forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathsuper.c
7429 lines (6579 loc) · 206 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
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext4/super.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card ([email protected])
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller ([email protected]), 1995
*/
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/parser.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/vfs.h>
#include <linux/random.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
#include <linux/ctype.h>
#include <linux/log2.h>
#include <linux/crc16.h>
#include <linux/dax.h>
#include <linux/uaccess.h>
#include <linux/iversion.h>
#include <linux/unicode.h>
#include <linux/part_stat.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/fsnotify.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include "ext4.h"
#include "ext4_extents.h" /* Needed for trace points definition */
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "mballoc.h"
#include "fsmap.h"
#define CREATE_TRACE_POINTS
#include <trace/events/ext4.h>
static struct ext4_lazy_init *ext4_li_info;
static DEFINE_MUTEX(ext4_li_mtx);
static struct ratelimit_state ext4_mount_msg_ratelimit;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
static int ext4_show_options(struct seq_file *seq, struct dentry *root);
static void ext4_update_super(struct super_block *sb);
static int ext4_commit_super(struct super_block *sb);
static int ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_clear_journal_err(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_sync_fs(struct super_block *sb, int wait);
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
static int ext4_unfreeze(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
static inline int ext2_feature_set_ok(struct super_block *sb);
static inline int ext3_feature_set_ok(struct super_block *sb);
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
static void ext4_clear_request_list(void);
static struct inode *ext4_get_journal_inode(struct super_block *sb,
unsigned int journal_inum);
static int ext4_validate_options(struct fs_context *fc);
static int ext4_check_opt_consistency(struct fs_context *fc,
struct super_block *sb);
static void ext4_apply_options(struct fs_context *fc, struct super_block *sb);
static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param);
static int ext4_get_tree(struct fs_context *fc);
static int ext4_reconfigure(struct fs_context *fc);
static void ext4_fc_free(struct fs_context *fc);
static int ext4_init_fs_context(struct fs_context *fc);
static void ext4_kill_sb(struct super_block *sb);
static const struct fs_parameter_spec ext4_param_specs[];
/*
* Lock ordering
*
* page fault path:
* mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start
* -> page lock -> i_data_sem (rw)
*
* buffered write path:
* sb_start_write -> i_mutex -> mmap_lock
* sb_start_write -> i_mutex -> transaction start -> page lock ->
* i_data_sem (rw)
*
* truncate:
* sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) ->
* page lock
* sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start ->
* i_data_sem (rw)
*
* direct IO:
* sb_start_write -> i_mutex -> mmap_lock
* sb_start_write -> i_mutex -> transaction start -> i_data_sem (rw)
*
* writepages:
* transaction start -> page lock(s) -> i_data_sem (rw)
*/
static const struct fs_context_operations ext4_context_ops = {
.parse_param = ext4_parse_param,
.get_tree = ext4_get_tree,
.reconfigure = ext4_reconfigure,
.free = ext4_fc_free,
};
#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2)
static struct file_system_type ext2_fs_type = {
.owner = THIS_MODULE,
.name = "ext2",
.init_fs_context = ext4_init_fs_context,
.parameters = ext4_param_specs,
.kill_sb = ext4_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("ext2");
MODULE_ALIAS("ext2");
#define IS_EXT2_SB(sb) ((sb)->s_type == &ext2_fs_type)
#else
#define IS_EXT2_SB(sb) (0)
#endif
static struct file_system_type ext3_fs_type = {
.owner = THIS_MODULE,
.name = "ext3",
.init_fs_context = ext4_init_fs_context,
.parameters = ext4_param_specs,
.kill_sb = ext4_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("ext3");
MODULE_ALIAS("ext3");
#define IS_EXT3_SB(sb) ((sb)->s_type == &ext3_fs_type)
static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
bh_end_io_t *end_io)
{
/*
* buffer's verified bit is no longer valid after reading from
* disk again due to write out error, clear it to make sure we
* recheck the buffer contents.
