forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
super.c
2296 lines (2012 loc) · 59.7 KB
/
super.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
/*
* This file is part of UBIFS.
*
* Copyright (C) 2006-2008 Nokia Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published by
* the Free Software Foundation.
*
* 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., 51
* Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*
* Authors: Artem Bityutskiy (Битюцкий Артём)
* Adrian Hunter
*/
/*
* This file implements UBIFS initialization and VFS superblock operations. Some
* initialization stuff which is rather large and complex is placed at
* corresponding subsystems, but most of it is here.
*/
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/kthread.h>
#include <linux/parser.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/math64.h>
#include <linux/writeback.h>
#include "ubifs.h"
/*
* Maximum amount of memory we may 'kmalloc()' without worrying that we are
* allocating too much.
*/
#define UBIFS_KMALLOC_OK (128*1024)
/* Slab cache for UBIFS inodes */
struct kmem_cache *ubifs_inode_slab;
/* UBIFS TNC shrinker description */
static struct shrinker ubifs_shrinker_info = {
.scan_objects = ubifs_shrink_scan,
.count_objects = ubifs_shrink_count,
.seeks = DEFAULT_SEEKS,
};
/**
* validate_inode - validate inode.
* @c: UBIFS file-system description object
* @inode: the inode to validate
*
* This is a helper function for 'ubifs_iget()' which validates various fields
* of a newly built inode to make sure they contain sane values and prevent
* possible vulnerabilities. Returns zero if the inode is all right and
* a non-zero error code if not.
*/
static int validate_inode(struct ubifs_info *c, const struct inode *inode)
{
int err;
const struct ubifs_inode *ui = ubifs_inode(inode);
if (inode->i_size > c->max_inode_sz) {
ubifs_err("inode is too large (%lld)",
(long long)inode->i_size);
return 1;
}
if (ui->compr_type < 0 || ui->compr_type >= UBIFS_COMPR_TYPES_CNT) {
ubifs_err("unknown compression type %d", ui->compr_type);
return 2;
}
if (ui->xattr_names + ui->xattr_cnt > XATTR_LIST_MAX)
return 3;
if (ui->data_len < 0 || ui->data_len > UBIFS_MAX_INO_DATA)
return 4;
if (ui->xattr && !S_ISREG(inode->i_mode))
return 5;
if (!ubifs_compr_present(ui->compr_type)) {
ubifs_warn("inode %lu uses '%s' compression, but it was not compiled in",
inode->i_ino, ubifs_compr_name(ui->compr_type));
}
err = dbg_check_dir(c, inode);
return err;
}
struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
{
int err;
union ubifs_key key;
struct ubifs_ino_node *ino;
struct ubifs_info *c = sb->s_fs_info;
struct inode *inode;
struct ubifs_inode *ui;
dbg_gen("inode %lu", inum);
inode = iget_locked(sb, inum);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
ui = ubifs_inode(inode);
ino = kmalloc(UBIFS_MAX_INO_NODE_SZ, GFP_NOFS);
if (!ino) {
err = -ENOMEM;
goto out;
}
ino_key_init(c, &key, inode->i_ino);
err = ubifs_tnc_lookup(c, &key, ino);
if (err)
goto out_ino;
inode->i_flags |= (S_NOCMTIME | S_NOATIME);
set_nlink(inode, le32_to_cpu(ino->nlink));
i_uid_write(inode, le32_to_cpu(ino->uid));
i_gid_write(inode, le32_to_cpu(ino->gid));
inode->i_atime.tv_sec = (int64_t)le64_to_cpu(ino->atime_sec);
inode->i_atime.tv_nsec = le32_to_cpu(ino->atime_nsec);
inode->i_mtime.tv_sec = (int64_t)le64_to_cpu(ino->mtime_sec);
inode->i_mtime.tv_nsec = le32_to_cpu(ino->mtime_nsec);
inode->i_ctime.tv_sec = (int64_t)le64_to_cpu(ino->ctime_sec);
inode->i_ctime.tv_nsec = le32_to_cpu(ino->ctime_nsec);
