_uptodate(bh);
set_bitmap_uptodate(bh);
}
unlock_buffer(bh);
put_bh(bh);
}
static int ext4_validate_inode_bitmap(struct super_block *sb,
struct ext4_group_desc *desc,
ext4_group_t block_group,
struct buffer_head *bh)
{
ext4_fsblk_t blk;
struct ext4_group_info *grp;
if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
return 0;
grp = ext4_get_group_info(sb, block_group);
if (buffer_verified(bh))
return 0;
if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
return -EFSCORRUPTED;
ext4_lock_group(sb, block_group);
if (buffer_verified(bh))
goto verified;
blk = ext4_inode_bitmap(sb, desc);
if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
EXT4_INODES_PER_GROUP(sb) / 8) ||
ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_CRC)) {
ext4_unlock_group(sb, block_group);
ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
"inode_bitmap = %llu", block_group, blk);
ext4_mark_group_bitmap_corrupted(sb, block_group,
EXT4_GROUP_INFO_IBITMAP_CORRUPT);
return -EFSBADCRC;
}
set_buffer_verified(bh);
verified:
ext4_unlock_group(sb, block_group);
return 0;
}
/*
* 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 an ERR_PTR on error.
*/
static struct buffer_head *
ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
{
struct ext4_group_desc *desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct buffer_head *bh = NULL;
ext4_fsblk_t bitmap_blk;
int err;
desc = ext4_get_group_desc(sb, block_group, NULL);
if (!desc)
return ERR_PTR(-EFSCORRUPTED);
bitmap_blk = ext4_inode_bitmap(sb, desc);
if ((bitmap_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
(bitmap_blk >= ext4_blocks_count(sbi->s_es))) {
ext4_error(sb, "Invalid inode bitmap blk %llu in "
"block_group %u", bitmap_blk, block_group);
ext4_mark_group_bitmap_corrupted(sb, block_group,
EXT4_GROUP_INFO_IBITMAP_CORRUPT);
return ERR_PTR(-EFSCORRUPTED);
}
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext4_warning(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return ERR_PTR(-ENOMEM);
}
if (bitmap_uptodate(bh))
goto verify;
lock_buffer(bh);
if (bitmap_uptodate(bh)) {
unlock_buffer(bh);
goto verify;
}
ext4_lock_group(sb, block_group);
if (ext4_has_group_desc_csum(sb) &&
(desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) {
if (block_group == 0) {
ext4_unlock_group(sb, block_group);
unlock_buffer(bh);
ext4_error(sb, "Inode bitmap for bg 0 marked "
"uninitialized");
err = -EFSCORRUPTED;
goto out;
}
memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
sb->s_blocksize * 8, bh->b_data);
set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
set_buffer_verified(bh);
ext4_unlock_group(sb, block_group);
unlock_buffer(bh);
return bh;
}
ext4_unlock_group(sb, block_group);
if (buffer_uptodate(bh)) {
/*
* if not uninit if bh is uptodate,
* bitmap is also uptodate
*/
set_bitmap_uptodate(bh);
unlock_buffer(bh);
goto verify;
}
/*
* submit the buffer_head for reading
*/
trace_ext4_load_inode_bitmap(sb, block_group);
ext4_read_bh(bh, REQ_META | REQ_PRIO, ext4_end_bitmap_read);
ext4_simulate_fail_bh(sb, bh, EXT4_SIM_IBITMAP_EIO);
if (!buffer_uptodate(bh)) {
put_bh(bh);
ext4_error_err(sb, EIO, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
ext4_mark_group_bitmap_corrupted(sb, block_group,
EXT4_GROUP_INFO_IBITMAP_CORRUPT);
return ERR_PTR(-EIO);
}
verify:
err = ext4_validate_inode_bitmap(sb, desc, block_group, bh);
if (err)
goto out;
return bh;
out:
put_bh(bh);
return ERR_PTR(err);
}
/*
* 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 ext4_free_inode(handle_t *handle, struct inode *inode)
{
struct super_block *sb = inode->i_sb;
int is_directory;
unsigned long ino;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
ext4_group_t block_group;
unsigned long bit;
struct ext4_group_desc *gdp;
struct ext4_super_block *es;
struct ext4_sb_info *sbi;
int fatal = 0, err, count, cleared;
struct ext4_group_info *grp;
if (!sb) {
