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
|
/*
* Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
* 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 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would 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 the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef __XFS_INODE_H__
#define __XFS_INODE_H__
struct posix_acl;
struct xfs_dinode;
struct xfs_inode;
/*
* Fork identifiers.
*/
#define XFS_DATA_FORK 0
#define XFS_ATTR_FORK 1
/*
* The following xfs_ext_irec_t struct introduces a second (top) level
* to the in-core extent allocation scheme. These structs are allocated
* in a contiguous block, creating an indirection array where each entry
* (irec) contains a pointer to a buffer of in-core extent records which
* it manages. Each extent buffer is 4k in size, since 4k is the system
* page size on Linux i386 and systems with larger page sizes don't seem
* to gain much, if anything, by using their native page size as the
* extent buffer size. Also, using 4k extent buffers everywhere provides
* a consistent interface for CXFS across different platforms.
*
* There is currently no limit on the number of irec's (extent lists)
* allowed, so heavily fragmented files may require an indirection array
* which spans multiple system pages of memory. The number of extents
* which would require this amount of contiguous memory is very large
* and should not cause problems in the foreseeable future. However,
* if the memory needed for the contiguous array ever becomes a problem,
* it is possible that a third level of indirection may be required.
*/
typedef struct xfs_ext_irec {
xfs_bmbt_rec_host_t *er_extbuf; /* block of extent records */
xfs_extnum_t er_extoff; /* extent offset in file */
xfs_extnum_t er_extcount; /* number of extents in page/block */
} xfs_ext_irec_t;
/*
* File incore extent information, present for each of data & attr forks.
*/
#define XFS_IEXT_BUFSZ 4096
#define XFS_LINEAR_EXTS (XFS_IEXT_BUFSZ / (uint)sizeof(xfs_bmbt_rec_t))
#define XFS_INLINE_EXTS 2
#define XFS_INLINE_DATA 32
typedef struct xfs_ifork {
int if_bytes; /* bytes in if_u1 */
int if_real_bytes; /* bytes allocated in if_u1 */
struct xfs_btree_block *if_broot; /* file's incore btree root */
short if_broot_bytes; /* bytes allocated for root */
unsigned char if_flags; /* per-fork flags */
unsigned char if_ext_max; /* max # of extent records */
union {
xfs_bmbt_rec_host_t *if_extents;/* linear map file exts */
xfs_ext_irec_t *if_ext_irec; /* irec map file exts */
char *if_data; /* inline file data */
} if_u1;
union {
xfs_bmbt_rec_host_t if_inline_ext[XFS_INLINE_EXTS];
/* very small file extents */
char if_inline_data[XFS_INLINE_DATA];
/* very small file data */
xfs_dev_t if_rdev; /* dev number if special */
uuid_t if_uuid; /* mount point value */
} if_u2;
} xfs_ifork_t;
/*
* Inode location information. Stored in the inode and passed to
* xfs_imap_to_bp() to get a buffer and dinode for a given inode.
*/
struct xfs_imap {
xfs_daddr_t im_blkno; /* starting BB of inode chunk */
ushort im_len; /* length in BBs of inode chunk */
ushort im_boffset; /* inode offset in block in bytes */
};
/*
* This is the xfs in-core inode structure.
* Most of the on-disk inode is embedded in the i_d field.
*
* The extent pointers/inline file space, however, are managed
* separately. The memory for this information is pointed to by
* the if_u1 unions depending on the type of the data.
* This is used to linearize the array of extents for fast in-core
* access. This is used until the file's number of extents
* surpasses XFS_MAX_INCORE_EXTENTS, at which point all extent pointers
* are accessed through the buffer cache.
*
* Other state kept in the in-core inode is used for identification,
* locking, transactional updating, etc of the inode.
*
* Generally, we do not want to hold the i_rlock while holding the
* i_ilock. Hierarchy is i_iolock followed by i_rlock.
*
* xfs_iptr_t contains all the inode fields up to and including the
* i_mnext and i_mprev fields, it is used as a marker in the inode
* chain off the mount structure by xfs_sync calls.