inode->i_mode = le32_to_cpu(ino->mode);
inode->i_size = le64_to_cpu(ino->size);
ui->data_len = le32_to_cpu(ino->data_len);
ui->flags = le32_to_cpu(ino->flags);
ui->compr_type = le16_to_cpu(ino->compr_type);
ui->creat_sqnum = le64_to_cpu(ino->creat_sqnum);
ui->xattr_cnt = le32_to_cpu(ino->xattr_cnt);
ui->xattr_size = le32_to_cpu(ino->xattr_size);
ui->xattr_names = le32_to_cpu(ino->xattr_names);
ui->synced_i_size = ui->ui_size = inode->i_size;
ui->xattr = (ui->flags & UBIFS_XATTR_FL) ? 1 : 0;
err = validate_inode(c, inode);
if (err)
goto out_invalid;
/* Disable read-ahead */
inode->i_mapping->backing_dev_info = &c->bdi;
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_mapping->a_ops = &ubifs_file_address_operations;
inode->i_op = &ubifs_file_inode_operations;
inode->i_fop = &ubifs_file_operations;
if (ui->xattr) {
ui->data = kmalloc(ui->data_len + 1, GFP_NOFS);
if (!ui->data) {
err = -ENOMEM;
goto out_ino;
}
memcpy(ui->data, ino->data, ui->data_len);
((char *)ui->data)[ui->data_len] = '\0';
} else if (ui->data_len != 0) {
err = 10;
goto out_invalid;
}
break;
case S_IFDIR:
inode->i_op = &ubifs_dir_inode_operations;
inode->i_fop = &ubifs_dir_operations;
if (ui->data_len != 0) {
err = 11;
goto out_invalid;
}
break;
case S_IFLNK:
inode->i_op = &ubifs_symlink_inode_operations;
if (ui->data_len <= 0 || ui->data_len > UBIFS_MAX_INO_DATA) {
err = 12;
goto out_invalid;
}
ui->data = kmalloc(ui->data_len + 1, GFP_NOFS);
if (!ui->data) {
err = -ENOMEM;
goto out_ino;
}
memcpy(ui->data, ino->data, ui->data_len);
((char *)ui->data)[ui->data_len] = '\0';
break;
case S_IFBLK:
case S_IFCHR:
{
dev_t rdev;
union ubifs_dev_desc *dev;
ui->data = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS);
if (!ui->data) {
err = -ENOMEM;
goto out_ino;
}
dev = (union ubifs_dev_desc *)ino->data;
if (ui->data_len == sizeof(dev->new))
rdev = new_decode_dev(le32_to_cpu(dev->new));
else if (ui->data_len == sizeof(dev->huge))
rdev = huge_decode_dev(le64_to_cpu(dev->huge));
else {
err = 13;
goto out_invalid;
}
memcpy(ui->data, ino->data, ui->data_len);
inode->i_op = &ubifs_file_inode_operations;
init_special_inode(inode, inode->i_mode, rdev);
break;
}
case S_IFSOCK:
case S_IFIFO:
inode->i_op = &ubifs_file_inode_operations;
init_special_inode(inode, inode->i_mode, 0);
if (ui->data_len != 0) {
err = 14;
goto out_invalid;
}
break;
default:
err = 15;
goto out_invalid;
}
kfree(ino);
ubifs_set_inode_flags(inode);
unlock_new_inode(inode);
return inode;
out_invalid:
ubifs_err("inode %lu validation failed, error %d", inode->i_ino, err);
ubifs_dump_node(c, ino);
ubifs_dump_inode(c, inode);
err = -EINVAL;
out_ino:
kfree(ino);
out:
ubifs_err("failed to read inode %lu, error %d", inode->i_ino, err);
iget_failed(inode);
return ERR_PTR(err);
}
static struct inode *ubifs_alloc_inode(struct super_block *sb)
{
struct ubifs_inode *ui;
ui = kmem_cache_alloc(ubifs_inode_slab, GFP_NOFS);
if (!ui)
return NULL;
memset((void *)ui + sizeof(struct inode), 0,
sizeof(struct ubifs_inode) - sizeof(struct inode));
mutex_init(&ui->ui_mutex);
spin_lock_init(&ui->ui_lock);
return &ui->vfs_inode;
};
static void ubifs_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
struct ubifs_inode *ui = ubifs_inode(inode);
kmem_cache_free(ubifs_inode_slab, ui);
}
static void ubifs_destroy_inode(struct inode *inode)
{
struct ubifs_inode *ui = ubifs_inode(inode);
kfree(ui->data);
call_rcu(&inode->i_rcu, ubifs_i_callback);
}
/*
* Note, Linux write-back code calls this without 'i_mutex'.
