forked from grate-driver/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ocfs2_fs.h
1446 lines (1253 loc) · 44 KB
/
ocfs2_fs.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
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* ocfs2_fs.h
*
* On-disk structures for OCFS2.
*
* Copyright (C) 2002, 2004 Oracle. All rights reserved.
*
* 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., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#ifndef _OCFS2_FS_H
#define _OCFS2_FS_H
/* Version */
#define OCFS2_MAJOR_REV_LEVEL 0
#define OCFS2_MINOR_REV_LEVEL 90
/*
* An OCFS2 volume starts this way:
* Sector 0: Valid ocfs1_vol_disk_hdr that cleanly fails to mount OCFS.
* Sector 1: Valid ocfs1_vol_label that cleanly fails to mount OCFS.
* Block OCFS2_SUPER_BLOCK_BLKNO: OCFS2 superblock.
*
* All other structures are found from the superblock information.
*
* OCFS2_SUPER_BLOCK_BLKNO is in blocks, not sectors. eg, for a
* blocksize of 2K, it is 4096 bytes into disk.
*/
#define OCFS2_SUPER_BLOCK_BLKNO 2
/*
* Cluster size limits. The maximum is kept arbitrarily at 1 MB, and could
* grow if needed.
*/
#define OCFS2_MIN_CLUSTERSIZE 4096
#define OCFS2_MAX_CLUSTERSIZE 1048576
/*
* Blocks cannot be bigger than clusters, so the maximum blocksize is the
* minimum cluster size.
*/
#define OCFS2_MIN_BLOCKSIZE 512
#define OCFS2_MAX_BLOCKSIZE OCFS2_MIN_CLUSTERSIZE
/* Filesystem magic number */
#define OCFS2_SUPER_MAGIC 0x7461636f
/* Object signatures */
#define OCFS2_SUPER_BLOCK_SIGNATURE "OCFSV2"
#define OCFS2_INODE_SIGNATURE "INODE01"
#define OCFS2_EXTENT_BLOCK_SIGNATURE "EXBLK01"
#define OCFS2_GROUP_DESC_SIGNATURE "GROUP01"
#define OCFS2_XATTR_BLOCK_SIGNATURE "XATTR01"
#define OCFS2_DIR_TRAILER_SIGNATURE "DIRTRL1"
#define OCFS2_DX_ROOT_SIGNATURE "DXDIR01"
#define OCFS2_DX_LEAF_SIGNATURE "DXLEAF1"
/* Compatibility flags */
#define OCFS2_HAS_COMPAT_FEATURE(sb,mask) \
( OCFS2_SB(sb)->s_feature_compat & (mask) )
#define OCFS2_HAS_RO_COMPAT_FEATURE(sb,mask) \
( OCFS2_SB(sb)->s_feature_ro_compat & (mask) )
#define OCFS2_HAS_INCOMPAT_FEATURE(sb,mask) \
( OCFS2_SB(sb)->s_feature_incompat & (mask) )
#define OCFS2_SET_COMPAT_FEATURE(sb,mask) \
OCFS2_SB(sb)->s_feature_compat |= (mask)
#define OCFS2_SET_RO_COMPAT_FEATURE(sb,mask) \
OCFS2_SB(sb)->s_feature_ro_compat |= (mask)
#define OCFS2_SET_INCOMPAT_FEATURE(sb,mask) \
OCFS2_SB(sb)->s_feature_incompat |= (mask)
#define OCFS2_CLEAR_COMPAT_FEATURE(sb,mask) \
OCFS2_SB(sb)->s_feature_compat &= ~(mask)
#define OCFS2_CLEAR_RO_COMPAT_FEATURE(sb,mask) \
OCFS2_SB(sb)->s_feature_ro_compat &= ~(mask)
#define OCFS2_CLEAR_INCOMPAT_FEATURE(sb,mask) \
OCFS2_SB(sb)->s_feature_incompat &= ~(mask)
#define OCFS2_FEATURE_COMPAT_SUPP (OCFS2_FEATURE_COMPAT_BACKUP_SB \
| OCFS2_FEATURE_COMPAT_JBD2_SB)
#define OCFS2_FEATURE_INCOMPAT_SUPP (OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT \
| OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC \
| OCFS2_FEATURE_INCOMPAT_INLINE_DATA \
| OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP \
| OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK \
| OCFS2_FEATURE_INCOMPAT_XATTR \
| OCFS2_FEATURE_INCOMPAT_META_ECC \
| OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS)
#define OCFS2_FEATURE_RO_COMPAT_SUPP (OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \
| OCFS2_FEATURE_RO_COMPAT_USRQUOTA \
| OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)
/*
* Heartbeat-only devices are missing journals and other files. The
* filesystem driver can't load them, but the library can. Never put
* this in OCFS2_FEATURE_INCOMPAT_SUPP, *ever*.
*/
#define OCFS2_FEATURE_INCOMPAT_HEARTBEAT_DEV 0x0002
/*
* tunefs sets this incompat flag before starting the resize and clears it
* at the end. This flag protects users from inadvertently mounting the fs
* after an aborted run without fsck-ing.
