-
Notifications
You must be signed in to change notification settings - Fork 52.3k
/
jbd2.h
1844 lines (1581 loc) · 51.4 KB
/
jbd2.h
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-or-later */
/*
* linux/include/linux/jbd2.h
*
* Written by Stephen C. Tweedie <sct@redhat.com>
*
* Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved
*
* Definitions for transaction data structures for the buffer cache
* filesystem journaling support.
*/
#ifndef _LINUX_JBD2_H
#define _LINUX_JBD2_H
/* Allow this file to be included directly into e2fsprogs */
#ifndef __KERNEL__
#include "jfs_compat.h"
#define JBD2_DEBUG
#else
#include <linux/types.h>
#include <linux/buffer_head.h>
#include <linux/journal-head.h>
#include <linux/stddef.h>
#include <linux/mutex.h>
#include <linux/timer.h>
#include <linux/slab.h>
#include <linux/bit_spinlock.h>
#include <linux/blkdev.h>
#include <crypto/hash.h>
#endif
#define journal_oom_retry 1
/*
* Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds
* certain classes of error which can occur due to failed IOs. Under
* normal use we want ext4 to continue after such errors, because
* hardware _can_ fail, but for debugging purposes when running tests on
* known-good hardware we may want to trap these errors.
*/
#undef JBD2_PARANOID_IOFAIL
/*
* The default maximum commit age, in seconds.
*/
#define JBD2_DEFAULT_MAX_COMMIT_AGE 5
#ifdef CONFIG_JBD2_DEBUG
/*
* Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal
* consistency checks. By default we don't do this unless
* CONFIG_JBD2_DEBUG is on.
*/
#define JBD2_EXPENSIVE_CHECKING
extern ushort jbd2_journal_enable_debug;
void __jbd2_debug(int level, const char *file, const char *func,
unsigned int line, const char *fmt, ...);
#define jbd_debug(n, fmt, a...) \
__jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a)
#else
#define jbd_debug(n, fmt, a...) no_printk(fmt, ##a)
#endif
extern void *jbd2_alloc(size_t size, gfp_t flags);
extern void jbd2_free(void *ptr, size_t size);
#define JBD2_MIN_JOURNAL_BLOCKS 1024
#define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256
#ifdef __KERNEL__
/**
* typedef handle_t - The handle_t type represents a single atomic update being performed by some process.
*
* All filesystem modifications made by the process go
* through this handle. Recursive operations (such as quota operations)
* are gathered into a single update.
*
* The buffer credits field is used to account for journaled buffers
* being modified by the running process. To ensure that there is
* enough log space for all outstanding operations, we need to limit the
* number of outstanding buffers possible at any time. When the
* operation completes, any buffer credits not used are credited back to
* the transaction, so that at all times we know how many buffers the
* outstanding updates on a transaction might possibly touch.
*
* This is an opaque datatype.
**/
typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */
/**
* typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem.
*
* journal_t is linked to from the fs superblock structure.
*
* We use the journal_t to keep track of all outstanding transaction
* activity on the filesystem, and to manage the state of the log
* writing process.
*
* This is an opaque datatype.
**/
typedef struct journal_s journal_t; /* Journal control structure */
#endif
/*
* Internal structures used by the logging mechanism:
*/
#define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */
/*
* On-disk structures
*/
/*
* Descriptor block types:
*/
#define JBD2_DESCRIPTOR_BLOCK 1
#define JBD2_COMMIT_BLOCK 2
#define JBD2_SUPERBLOCK_V1 3
#define JBD2_SUPERBLOCK_V2 4
#define JBD2_REVOKE_BLOCK 5
/*
* Standard header for all descriptor blocks:
*/
typedef struct journal_header_s
{
__be32 h_magic;
__be32 h_blocktype;
__be32 h_sequence;
} journal_header_t;
/*
* Checksum types.
*/
#define JBD2_CRC32_CHKSUM 1
#define JBD2_MD5_CHKSUM 2
#define JBD2_SHA1_CHKSUM 3
#define JBD2_CRC32C_CHKSUM 4
#define JBD2_CRC32_CHKSUM_SIZE 4
#define JBD2_CHECKSUM_BYTES (32 / sizeof(u32))
/*
* Commit block header for storing transactional checksums:
*
* NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum*
* fields are used to store a checksum of the descriptor and data blocks.
*
* If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum
* field is used to store crc32c(uuid+commit_block). Each journal metadata
* block gets its own checksum, and data block checksums are stored in
* journal_block_tag (in the descriptor). The other h_chksum* fields are
* not used.