*/
static int ubifs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int err = 0;
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct ubifs_inode *ui = ubifs_inode(inode);
ubifs_assert(!ui->xattr);
if (is_bad_inode(inode))
return 0;
mutex_lock(&ui->ui_mutex);
/*
* Due to races between write-back forced by budgeting
* (see 'sync_some_inodes()') and background write-back, the inode may
* have already been synchronized, do not do this again. This might
* also happen if it was synchronized in an VFS operation, e.g.
* 'ubifs_link()'.
*/
if (!ui->dirty) {
mutex_unlock(&ui->ui_mutex);
return 0;
}
/*
* As an optimization, do not write orphan inodes to the media just
* because this is not needed.
*/
dbg_gen("inode %lu, mode %#x, nlink %u",
inode->i_ino, (int)inode->i_mode, inode->i_nlink);
if (inode->i_nlink) {
err = ubifs_jnl_write_inode(c, inode);
if (err)
ubifs_err("can't write inode %lu, error %d",
inode->i_ino, err);
else
err = dbg_check_inode_size(c, inode, ui->ui_size);
}
ui->dirty = 0;
mutex_unlock(&ui->ui_mutex);
ubifs_release_dirty_inode_budget(c, ui);
return err;
}
static void ubifs_evict_inode(struct inode *inode)
{
int err;
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct ubifs_inode *ui = ubifs_inode(inode);
if (ui->xattr)
/*
* Extended attribute inode deletions are fully handled in
* 'ubifs_removexattr()'. These inodes are special and have
* limited usage, so there is nothing to do here.
*/
goto out;
dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode);
ubifs_assert(!atomic_read(&inode->i_count));
truncate_inode_pages(&inode->i_data, 0);
if (inode->i_nlink)
goto done;
if (is_bad_inode(inode))
goto out;
ui->ui_size = inode->i_size = 0;
err = ubifs_jnl_delete_inode(c, inode);
if (err)
/*
* Worst case we have a lost orphan inode wasting space, so a
* simple error message is OK here.
*/
ubifs_err("can't delete inode %lu, error %d",
inode->i_ino, err);
out:
if (ui->dirty)
ubifs_release_dirty_inode_budget(c, ui);
else {
/* We've deleted something - clean the "no space" flags */
c->bi.nospace = c->bi.nospace_rp = 0;
smp_wmb();
}
done:
clear_inode(inode);
}
static void ubifs_dirty_inode(struct inode *inode, int flags)
{
struct ubifs_inode *ui = ubifs_inode(inode);
ubifs_assert(mutex_is_locked(&ui->ui_mutex));
if (!ui->dirty) {
ui->dirty = 1;
dbg_gen("inode %lu", inode->i_ino);
}
}
static int ubifs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct ubifs_info *c = dentry->d_sb->s_fs_info;
unsigned long long free;
__le32 *uuid = (__le32 *)c->uuid;
free = ubifs_get_free_space(c);
dbg_gen("free space %lld bytes (%lld blocks)",
free, free >> UBIFS_BLOCK_SHIFT);
buf->f_type = UBIFS_SUPER_MAGIC;
buf->f_bsize = UBIFS_BLOCK_SIZE;
buf->f_blocks = c->block_cnt;
buf->f_bfree = free >> UBIFS_BLOCK_SHIFT;
if (free > c->report_rp_size)
buf->f_bavail = (free - c->report_rp_size) >> UBIFS_BLOCK_SHIFT;
else
buf->f_bavail = 0;
buf->f_files = 0;
buf->f_ffree = 0;
buf->f_namelen = UBIFS_MAX_NLEN;
buf->f_fsid.val[0] = le32_to_cpu(uuid[0]) ^ le32_to_cpu(uuid[2]);
buf->f_fsid.val[1] = le32_to_cpu(uuid[1]) ^ le32_to_cpu(uuid[3]);
ubifs_assert(buf->f_bfree <= c->block_cnt);