printk(KERN_ERR "EXT4-fs: %s:%d: inode on "
"nonexistent device\n", __func__, __LINE__);
return;
}
if (atomic_read(&inode->i_count) > 1) {
ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: count=%d",
__func__, __LINE__, inode->i_ino,
atomic_read(&inode->i_count));
return;
}
if (inode->i_nlink) {
ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: nlink=%d\n",
__func__, __LINE__, inode->i_ino, inode->i_nlink);
return;
}
sbi = EXT4_SB(sb);
ino = inode->i_ino;
ext4_debug("freeing inode %lu\n", ino);
trace_ext4_free_inode(inode);
dquot_initialize(inode);
dquot_free_inode(inode);
is_directory = S_ISDIR(inode->i_mode);
/* Do this BEFORE marking the inode not in use or returning an error */
ext4_clear_inode(inode);
es = sbi->s_es;
if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext4_error(sb, "reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
/* Don't bother if the inode bitmap is corrupt. */
if (IS_ERR(bitmap_bh)) {
fatal = PTR_ERR(bitmap_bh);
bitmap_bh = NULL;
goto error_return;
}
if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
grp = ext4_get_group_info(sb, block_group);
if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) {
fatal = -EFSCORRUPTED;
goto error_return;
}
}
BUFFER_TRACE(bitmap_bh, "get_write_access");
fatal = ext4_journal_get_write_access(handle, bitmap_bh);
if (fatal)
goto error_return;
fatal = -ESRCH;
gdp = ext4_get_group_desc(sb, block_group, &bh2);
if (gdp) {
BUFFER_TRACE(bh2, "get_write_access");
fatal = ext4_journal_get_write_access(handle, bh2);
}
ext4_lock_group(sb, block_group);
cleared = ext4_test_and_clear_bit(bit, bitmap_bh->b_data);
if (fatal || !cleared) {
ext4_unlock_group(sb, block_group);
goto out;
}
count = ext4_free_inodes_count(sb, gdp) + 1;
ext4_free_inodes_set(sb, gdp, count);
if (is_directory) {
count = ext4_used_dirs_count(sb, gdp) - 1;
ext4_used_dirs_set(sb, gdp, count);
if (percpu_counter_initialized(&sbi->s_dirs_counter))
percpu_counter_dec(&sbi->s_dirs_counter);
}
ext4_inode_bitmap_csum_set(sb, block_group, gdp, bitmap_bh,
EXT4_INODES_PER_GROUP(sb) / 8);
ext4_group_desc_csum_set(sb, block_group, gdp);
ext4_unlock_group(sb, block_group);
if (percpu_counter_initialized(&sbi->s_freeinodes_counter))
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (sbi->s_log_groups_per_flex) {
struct flex_groups *fg;
fg = sbi_array_rcu_deref(sbi, s_flex_groups,
ext4_flex_group(sbi, block_group));
atomic_inc(&fg->free_inodes);
if (is_directory)
atomic_dec(&fg->used_dirs);
}
BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
out:
if (cleared) {
BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!fatal)
fatal = err;
} else {
ext4_error(sb, "bit already cleared for inode %lu", ino);
ext4_mark_group_bitmap_corrupted(sb, block_group,
EXT4_GROUP_INFO_IBITMAP_CORRUPT);
}
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, fatal);
}
struct orlov_stats {
__u64 free_clusters;
__u32 free_inodes;
__u32 used_dirs;
};
/*
* Helper function for Orlov's allocator; returns critical information
* for a particular block group or flex_bg. If flex_size is 1, then g
* is a block group number; otherwise it is flex_bg number.
*/
static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
int flex_size, struct orlov_stats *stats)
{
struct ext4_group_desc *desc;
if (flex_size > 1) {
struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb),
s_flex_groups, g);
stats->free_inodes = atomic_read(&fg->free_inodes);
stats->free_clusters = atomic64_read(&fg->free_clusters);
stats->used_dirs = atomic_read(&fg->used_dirs);
return;
}
desc = ext4_get_group_desc(sb, g, NULL);
if (desc) {
stats->free_inodes = ext4_free_inodes_count(sb, desc);
stats->free_clusters = ext4_free_group_clusters(sb, desc);
stats->used_dirs = ext4_used_dirs_count(sb, desc);
} else {
stats->free_inodes = 0;
stats->free_clusters = 0;
stats->used_dirs = 0;
}
}
/*
* Orlov's allocator for directories.