*
* If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses
* journal_block_tag3_t to store a full 32-bit checksum. Everything else
* is the same as v2.
*
* Checksum v1, v2, and v3 are mutually exclusive features.
*/
struct commit_header {
__be32 h_magic;
__be32 h_blocktype;
__be32 h_sequence;
unsigned char h_chksum_type;
unsigned char h_chksum_size;
unsigned char h_padding[2];
__be32 h_chksum[JBD2_CHECKSUM_BYTES];
__be64 h_commit_sec;
__be32 h_commit_nsec;
};
/*
* The block tag: used to describe a single buffer in the journal.
* t_blocknr_high is only used if INCOMPAT_64BIT is set, so this
* raw struct shouldn't be used for pointer math or sizeof() - use
* journal_tag_bytes(journal) instead to compute this.
*/
typedef struct journal_block_tag3_s
{
__be32 t_blocknr; /* The on-disk block number */
__be32 t_flags; /* See below */
__be32 t_blocknr_high; /* most-significant high 32bits. */
__be32 t_checksum; /* crc32c(uuid+seq+block) */
} journal_block_tag3_t;
typedef struct journal_block_tag_s
{
__be32 t_blocknr; /* The on-disk block number */
__be16 t_checksum; /* truncated crc32c(uuid+seq+block) */
__be16 t_flags; /* See below */
__be32 t_blocknr_high; /* most-significant high 32bits. */
} journal_block_tag_t;
/* Tail of descriptor or revoke block, for checksumming */
struct jbd2_journal_block_tail {
__be32 t_checksum; /* crc32c(uuid+descr_block) */
};
/*
* The revoke descriptor: used on disk to describe a series of blocks to
* be revoked from the log
*/
typedef struct jbd2_journal_revoke_header_s
{
journal_header_t r_header;
__be32 r_count; /* Count of bytes used in the block */
} jbd2_journal_revoke_header_t;
/* Definitions for the journal tag flags word: */
#define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */
#define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */
#define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */
#define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */
/*
* The journal superblock. All fields are in big-endian byte order.
*/
typedef struct journal_superblock_s
{
/* 0x0000 */
journal_header_t s_header;
/* 0x000C */
/* Static information describing the journal */
__be32 s_blocksize; /* journal device blocksize */
__be32 s_maxlen; /* total blocks in journal file */
__be32 s_first; /* first block of log information */
/* 0x0018 */
/* Dynamic information describing the current state of the log */
__be32 s_sequence; /* first commit ID expected in log */
__be32 s_start; /* blocknr of start of log */
/* 0x0020 */
/* Error value, as set by jbd2_journal_abort(). */
__be32 s_errno;
/* 0x0024 */
/* Remaining fields are only valid in a version-2 superblock */
__be32 s_feature_compat; /* compatible feature set */
__be32 s_feature_incompat; /* incompatible feature set */
__be32 s_feature_ro_compat; /* readonly-compatible feature set */
/* 0x0030 */
__u8 s_uuid[16]; /* 128-bit uuid for journal */
/* 0x0040 */
__be32 s_nr_users; /* Nr of filesystems sharing log */
__be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/
/* 0x0048 */
__be32 s_max_transaction; /* Limit of journal blocks per trans.*/
__be32 s_max_trans_data; /* Limit of data blocks per trans. */
/* 0x0050 */
__u8 s_checksum_type; /* checksum type */
__u8 s_padding2[3];
/* 0x0054 */
__be32 s_num_fc_blks; /* Number of fast commit blocks */
/* 0x0058 */
__u32 s_padding[41];
__be32 s_checksum; /* crc32c(superblock) */
/* 0x0100 */
__u8 s_users[16*48]; /* ids of all fs'es sharing the log */
/* 0x0400 */
} journal_superblock_t;
/* Use the jbd2_{has,set,clear}_feature_* helpers; these will be removed */
#define JBD2_HAS_COMPAT_FEATURE(j,mask) \
((j)->j_format_version >= 2 && \
((j)->j_superblock->s_feature_compat & cpu_to_be32((mask))))
#define JBD2_HAS_RO_COMPAT_FEATURE(j,mask) \
((j)->j_format_version >= 2 && \
((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask))))
#define JBD2_HAS_INCOMPAT_FEATURE(j,mask) \
((j)->j_format_version >= 2 && \
((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask))))
#define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001
#define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001
#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002
#define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004