return 0;
}
static int ubifs_show_options(struct seq_file *s, struct dentry *root)
{
struct ubifs_info *c = root->d_sb->s_fs_info;
if (c->mount_opts.unmount_mode == 2)
seq_printf(s, ",fast_unmount");
else if (c->mount_opts.unmount_mode == 1)
seq_printf(s, ",norm_unmount");
if (c->mount_opts.bulk_read == 2)
seq_printf(s, ",bulk_read");
else if (c->mount_opts.bulk_read == 1)
seq_printf(s, ",no_bulk_read");
if (c->mount_opts.chk_data_crc == 2)
seq_printf(s, ",chk_data_crc");
else if (c->mount_opts.chk_data_crc == 1)
seq_printf(s, ",no_chk_data_crc");
if (c->mount_opts.override_compr) {
seq_printf(s, ",compr=%s",
ubifs_compr_name(c->mount_opts.compr_type));
}
return 0;
}
static int ubifs_sync_fs(struct super_block *sb, int wait)
{
int i, err;
struct ubifs_info *c = sb->s_fs_info;
/*
* Zero @wait is just an advisory thing to help the file system shove
* lots of data into the queues, and there will be the second
* '->sync_fs()' call, with non-zero @wait.
*/
if (!wait)
return 0;
/*
* Synchronize write buffers, because 'ubifs_run_commit()' does not
* do this if it waits for an already running commit.
*/
for (i = 0; i < c->jhead_cnt; i++) {
err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
if (err)
return err;
}
/*
* Strictly speaking, it is not necessary to commit the journal here,
* synchronizing write-buffers would be enough. But committing makes
* UBIFS free space predictions much more accurate, so we want to let
* the user be able to get more accurate results of 'statfs()' after
* they synchronize the file system.
*/
err = ubifs_run_commit(c);
if (err)
return err;
return ubi_sync(c->vi.ubi_num);
}
/**
* init_constants_early - initialize UBIFS constants.
* @c: UBIFS file-system description object
*
* This function initialize UBIFS constants which do not need the superblock to
* be read. It also checks that the UBI volume satisfies basic UBIFS
* requirements. Returns zero in case of success and a negative error code in
* case of failure.
*/
static int init_constants_early(struct ubifs_info *c)
{
if (c->vi.corrupted) {
ubifs_warn("UBI volume is corrupted - read-only mode");
c->ro_media = 1;
}
if (c->di.ro_mode) {
ubifs_msg("read-only UBI device");
c->ro_media = 1;
}
if (c->vi.vol_type == UBI_STATIC_VOLUME) {
ubifs_msg("static UBI volume - read-only mode");
c->ro_media = 1;
}
c->leb_cnt = c->vi.size;
c->leb_size = c->vi.usable_leb_size;
c->leb_start = c->di.leb_start;
c->half_leb_size = c->leb_size / 2;
c->min_io_size = c->di.min_io_size;
c->min_io_shift = fls(c->min_io_size) - 1;
c->max_write_size = c->di.max_write_size;
c->max_write_shift = fls(c->max_write_size) - 1;
if (c->leb_size < UBIFS_MIN_LEB_SZ) {
ubifs_err("too small LEBs (%d bytes), min. is %d bytes",
c->leb_size, UBIFS_MIN_LEB_SZ);
return -EINVAL;
}
if (c->leb_cnt < UBIFS_MIN_LEB_CNT) {
ubifs_err("too few LEBs (%d), min. is %d",
c->leb_cnt, UBIFS_MIN_LEB_CNT);
return -EINVAL;
}
if (!is_power_of_2(c->min_io_size)) {
ubifs_err("bad min. I/O size %d", c->min_io_size);
return -EINVAL;
}
/*
* Maximum write size has to be greater or equivalent to min. I/O
* size, and be multiple of min. I/O size.