*/
clear_buffer_verified(bh);
bh->b_end_io = end_io ? end_io : end_buffer_read_sync;
get_bh(bh);
submit_bh(REQ_OP_READ | op_flags, bh);
}
void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
bh_end_io_t *end_io)
{
BUG_ON(!buffer_locked(bh));
if (ext4_buffer_uptodate(bh)) {
unlock_buffer(bh);
return;
}
__ext4_read_bh(bh, op_flags, end_io);
}
int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io)
{
BUG_ON(!buffer_locked(bh));
if (ext4_buffer_uptodate(bh)) {
unlock_buffer(bh);
return 0;
}
__ext4_read_bh(bh, op_flags, end_io);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return 0;
return -EIO;
}
int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait)
{
lock_buffer(bh);
if (!wait) {
ext4_read_bh_nowait(bh, op_flags, NULL);
return 0;
}
return ext4_read_bh(bh, op_flags, NULL);
}
/*
* This works like __bread_gfp() except it uses ERR_PTR for error
* returns. Currently with sb_bread it's impossible to distinguish
* between ENOMEM and EIO situations (since both result in a NULL
* return.
*/
static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb,
sector_t block,
blk_opf_t op_flags, gfp_t gfp)
{
struct buffer_head *bh;
int ret;
bh = sb_getblk_gfp(sb, block, gfp);
if (bh == NULL)
return ERR_PTR(-ENOMEM);
if (ext4_buffer_uptodate(bh))
return bh;
ret = ext4_read_bh_lock(bh, REQ_META | op_flags, true);
if (ret) {
put_bh(bh);
return ERR_PTR(ret);
}
return bh;
}
struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block,
blk_opf_t op_flags)
{
gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping,
~__GFP_FS) | __GFP_MOVABLE;
return __ext4_sb_bread_gfp(sb, block, op_flags, gfp);
}
struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
sector_t block)
{
gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping,
~__GFP_FS);
return __ext4_sb_bread_gfp(sb, block, 0, gfp);
}
void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block)
{
struct buffer_head *bh = bdev_getblk(sb->s_bdev, block,
sb->s_blocksize, GFP_NOWAIT | __GFP_NOWARN);
if (likely(bh)) {
if (trylock_buffer(bh))
ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL);
brelse(bh);
}
}
static int ext4_verify_csum_type(struct super_block *sb,
struct ext4_super_block *es)
{
if (!ext4_has_feature_metadata_csum(sb))
return 1;
return es->s_checksum_type == EXT4_CRC32C_CHKSUM;
}
__le32 ext4_superblock_csum(struct super_block *sb,
struct ext4_super_block *es)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
int offset = offsetof(struct ext4_super_block, s_checksum);
__u32 csum;
csum = ext4_chksum(sbi, ~0, (char *)es, offset);
return cpu_to_le32(csum);
}
static int ext4_superblock_csum_verify(struct super_block *sb,
struct ext4_super_block *es)
{
if (!ext4_has_metadata_csum(sb))
return 1;
return es->s_checksum == ext4_superblock_csum(sb, es);
}
void ext4_superblock_csum_set(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
if (!ext4_has_metadata_csum(sb))
return;
es->s_checksum = ext4_superblock_csum(sb, es);
}
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le32_to_cpu(bg->bg_block_bitmap_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
}
ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le32_to_cpu(bg->bg_inode_bitmap_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
}
ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le32_to_cpu(bg->bg_inode_table_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}
__u32 ext4_free_group_clusters(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_free_blocks_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
}
__u32 ext4_free_inodes_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_free_inodes_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
}
__u32 ext4_used_dirs_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_used_dirs_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
}
__u32 ext4_itable_unused_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_itable_unused_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
}
void ext4_block_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32);
}
void ext4_inode_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32);
}
void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_inode_table_lo = cpu_to_le32((u32)blk);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
}
void ext4_free_group_clusters_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16);
}
void ext4_free_inodes_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
}
void ext4_used_dirs_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16);
}
void ext4_itable_unused_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_itable_unused_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
}
static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now)
{
now = clamp_val(now, 0, (1ull << 40) - 1);
*lo = cpu_to_le32(lower_32_bits(now));
*hi = upper_32_bits(now);
}
static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi)
{
return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo);
}
#define ext4_update_tstamp(es, tstamp) \
__ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi, \
ktime_get_real_seconds())
#define ext4_get_tstamp(es, tstamp) \
__ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
#define EXT4_SB_REFRESH_INTERVAL_SEC (3600) /* seconds (1 hour) */
#define EXT4_SB_REFRESH_INTERVAL_KB (16384) /* kilobytes (16MB) */
/*
* The ext4_maybe_update_superblock() function checks and updates the
* superblock if needed.