*/
#define OCFS2_FEATURE_INCOMPAT_RESIZE_INPROG 0x0004
/* Used to denote a non-clustered volume */
#define OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT 0x0008
/* Support for sparse allocation in b-trees */
#define OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC 0x0010
/*
* Tunefs sets this incompat flag before starting an operation which
* would require cleanup on abort. This is done to protect users from
* inadvertently mounting the fs after an aborted run without
* fsck-ing.
*
* s_tunefs_flags on the super block describes precisely which
* operations were in progress.
*/
#define OCFS2_FEATURE_INCOMPAT_TUNEFS_INPROG 0x0020
/* Support for data packed into inode blocks */
#define OCFS2_FEATURE_INCOMPAT_INLINE_DATA 0x0040
/*
* Support for alternate, userspace cluster stacks. If set, the superblock
* field s_cluster_info contains a tag for the alternate stack in use as
* well as the name of the cluster being joined.
* mount.ocfs2 must pass in a matching stack name.
*
* If not set, the classic stack will be used. This is compatbile with
* all older versions.
*/
#define OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK 0x0080
/* Support for the extended slot map */
#define OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP 0x100
/* Support for extended attributes */
#define OCFS2_FEATURE_INCOMPAT_XATTR 0x0200
/* Support for indexed directores */
#define OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS 0x0400
/* Metadata checksum and error correction */
#define OCFS2_FEATURE_INCOMPAT_META_ECC 0x0800
/*
* backup superblock flag is used to indicate that this volume
* has backup superblocks.
*/
#define OCFS2_FEATURE_COMPAT_BACKUP_SB 0x0001
/*
* The filesystem will correctly handle journal feature bits.
*/
#define OCFS2_FEATURE_COMPAT_JBD2_SB 0x0002
/*
* Unwritten extents support.
*/
#define OCFS2_FEATURE_RO_COMPAT_UNWRITTEN 0x0001
/*
* Maintain quota information for this filesystem
*/
#define OCFS2_FEATURE_RO_COMPAT_USRQUOTA 0x0002
#define OCFS2_FEATURE_RO_COMPAT_GRPQUOTA 0x0004
/* The byte offset of the first backup block will be 1G.
* The following will be 4G, 16G, 64G, 256G and 1T.
*/
#define OCFS2_BACKUP_SB_START 1 << 30
/* the max backup superblock nums */
#define OCFS2_MAX_BACKUP_SUPERBLOCKS 6
/*
* Flags on ocfs2_super_block.s_tunefs_flags
*/
#define OCFS2_TUNEFS_INPROG_REMOVE_SLOT 0x0001 /* Removing slots */
/*
* Flags on ocfs2_dinode.i_flags
*/
#define OCFS2_VALID_FL (0x00000001) /* Inode is valid */
#define OCFS2_UNUSED2_FL (0x00000002)
#define OCFS2_ORPHANED_FL (0x00000004) /* On the orphan list */
#define OCFS2_UNUSED3_FL (0x00000008)
/* System inode flags */
#define OCFS2_SYSTEM_FL (0x00000010) /* System inode */
#define OCFS2_SUPER_BLOCK_FL (0x00000020) /* Super block */
#define OCFS2_LOCAL_ALLOC_FL (0x00000040) /* Slot local alloc bitmap */
#define OCFS2_BITMAP_FL (0x00000080) /* Allocation bitmap */
#define OCFS2_JOURNAL_FL (0x00000100) /* Slot local journal */
#define OCFS2_HEARTBEAT_FL (0x00000200) /* Heartbeat area */
#define OCFS2_CHAIN_FL (0x00000400) /* Chain allocator */
#define OCFS2_DEALLOC_FL (0x00000800) /* Truncate log */
#define OCFS2_QUOTA_FL (0x00001000) /* Quota file */
/*
* Flags on ocfs2_dinode.i_dyn_features
*
* These can change much more often than i_flags. When adding flags,
* keep in mind that i_dyn_features is only 16 bits wide.
*/
#define OCFS2_INLINE_DATA_FL (0x0001) /* Data stored in inode block */
#define OCFS2_HAS_XATTR_FL (0x0002)
#define OCFS2_INLINE_XATTR_FL (0x0004)
#define OCFS2_INDEXED_DIR_FL (0x0008)
/* Inode attributes, keep in sync with EXT2 */
#define OCFS2_SECRM_FL (0x00000001) /* Secure deletion */
#define OCFS2_UNRM_FL (0x00000002) /* Undelete */
#define OCFS2_COMPR_FL (0x00000004) /* Compress file */
#define OCFS2_SYNC_FL (0x00000008) /* Synchronous updates */
#define OCFS2_IMMUTABLE_FL (0x00000010) /* Immutable file */
#define OCFS2_APPEND_FL (0x00000020) /* writes to file may only append */
#define OCFS2_NODUMP_FL (0x00000040) /* do not dump file */
#define OCFS2_NOATIME_FL (0x00000080) /* do not update atime */
#define OCFS2_DIRSYNC_FL (0x00010000) /* dirsync behaviour (directories only) */
#define OCFS2_FL_VISIBLE (0x000100FF) /* User visible flags */
#define OCFS2_FL_MODIFIABLE (0x000100FF) /* User modifiable flags */
/*
* Extent record flags (e_node.leaf.flags)
*/
#define OCFS2_EXT_UNWRITTEN (0x01) /* Extent is allocated but
* unwritten */
/*
* ioctl commands
*/
#define OCFS2_IOC_GETFLAGS _IOR('f', 1, long)
#define OCFS2_IOC_SETFLAGS _IOW('f', 2, long)
#define OCFS2_IOC32_GETFLAGS _IOR('f', 1, int)
#define OCFS2_IOC32_SETFLAGS _IOW('f', 2, int)
/*
* Space reservation / allocation / free ioctls and argument structure
* are designed to be compatible with XFS.