*
* We always try to spread first-level directories.
*
* If there are blockgroups with both free inodes and free clusters counts
* not worse than average we return one with smallest directory count.
* Otherwise we simply return a random group.
*
* For the rest rules look so:
*
* It's OK to put directory into a group unless
* it has too many directories already (max_dirs) or
* it has too few free inodes left (min_inodes) or
* it has too few free clusters left (min_clusters) or
* Parent's group is preferred, if it doesn't satisfy these
* conditions we search cyclically through the rest. If none
* of the groups look good we just look for a group with more
* free inodes than average (starting at parent's group).
*/
static int find_group_orlov(struct super_block *sb, struct inode *parent,
ext4_group_t *group, umode_t mode,
const struct qstr *qstr)
{
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t real_ngroups = ext4_get_groups_count(sb);
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei, grp_free;
ext4_fsblk_t freec, avefreec;
unsigned int ndirs;
int max_dirs, min_inodes;
ext4_grpblk_t min_clusters;
ext4_group_t i, grp, g, ngroups;
struct ext4_group_desc *desc;
struct orlov_stats stats;
int flex_size = ext4_flex_bg_size(sbi);
struct dx_hash_info hinfo;
ngroups = real_ngroups;
if (flex_size > 1) {
ngroups = (real_ngroups + flex_size - 1) >>
sbi->s_log_groups_per_flex;
parent_group >>= sbi->s_log_groups_per_flex;
}
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
avefreei = freei / ngroups;
freec = percpu_counter_read_positive(&sbi->s_freeclusters_counter);
avefreec = freec;
do_div(avefreec, ngroups);
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if (S_ISDIR(mode) &&
((parent == d_inode(sb->s_root)) ||
(ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) {
int best_ndir = inodes_per_group;
int ret = -1;
if (qstr) {
hinfo.hash_version = DX_HASH_HALF_MD4;
hinfo.seed = sbi->s_hash_seed;
ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo);
grp = hinfo.hash;
} else
grp = prandom_u32();
parent_group = (unsigned)grp % ngroups;
for (i = 0; i < ngroups; i++) {
g = (parent_group + i) % ngroups;
get_orlov_stats(sb, g, flex_size, &stats);
if (!stats.free_inodes)
continue;
if (stats.used_dirs >= best_ndir)
continue;
if (stats.free_inodes < avefreei)
continue;
if (stats.free_clusters < avefreec)
continue;
grp = g;
ret = 0;
best_ndir = stats.used_dirs;
}
if (ret)
goto fallback;
found_flex_bg:
if (flex_size == 1) {
*group = grp;
return 0;
}
/*
* We pack inodes at the beginning of the flexgroup's
* inode tables. Block allocation decisions will do
* something similar, although regular files will
* start at 2nd block group of the flexgroup. See
* ext4_ext_find_goal() and ext4_find_near().
*/
grp *= flex_size;
for (i = 0; i < flex_size; i++) {
if (grp+i >= real_ngroups)
break;
desc = ext4_get_group_desc(sb, grp+i, NULL);
if (desc && ext4_free_inodes_count(sb, desc)) {
*group = grp+i;
return 0;
}
}
goto fallback;
}
max_dirs = ndirs / ngroups + inodes_per_group / 16;
min_inodes = avefreei - inodes_per_group*flex_size / 4;
if (min_inodes < 1)
min_inodes = 1;
min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4;
/*
* Start looking in the flex group where we last allocated an
* inode for this parent directory
*/
if (EXT4_I(parent)->i_last_alloc_group != ~0) {
parent_group = EXT4_I(parent)->i_last_alloc_group;
if (flex_size > 1)
parent_group >>= sbi->s_log_groups_per_flex;
}
for (i = 0; i < ngroups; i++) {
grp = (parent_group + i) % ngroups;
get_orlov_stats(sb, grp, flex_size, &stats);
if (stats.used_dirs >= max_dirs)
continue;
if (stats.free_inodes < min_inodes)
continue;
if (stats.free_clusters < min_clusters)
continue;
goto found_flex_bg;
}
fallback:
ngroups = real_ngroups;
avefreei = freei / ngroups;
fallback_retry:
parent_group = EXT4_I(parent)->i_block_group;
for (i = 0; i < ngroups; i++) {
grp = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, grp, NULL);
if (desc) {
grp_free = ext4_free_inodes_count(sb, desc);
if (grp_free && grp_free >= avefreei) {
*group = grp;
return 0;
}
}
}
if (avefreei) {
/*
* The free-inodes counter is approximate, and for really small
* filesystems the above test can fail to find any blockgroups
*/
avefreei = 0;
goto fallback_retry;
}
return -1;
}
static int find_group_other(struct super_block *sb, struct inode *parent,
ext4_group_t *group, umode_t mode)
{
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
ext4_group_t i, last, ngroups = ext4_get_groups_count(sb);
struct ext4_group_desc *desc;
int flex_size = ext4_flex_bg_size(EXT4_SB(sb));
/*
* Try to place the inode is the same flex group as its
* parent. If we can't find space, use the Orlov algorithm to
* find another flex group, and store that information in the
* parent directory's inode information so that use that flex
* group for future allocations.