*
* This function is designed to update the on-disk superblock only under
* certain conditions to prevent excessive disk writes and unnecessary
* waking of the disk from sleep. The superblock will be updated if:
* 1. More than an hour has passed since the last superblock update, and
* 2. More than 16MB have been written since the last superblock update.
*
* @sb: The superblock
*/
static void ext4_maybe_update_superblock(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
journal_t *journal = sbi->s_journal;
time64_t now;
__u64 last_update;
__u64 lifetime_write_kbytes;
__u64 diff_size;
if (sb_rdonly(sb) || !(sb->s_flags & SB_ACTIVE) ||
!journal || (journal->j_flags & JBD2_UNMOUNT))
return;
now = ktime_get_real_seconds();
last_update = ext4_get_tstamp(es, s_wtime);
if (likely(now - last_update < EXT4_SB_REFRESH_INTERVAL_SEC))
return;
lifetime_write_kbytes = sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
sbi->s_sectors_written_start) >> 1);
/* Get the number of kilobytes not written to disk to account
* for statistics and compare with a multiple of 16 MB. This
* is used to determine when the next superblock commit should
* occur (i.e. not more often than once per 16MB if there was
* less written in an hour).
*/
diff_size = lifetime_write_kbytes - le64_to_cpu(es->s_kbytes_written);
if (diff_size > EXT4_SB_REFRESH_INTERVAL_KB)
schedule_work(&EXT4_SB(sb)->s_sb_upd_work);
}
static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
{
struct super_block *sb = journal->j_private;
struct ext4_sb_info *sbi = EXT4_SB(sb);
int error = is_journal_aborted(journal);
struct ext4_journal_cb_entry *jce;
BUG_ON(txn->t_state == T_FINISHED);
ext4_process_freed_data(sb, txn->t_tid);
ext4_maybe_update_superblock(sb);
spin_lock(&sbi->s_md_lock);
while (!list_empty(&txn->t_private_list)) {
jce = list_entry(txn->t_private_list.next,
struct ext4_journal_cb_entry, jce_list);
list_del_init(&jce->jce_list);
spin_unlock(&sbi->s_md_lock);
jce->jce_func(sb, jce, error);
spin_lock(&sbi->s_md_lock);
}
spin_unlock(&sbi->s_md_lock);
}
/*
* This writepage callback for write_cache_pages()
* takes care of a few cases after page cleaning.
*
* write_cache_pages() already checks for dirty pages
* and calls clear_page_dirty_for_io(), which we want,
* to write protect the pages.
*
* However, we may have to redirty a page (see below.)
*/
static int ext4_journalled_writepage_callback(struct folio *folio,
struct writeback_control *wbc,
void *data)
{
transaction_t *transaction = (transaction_t *) data;
struct buffer_head *bh, *head;
struct journal_head *jh;
bh = head = folio_buffers(folio);
do {
/*
* We have to redirty a page in these cases:
* 1) If buffer is dirty, it means the page was dirty because it
* contains a buffer that needs checkpointing. So the dirty bit
* needs to be preserved so that checkpointing writes the buffer
* properly.
* 2) If buffer is not part of the committing transaction
* (we may have just accidentally come across this buffer because
* inode range tracking is not exact) or if the currently running
* transaction already contains this buffer as well, dirty bit
* needs to be preserved so that the buffer gets writeprotected
* properly on running transaction's commit.