*/
if (c->max_write_size < c->min_io_size ||
c->max_write_size % c->min_io_size ||
!is_power_of_2(c->max_write_size)) {
ubifs_err("bad write buffer size %d for %d min. I/O unit",
c->max_write_size, c->min_io_size);
return -EINVAL;
}
/*
* UBIFS aligns all node to 8-byte boundary, so to make function in
* io.c simpler, assume minimum I/O unit size to be 8 bytes if it is
* less than 8.
*/
if (c->min_io_size < 8) {
c->min_io_size = 8;
c->min_io_shift = 3;
if (c->max_write_size < c->min_io_size) {
c->max_write_size = c->min_io_size;
c->max_write_shift = c->min_io_shift;
}
}
c->ref_node_alsz = ALIGN(UBIFS_REF_NODE_SZ, c->min_io_size);
c->mst_node_alsz = ALIGN(UBIFS_MST_NODE_SZ, c->min_io_size);
/*
* Initialize node length ranges which are mostly needed for node
* length validation.
*/
c->ranges[UBIFS_PAD_NODE].len = UBIFS_PAD_NODE_SZ;
c->ranges[UBIFS_SB_NODE].len = UBIFS_SB_NODE_SZ;
c->ranges[UBIFS_MST_NODE].len = UBIFS_MST_NODE_SZ;
c->ranges[UBIFS_REF_NODE].len = UBIFS_REF_NODE_SZ;
c->ranges[UBIFS_TRUN_NODE].len = UBIFS_TRUN_NODE_SZ;
c->ranges[UBIFS_CS_NODE].len = UBIFS_CS_NODE_SZ;
c->ranges[UBIFS_INO_NODE].min_len = UBIFS_INO_NODE_SZ;
c->ranges[UBIFS_INO_NODE].max_len = UBIFS_MAX_INO_NODE_SZ;
c->ranges[UBIFS_ORPH_NODE].min_len =
UBIFS_ORPH_NODE_SZ + sizeof(__le64);
c->ranges[UBIFS_ORPH_NODE].max_len = c->leb_size;
c->ranges[UBIFS_DENT_NODE].min_len = UBIFS_DENT_NODE_SZ;
c->ranges[UBIFS_DENT_NODE].max_len = UBIFS_MAX_DENT_NODE_SZ;
c->ranges[UBIFS_XENT_NODE].min_len = UBIFS_XENT_NODE_SZ;
c->ranges[UBIFS_XENT_NODE].max_len = UBIFS_MAX_XENT_NODE_SZ;
c->ranges[UBIFS_DATA_NODE].min_len = UBIFS_DATA_NODE_SZ;
c->ranges[UBIFS_DATA_NODE].max_len = UBIFS_MAX_DATA_NODE_SZ;
/*
* Minimum indexing node size is amended later when superblock is
* read and the key length is known.
*/
c->ranges[UBIFS_IDX_NODE].min_len = UBIFS_IDX_NODE_SZ + UBIFS_BRANCH_SZ;
/*
* Maximum indexing node size is amended later when superblock is
* read and the fanout is known.
*/
c->ranges[UBIFS_IDX_NODE].max_len = INT_MAX;
/*
* Initialize dead and dark LEB space watermarks. See gc.c for comments
* about these values.
*/
c->dead_wm = ALIGN(MIN_WRITE_SZ, c->min_io_size);
c->dark_wm = ALIGN(UBIFS_MAX_NODE_SZ, c->min_io_size);
/*
* Calculate how many bytes would be wasted at the end of LEB if it was
* fully filled with data nodes of maximum size. This is used in
* calculations when reporting free space.
*/
c->leb_overhead = c->leb_size % UBIFS_MAX_DATA_NODE_SZ;
/* Buffer size for bulk-reads */
c->max_bu_buf_len = UBIFS_MAX_BULK_READ * UBIFS_MAX_DATA_NODE_SZ;
if (c->max_bu_buf_len > c->leb_size)
c->max_bu_buf_len = c->leb_size;
return 0;
}
/**
* bud_wbuf_callback - bud LEB write-buffer synchronization call-back.