#define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008
#define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010
#define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020
/* See "journal feature predicate functions" below */
/* Features known to this kernel version: */
#define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM
#define JBD2_KNOWN_ROCOMPAT_FEATURES 0
#define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \
JBD2_FEATURE_INCOMPAT_64BIT | \
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
JBD2_FEATURE_INCOMPAT_CSUM_V3 | \
JBD2_FEATURE_INCOMPAT_FAST_COMMIT)
#ifdef __KERNEL__
#include <linux/fs.h>
#include <linux/sched.h>
enum jbd_state_bits {
BH_JBD /* Has an attached ext3 journal_head */
= BH_PrivateStart,
BH_JWrite, /* Being written to log (@@@ DEBUGGING) */
BH_Freed, /* Has been freed (truncated) */
BH_Revoked, /* Has been revoked from the log */
BH_RevokeValid, /* Revoked flag is valid */
BH_JBDDirty, /* Is dirty but journaled */
BH_JournalHead, /* Pins bh->b_private and jh->b_bh */
BH_Shadow, /* IO on shadow buffer is running */
BH_Verified, /* Metadata block has been verified ok */
BH_JBDPrivateStart, /* First bit available for private use by FS */
};
BUFFER_FNS(JBD, jbd)
BUFFER_FNS(JWrite, jwrite)
BUFFER_FNS(JBDDirty, jbddirty)
TAS_BUFFER_FNS(JBDDirty, jbddirty)
BUFFER_FNS(Revoked, revoked)
TAS_BUFFER_FNS(Revoked, revoked)
BUFFER_FNS(RevokeValid, revokevalid)
TAS_BUFFER_FNS(RevokeValid, revokevalid)
BUFFER_FNS(Freed, freed)
BUFFER_FNS(Shadow, shadow)
BUFFER_FNS(Verified, verified)
static inline struct buffer_head *jh2bh(struct journal_head *jh)
{
return jh->b_bh;
}
static inline struct journal_head *bh2jh(struct buffer_head *bh)
{
return bh->b_private;
}
static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
{
bit_spin_lock(BH_JournalHead, &bh->b_state);
}
static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
{
bit_spin_unlock(BH_JournalHead, &bh->b_state);
}
#define J_ASSERT(assert) BUG_ON(!(assert))
#define J_ASSERT_BH(bh, expr) J_ASSERT(expr)
#define J_ASSERT_JH(jh, expr) J_ASSERT(expr)
#if defined(JBD2_PARANOID_IOFAIL)
#define J_EXPECT(expr, why...) J_ASSERT(expr)
#define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr)
#define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr)
#else
#define __journal_expect(expr, why...) \
({ \
int val = (expr); \
if (!val) { \
printk(KERN_ERR \
"JBD2 unexpected failure: %s: %s;\n", \
__func__, #expr); \
printk(KERN_ERR why "\n"); \
} \
val; \
})
#define J_EXPECT(expr, why...) __journal_expect(expr, ## why)
#define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why)
#define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why)
#endif
/* Flags in jbd_inode->i_flags */
#define __JI_COMMIT_RUNNING 0
#define __JI_WRITE_DATA 1
#define __JI_WAIT_DATA 2
/*
* Commit of the inode data in progress. We use this flag to protect us from
* concurrent deletion of inode. We cannot use reference to inode for this
* since we cannot afford doing last iput() on behalf of kjournald
*/
#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING)
/* Write allocated dirty buffers in this inode before commit */
#define JI_WRITE_DATA (1 << __JI_WRITE_DATA)
/* Wait for outstanding data writes for this inode before commit */
#define JI_WAIT_DATA (1 << __JI_WAIT_DATA)
/**
* struct jbd2_inode - The jbd_inode type is the structure linking inodes in
* ordered mode present in a transaction so that we can sync them during commit.
*/
struct jbd2_inode {
/**
* @i_transaction:
*
* Which transaction does this inode belong to? Either the running
* transaction or the committing one. [j_list_lock]
*/
transaction_t *i_transaction;
/**
* @i_next_transaction:
*
* Pointer to the running transaction modifying inode's data in case
* there is already a committing transaction touching it. [j_list_lock]
*/
transaction_t *i_next_transaction;
/**
* @i_list: List of inodes in the i_transaction [j_list_lock]
*/
struct list_head i_list;
/**
* @i_vfs_inode:
*
* VFS inode this inode belongs to [constant for lifetime of structure]
*/
struct inode *i_vfs_inode;
/**
* @i_flags: Flags of inode [j_list_lock]
*/
unsigned long i_flags;
/**
* @i_dirty_start:
*
* Offset in bytes where the dirty range for this inode starts.