*/
if (flex_size > 1) {
int retry = 0;
try_again:
parent_group &= ~(flex_size-1);
last = parent_group + flex_size;
if (last > ngroups)
last = ngroups;
for (i = parent_group; i < last; i++) {
desc = ext4_get_group_desc(sb, i, NULL);
if (desc && ext4_free_inodes_count(sb, desc)) {
*group = i;
return 0;
}
}
if (!retry && EXT4_I(parent)->i_last_alloc_group != ~0) {
retry = 1;
parent_group = EXT4_I(parent)->i_last_alloc_group;
goto try_again;
}
/*
* If this didn't work, use the Orlov search algorithm
* to find a new flex group; we pass in the mode to
* avoid the topdir algorithms.
*/
*group = parent_group + flex_size;
if (*group > ngroups)
*group = 0;
return find_group_orlov(sb, parent, group, mode, NULL);
}
/*
* Try to place the inode in its parent directory
*/
*group = parent_group;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && ext4_free_inodes_count(sb, desc) &&
ext4_free_group_clusters(sb, desc))
return 0;
/*
* We're going to place this inode in a different blockgroup from its
* parent. We want to cause files in a common directory to all land in
* the same blockgroup. But we want files which are in a different
* directory which shares a blockgroup with our parent to land in a
* different blockgroup.
*
* So add our directory's i_ino into the starting point for the hash.
*/
*group = (*group + parent->i_ino) % ngroups;
/*
* Use a quadratic hash to find a group with a free inode and some free
* blocks.
*/
for (i = 1; i < ngroups; i <<= 1) {
*group += i;
if (*group >= ngroups)
*group -= ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && ext4_free_inodes_count(sb, desc) &&
ext4_free_group_clusters(sb, desc))
return 0;
}
/*
* That failed: try linear search for a free inode, even if that group
* has no free blocks.
*/
*group = parent_group;
for (i = 0; i < ngroups; i++) {
if (++*group >= ngroups)
*group = 0;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && ext4_free_inodes_count(sb, desc))
return 0;
}
return -1;
}
/*
* In no journal mode, if an inode has recently been deleted, we want
* to avoid reusing it until we're reasonably sure the inode table
* block has been written back to disk. (Yes, these values are
* somewhat arbitrary...)
*/
#define RECENTCY_MIN 60
#define RECENTCY_DIRTY 300
static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
{
struct ext4_group_desc *gdp;
struct ext4_inode *raw_inode;
struct buffer_head *bh;
int inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
int offset, ret = 0;
int recentcy = RECENTCY_MIN;
u32 dtime, now;
gdp = ext4_get_group_desc(sb, group, NULL);
if (unlikely(!gdp))
return 0;
bh = sb_find_get_block(sb, ext4_inode_table(sb, gdp) +
(ino / inodes_per_block));
if (!bh || !buffer_uptodate(bh))
/*
* If the block is not in the buffer cache, then it
* must have been written out.