* @c: UBIFS file-system description object
* @lnum: LEB the write-buffer was synchronized to
* @free: how many free bytes left in this LEB
* @pad: how many bytes were padded
*
* This is a callback function which is called by the I/O unit when the
* write-buffer is synchronized. We need this to correctly maintain space
* accounting in bud logical eraseblocks. This function returns zero in case of
* success and a negative error code in case of failure.
*
* This function actually belongs to the journal, but we keep it here because
* we want to keep it static.
*/
static int bud_wbuf_callback(struct ubifs_info *c, int lnum, int free, int pad)
{
return ubifs_update_one_lp(c, lnum, free, pad, 0, 0);
}
/*
* init_constants_sb - initialize UBIFS constants.
* @c: UBIFS file-system description object
*
* This is a helper function which initializes various UBIFS constants after
* the superblock has been read. It also checks various UBIFS parameters and
* makes sure they are all right. Returns zero in case of success and a
* negative error code in case of failure.
*/
static int init_constants_sb(struct ubifs_info *c)
{
int tmp, err;
long long tmp64;
c->main_bytes = (long long)c->main_lebs * c->leb_size;
c->max_znode_sz = sizeof(struct ubifs_znode) +
c->fanout * sizeof(struct ubifs_zbranch);
tmp = ubifs_idx_node_sz(c, 1);
c->ranges[UBIFS_IDX_NODE].min_len = tmp;
c->min_idx_node_sz = ALIGN(tmp, 8);
tmp = ubifs_idx_node_sz(c, c->fanout);
c->ranges[UBIFS_IDX_NODE].max_len = tmp;
c->max_idx_node_sz = ALIGN(tmp, 8);
/* Make sure LEB size is large enough to fit full commit */
tmp = UBIFS_CS_NODE_SZ + UBIFS_REF_NODE_SZ * c->jhead_cnt;
tmp = ALIGN(tmp, c->min_io_size);
if (tmp > c->leb_size) {
ubifs_err("too small LEB size %d, at least %d needed",
c->leb_size, tmp);
return -EINVAL;
}
/*
* Make sure that the log is large enough to fit reference nodes for
* all buds plus one reserved LEB.
*/
tmp64 = c->max_bud_bytes + c->leb_size - 1;
c->max_bud_cnt = div_u64(tmp64, c->leb_size);
tmp = (c->ref_node_alsz * c->max_bud_cnt + c->leb_size - 1);
tmp /= c->leb_size;
tmp += 1;
if (c->log_lebs < tmp) {
ubifs_err("too small log %d LEBs, required min. %d LEBs",
c->log_lebs, tmp);
return -EINVAL;
}
/*
* When budgeting we assume worst-case scenarios when the pages are not
* be compressed and direntries are of the maximum size.
*
* Note, data, which may be stored in inodes is budgeted separately, so
* it is not included into 'c->bi.inode_budget'.
*/
c->bi.page_budget = UBIFS_MAX_DATA_NODE_SZ * UBIFS_BLOCKS_PER_PAGE;
c->bi.inode_budget = UBIFS_INO_NODE_SZ;
c->bi.dent_budget = UBIFS_MAX_DENT_NODE_SZ;
/*
* When the amount of flash space used by buds becomes
* 'c->max_bud_bytes', UBIFS just blocks all writers and starts commit.
* The writers are unblocked when the commit is finished. To avoid
* writers to be blocked UBIFS initiates background commit in advance,
* when number of bud bytes becomes above the limit defined below.
*/
c->bg_bud_bytes = (c->max_bud_bytes * 13) >> 4;
/*
* Ensure minimum journal size. All the bytes in the journal heads are
* considered to be used, when calculating the current journal usage.
* Consequently, if the journal is too small, UBIFS will treat it as
* always full.