*/
jh = bh2jh(bh);
if (buffer_dirty(bh) ||
(jh && (jh->b_transaction != transaction ||
jh->b_next_transaction))) {
folio_redirty_for_writepage(wbc, folio);
goto out;
}
} while ((bh = bh->b_this_page) != head);
out:
return AOP_WRITEPAGE_ACTIVATE;
}
static int ext4_journalled_submit_inode_data_buffers(struct jbd2_inode *jinode)
{
struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = jinode->i_dirty_start,
.range_end = jinode->i_dirty_end,
};
return write_cache_pages(mapping, &wbc,
ext4_journalled_writepage_callback,
jinode->i_transaction);
}
static int ext4_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
{
int ret;
if (ext4_should_journal_data(jinode->i_vfs_inode))
ret = ext4_journalled_submit_inode_data_buffers(jinode);
else
ret = ext4_normal_submit_inode_data_buffers(jinode);
return ret;
}
static int ext4_journal_finish_inode_data_buffers(struct jbd2_inode *jinode)
{
int ret = 0;
if (!ext4_should_journal_data(jinode->i_vfs_inode))
ret = jbd2_journal_finish_inode_data_buffers(jinode);
return ret;
}
static bool system_going_down(void)
{
return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF
|| system_state == SYSTEM_RESTART;
}
struct ext4_err_translation {
int code;
int errno;
};
#define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err }
static struct ext4_err_translation err_translation[] = {
EXT4_ERR_TRANSLATE(EIO),
EXT4_ERR_TRANSLATE(ENOMEM),
EXT4_ERR_TRANSLATE(EFSBADCRC),
EXT4_ERR_TRANSLATE(EFSCORRUPTED),
EXT4_ERR_TRANSLATE(ENOSPC),
EXT4_ERR_TRANSLATE(ENOKEY),
EXT4_ERR_TRANSLATE(EROFS),
EXT4_ERR_TRANSLATE(EFBIG),
EXT4_ERR_TRANSLATE(EEXIST),
EXT4_ERR_TRANSLATE(ERANGE),
EXT4_ERR_TRANSLATE(EOVERFLOW),
EXT4_ERR_TRANSLATE(EBUSY),
EXT4_ERR_TRANSLATE(ENOTDIR),
EXT4_ERR_TRANSLATE(ENOTEMPTY),
EXT4_ERR_TRANSLATE(ESHUTDOWN),
EXT4_ERR_TRANSLATE(EFAULT),
};
static int ext4_errno_to_code(int errno)
{
int i;
for (i = 0; i < ARRAY_SIZE(err_translation); i++)
if (err_translation[i].errno == errno)
return err_translation[i].code;
return EXT4_ERR_UNKNOWN;
}
static void save_error_info(struct super_block *sb, int error,
__u32 ino, __u64 block,
const char *func, unsigned int line)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
/* We default to EFSCORRUPTED error... */
if (error == 0)
error = EFSCORRUPTED;
spin_lock(&sbi->s_error_lock);
sbi->s_add_error_count++;
sbi->s_last_error_code = error;
sbi->s_last_error_line = line;
sbi->s_last_error_ino = ino;
sbi->s_last_error_block = block;
sbi->s_last_error_func = func;
sbi->s_last_error_time = ktime_get_real_seconds();
if (!sbi->s_first_error_time) {
sbi->s_first_error_code = error;
sbi->s_first_error_line = line;
sbi->s_first_error_ino = ino;
sbi->s_first_error_block = block;
sbi->s_first_error_func = func;
sbi->s_first_error_time = sbi->s_last_error_time;
}
spin_unlock(&sbi->s_error_lock);
}
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
*
* On ext2, we can store the error state of the filesystem in the
* superblock. That is not possible on ext4, because we may have other
* write ordering constraints on the superblock which prevent us from
* writing it out straight away; and given that the journal is about to
* be aborted, we can't rely on the current, or future, transactions to
* write out the superblock safely.