*/
goto out;
offset = (ino % inodes_per_block) * EXT4_INODE_SIZE(sb);
raw_inode = (struct ext4_inode *) (bh->b_data + offset);
/* i_dtime is only 32 bits on disk, but we only care about relative
* times in the range of a few minutes (i.e. long enough to sync a
* recently-deleted inode to disk), so using the low 32 bits of the
* clock (a 68 year range) is enough, see time_before32() */
dtime = le32_to_cpu(raw_inode->i_dtime);
now = ktime_get_real_seconds();
if (buffer_dirty(bh))
recentcy += RECENTCY_DIRTY;
if (dtime && time_before32(dtime, now) &&
time_before32(now, dtime + recentcy))
ret = 1;
out:
brelse(bh);
return ret;
}
static int find_inode_bit(struct super_block *sb, ext4_group_t group,
struct buffer_head *bitmap, unsigned long *ino)
{
bool check_recently_deleted = EXT4_SB(sb)->s_journal == NULL;
unsigned long recently_deleted_ino = EXT4_INODES_PER_GROUP(sb);
next:
*ino = ext4_find_next_zero_bit((unsigned long *)
bitmap->b_data,
EXT4_INODES_PER_GROUP(sb), *ino);
if (*ino >= EXT4_INODES_PER_GROUP(sb))
goto not_found;
if (check_recently_deleted && recently_deleted(sb, group, *ino)) {
recently_deleted_ino = *ino;
*ino = *ino + 1;
if (*ino < EXT4_INODES_PER_GROUP(sb))
goto next;
goto not_found;
}
return 1;
not_found:
if (recently_deleted_ino >= EXT4_INODES_PER_GROUP(sb))
return 0;
/*
* Not reusing recently deleted inodes is mostly a preference. We don't
* want to report ENOSPC or skew allocation patterns because of that.
* So return even recently deleted inode if we could find better in the
* given range.
*/
*ino = recently_deleted_ino;
return 1;
}
int ext4_mark_inode_used(struct super_block *sb, int ino)
{
unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
struct buffer_head *inode_bitmap_bh = NULL, *group_desc_bh = NULL;
struct ext4_group_desc *gdp;
ext4_group_t group;
int bit;
int err = -EFSCORRUPTED;
if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
goto out;
group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
if (IS_ERR(inode_bitmap_bh))
return PTR_ERR(inode_bitmap_bh);
if (ext4_test_bit(bit, inode_bitmap_bh->b_data)) {
err = 0;
goto out;
}
gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
if (!gdp || !group_desc_bh) {
err = -EINVAL;
goto out;
}
ext4_set_bit(bit, inode_bitmap_bh->b_data);
BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(NULL, NULL, inode_bitmap_bh);
if (err) {
ext4_std_error(sb, err);
goto out;
}
err = sync_dirty_buffer(inode_bitmap_bh);
if (err) {
ext4_std_error(sb, err);
goto out;
}
/* We may have to initialize the block bitmap if it isn't already */
if (ext4_has_group_desc_csum(sb) &&
gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
struct buffer_head *block_bitmap_bh;
block_bitmap_bh = ext4_read_block_bitmap(sb, group);
if (IS_ERR(block_bitmap_bh)) {
err = PTR_ERR(block_bitmap_bh);
goto out;
}
BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
err = ext4_handle_dirty_metadata(NULL, NULL, block_bitmap_bh);
sync_dirty_buffer(block_bitmap_bh);
/* recheck and clear flag under lock if we still need to */
ext4_lock_group(sb, group);
if (ext4_has_group_desc_csum(sb) &&
(gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
ext4_free_group_clusters_set(sb, gdp,
ext4_free_clusters_after_init(sb, group, gdp));
ext4_block_bitmap_csum_set(sb, group, gdp,
block_bitmap_bh);
ext4_group_desc_csum_set(sb, group, gdp);
}
ext4_unlock_group(sb, group);
brelse(block_bitmap_bh);
if (err) {
ext4_std_error(sb, err);
goto out;
}
}
/* Update the relevant bg descriptor fields */
if (ext4_has_group_desc_csum(sb)) {
int free;
ext4_lock_group(sb, group); /* while we modify the bg desc */
free = EXT4_INODES_PER_GROUP(sb) -
ext4_itable_unused_count(sb, gdp);
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