*/
tmp64 = (long long)(c->jhead_cnt + 1) * c->leb_size + 1;
if (c->bg_bud_bytes < tmp64)
c->bg_bud_bytes = tmp64;
if (c->max_bud_bytes < tmp64 + c->leb_size)
c->max_bud_bytes = tmp64 + c->leb_size;
err = ubifs_calc_lpt_geom(c);
if (err)
return err;
/* Initialize effective LEB size used in budgeting calculations */
c->idx_leb_size = c->leb_size - c->max_idx_node_sz;
return 0;
}
/*
* init_constants_master - initialize UBIFS constants.
* @c: UBIFS file-system description object
*
* This is a helper function which initializes various UBIFS constants after
* the master node has been read. It also checks various UBIFS parameters and
* makes sure they are all right.
*/
static void init_constants_master(struct ubifs_info *c)
{
long long tmp64;
c->bi.min_idx_lebs = ubifs_calc_min_idx_lebs(c);
c->report_rp_size = ubifs_reported_space(c, c->rp_size);
/*
* Calculate total amount of FS blocks. This number is not used
* internally because it does not make much sense for UBIFS, but it is
* necessary to report something for the 'statfs()' call.
*
* Subtract the LEB reserved for GC, the LEB which is reserved for
* deletions, minimum LEBs for the index, and assume only one journal
* head is available.
*/
tmp64 = c->main_lebs - 1 - 1 - MIN_INDEX_LEBS - c->jhead_cnt + 1;
tmp64 *= (long long)c->leb_size - c->leb_overhead;
tmp64 = ubifs_reported_space(c, tmp64);
c->block_cnt = tmp64 >> UBIFS_BLOCK_SHIFT;
}
/**
* take_gc_lnum - reserve GC LEB.
* @c: UBIFS file-system description object
*
* This function ensures that the LEB reserved for garbage collection is marked
* as "taken" in lprops. We also have to set free space to LEB size and dirty
* space to zero, because lprops may contain out-of-date information if the
* file-system was un-mounted before it has been committed. This function
* returns zero in case of success and a negative error code in case of
* failure.
*/
static int take_gc_lnum(struct ubifs_info *c)
{
int err;
if (c->gc_lnum == -1) {
ubifs_err("no LEB for GC");
return -EINVAL;
}
/* And we have to tell lprops that this LEB is taken */
err = ubifs_change_one_lp(c, c->gc_lnum, c->leb_size, 0,
LPROPS_TAKEN, 0, 0);
return err;
}
/**
* alloc_wbufs - allocate write-buffers.
* @c: UBIFS file-system description object
*
* This helper function allocates and initializes UBIFS write-buffers. Returns
* zero in case of success and %-ENOMEM in case of failure.
*/
static int alloc_wbufs(struct ubifs_info *c)
{
int i, err;
c->jheads = kzalloc(c->jhead_cnt * sizeof(struct ubifs_jhead),
GFP_KERNEL);
if (!c->jheads)
return -ENOMEM;
/* Initialize journal heads */
for (i = 0; i < c->jhead_cnt; i++) {
INIT_LIST_HEAD(&c->jheads[i].buds_list);
err = ubifs_wbuf_init(c, &c->jheads[i].wbuf);
if (err)
return err;
c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback;
c->jheads[i].wbuf.jhead = i;
c->jheads[i].grouped = 1;
}
/*
* Garbage Collector head does not need to be synchronized by timer.
* Also GC head nodes are not grouped.
*/
c->jheads[GCHD].wbuf.no_timer = 1;
c->jheads[GCHD].grouped = 0;
return 0;
}
/**
* free_wbufs - free write-buffers.
* @c: UBIFS file-system description object
*/
static void free_wbufs(struct ubifs_info *c)
{
int i;
if (c->jheads) {
for (i = 0; i < c->jhead_cnt; i++) {
kfree(c->jheads[i].wbuf.buf);
kfree(c->jheads[i].wbuf.inodes);
}
kfree(c->jheads);
c->jheads = NULL;
}
}
/**
* free_orphans - free orphans.