*/
typedef struct xfs_ictimestamp {
__int32_t t_sec; /* timestamp seconds */
__int32_t t_nsec; /* timestamp nanoseconds */
} xfs_ictimestamp_t;
/*
* NOTE: This structure must be kept identical to struct xfs_dinode
* in xfs_dinode.h except for the endianness annotations.
*/
typedef struct xfs_icdinode {
__uint16_t di_magic; /* inode magic # = XFS_DINODE_MAGIC */
__uint16_t di_mode; /* mode and type of file */
__int8_t di_version; /* inode version */
__int8_t di_format; /* format of di_c data */
__uint16_t di_onlink; /* old number of links to file */
__uint32_t di_uid; /* owner's user id */
__uint32_t di_gid; /* owner's group id */
__uint32_t di_nlink; /* number of links to file */
__uint16_t di_projid_lo; /* lower part of owner's project id */
__uint16_t di_projid_hi; /* higher part of owner's project id */
__uint8_t di_pad[6]; /* unused, zeroed space */
__uint16_t di_flushiter; /* incremented on flush */
xfs_ictimestamp_t di_atime; /* time last accessed */
xfs_ictimestamp_t di_mtime; /* time last modified */
xfs_ictimestamp_t di_ctime; /* time created/inode modified */
xfs_fsize_t di_size; /* number of bytes in file */
xfs_drfsbno_t di_nblocks; /* # of direct & btree blocks used */
xfs_extlen_t di_extsize; /* basic/minimum extent size for file */
xfs_extnum_t di_nextents; /* number of extents in data fork */
xfs_aextnum_t di_anextents; /* number of extents in attribute fork*/
__uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */
__int8_t di_aformat; /* format of attr fork's data */
__uint32_t di_dmevmask; /* DMIG event mask */
__uint16_t di_dmstate; /* DMIG state info */
__uint16_t di_flags; /* random flags, XFS_DIFLAG_... */
__uint32_t di_gen; /* generation number */
} xfs_icdinode_t;
/*
* Flags for xfs_ichgtime().
*/
#define XFS_ICHGTIME_MOD 0x1 /* data fork modification timestamp */
#define XFS_ICHGTIME_CHG 0x2 /* inode field change timestamp */
/*
* Per-fork incore inode flags.
*/
#define XFS_IFINLINE 0x01 /* Inline data is read in */
#define XFS_IFEXTENTS 0x02 /* All extent pointers are read in */
#define XFS_IFBROOT 0x04 /* i_broot points to the bmap b-tree root */
#define XFS_IFEXTIREC 0x08 /* Indirection array of extent blocks */
/*
* Fork handling.
*/
#define XFS_IFORK_Q(ip) ((ip)->i_d.di_forkoff != 0)
#define XFS_IFORK_BOFF(ip) ((int)((ip)->i_d.di_forkoff << 3))
#define XFS_IFORK_PTR(ip,w) \
((w) == XFS_DATA_FORK ? \
&(ip)->i_df : \
(ip)->i_afp)
#define XFS_IFORK_DSIZE(ip) \
(XFS_IFORK_Q(ip) ? \
XFS_IFORK_BOFF(ip) : \
XFS_LITINO((ip)->i_mount))
#define XFS_IFORK_ASIZE(ip) \
(XFS_IFORK_Q(ip) ? \
XFS_LITINO((ip)->i_mount) - XFS_IFORK_BOFF(ip) : \
0)
#define XFS_IFORK_SIZE(ip,w) \
((w) == XFS_DATA_FORK ? \
XFS_IFORK_DSIZE(ip) : \
XFS_IFORK_ASIZE(ip))
#define XFS_IFORK_FORMAT(ip,w) \
((w) == XFS_DATA_FORK ? \
(ip)->i_d.di_format : \
(ip)->i_d.di_aformat)
#define XFS_IFORK_FMT_SET(ip,w,n) \
((w) == XFS_DATA_FORK ? \
((ip)->i_d.di_format = (n)) : \
((ip)->i_d.di_aformat = (n)))
#define XFS_IFORK_NEXTENTS(ip,w) \
((w) == XFS_DATA_FORK ? \
(ip)->i_d.di_nextents : \
(ip)->i_d.di_anextents)