*
* ALLOCSP* and FREESP* are not and will never be supported, but are
* included here for completeness.
*/
struct ocfs2_space_resv {
__s16 l_type;
__s16 l_whence;
__s64 l_start;
__s64 l_len; /* len == 0 means until end of file */
__s32 l_sysid;
__u32 l_pid;
__s32 l_pad[4]; /* reserve area */
};
#define OCFS2_IOC_ALLOCSP _IOW ('X', 10, struct ocfs2_space_resv)
#define OCFS2_IOC_FREESP _IOW ('X', 11, struct ocfs2_space_resv)
#define OCFS2_IOC_RESVSP _IOW ('X', 40, struct ocfs2_space_resv)
#define OCFS2_IOC_UNRESVSP _IOW ('X', 41, struct ocfs2_space_resv)
#define OCFS2_IOC_ALLOCSP64 _IOW ('X', 36, struct ocfs2_space_resv)
#define OCFS2_IOC_FREESP64 _IOW ('X', 37, struct ocfs2_space_resv)
#define OCFS2_IOC_RESVSP64 _IOW ('X', 42, struct ocfs2_space_resv)
#define OCFS2_IOC_UNRESVSP64 _IOW ('X', 43, struct ocfs2_space_resv)
/* Used to pass group descriptor data when online resize is done */
struct ocfs2_new_group_input {
__u64 group; /* Group descriptor's blkno. */
__u32 clusters; /* Total number of clusters in this group */
__u32 frees; /* Total free clusters in this group */
__u16 chain; /* Chain for this group */
__u16 reserved1;
__u32 reserved2;
};
#define OCFS2_IOC_GROUP_EXTEND _IOW('o', 1, int)
#define OCFS2_IOC_GROUP_ADD _IOW('o', 2,struct ocfs2_new_group_input)
#define OCFS2_IOC_GROUP_ADD64 _IOW('o', 3,struct ocfs2_new_group_input)
/*
* Journal Flags (ocfs2_dinode.id1.journal1.i_flags)
*/
#define OCFS2_JOURNAL_DIRTY_FL (0x00000001) /* Journal needs recovery */
/*
* superblock s_state flags
*/
#define OCFS2_ERROR_FS (0x00000001) /* FS saw errors */
/* Limit of space in ocfs2_dir_entry */
#define OCFS2_MAX_FILENAME_LEN 255
/* Maximum slots on an ocfs2 file system */
#define OCFS2_MAX_SLOTS 255
/* Slot map indicator for an empty slot */
#define OCFS2_INVALID_SLOT -1
#define OCFS2_VOL_UUID_LEN 16
#define OCFS2_MAX_VOL_LABEL_LEN 64
/* The alternate, userspace stack fields */
#define OCFS2_STACK_LABEL_LEN 4
#define OCFS2_CLUSTER_NAME_LEN 16
/* Journal limits (in bytes) */
#define OCFS2_MIN_JOURNAL_SIZE (4 * 1024 * 1024)
/*
* Default local alloc size (in megabytes)
*
* The value chosen should be such that most allocations, including new
* block groups, use local alloc.
*/
#define OCFS2_DEFAULT_LOCAL_ALLOC_SIZE 8
/*
* Inline extended attribute size (in bytes)
* The value chosen should be aligned to 16 byte boundaries.