*
* We'll just use the jbd2_journal_abort() error code to record an error in
* the journal instead. On recovery, the journal will complain about
* that error until we've noted it down and cleared it.
*
* If force_ro is set, we unconditionally force the filesystem into an
* ABORT|READONLY state, unless the error response on the fs has been set to
* panic in which case we take the easy way out and panic immediately. This is
* used to deal with unrecoverable failures such as journal IO errors or ENOMEM
* at a critical moment in log management.
*/
static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
__u32 ino, __u64 block,
const char *func, unsigned int line)
{
journal_t *journal = EXT4_SB(sb)->s_journal;
bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT);
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
if (test_opt(sb, WARN_ON_ERROR))
WARN_ON_ONCE(1);
if (!continue_fs && !sb_rdonly(sb)) {
set_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags);
if (journal)
jbd2_journal_abort(journal, -EIO);
}
if (!bdev_read_only(sb->s_bdev)) {
save_error_info(sb, error, ino, block, func, line);
/*
* In case the fs should keep running, we need to writeout
* superblock through the journal. Due to lock ordering
* constraints, it may not be safe to do it right here so we
* defer superblock flushing to a workqueue.
*/
if (continue_fs && journal)
schedule_work(&EXT4_SB(sb)->s_sb_upd_work);
else
ext4_commit_super(sb);
}
/*
* We force ERRORS_RO behavior when system is rebooting. Otherwise we
* could panic during 'reboot -f' as the underlying device got already
* disabled.
*/
if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
}
if (sb_rdonly(sb) || continue_fs)
return;
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
/*
* Make sure updated value of ->s_mount_flags will be visible before
* ->s_flags update
*/
smp_wmb();
sb->s_flags |= SB_RDONLY;
}
static void update_super_work(struct work_struct *work)
{
struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info,
s_sb_upd_work);
journal_t *journal = sbi->s_journal;
handle_t *handle;
/*
* If the journal is still running, we have to write out superblock
* through the journal to avoid collisions of other journalled sb
* updates.
*
* We use directly jbd2 functions here to avoid recursing back into
* ext4 error handling code during handling of previous errors.
*/
if (!sb_rdonly(sbi->s_sb) && journal) {
struct buffer_head *sbh = sbi->s_sbh;
bool call_notify_err = false;
handle = jbd2_journal_start(journal, 1);
if (IS_ERR(handle))
goto write_directly;
if (jbd2_journal_get_write_access(handle, sbh)) {
jbd2_journal_stop(handle);
goto write_directly;
}
if (sbi->s_add_error_count > 0)
call_notify_err = true;
ext4_update_super(sbi->s_sb);
if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) {
ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to "
"superblock detected");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
if (jbd2_journal_dirty_metadata(handle, sbh)) {
jbd2_journal_stop(handle);
goto write_directly;
}
jbd2_journal_stop(handle);
if (call_notify_err)
ext4_notify_error_sysfs(sbi);
return;
}
write_directly:
/*
* Write through journal failed. Write sb directly to get error info
* out and hope for the best.
*/
ext4_commit_super(sbi->s_sb);
ext4_notify_error_sysfs(sbi);
}
#define ext4_error_ratelimit(sb) \
___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state), \
"EXT4-fs error")
void __ext4_error(struct super_block *sb, const char *function,
unsigned int line, bool force_ro, int error, __u64 block,
const char *fmt, ...)
{
struct va_format vaf;
va_list args;
if (unlikely(ext4_forced_shutdown(sb)))
return;
trace_ext4_error(sb, function, line);
if (ext4_error_ratelimit(sb)) {
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk(KERN_CRIT
"EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
sb->s_id, function, line, current->comm, &vaf);
va_end(args);
}
fsnotify_sb_error(sb, NULL, error ? error : EFSCORRUPTED);
ext4_handle_error(sb, force_ro, error, 0, block, function, line);
}
void __ext4_error_inode(struct inode *inode, const char *function,
unsigned int line, ext4_fsblk_t block, int error,
const char *fmt, ...)