free = 0;
}
/*
* Check the relative inode number against the last used
* relative inode number in this group. if it is greater
* we need to update the bg_itable_unused count
*/
if (bit >= free)
ext4_itable_unused_set(sb, gdp,
(EXT4_INODES_PER_GROUP(sb) - bit - 1));
} else {
ext4_lock_group(sb, group);
}
ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
if (ext4_has_group_desc_csum(sb)) {
ext4_inode_bitmap_csum_set(sb, group, gdp, inode_bitmap_bh,
EXT4_INODES_PER_GROUP(sb) / 8);
ext4_group_desc_csum_set(sb, group, gdp);
}
ext4_unlock_group(sb, group);
err = ext4_handle_dirty_metadata(NULL, NULL, group_desc_bh);
sync_dirty_buffer(group_desc_bh);
out:
return err;
}
static int ext4_xattr_credits_for_new_inode(struct inode *dir, mode_t mode,
bool encrypt)
{
struct super_block *sb = dir->i_sb;
int nblocks = 0;
#ifdef CONFIG_EXT4_FS_POSIX_ACL
struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT);
if (IS_ERR(p))
return PTR_ERR(p);
if (p) {
int acl_size = p->a_count * sizeof(ext4_acl_entry);
nblocks += (S_ISDIR(mode) ? 2 : 1) *
__ext4_xattr_set_credits(sb, NULL /* inode */,
NULL /* block_bh */, acl_size,
true /* is_create */);
posix_acl_release(p);
}
#endif
#ifdef CONFIG_SECURITY
{
int num_security_xattrs = 1;
#ifdef CONFIG_INTEGRITY
num_security_xattrs++;
#endif
/*
* We assume that security xattrs are never more than 1k.
* In practice they are under 128 bytes.
*/
nblocks += num_security_xattrs *
__ext4_xattr_set_credits(sb, NULL /* inode */,
NULL /* block_bh */, 1024,
true /* is_create */);
}
#endif
if (encrypt)
nblocks += __ext4_xattr_set_credits(sb,
NULL /* inode */,
NULL /* block_bh */,
FSCRYPT_SET_CONTEXT_MAX_SIZE,
true /* is_create */);
return nblocks;
}
/*
* 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.
*/
struct inode *__ext4_new_inode(struct user_namespace *mnt_userns,
handle_t *handle, struct inode *dir,
umode_t mode, const struct qstr *qstr,
__u32 goal, uid_t *owner, __u32 i_flags,
int handle_type, unsigned int line_no,
int nblocks)
{
struct super_block *sb;
struct buffer_head *inode_bitmap_bh = NULL;
struct buffer_head *group_desc_bh;
ext4_group_t ngroups, group = 0;
unsigned long ino = 0;
struct inode *inode;
struct ext4_group_desc *gdp = NULL;
struct ext4_inode_info *ei;
struct ext4_sb_info *sbi;
int ret2, err;
struct inode *ret;
ext4_group_t i;
ext4_group_t flex_group;
struct ext4_group_info *grp = NULL;
bool encrypt = false;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
return ERR_PTR(-EPERM);
sb = dir->i_sb;
sbi = EXT4_SB(sb);
if (unlikely(ext4_forced_shutdown(sbi)))
return ERR_PTR(-EIO);
ngroups = ext4_get_groups_count(sb);
trace_ext4_request_inode(dir, mode);
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
ei = EXT4_I(inode);
/*
* Initialize owners and quota early so that we don't have to account
* for quota initialization worst case in standard inode creating
* transaction
*/
if (owner) {
inode->i_mode = mode;
i_uid_write(inode, owner[0]);
i_gid_write(inode, owner[1]);
} else if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
inode_fsuid_set(inode, mnt_userns);
inode->i_gid = dir->i_gid;
} else
inode_init_owner(mnt_userns, inode, dir, mode);
if (ext4_has_feature_project(sb) &&
ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT))
ei->i_projid = EXT4_I(dir)->i_projid;
else
ei->i_projid = make_kprojid(&init_user_ns, EXT4_DEF_PROJID);
if (!(i_flags & EXT4_EA_INODE_FL)) {
err = fscrypt_prepare_new_inode(dir, inode, &encrypt);
if (err)
goto out;
}
err = dquot_initialize(inode);
if (err)
goto out;
if (!handle && sbi->s_journal && !(i_flags & EXT4_EA_INODE_FL)) {
ret2 = ext4_xattr_credits_for_new_inode(dir, mode, encrypt);
if (ret2 < 0) {
err = ret2;
goto out;
}