* [j_list_lock]
*/
loff_t i_dirty_start;
/**
* @i_dirty_end:
*
* Inclusive offset in bytes where the dirty range for this inode
* ends. [j_list_lock]
*/
loff_t i_dirty_end;
};
struct jbd2_revoke_table_s;
/**
* struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete
* type associated with handle_t.
* @h_transaction: Which compound transaction is this update a part of?
* @h_journal: Which journal handle belongs to - used iff h_reserved set.
* @h_rsv_handle: Handle reserved for finishing the logical operation.
* @h_total_credits: Number of remaining buffers we are allowed to add to
* journal. These are dirty buffers and revoke descriptor blocks.
* @h_revoke_credits: Number of remaining revoke records available for handle
* @h_ref: Reference count on this handle.
* @h_err: Field for caller's use to track errors through large fs operations.
* @h_sync: Flag for sync-on-close.
* @h_jdata: Flag to force data journaling.
* @h_reserved: Flag for handle for reserved credits.
* @h_aborted: Flag indicating fatal error on handle.
* @h_type: For handle statistics.
* @h_line_no: For handle statistics.
* @h_start_jiffies: Handle Start time.
* @h_requested_credits: Holds @h_total_credits after handle is started.
* @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started.
* @saved_alloc_context: Saved context while transaction is open.
**/
/* Docbook can't yet cope with the bit fields, but will leave the documentation
* in so it can be fixed later.
*/
struct jbd2_journal_handle
{
union {
transaction_t *h_transaction;
/* Which journal handle belongs to - used iff h_reserved set */
journal_t *h_journal;
};
handle_t *h_rsv_handle;
int h_total_credits;
int h_revoke_credits;
int h_revoke_credits_requested;
int h_ref;
int h_err;
/* Flags [no locking] */
unsigned int h_sync: 1;
unsigned int h_jdata: 1;
unsigned int h_reserved: 1;
unsigned int h_aborted: 1;
unsigned int h_type: 8;
unsigned int h_line_no: 16;
unsigned long h_start_jiffies;
unsigned int h_requested_credits;
unsigned int saved_alloc_context;
};
/*
* Some stats for checkpoint phase
*/
struct transaction_chp_stats_s {
unsigned long cs_chp_time;
__u32 cs_forced_to_close;
__u32 cs_written;
__u32 cs_dropped;
};
/* The transaction_t type is the guts of the journaling mechanism. It
* tracks a compound transaction through its various states:
*
* RUNNING: accepting new updates
* LOCKED: Updates still running but we don't accept new ones
* RUNDOWN: Updates are tidying up but have finished requesting
* new buffers to modify (state not used for now)
* FLUSH: All updates complete, but we are still writing to disk
* COMMIT: All data on disk, writing commit record
* FINISHED: We still have to keep the transaction for checkpointing.
*
* The transaction keeps track of all of the buffers modified by a
* running transaction, and all of the buffers committed but not yet
* flushed to home for finished transactions.
* (Locking Documentation improved by LockDoc)
*/
/*
* Lock ranking:
*
* j_list_lock
* ->jbd_lock_bh_journal_head() (This is "innermost")
*
* j_state_lock
* ->b_state_lock
*
* b_state_lock
* ->j_list_lock
*
* j_state_lock
* ->t_handle_lock
*
* j_state_lock
* ->j_list_lock (journal_unmap_buffer)
*
*/
struct transaction_s
{
/* Pointer to the journal for this transaction. [no locking] */
journal_t *t_journal;
/* Sequence number for this transaction [no locking] */
tid_t t_tid;
/*
* Transaction's current state
* [no locking - only kjournald2 alters this]
* [j_list_lock] guards transition of a transaction into T_FINISHED
* state and subsequent call of __jbd2_journal_drop_transaction()
* FIXME: needs barriers
* KLUDGE: [use j_state_lock]
*/
enum {
T_RUNNING,
T_LOCKED,
T_SWITCH,
T_FLUSH,
T_COMMIT,
T_COMMIT_DFLUSH,
T_COMMIT_JFLUSH,
T_COMMIT_CALLBACK,
T_FINISHED
} t_state;
/*
* Where in the log does this transaction's commit start? [no locking]
*/
unsigned long t_log_start;
/*
* Number of buffers on the t_buffers list [j_list_lock, no locks
* needed for jbd2 thread]
*/
int t_nr_buffers;
/*
* Doubly-linked circular list of all buffers reserved but not yet
* modified by this transaction [j_list_lock, no locks needed fo