*/
#define OCFS2_MIN_XATTR_INLINE_SIZE 256
struct ocfs2_system_inode_info {
char *si_name;
int si_iflags;
int si_mode;
};
/* System file index */
enum {
BAD_BLOCK_SYSTEM_INODE = 0,
GLOBAL_INODE_ALLOC_SYSTEM_INODE,
SLOT_MAP_SYSTEM_INODE,
#define OCFS2_FIRST_ONLINE_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE
HEARTBEAT_SYSTEM_INODE,
GLOBAL_BITMAP_SYSTEM_INODE,
USER_QUOTA_SYSTEM_INODE,
GROUP_QUOTA_SYSTEM_INODE,
#define OCFS2_LAST_GLOBAL_SYSTEM_INODE GROUP_QUOTA_SYSTEM_INODE
ORPHAN_DIR_SYSTEM_INODE,
EXTENT_ALLOC_SYSTEM_INODE,
INODE_ALLOC_SYSTEM_INODE,
JOURNAL_SYSTEM_INODE,
LOCAL_ALLOC_SYSTEM_INODE,
TRUNCATE_LOG_SYSTEM_INODE,
LOCAL_USER_QUOTA_SYSTEM_INODE,
LOCAL_GROUP_QUOTA_SYSTEM_INODE,
NUM_SYSTEM_INODES
};
static struct ocfs2_system_inode_info ocfs2_system_inodes[NUM_SYSTEM_INODES] = {
/* Global system inodes (single copy) */
/* The first two are only used from userspace mfks/tunefs */
[BAD_BLOCK_SYSTEM_INODE] = { "bad_blocks", 0, S_IFREG | 0644 },
[GLOBAL_INODE_ALLOC_SYSTEM_INODE] = { "global_inode_alloc", OCFS2_BITMAP_FL | OCFS2_CHAIN_FL, S_IFREG | 0644 },
/* These are used by the running filesystem */
[SLOT_MAP_SYSTEM_INODE] = { "slot_map", 0, S_IFREG | 0644 },
[HEARTBEAT_SYSTEM_INODE] = { "heartbeat", OCFS2_HEARTBEAT_FL, S_IFREG | 0644 },
[GLOBAL_BITMAP_SYSTEM_INODE] = { "global_bitmap", 0, S_IFREG | 0644 },
[USER_QUOTA_SYSTEM_INODE] = { "aquota.user", OCFS2_QUOTA_FL, S_IFREG | 0644 },
[GROUP_QUOTA_SYSTEM_INODE] = { "aquota.group", OCFS2_QUOTA_FL, S_IFREG | 0644 },
/* Slot-specific system inodes (one copy per slot) */
[ORPHAN_DIR_SYSTEM_INODE] = { "orphan_dir:%04d", 0, S_IFDIR | 0755 },
[EXTENT_ALLOC_SYSTEM_INODE] = { "extent_alloc:%04d", OCFS2_BITMAP_FL | OCFS2_CHAIN_FL, S_IFREG | 0644 },
[INODE_ALLOC_SYSTEM_INODE] = { "inode_alloc:%04d", OCFS2_BITMAP_FL | OCFS2_CHAIN_FL, S_IFREG | 0644 },
[JOURNAL_SYSTEM_INODE] = { "journal:%04d", OCFS2_JOURNAL_FL, S_IFREG | 0644 },
[LOCAL_ALLOC_SYSTEM_INODE] = { "local_alloc:%04d", OCFS2_BITMAP_FL | OCFS2_LOCAL_ALLOC_FL, S_IFREG | 0644 },
[TRUNCATE_LOG_SYSTEM_INODE] = { "truncate_log:%04d", OCFS2_DEALLOC_FL, S_IFREG | 0644 },
[LOCAL_USER_QUOTA_SYSTEM_INODE] = { "aquota.user:%04d", OCFS2_QUOTA_FL, S_IFREG | 0644 },
[LOCAL_GROUP_QUOTA_SYSTEM_INODE] = { "aquota.group:%04d", OCFS2_QUOTA_FL, S_IFREG | 0644 },
};
/* Parameter passed from mount.ocfs2 to module */
#define OCFS2_HB_NONE "heartbeat=none"
#define OCFS2_HB_LOCAL "heartbeat=local"
/*
* OCFS2 directory file types. Only the low 3 bits are used. The
* other bits are reserved for now.
*/
#define OCFS2_FT_UNKNOWN 0
#define OCFS2_FT_REG_FILE 1
#define OCFS2_FT_DIR 2
#define OCFS2_FT_CHRDEV 3
#define OCFS2_FT_BLKDEV 4
#define OCFS2_FT_FIFO 5
#define OCFS2_FT_SOCK 6
#define OCFS2_FT_SYMLINK 7
#define OCFS2_FT_MAX 8
/*
* OCFS2_DIR_PAD defines the directory entries boundaries
*
* NOTE: It must be a multiple of 4
*/
#define OCFS2_DIR_PAD 4
#define OCFS2_DIR_ROUND (OCFS2_DIR_PAD - 1)
#define OCFS2_DIR_MEMBER_LEN offsetof(struct ocfs2_dir_entry, name)
#define OCFS2_DIR_REC_LEN(name_len) (((name_len) + OCFS2_DIR_MEMBER_LEN + \
OCFS2_DIR_ROUND) & \
~OCFS2_DIR_ROUND)
#define OCFS2_DIR_MIN_REC_LEN OCFS2_DIR_REC_LEN(1)
#define OCFS2_LINK_MAX 32000
#define OCFS2_DX_LINK_MAX ((1U << 31) - 1U)
#define OCFS2_LINKS_HI_SHIFT 16
#define OCFS2_DX_ENTRIES_MAX (0xffffffffU)
#define S_SHIFT 12
static unsigned char ocfs2_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFREG >> S_SHIFT] = OCFS2_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = OCFS2_FT_DIR,
[S_IFCHR >> S_SHIFT] = OCFS2_FT_CHRDEV,
[S_IFBLK >> S_SHIFT] = OCFS2_FT_BLKDEV,
[S_IFIFO >> S_SHIFT] = OCFS2_FT_FIFO,
[S_IFSOCK >> S_SHIFT] = OCFS2_FT_SOCK,
[S_IFLNK >> S_SHIFT] = OCFS2_FT_SYMLINK,
};
/*
* Convenience casts
*/
#define OCFS2_RAW_SB(dinode) (&((dinode)->id2.i_super))
/*
* Block checking structure. This is used in metadata to validate the
* contents. If OCFS2_FEATURE_INCOMPAT_META_ECC is not set, it is all
* zeros.
*/
struct ocfs2_block_check {
/*00*/ __le32 bc_crc32e; /* 802.3 Ethernet II CRC32 */
__le16 bc_ecc; /* Single-error-correction parity vector.
This is a simple Hamming code dependant
on the blocksize. OCFS2's maximum
blocksize, 4K, requires 16 parity bits,
so we fit in __le16. */
__le16 bc_reserved1;
/*08*/
};
/*
* On disk extent record for OCFS2
* It describes a range of clusters on disk.
*
* Length fields are divided into interior and leaf node versions.
* This leaves room for a flags field (OCFS2_EXT_*) in the leaf nodes.
*/
struct ocfs2_extent_rec {
/*00*/ __le32 e_cpos; /* Offset into the file, in clusters */
union {
__le32 e_int_clusters; /* Clusters covered by all children */
struct {
__le16 e_leaf_clusters; /* Clusters covered by this
extent */
__u8 e_reserved1;
__u8 e_flags; /* Extent flags */
};
};
__le64 e_blkno; /* Physical disk offset, in blocks */
/*10*/
};
struct ocfs2_chain_rec {
__le32 c_free; /* Number of free bits in this chain. */
__le32 c_total; /* Number of total bits in this chain */
__le64 c_blkno; /* Physical disk offset (blocks) of 1st group */
};
struct ocfs2_truncate_rec {
__le32 t_start; /* 1st cluster in this log */
__le32 t_clusters; /* Number of total clusters covered */
};
/*
* On disk extent list for OCFS2 (node in the tree). Note that this
* is contained inside ocfs2_dinode or ocfs2_extent_block, so the
* offsets are relative to ocfs2_dinode.id2.i_list or
* ocfs2_extent_block.h_list, respectively.
*/
struct ocfs2_extent_list {
/*00*/ __le16 l_tree_depth; /* Extent tree depth from this
point. 0 means data extents
hang directly off this
header (a leaf)
NOTE: The high 8 bits cannot be
used - tree_depth is never that big.
*/
__le16 l_count; /* Number of extent records */
__le16 l_next_free_rec; /* Next unused extent slot */
__le16 l_reserved1;
__le64 l_reserved2; /* Pad to
sizeof(ocfs2_extent_rec) */
/*10*/ struct ocfs2_extent_rec l_recs[0]; /* Extent records */
};
/*
* On disk allocation chain list for OCFS2. Note that this is
* contained inside ocfs2_dinode, so the offsets are relative to
* ocfs2_dinode.id2.i_chain.
*/
struct ocfs2_chain_list {
/*00*/ __le16 cl_cpg; /* Clusters per Block Group */
__le16 cl_bpc; /* Bits per cluster */
__le16 cl_count; /* Total chains in this list */
__le16 cl_next_free_rec; /* Next unused chain slot */
__le64 cl_reserved1;
/*10*/ struct ocfs2_chain_rec cl_recs[0]; /* Chain records */
};
/*
* On disk deallocation log for OCFS2. Note that this is
* contained inside ocfs2_dinode, so the offsets are relative to
* ocfs2_dinode.id2.i_dealloc.
*/
struct ocfs2_truncate_log {
/*00*/ __le16 tl_count; /* Total records in this log */
__le16 tl_used; /* Number of records in use */
__le32 tl_reserved1;
/*08*/ struct ocfs2_truncate_rec tl_recs[0]; /* Truncate records */
};
/*
* On disk extent block (indirect block) for OCFS2
*/
struct ocfs2_extent_block
{
/*00*/ __u8 h_signature[8]; /* Signature for verification */
struct ocfs2_block_check h_check; /* Error checking */
/*10*/ __le16 h_suballoc_slot; /* Slot suballocator this
extent_header belongs to */
__le16 h_suballoc_bit; /* Bit offset in suballocator
block group */
__le32 h_fs_generation; /* Must match super block */
__le64 h_blkno; /* Offset on disk, in blocks */
/*20*/ __le64 h_reserved3;
__le64 h_next_leaf_blk; /* Offset on disk, in blocks,
of next leaf header pointing
to data */
/*30*/ struct ocfs2_extent_list h_list; /* Extent record list */
/* Actual on-disk size is one block */
};
/*
* On disk slot map for OCFS2. This defines the contents of the "slot_map"
* system file. A slot is valid if it contains a node number >= 0. The
* value -1 (0xFFFF) is OCFS2_INVALID_SLOT. This marks a slot empty.
*/
struct ocfs2_slot_map {
/*00*/ __le16 sm_slots[0];
/*
* Actual on-disk size is one block. OCFS2_MAX_SLOTS is 255,
* 255 * sizeof(__le16) == 512B, within the 512B block minimum blocksize.
*/
};
struct ocfs2_extended_slot {
/*00*/ __u8 es_valid;
__u8 es_reserved1[3];
__le32 es_node_num;
/*10*/
};
/*
* The extended slot map, used when OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP
* is set. It separates out the valid marker from the node number, and
* has room to grow. Unlike the old slot map, this format is defined by
* i_size.
*/
struct ocfs2_slot_map_extended {
/*00*/ struct ocfs2_extended_slot se_slots[0];
/*
* Actual size is i_size of the slot_map system file. It should
* match s_max_slots * sizeof(struct ocfs2_extended_slot)
*/
};
struct ocfs2_cluster_info {
/*00*/ __u8 ci_stack[OCFS2_STACK_LABEL_LEN];
__le32 ci_reserved;
/*08*/ __u8 ci_cluster[OCFS2_CLUSTER_NAME_LEN];
/*18*/
};
/*
* On disk superblock for OCFS2
* Note that it is contained inside an ocfs2_dinode, so all offsets
* are relative to the start of ocfs2_dinode.id2.
*/
struct ocfs2_super_block {
/*00*/ __le16 s_major_rev_level;
__le16 s_minor_rev_level;
__le16 s_mnt_count;
__le16 s_max_mnt_count;
__le16 s_state; /* File system state */
__le16 s_errors; /* Behaviour when detecting errors */
__le32 s_checkinterval; /* Max time between checks */
/*10*/ __le64 s_lastcheck; /* Time of last check */
__le32 s_creator_os; /* OS */
__le32 s_feature_compat; /* Compatible feature set */
/*20*/ __le32 s_feature_incompat; /* Incompatible feature set */
__le32 s_feature_ro_compat; /* Readonly-compatible feature set */
__le64 s_root_blkno; /* Offset, in blocks, of root directory
dinode */
/*30*/ __le64 s_system_dir_blkno; /* Offset, in blocks, of system
directory dinode */
__le32 s_blocksize_bits; /* Blocksize for this fs */
__le32 s_clustersize_bits; /* Clustersize for this fs */
/*40*/ __le16 s_max_slots; /* Max number of simultaneous mounts
before tunefs required */
__le16 s_tunefs_flag;
__le32 s_uuid_hash; /* hash value of uuid */
__le64 s_first_cluster_group; /* Block offset of 1st cluster
* group header */
/*50*/ __u8 s_label[OCFS2_MAX_VOL_LABEL_LEN]; /* Label for mounting, etc. */
/*90*/ __u8 s_uuid[OCFS2_VOL_UUID_LEN]; /* 128-bit uuid */
/*A0*/ struct ocfs2_cluster_info s_cluster_info; /* Selected userspace
stack. Only valid
with INCOMPAT flag. */
/*B8*/ __le16 s_xattr_inline_size; /* extended attribute inline size
for this fs*/
__le16 s_reserved0;
__le32 s_dx_seed[3]; /* seed[0-2] for dx dir hash.
* s_uuid_hash serves as seed[3]. */
/*C0*/ __le64 s_reserved2[15]; /* Fill out superblock */
/*140*/
/*
* NOTE: As stated above, all offsets are relative to
* ocfs2_dinode.id2, which is at 0xC0 in the inode.
* 0xC0 + 0x140 = 0x200 or 512 bytes. A superblock must fit within
* our smallest blocksize, which is 512 bytes. To ensure this,
* we reserve the space in s_reserved2. Anything past s_reserved2
* will not be available on the smallest blocksize.
*/
};
/*
* Local allocation bitmap for OCFS2 slots
* Note that it exists inside an ocfs2_dinode, so all offsets are
* relative to the start of ocfs2_dinode.id2.
*/
struct ocfs2_local_alloc
{
/*00*/ __le32 la_bm_off; /* Starting bit offset in main bitmap */
__le16 la_size; /* Size of included bitmap, in bytes */
__le16 la_reserved1;
__le64 la_reserved2;
/*10*/ __u8 la_bitmap[0];
};
/*
* Data-in-inode header. This is only used if i_dyn_features has
* OCFS2_INLINE_DATA_FL set.
*/
struct ocfs2_inline_data
{
/*00*/ __le16 id_count; /* Number of bytes that can be used
* for data, starting at id_data */
__le16 id_reserved0;
__le32 id_reserved1;
__u8 id_data[0]; /* Start of user data */
};
/*
* On disk inode for OCFS2
*/
struct ocfs2_dinode {
/*00*/ __u8 i_signature[8]; /* Signature for validation */
__le32 i_generation; /* Generation number */
__le16 i_suballoc_slot; /* Slot suballocator this inode
belongs to */
__le16 i_suballoc_bit; /* Bit offset in suballocator
block group */
/*10*/ __le16 i_links_count_hi; /* High 16 bits of links count */
__le16 i_xattr_inline_size;
__le32 i_clusters; /* Cluster count */
__le32 i_uid; /* Owner UID */
__le32 i_gid; /* Owning GID */
/*20*/ __le64 i_size; /* Size in bytes */
__le16 i_mode; /* File mode */
__le16 i_links_count; /* Links count */
__le32 i_flags; /* File flags */
/*30*/ __le64 i_atime; /* Access time */
__le64 i_ctime; /* Creation time */
/*40*/ __le64 i_mtime; /* Modification time */
__le64 i_dtime; /* Deletion time */
/*50*/ __le64 i_blkno; /* Offset on disk, in blocks */
__le64 i_last_eb_blk; /* Pointer to last extent
block */
/*60*/ __le32 i_fs_generation; /* Generation per fs-instance */
__le32 i_atime_nsec;
__le32 i_ctime_nsec;
__le32 i_mtime_nsec;
/*70*/ __le32 i_attr;
__le16 i_orphaned_slot; /* Only valid when OCFS2_ORPHANED_FL
was set in i_flags */
__le16 i_dyn_features;
__le64 i_xattr_loc;
/*80*/ struct ocfs2_block_check i_check; /* Error checking */
/*88*/ __le64 i_dx_root; /* Pointer to dir index root block */
__le64 i_reserved2[5];
/*B8*/ union {
__le64 i_pad1; /* Generic way to refer to this
64bit union */
struct {
__le64 i_rdev; /* Device number */
} dev1;
struct { /* Info for bitmap system
inodes */
__le32 i_used; /* Bits (ie, clusters) used */
__le32 i_total; /* Total bits (clusters)
available */
} bitmap1;
struct { /* Info for journal system
inodes */
__le32 ij_flags; /* Mounted, version, etc. */
__le32 ij_recovery_generation; /* Incremented when the
journal is recovered
after an unclean
shutdown */
} journal1;
} id1; /* Inode type dependant 1 */
/*C0*/ union {
struct ocfs2_super_block i_super;
struct ocfs2_local_alloc i_lab;
struct ocfs2_chain_list i_chain;
struct ocfs2_extent_list i_list;
struct ocfs2_truncate_log i_dealloc;
struct ocfs2_inline_data i_data;
__u8 i_symlink[0];
} id2;
/* Actual on-disk size is one block */
};
/*
* On-disk directory entry structure for OCFS2
*
* Packed as this structure could be accessed unaligned on 64-bit platforms
*/
struct ocfs2_dir_entry {
/*00*/ __le64 inode; /* Inode number */
__le16 rec_len; /* Directory entry length */
__u8 name_len; /* Name length */
__u8 file_type;
/*0C*/ char name[OCFS2_MAX_FILENAME_LEN]; /* File name */
/* Actual on-disk length specified by rec_len */
} __attribute__ ((packed));
/*
* Per-block record for the unindexed directory btree. This is carefully
* crafted so that the rec_len and name_len records of an ocfs2_dir_entry are
* mirrored. That way, the directory manipulation code needs a minimal amount
* of update.
*
* NOTE: Keep this structure aligned to a multiple of 4 bytes.
*/
struct ocfs2_dir_block_trailer {
/*00*/ __le64 db_compat_inode; /* Always zero. Was inode */
__le16 db_compat_rec_len; /* Backwards compatible with
* ocfs2_dir_entry. */
__u8 db_compat_name_len; /* Always zero. Was name_len */
__u8 db_reserved0;
__le16 db_reserved1;
__le16 db_free_rec_len; /* Size of largest empty hole
* in this block. (unused) */
/*10*/ __u8 db_signature[8]; /* Signature for verification */
__le64 db_reserved2;
__le64 db_free_next; /* Next block in list (unused) */
/*20*/ __le64 db_blkno; /* Offset on disk, in blocks */
__le64 db_parent_dinode; /* dinode which owns me, in
blocks */
/*30*/ struct ocfs2_block_check db_check; /* Error checking */
/*40*/
};
/*
* A directory entry in the indexed tree. We don't store the full name here,
* but instead provide a pointer to the full dirent in the unindexed tree.
*
* We also store name_len here so as to reduce the number of leaf blocks we
* need to search in case of collisions.
*/
struct ocfs2_dx_entry {
__le32 dx_major_hash; /* Used to find logical
* cluster in index */
__le32 dx_minor_hash; /* Lower bits used to find
* block in cluster */
__le64 dx_dirent_blk; /* Physical block in unindexed
* tree holding this dirent. */
};
struct ocfs2_dx_entry_list {
__le32 de_reserved;
__le16 de_count; /* Maximum number of entries
* possible in de_entries */
__le16 de_num_used; /* Current number of
* de_entries entries */
struct ocfs2_dx_entry de_entries[0]; /* Indexed dir entries
* in a packed array of
* length de_num_used */
};
#define OCFS2_DX_FLAG_INLINE 0x01
/*
* A directory indexing block. Each indexed directory has one of these,
* pointed to by ocfs2_dinode.
*
* This block stores an indexed btree root, and a set of free space
* start-of-list pointers.
*/
struct ocfs2_dx_root_block {
__u8 dr_signature[8]; /* Signature for verification */
struct ocfs2_block_check dr_check; /* Error checking */
__le16 dr_suballoc_slot; /* Slot suballocator this
* block belongs to. */
__le16 dr_suballoc_bit; /* Bit offset in suballocator
* block group */
__le32 dr_fs_generation; /* Must match super block */
__le64 dr_blkno; /* Offset on disk, in blocks */
__le64 dr_last_eb_blk; /* Pointer to last
* extent block */
__le32 dr_clusters; /* Clusters allocated
* to the indexed tree. */
__u8 dr_flags; /* OCFS2_DX_FLAG_* flags */
__u8 dr_reserved0;
__le16 dr_reserved1;
__le64 dr_dir_blkno; /* Pointer to parent inode */
__le32 dr_num_entries; /* Total number of
* names stored in
* this directory.*/
__le32 dr_reserved2;
__le64 dr_free_blk; /* Pointer to head of free
* unindexed block list. */
__le64 dr_reserved3[15];
union {
struct ocfs2_extent_list dr_list; /* Keep this aligned to 128
* bits for maximum space
* efficiency. */
struct ocfs2_dx_entry_list dr_entries; /* In-root-block list of
* entries. We grow out
* to extents if this
* gets too big. */
};
};
/*
* The header of a leaf block in the indexed tree.