{
va_list args;
struct va_format vaf;
if (unlikely(ext4_forced_shutdown(inode->i_sb)))
return;
trace_ext4_error(inode->i_sb, function, line);
if (ext4_error_ratelimit(inode->i_sb)) {
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (block)
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
"inode #%lu: block %llu: comm %s: %pV\n",
inode->i_sb->s_id, function, line, inode->i_ino,
block, current->comm, &vaf);
else
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
"inode #%lu: comm %s: %pV\n",
inode->i_sb->s_id, function, line, inode->i_ino,
current->comm, &vaf);
va_end(args);
}
fsnotify_sb_error(inode->i_sb, inode, error ? error : EFSCORRUPTED);
ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
function, line);
}
void __ext4_error_file(struct file *file, const char *function,
unsigned int line, ext4_fsblk_t block,
const char *fmt, ...)
{
va_list args;
struct va_format vaf;
struct inode *inode = file_inode(file);
char pathname[80], *path;
if (unlikely(ext4_forced_shutdown(inode->i_sb)))
return;
trace_ext4_error(inode->i_sb, function, line);
if (ext4_error_ratelimit(inode->i_sb)) {
path = file_path(file, pathname, sizeof(pathname));
if (IS_ERR(path))
path = "(unknown)";
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (block)
printk(KERN_CRIT
"EXT4-fs error (device %s): %s:%d: inode #%lu: "
"block %llu: comm %s: path %s: %pV\n",
inode->i_sb->s_id, function, line, inode->i_ino,
block, current->comm, path, &vaf);
else
printk(KERN_CRIT
"EXT4-fs error (device %s): %s:%d: inode #%lu: "
"comm %s: path %s: %pV\n",
inode->i_sb->s_id, function, line, inode->i_ino,
current->comm, path, &vaf);
va_end(args);
}
fsnotify_sb_error(inode->i_sb, inode, EFSCORRUPTED);
ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
function, line);
}
const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16])
{
char *errstr = NULL;
switch (errno) {
case -EFSCORRUPTED:
errstr = "Corrupt filesystem";
break;
case -EFSBADCRC:
errstr = "Filesystem failed CRC";
break;
case -EIO:
errstr = "IO failure";
break;
case -ENOMEM:
errstr = "Out of memory";
break;
case -EROFS:
if (!sb || (EXT4_SB(sb)->s_journal &&
EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT))
errstr = "Journal has aborted";
else
errstr = "Readonly filesystem";
break;
default:
/* If the caller passed in an extra buffer for unknown
* errors, textualise them now. Else we just return
* NULL. */
if (nbuf) {
/* Check for truncated error codes... */
if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
errstr = nbuf;
}
break;
}
return errstr;
}
/* __ext4_std_error decodes expected errors from journaling functions
* automatically and invokes the appropriate error response. */
void __ext4_std_error(struct super_block *sb, const char *function,
unsigned int line, int errno)
{
char nbuf[16];
const char *errstr;
if (unlikely(ext4_forced_shutdown(sb)))
return;
/* Special case: if the error is EROFS, and we're not already
* inside a transaction, then there's really no point in logging
* an error. */
if (errno == -EROFS && journal_current_handle() == NULL && sb_rdonly(sb))
return;
if (ext4_error_ratelimit(sb)) {
errstr = ext4_decode_error(sb, errno, nbuf);
printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
sb->s_id, function, line, errstr);
}
fsnotify_sb_error(sb, NULL, errno ? errno : EFSCORRUPTED);
ext4_handle_error(sb, false, -errno, 0, 0, function, line);
}
void __ext4_msg(struct super_block *sb,
const char *prefix, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
if (sb) {
atomic_inc(&EXT4_SB(sb)->s_msg_count);
if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state),
"EXT4-fs"))
return;
}
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (sb)
printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf);
else
printk("%sEXT4-fs: %pV\n", prefix, &vaf);
va_end(args);
}
static int ext4_warning_ratelimit(struct super_block *sb)
{
atomic_inc(&EXT4_SB(sb)->s_warning_count);
return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),
"EXT4-fs warning");