* jbd2 thread]
*/
struct journal_head *t_reserved_list;
/*
* Doubly-linked circular list of all metadata buffers owned by this
* transaction [j_list_lock, no locks needed for jbd2 thread]
*/
struct journal_head *t_buffers;
/*
* Doubly-linked circular list of all forget buffers (superseded
* buffers which we can un-checkpoint once this transaction commits)
* [j_list_lock]
*/
struct journal_head *t_forget;
/*
* Doubly-linked circular list of all buffers still to be flushed before
* this transaction can be checkpointed. [j_list_lock]
*/
struct journal_head *t_checkpoint_list;
/*
* Doubly-linked circular list of all buffers submitted for IO while
* checkpointing. [j_list_lock]
*/
struct journal_head *t_checkpoint_io_list;
/*
* Doubly-linked circular list of metadata buffers being
* shadowed by log IO. The IO buffers on the iobuf list and
* the shadow buffers on this list match each other one for
* one at all times. [j_list_lock, no locks needed for jbd2
* thread]
*/
struct journal_head *t_shadow_list;
/*
* List of inodes associated with the transaction; e.g., ext4 uses
* this to track inodes in data=ordered and data=journal mode that
* need special handling on transaction commit; also used by ocfs2.
* [j_list_lock]
*/
struct list_head t_inode_list;
/*
* Protects info related to handles
*/
spinlock_t t_handle_lock;
/*
* Longest time some handle had to wait for running transaction
*/
unsigned long t_max_wait;
/*
* When transaction started
*/
unsigned long t_start;
/*
* When commit was requested [j_state_lock]
*/
unsigned long t_requested;
/*
* Checkpointing stats [j_list_lock]
*/
struct transaction_chp_stats_s t_chp_stats;
/*
* Number of outstanding updates running on this transaction
* [none]
*/
atomic_t t_updates;
/*
* Number of blocks reserved for this transaction in the journal.
* This is including all credits reserved when starting transaction
* handles as well as all journal descriptor blocks needed for this
* transaction. [none]
*/
atomic_t t_outstanding_credits;
/*
* Number of revoke records for this transaction added by already
* stopped handles. [none]
*/
atomic_t t_outstanding_revokes;
/*
* How many handles used this transaction? [none]
*/
atomic_t t_handle_count;
/*
* Forward and backward links for the circular list of all transactions
* awaiting checkpoint. [j_list_lock]
*/
transaction_t *t_cpnext, *t_cpprev;
/*
* When will the transaction expire (become due for commit), in jiffies?
* [no locking]
*/
unsigned long t_expires;
/*
* When this transaction started, in nanoseconds [no locking]
*/
ktime_t t_start_time;
/*
* This transaction is being forced and some process is
* waiting for it to finish.
*/
unsigned int t_synchronous_commit:1;
/* Disk flush needs to be sent to fs partition [no locking] */
int t_need_data_flush;
/*
* For use by the filesystem to store fs-specific data
* structures associated with the transaction
*/
struct list_head t_private_list;
};
struct transaction_run_stats_s {
unsigned long rs_wait;
unsigned long rs_request_delay;
unsigned long rs_running;
unsigned long rs_locked;
unsigned long rs_flushing;
unsigned long rs_logging;
__u32 rs_handle_count;
__u32 rs_blocks;
__u32 rs_blocks_logged;
};
struct transaction_stats_s {
unsigned long ts_tid;
unsigned long ts_requested;
struct transaction_run_stats_s run;
};
static inline unsigned long
jbd2_time_diff(unsigned long start, unsigned long end)
{
if (end >= start)
return end - start;
return end + (MAX_JIFFY_OFFSET - start);
}
#define JBD2_NR_BATCH 64
enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
#define JBD2_FC_REPLAY_STOP 0
#define JBD2_FC_REPLAY_CONTINUE 1
/**
* struct journal_s - The journal_s type is the concrete type associated with
* journal_t.
*/
struct journal_s
{
/**
* @j_flags: General journaling state flags [j_state_lock,
* no lock for quick racy checks]
*/
unsigned long j_flags;
/**
* @j_atomic_flags: Atomic journaling state flags.
*/
unsigned long j_atomic_flags;
/**
* @j_errno:
*
* Is there an outstanding uncleared error on the journal (from a prior
* abort)? [j_state_lock]
*/
int j_errno;
/**
* @j_abort_mutex: Lock the whole aborting procedure.