*/
struct ocfs2_dx_leaf {
__u8 dl_signature[8];/* Signature for verification */
struct ocfs2_block_check dl_check; /* Error checking */
__le64 dl_blkno; /* Offset on disk, in blocks */
__le32 dl_fs_generation;/* Must match super block */
__le32 dl_reserved0;
__le64 dl_reserved1;
struct ocfs2_dx_entry_list dl_list;
};
/*
* On disk allocator group structure for OCFS2
*/
struct ocfs2_group_desc
{
/*00*/ __u8 bg_signature[8]; /* Signature for validation */
__le16 bg_size; /* Size of included bitmap in
bytes. */
__le16 bg_bits; /* Bits represented by this
group. */
__le16 bg_free_bits_count; /* Free bits count */
__le16 bg_chain; /* What chain I am in. */
/*10*/ __le32 bg_generation;
__le32 bg_reserved1;
__le64 bg_next_group; /* Next group in my list, in
blocks */
/*20*/ __le64 bg_parent_dinode; /* dinode which owns me, in
blocks */
__le64 bg_blkno; /* Offset on disk, in blocks */
/*30*/ struct ocfs2_block_check bg_check; /* Error checking */
__le64 bg_reserved2;
/*40*/ __u8 bg_bitmap[0];
};
/*
* On disk extended attribute structure for OCFS2.
*/
/*
* ocfs2_xattr_entry indicates one extend attribute.
*
* Note that it can be stored in inode, one block or one xattr bucket.
*/
struct ocfs2_xattr_entry {
__le32 xe_name_hash; /* hash value of xattr prefix+suffix. */
__le16 xe_name_offset; /* byte offset from the 1st entry in the
local xattr storage(inode, xattr block or
xattr bucket). */
__u8 xe_name_len; /* xattr name len, does't include prefix. */
__u8 xe_type; /* the low 7 bits indicate the name prefix
* type and the highest bit indicates whether
* the EA is stored in the local storage. */
__le64 xe_value_size; /* real xattr value length. */
};
/*
* On disk structure for xattr header.
*
* One ocfs2_xattr_header describes how many ocfs2_xattr_entry records in
* the local xattr storage.
*/
struct ocfs2_xattr_header {
__le16 xh_count; /* contains the count of how
many records are in the
local xattr storage. */
__le16 xh_free_start; /* current offset for storing
xattr. */
__le16 xh_name_value_len; /* total length of name/value
length in this bucket. */
__le16 xh_num_buckets; /* Number of xattr buckets
in this extent record,
only valid in the first
bucket. */
struct ocfs2_block_check xh_check; /* Error checking
(Note, this is only
used for xattr
buckets. A block uses
xb_check and sets
this field to zero.) */
struct ocfs2_xattr_entry xh_entries[0]; /* xattr entry list. */
};
/*
* On disk structure for xattr value root.
*
* When an xattr's value is large enough, it is stored in an external
* b-tree like file data. The xattr value root points to this structure.
*/
struct ocfs2_xattr_value_root {
/*00*/ __le32 xr_clusters; /* clusters covered by xattr value. */
__le32 xr_reserved0;
__le64 xr_last_eb_blk; /* Pointer to last extent block */
/*10*/ struct ocfs2_extent_list xr_list; /* Extent record list */
};
/*
* On disk structure for xattr tree root.
*
* It is used when there are too many extended attributes for one file. These
* attributes will be organized and stored in an indexed-btree.
*/
struct ocfs2_xattr_tree_root {
/*00*/ __le32 xt_clusters; /* clusters covered by xattr. */
__le32 xt_reserved0;
__le64 xt_last_eb_blk; /* Pointer to last extent block */
/*10*/ struct ocfs2_extent_list xt_list; /* Extent record list */
};
#define OCFS2_XATTR_INDEXED 0x1
#define OCFS2_HASH_SHIFT 5
#define OCFS2_XATTR_ROUND 3
#define OCFS2_XATTR_SIZE(size) (((size) + OCFS2_XATTR_ROUND) & \
~(OCFS2_XATTR_ROUND))
#define OCFS2_XATTR_BUCKET_SIZE 4096
#define OCFS2_XATTR_MAX_BLOCKS_PER_BUCKET (OCFS2_XATTR_BUCKET_SIZE \
/ OCFS2_MIN_BLOCKSIZE)
/*
* On disk structure for xattr block.
*/
struct ocfs2_xattr_block {
/*00*/ __u8 xb_signature[8]; /* Signature for verification */
__le16 xb_suballoc_slot; /* Slot suballocator this
block belongs to. */
__le16 xb_suballoc_bit; /* Bit offset in suballocator
block group */
__le32 xb_fs_generation; /* Must match super block */
/*10*/ __le64 xb_blkno; /* Offset on disk, in blocks */
struct ocfs2_block_check xb_check; /* Error checking */
/*20*/ __le16 xb_flags; /* Indicates whether this block contains