#define XFS_IFORK_NEXT_SET(ip,w,n) \
((w) == XFS_DATA_FORK ? \
((ip)->i_d.di_nextents = (n)) : \
((ip)->i_d.di_anextents = (n)))
#ifdef __KERNEL__
struct bhv_desc;
struct xfs_buf;
struct xfs_bmap_free;
struct xfs_bmbt_irec;
struct xfs_inode_log_item;
struct xfs_mount;
struct xfs_trans;
struct xfs_dquot;
typedef struct dm_attrs_s {
__uint32_t da_dmevmask; /* DMIG event mask */
__uint16_t da_dmstate; /* DMIG state info */
__uint16_t da_pad; /* DMIG extra padding */
} dm_attrs_t;
typedef struct xfs_inode {
/* Inode linking and identification information. */
struct xfs_mount *i_mount; /* fs mount struct ptr */
struct xfs_dquot *i_udquot; /* user dquot */
struct xfs_dquot *i_gdquot; /* group dquot */
/* Inode location stuff */
xfs_ino_t i_ino; /* inode number (agno/agino)*/
struct xfs_imap i_imap; /* location for xfs_imap() */
/* Extent information. */
xfs_ifork_t *i_afp; /* attribute fork pointer */
xfs_ifork_t i_df; /* data fork */
/* Transaction and locking information. */
struct xfs_inode_log_item *i_itemp; /* logging information */
mrlock_t i_lock; /* inode lock */
mrlock_t i_iolock; /* inode IO lock */
struct completion i_flush; /* inode flush completion q */
atomic_t i_pincount; /* inode pin count */
wait_queue_head_t i_ipin_wait; /* inode pinning wait queue */
spinlock_t i_flags_lock; /* inode i_flags lock */
/* Miscellaneous state. */
unsigned short i_flags; /* see defined flags below */
unsigned char i_update_core; /* timestamps/size is dirty */
unsigned int i_delayed_blks; /* count of delay alloc blks */
xfs_icdinode_t i_d; /* most of ondisk inode */
xfs_fsize_t i_size; /* in-memory size */
xfs_fsize_t i_new_size; /* size when write completes */
atomic_t i_iocount; /* outstanding I/O count */
/* VFS inode */
struct inode i_vnode; /* embedded VFS inode */
} xfs_inode_t;
#define XFS_ISIZE(ip) S_ISREG((ip)->i_d.di_mode) ? \
(ip)->i_size : (ip)->i_d.di_size;
/* Convert from vfs inode to xfs inode */
static inline struct xfs_inode *XFS_I(struct inode *inode)
{
return container_of(inode, struct xfs_inode, i_vnode);
}
/* convert from xfs inode to vfs inode */
static inline struct inode *VFS_I(struct xfs_inode *ip)
{
return &ip->i_vnode;
}
/*
* i_flags helper functions
*/
static inline void
__xfs_iflags_set(xfs_inode_t *ip, unsigned short flags)
{
ip->i_flags |= flags;
}
static inline void
xfs_iflags_set(xfs_inode_t *ip, unsigned short flags)
{
spin_lock(&ip->i_flags_lock);
__xfs_iflags_set(ip, flags);
spin_unlock(&ip->i_flags_lock);
}
static inline void
xfs_iflags_clear(xfs_inode_t *ip, unsigned short flags)
{
spin_lock(&ip->i_flags_lock);
ip->i_flags &= ~flags;
spin_unlock(&ip->i_flags_lock);
}
static inline int
__xfs_iflags_test(xfs_inode_t *ip, unsigned short flags)
{
return (ip->i_flags & flags);
}
static inline int
xfs_iflags_test(xfs_inode_t *ip, unsigned short flags)
{
int ret;
spin_lock(&ip->i_flags_lock);
ret = __xfs_iflags_test(ip, flags);
spin_unlock(&ip->i_flags_lock);
return ret;
}
static inline int
xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned short flags
|