*/
struct mutex j_abort_mutex;
/**
* @j_sb_buffer: The first part of the superblock buffer.
*/
struct buffer_head *j_sb_buffer;
/**
* @j_superblock: The second part of the superblock buffer.
*/
journal_superblock_t *j_superblock;
/**
* @j_format_version: Version of the superblock format.
*/
int j_format_version;
/**
* @j_state_lock: Protect the various scalars in the journal.
*/
rwlock_t j_state_lock;
/**
* @j_barrier_count:
*
* Number of processes waiting to create a barrier lock [j_state_lock,
* no lock for quick racy checks]
*/
int j_barrier_count;
/**
* @j_barrier: The barrier lock itself.
*/
struct mutex j_barrier;
/**
* @j_running_transaction:
*
* Transactions: The current running transaction...
* [j_state_lock, no lock for quick racy checks] [caller holding
* open handle]
*/
transaction_t *j_running_transaction;
/**
* @j_committing_transaction:
*
* the transaction we are pushing to disk
* [j_state_lock] [caller holding open handle]
*/
transaction_t *j_committing_transaction;
/**
* @j_checkpoint_transactions:
*
* ... and a linked circular list of all transactions waiting for
* checkpointing. [j_list_lock]
*/
transaction_t *j_checkpoint_transactions;
/**
* @j_wait_transaction_locked:
*
* Wait queue for waiting for a locked transaction to start committing,
* or for a barrier lock to be released.
*/
wait_queue_head_t j_wait_transaction_locked;
/**
* @j_wait_done_commit: Wait queue for waiting for commit to complete.
*/
wait_queue_head_t j_wait_done_commit;
/**
* @j_wait_commit: Wait queue to trigger commit.
*/
wait_queue_head_t j_wait_commit;
/**
* @j_wait_updates: Wait queue to wait for updates to complete.
*/
wait_queue_head_t j_wait_updates;
/**
* @j_wait_reserved:
*
* Wait queue to wait for reserved buffer credits to drop.
*/
wait_queue_head_t j_wait_reserved;
/**
* @j_fc_wait:
*
* Wait queue to wait for completion of async fast commits.
*/
wait_queue_head_t j_fc_wait;
/**
* @j_checkpoint_mutex:
*
* Semaphore for locking against concurrent checkpoints.
*/
struct mutex j_checkpoint_mutex;
/**
* @j_chkpt_bhs:
*
* List of buffer heads used by the checkpoint routine. This
* was moved from jbd2_log_do_checkpoint() to reduce stack
* usage. Access to this array is controlled by the
* @j_checkpoint_mutex. [j_checkpoint_mutex]
*/
struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH];
/**
* @j_shrinker:
*
* Journal head shrinker, reclaim buffer's journal head which
* has been written back.
*/
struct shrinker j_shrinker;
/**
* @j_checkpoint_jh_count:
*
* Number of journal buffers on the checkpoint list. [j_list_lock]
*/
struct percpu_counter j_checkpoint_jh_count;
/**
* @j_shrink_transaction:
*
* Record next transaction will shrink on the checkpoint list.
* [j_list_lock]
*/
transaction_t *j_shrink_transaction;
/**
* @j_head:
*
* Journal head: identifies the first unused block in the journal.
* [j_state_lock]
*/
unsigned long j_head;
/**
* @j_tail:
*
* Journal tail: identifies the oldest still-used block in the journal.
* [j_state_lock]
*/
unsigned long j_tail;
/**
* @j_free:
*
* Journal free: how many free blocks are there in the journal?
* [j_state_lock]
*/
unsigned long j_free;
/**
* @j_first:
*
* The block number of the first usable block in the journal
* [j_state_lock].
*/
unsigned long j_first;
/**
* @j_last:
*
* The block number one beyond the last usable block in the journal
* [j_state_lock].
*/
unsigned long j_last;
/**
* @j_fc_first:
*
* The block number of the first fast commit block in the journal
* [j_state_lock].
*/
unsigned long j_fc_first;
/**
* @j_fc_off:
*
* Number of fast commit blocks currently allocated. Accessed only
* during fast commit. Currently only process can do fast commit, so
* this field is not protected by any lock.
*/
unsigned long j_fc_off;
/**
* @j_fc_last:
*
* The block number one beyond the last fast commit block in the journal
* [j_state_lock].
*/
unsigned long j_fc_last;
/**