* @c: UBIFS file-system description object
*/
static void free_orphans(struct ubifs_info *c)
{
struct ubifs_orphan *orph;
while (c->orph_dnext) {
orph = c->orph_dnext;
c->orph_dnext = orph->dnext;
list_del(&orph->list);
kfree(orph);
}
while (!list_empty(&c->orph_list)) {
orph = list_entry(c->orph_list.next, struct ubifs_orphan, list);
list_del(&orph->list);
kfree(orph);
ubifs_err("orphan list not empty at unmount");
}
vfree(c->orph_buf);
c->orph_buf = NULL;
}
/**
* free_buds - free per-bud objects.
* @c: UBIFS file-system description object
*/
static void free_buds(struct ubifs_info *c)
{
struct ubifs_bud *bud, *n;
rbtree_postorder_for_each_entry_safe(bud, n, &c->buds, rb)
kfree(bud);
}
/**
* check_volume_empty - check if the UBI volume is empty.
* @c: UBIFS file-system description object
*
* This function checks if the UBIFS volume is empty by looking if its LEBs are
* mapped or not. The result of checking is stored in the @c->empty variable.
* Returns zero in case of success and a negative error code in case of
* failure.
*/
static int check_volume_empty(struct ubifs_info *c)
{
int lnum, err;
c->empty = 1;
for (lnum = 0; lnum < c->leb_cnt; lnum++) {
err = ubifs_is_mapped(c, lnum);
if (unlikely(err < 0))
return err;
if (err == 1) {
c->empty = 0;
break;
}
cond_resched();
}
return 0;
}
/*
* UBIFS mount options.
*
* Opt_fast_unmount: do not run a journal commit before un-mounting
* Opt_norm_unmount: run a journal commit before un-mounting
* Opt_bulk_read: enable bulk-reads
* Opt_no_bulk_read: disable bulk-reads
* Opt_chk_data_crc: check CRCs when reading data nodes
* Opt_no_chk_data_crc: do not check CRCs when reading data nodes
* Opt_override_compr: override default compressor
* Opt_err: just end of array marker
*/
enum {
Opt_fast_unmount,
Opt_norm_unmount,
Opt_bulk_read,
Opt_no_bulk_read,
Opt_chk_data_crc,
Opt_no_chk_data_crc,
Opt_override_compr,
Opt_err,
};
static const match_table_t tokens = {
{Opt_fast_unmount, "fast_unmount"},
{Opt_norm_unmount, "norm_unmount"},
{Opt_bulk_read, "bulk_read"},
{Opt_no_bulk_read, "no_bulk_read"},
{Opt_chk_data_crc, "chk_data_crc"},
{Opt_no_chk_data_crc, "no_chk_data_crc"},
{Opt_override_compr, "compr=%s"},
{Opt_err, NULL},
};
/**
* parse_standard_option - parse a standard mount option.
* @option: the option to parse
*
* Normally, standard mount options like "sync" are passed to file-systems as
* flags. However, when a "rootflags=" kernel boot parameter is used, they may
* be present in the options string. This function tries to deal with this
* situation and parse standard options. Returns 0 if the option was not
* recognized, and the corresponding integer flag if it was.
*
* UBIFS is only interested in the "sync" option, so do not check for anything
* else.
*/
static int parse_standard_option(const char *option)
{
ubifs_msg("parse %s", option);
if (!strcmp(option, "sync"))
return MS_SYNCHRONOUS;
return 0;
}
/**
* ubifs_parse_options - parse mount parameters.
* @c: UBIFS file-system description object
* @options: parameters to parse
* @is_remount: non-zero if this is FS re-mount
*
* This function parses UBIFS mount options and returns zero in case success
* and a negative error code in case of failure.
*/
static int ubifs_parse_options(struct ubifs_info *c, char *options,
int is_remount)
{
char *p;
substring_t args[MAX_OPT_ARGS];
if (!options)
return 0;
while ((p = strsep(&options, ","))) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
/*
* %Opt_fast_unmount and %Opt_norm_unmount options are ignored.
* We accept them in order to be backward-compatible. But this
* should be removed at some point.
*/
case Opt_fast_unmount:
c->mount_opts.unmount_mode = 2;
break;
case Opt_norm_unmount: