forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
xfs_inode.c
3984 lines (3654 loc) · 114 KB
/
xfs_inode.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
/*
* Copyright (c) 2000-2006 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
*/
#include <linux/log2.h>
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_buf_item.h"
#include "xfs_inode_item.h"
#include "xfs_btree.h"
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_utils.h"
#include "xfs_quota.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
kmem_zone_t *xfs_ifork_zone;
kmem_zone_t *xfs_inode_zone;
/*
* Used in xfs_itruncate_extents(). This is the maximum number of extents
* freed from a file in a single transaction.
*/
#define XFS_ITRUNC_MAX_EXTENTS 2
STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *);
STATIC int xfs_iformat_local(xfs_inode_t *, xfs_dinode_t *, int, int);
STATIC int xfs_iformat_extents(xfs_inode_t *, xfs_dinode_t *, int);
STATIC int xfs_iformat_btree(xfs_inode_t *, xfs_dinode_t *, int);
/*
* helper function to extract extent size hint from inode
*/
xfs_extlen_t
xfs_get_extsz_hint(
struct xfs_inode *ip)
{
if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
return ip->i_d.di_extsize;
if (XFS_IS_REALTIME_INODE(ip))
return ip->i_mount->m_sb.sb_rextsize;
return 0;
}
/*
* This is a wrapper routine around the xfs_ilock() routine used to centralize
* some grungy code. It is used in places that wish to lock the inode solely
* for reading the extents. The reason these places can't just call
* xfs_ilock(SHARED) is that the inode lock also guards to bringing in of the
* extents from disk for a file in b-tree format. If the inode is in b-tree
* format, then we need to lock the inode exclusively until the extents are read
* in. Locking it exclusively all the time would limit our parallelism
* unnecessarily, though. What we do instead is check to see if the extents
* have been read in yet, and only lock the inode exclusively if they have not.
*
* The function returns a value which should be given to the corresponding
* xfs_iunlock_map_shared(). This value is the mode in which the lock was
* actually taken.
*/
uint
xfs_ilock_map_shared(
xfs_inode_t *ip)
{
uint lock_mode;
if ((ip->i_d.di_format == XFS_DINODE_FMT_BTREE) &&
((ip->i_df.if_flags & XFS_IFEXTENTS) == 0)) {
lock_mode = XFS_ILOCK_EXCL;
} else {
lock_mode = XFS_ILOCK_SHARED;
}
xfs_ilock(ip, lock_mode);
return lock_mode;
}
/*
* This is simply the unlock routine to go with xfs_ilock_map_shared().
* All it does is call xfs_iunlock() with the given lock_mode.
*/
void
xfs_iunlock_map_shared(
xfs_inode_t *ip,
unsigned int lock_mode)
{
xfs_iunlock(ip, lock_mode);
}
/*
* The xfs inode contains 2 locks: a multi-reader lock called the
* i_iolock and a multi-reader lock called the i_lock. This routine
* allows either or both of the locks to be obtained.
*
* The 2 locks should always be ordered so that the IO lock is
* obtained first in order to prevent deadlock.
*
* ip -- the inode being locked
* lock_flags -- this parameter indicates the inode's locks
* to be locked. It can be:
* XFS_IOLOCK_SHARED,
* XFS_IOLOCK_EXCL,
* XFS_ILOCK_SHARED,
* XFS_ILOCK_EXCL,
* XFS_IOLOCK_SHARED | XFS_ILOCK_SHARED,
* XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL,
* XFS_IOLOCK_EXCL | XFS_ILOCK_SHARED,
* XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL
*/
void
xfs_ilock(
xfs_inode_t *ip,
uint lock_flags)
{
trace_xfs_ilock(ip, lock_flags, _RET_IP_);
/*
* You can't set both SHARED and EXCL for the same lock,
* and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
* and XFS_ILOCK_EXCL are valid values to set in lock_flags.
*/
ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
(XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
if (lock_flags & XFS_IOLOCK_EXCL)
mrupdate_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags));
else if (lock_flags & XFS_IOLOCK_SHARED)
mraccess_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags));
if (lock_flags & XFS_ILOCK_EXCL)
mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
else if (lock_flags & XFS_ILOCK_SHARED)
mraccess_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
}
/*
* This is just like xfs_ilock(), except that the caller
* is guaranteed not to sleep. It returns 1 if it gets
* the requested locks and 0 otherwise. If the IO lock is
* obtained but the inode lock cannot be, then the IO lock
* is dropped before returning.
*
* ip -- the inode being locked
* lock_flags -- this parameter indicates the inode's locks to be
* to be locked. See the comment for xfs_ilock() for a list
* of valid values.
*/
int
xfs_ilock_nowait(
xfs_inode_t *ip,
uint lock_flags)
{
trace_xfs_ilock_nowait(ip, lock_flags, _RET_IP_);
/*
* You can't set both SHARED and EXCL for the same lock,
* and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
* and XFS_ILOCK_EXCL are valid values to set in lock_flags.
*/
ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
(XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
if (lock_flags & XFS_IOLOCK_EXCL) {
if (!mrtryupdate(&ip->i_iolock))
goto out;
} else if (lock_flags & XFS_IOLOCK_SHARED) {
if (!mrtryaccess(&ip->i_iolock))
goto out;
}
if (lock_flags & XFS_ILOCK_EXCL) {
if (!mrtryupdate(&ip->i_lock))
goto out_undo_iolock;
} else if (lock_flags & XFS_ILOCK_SHARED) {
if (!mrtryaccess(&ip->i_lock))
goto out_undo_iolock;
}
return 1;
out_undo_iolock:
if (lock_flags & XFS_IOLOCK_EXCL)
mrunlock_excl(&ip->i_iolock);
else if (lock_flags & XFS_IOLOCK_SHARED)
mrunlock_shared(&ip->i_iolock);
out:
return 0;
}
/*
* xfs_iunlock() is used to drop the inode locks acquired with
* xfs_ilock() and xfs_ilock_nowait(). The caller must pass
* in the flags given to xfs_ilock() or xfs_ilock_nowait() so
* that we know which locks to drop.
*
* ip -- the inode being unlocked
* lock_flags -- this parameter indicates the inode's locks to be
* to be unlocked. See the comment for xfs_ilock() for a list
* of valid values for this parameter.
*
*/
void
xfs_iunlock(
xfs_inode_t *ip,
uint lock_flags)
{
/*
* You can't set both SHARED and EXCL for the same lock,
* and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
* and XFS_ILOCK_EXCL are valid values to set in lock_flags.
*/
ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
(XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
ASSERT(lock_flags != 0);
if (lock_flags & XFS_IOLOCK_EXCL)
mrunlock_excl(&ip->i_iolock);
else if (lock_flags & XFS_IOLOCK_SHARED)
mrunlock_shared(&ip->i_iolock);
if (lock_flags & XFS_ILOCK_EXCL)
mrunlock_excl(&ip->i_lock);
else if (lock_flags & XFS_ILOCK_SHARED)
mrunlock_shared(&ip->i_lock);
trace_xfs_iunlock(ip, lock_flags, _RET_IP_);
}
/*
* give up write locks. the i/o lock cannot be held nested
* if it is being demoted.
*/
void
xfs_ilock_demote(
xfs_inode_t *ip,
uint lock_flags)
{
ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL));
ASSERT((lock_flags & ~(XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL)) == 0);
if (lock_flags & XFS_ILOCK_EXCL)
mrdemote(&ip->i_lock);
if (lock_flags & XFS_IOLOCK_EXCL)
mrdemote(&ip->i_iolock);
trace_xfs_ilock_demote(ip, lock_flags, _RET_IP_);
}
#ifdef DEBUG
int
xfs_isilocked(
xfs_inode_t *ip,
uint lock_flags)
{
if (lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) {
if (!(lock_flags & XFS_ILOCK_SHARED))
return !!ip->i_lock.mr_writer;
return rwsem_is_locked(&ip->i_lock.mr_lock);
}
if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) {
if (!(lock_flags & XFS_IOLOCK_SHARED))
return !!ip->i_iolock.mr_writer;
return rwsem_is_locked(&ip->i_iolock.mr_lock);
}
ASSERT(0);
return 0;
}
#endif
void
__xfs_iflock(
struct xfs_inode *ip)
{
wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT);
DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);
do {
prepare_to_wait_exclusive(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
if (xfs_isiflocked(ip))
io_schedule();
} while (!xfs_iflock_nowait(ip));
finish_wait(wq, &wait.wait);
}
#ifdef DEBUG
/*
* Make sure that the extents in the given memory buffer
* are valid.
*/
STATIC void
xfs_validate_extents(
xfs_ifork_t *ifp,
int nrecs,
xfs_exntfmt_t fmt)
{
xfs_bmbt_irec_t irec;
xfs_bmbt_rec_host_t rec;
int i;
for (i = 0; i < nrecs; i++) {
xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
rec.l0 = get_unaligned(&ep->l0);
rec.l1 = get_unaligned(&ep->l1);
xfs_bmbt_get_all(&rec, &irec);
if (fmt == XFS_EXTFMT_NOSTATE)
ASSERT(irec.br_state == XFS_EXT_NORM);
}
}
#else /* DEBUG */
#define xfs_validate_extents(ifp, nrecs, fmt)
#endif /* DEBUG */
/*
* Check that none of the inode's in the buffer have a next
* unlinked field of 0.
*/
#if defined(DEBUG)
void
xfs_inobp_check(
xfs_mount_t *mp,
xfs_buf_t *bp)
{
int i;
int j;
xfs_dinode_t *dip;
j = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;
for (i = 0; i < j; i++) {
dip = (xfs_dinode_t *)xfs_buf_offset(bp,
i * mp->m_sb.sb_inodesize);
if (!dip->di_next_unlinked) {
xfs_alert(mp,
"Detected bogus zero next_unlinked field in incore inode buffer 0x%p.",
bp);
ASSERT(dip->di_next_unlinked);
}
}
}
#endif
static void
xfs_inode_buf_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
int i;
int ni;
/*
* Validate the magic number and version of every inode in the buffer
*/
ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
for (i = 0; i < ni; i++) {
int di_ok;
xfs_dinode_t *dip;
dip = (struct xfs_dinode *)xfs_buf_offset(bp,
(i << mp->m_sb.sb_inodelog));
di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
XFS_DINODE_GOOD_VERSION(dip->di_version);
if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
XFS_ERRTAG_ITOBP_INOTOBP,
XFS_RANDOM_ITOBP_INOTOBP))) {
xfs_buf_ioerror(bp, EFSCORRUPTED);
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
mp, dip);
#ifdef DEBUG
xfs_emerg(mp,
"bad inode magic/vsn daddr %lld #%d (magic=%x)",
(unsigned long long)bp->b_bn, i,
be16_to_cpu(dip->di_magic));
ASSERT(0);
#endif
}
}
xfs_inobp_check(mp, bp);
}
static void
xfs_inode_buf_read_verify(
struct xfs_buf *bp)
{
xfs_inode_buf_verify(bp);
}
static void
xfs_inode_buf_write_verify(
struct xfs_buf *bp)
{
xfs_inode_buf_verify(bp);
}
const struct xfs_buf_ops xfs_inode_buf_ops = {
.verify_read = xfs_inode_buf_read_verify,
.verify_write = xfs_inode_buf_write_verify,
};
/*
* This routine is called to map an inode to the buffer containing the on-disk
* version of the inode. It returns a pointer to the buffer containing the
* on-disk inode in the bpp parameter, and in the dipp parameter it returns a
* pointer to the on-disk inode within that buffer.
*
* If a non-zero error is returned, then the contents of bpp and dipp are
* undefined.
*/
int
xfs_imap_to_bp(
struct xfs_mount *mp,
struct xfs_trans *tp,
struct xfs_imap *imap,
struct xfs_dinode **dipp,
struct xfs_buf **bpp,
uint buf_flags,
uint iget_flags)
{
struct xfs_buf *bp;
int error;
buf_flags |= XBF_UNMAPPED;
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
(int)imap->im_len, buf_flags, &bp,
&xfs_inode_buf_ops);
if (error) {
if (error == EAGAIN) {
ASSERT(buf_flags & XBF_TRYLOCK);
return error;
}
if (error == EFSCORRUPTED &&
(iget_flags & XFS_IGET_UNTRUSTED))
return XFS_ERROR(EINVAL);
xfs_warn(mp, "%s: xfs_trans_read_buf() returned error %d.",
__func__, error);
return error;
}
*bpp = bp;
*dipp = (struct xfs_dinode *)xfs_buf_offset(bp, imap->im_boffset);
return 0;
}
/*
* Move inode type and inode format specific information from the
* on-disk inode to the in-core inode. For fifos, devs, and sockets
* this means set if_rdev to the proper value. For files, directories,
* and symlinks this means to bring in the in-line data or extent
* pointers. For a file in B-tree format, only the root is immediately
* brought in-core. The rest will be in-lined in if_extents when it
* is first referenced (see xfs_iread_extents()).
*/
STATIC int
xfs_iformat(
xfs_inode_t *ip,
xfs_dinode_t *dip)
{
xfs_attr_shortform_t *atp;
int size;
int error = 0;
xfs_fsize_t di_size;
if (unlikely(be32_to_cpu(dip->di_nextents) +
be16_to_cpu(dip->di_anextents) >
be64_to_cpu(dip->di_nblocks))) {
xfs_warn(ip->i_mount,
"corrupt dinode %Lu, extent total = %d, nblocks = %Lu.",
(unsigned long long)ip->i_ino,
(int)(be32_to_cpu(dip->di_nextents) +
be16_to_cpu(dip->di_anextents)),
(unsigned long long)
be64_to_cpu(dip->di_nblocks));
XFS_CORRUPTION_ERROR("xfs_iformat(1)", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
if (unlikely(dip->di_forkoff > ip->i_mount->m_sb.sb_inodesize)) {
xfs_warn(ip->i_mount, "corrupt dinode %Lu, forkoff = 0x%x.",
(unsigned long long)ip->i_ino,
dip->di_forkoff);
XFS_CORRUPTION_ERROR("xfs_iformat(2)", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
if (unlikely((ip->i_d.di_flags & XFS_DIFLAG_REALTIME) &&
!ip->i_mount->m_rtdev_targp)) {
xfs_warn(ip->i_mount,
"corrupt dinode %Lu, has realtime flag set.",
ip->i_ino);
XFS_CORRUPTION_ERROR("xfs_iformat(realtime)",
XFS_ERRLEVEL_LOW, ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
switch (ip->i_d.di_mode & S_IFMT) {
case S_IFIFO:
case S_IFCHR:
case S_IFBLK:
case S_IFSOCK:
if (unlikely(dip->di_format != XFS_DINODE_FMT_DEV)) {
XFS_CORRUPTION_ERROR("xfs_iformat(3)", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
ip->i_d.di_size = 0;
ip->i_df.if_u2.if_rdev = xfs_dinode_get_rdev(dip);
break;
case S_IFREG:
case S_IFLNK:
case S_IFDIR:
switch (dip->di_format) {
case XFS_DINODE_FMT_LOCAL:
/*
* no local regular files yet
*/
if (unlikely(S_ISREG(be16_to_cpu(dip->di_mode)))) {
xfs_warn(ip->i_mount,
"corrupt inode %Lu (local format for regular file).",
(unsigned long long) ip->i_ino);
XFS_CORRUPTION_ERROR("xfs_iformat(4)",
XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
di_size = be64_to_cpu(dip->di_size);
if (unlikely(di_size > XFS_DFORK_DSIZE(dip, ip->i_mount))) {
xfs_warn(ip->i_mount,
"corrupt inode %Lu (bad size %Ld for local inode).",
(unsigned long long) ip->i_ino,
(long long) di_size);
XFS_CORRUPTION_ERROR("xfs_iformat(5)",
XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
size = (int)di_size;
error = xfs_iformat_local(ip, dip, XFS_DATA_FORK, size);
break;
case XFS_DINODE_FMT_EXTENTS:
error = xfs_iformat_extents(ip, dip, XFS_DATA_FORK);
break;
case XFS_DINODE_FMT_BTREE:
error = xfs_iformat_btree(ip, dip, XFS_DATA_FORK);
break;
default:
XFS_ERROR_REPORT("xfs_iformat(6)", XFS_ERRLEVEL_LOW,
ip->i_mount);
return XFS_ERROR(EFSCORRUPTED);
}
break;
default:
XFS_ERROR_REPORT("xfs_iformat(7)", XFS_ERRLEVEL_LOW, ip->i_mount);
return XFS_ERROR(EFSCORRUPTED);
}
if (error) {
return error;
}
if (!XFS_DFORK_Q(dip))
return 0;
ASSERT(ip->i_afp == NULL);
ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP | KM_NOFS);
switch (dip->di_aformat) {
case XFS_DINODE_FMT_LOCAL:
atp = (xfs_attr_shortform_t *)XFS_DFORK_APTR(dip);
size = be16_to_cpu(atp->hdr.totsize);
if (unlikely(size < sizeof(struct xfs_attr_sf_hdr))) {
xfs_warn(ip->i_mount,
"corrupt inode %Lu (bad attr fork size %Ld).",
(unsigned long long) ip->i_ino,
(long long) size);
XFS_CORRUPTION_ERROR("xfs_iformat(8)",
XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
error = xfs_iformat_local(ip, dip, XFS_ATTR_FORK, size);
break;
case XFS_DINODE_FMT_EXTENTS:
error = xfs_iformat_extents(ip, dip, XFS_ATTR_FORK);
break;
case XFS_DINODE_FMT_BTREE:
error = xfs_iformat_btree(ip, dip, XFS_ATTR_FORK);
break;
default:
error = XFS_ERROR(EFSCORRUPTED);
break;
}
if (error) {
kmem_zone_free(xfs_ifork_zone, ip->i_afp);
ip->i_afp = NULL;
xfs_idestroy_fork(ip, XFS_DATA_FORK);
}
return error;
}
/*
* The file is in-lined in the on-disk inode.
* If it fits into if_inline_data, then copy
* it there, otherwise allocate a buffer for it
* and copy the data there. Either way, set
* if_data to point at the data.
* If we allocate a buffer for the data, make
* sure that its size is a multiple of 4 and
* record the real size in i_real_bytes.
*/
STATIC int
xfs_iformat_local(
xfs_inode_t *ip,
xfs_dinode_t *dip,
int whichfork,
int size)
{
xfs_ifork_t *ifp;
int real_size;
/*
* If the size is unreasonable, then something
* is wrong and we just bail out rather than crash in
* kmem_alloc() or memcpy() below.
*/
if (unlikely(size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
xfs_warn(ip->i_mount,
"corrupt inode %Lu (bad size %d for local fork, size = %d).",
(unsigned long long) ip->i_ino, size,
XFS_DFORK_SIZE(dip, ip->i_mount, whichfork));
XFS_CORRUPTION_ERROR("xfs_iformat_local", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
ifp = XFS_IFORK_PTR(ip, whichfork);
real_size = 0;
if (size == 0)
ifp->if_u1.if_data = NULL;
else if (size <= sizeof(ifp->if_u2.if_inline_data))
ifp->if_u1.if_data = ifp->if_u2.if_inline_data;
else {
real_size = roundup(size, 4);
ifp->if_u1.if_data = kmem_alloc(real_size, KM_SLEEP | KM_NOFS);
}
ifp->if_bytes = size;
ifp->if_real_bytes = real_size;
if (size)
memcpy(ifp->if_u1.if_data, XFS_DFORK_PTR(dip, whichfork), size);
ifp->if_flags &= ~XFS_IFEXTENTS;
ifp->if_flags |= XFS_IFINLINE;
return 0;
}
/*
* The file consists of a set of extents all
* of which fit into the on-disk inode.
* If there are few enough extents to fit into
* the if_inline_ext, then copy them there.
* Otherwise allocate a buffer for them and copy
* them into it. Either way, set if_extents
* to point at the extents.
*/
STATIC int
xfs_iformat_extents(
xfs_inode_t *ip,
xfs_dinode_t *dip,
int whichfork)
{
xfs_bmbt_rec_t *dp;
xfs_ifork_t *ifp;
int nex;
int size;
int i;
ifp = XFS_IFORK_PTR(ip, whichfork);
nex = XFS_DFORK_NEXTENTS(dip, whichfork);
size = nex * (uint)sizeof(xfs_bmbt_rec_t);
/*
* If the number of extents is unreasonable, then something
* is wrong and we just bail out rather than crash in
* kmem_alloc() or memcpy() below.
*/
if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
xfs_warn(ip->i_mount, "corrupt inode %Lu ((a)extents = %d).",
(unsigned long long) ip->i_ino, nex);
XFS_CORRUPTION_ERROR("xfs_iformat_extents(1)", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
ifp->if_real_bytes = 0;
if (nex == 0)
ifp->if_u1.if_extents = NULL;
else if (nex <= XFS_INLINE_EXTS)
ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext;
else
xfs_iext_add(ifp, 0, nex);
ifp->if_bytes = size;
if (size) {
dp = (xfs_bmbt_rec_t *) XFS_DFORK_PTR(dip, whichfork);
xfs_validate_extents(ifp, nex, XFS_EXTFMT_INODE(ip));
for (i = 0; i < nex; i++, dp++) {
xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
ep->l0 = get_unaligned_be64(&dp->l0);
ep->l1 = get_unaligned_be64(&dp->l1);
}
XFS_BMAP_TRACE_EXLIST(ip, nex, whichfork);
if (whichfork != XFS_DATA_FORK ||
XFS_EXTFMT_INODE(ip) == XFS_EXTFMT_NOSTATE)
if (unlikely(xfs_check_nostate_extents(
ifp, 0, nex))) {
XFS_ERROR_REPORT("xfs_iformat_extents(2)",
XFS_ERRLEVEL_LOW,
ip->i_mount);
return XFS_ERROR(EFSCORRUPTED);
}
}
ifp->if_flags |= XFS_IFEXTENTS;
return 0;
}
/*
* The file has too many extents to fit into
* the inode, so they are in B-tree format.
* Allocate a buffer for the root of the B-tree
* and copy the root into it. The i_extents
* field will remain NULL until all of the
* extents are read in (when they are needed).
*/
STATIC int
xfs_iformat_btree(
xfs_inode_t *ip,
xfs_dinode_t *dip,
int whichfork)
{
xfs_bmdr_block_t *dfp;
xfs_ifork_t *ifp;
/* REFERENCED */
int nrecs;
int size;
ifp = XFS_IFORK_PTR(ip, whichfork);
dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork);
size = XFS_BMAP_BROOT_SPACE(dfp);
nrecs = be16_to_cpu(dfp->bb_numrecs);
/*
* blow out if -- fork has less extents than can fit in
* fork (fork shouldn't be a btree format), root btree
* block has more records than can fit into the fork,
* or the number of extents is greater than the number of
* blocks.
*/
if (unlikely(XFS_IFORK_NEXTENTS(ip, whichfork) <=
XFS_IFORK_MAXEXT(ip, whichfork) ||
XFS_BMDR_SPACE_CALC(nrecs) >
XFS_DFORK_SIZE(dip, ip->i_mount, whichfork) ||
XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) {
xfs_warn(ip->i_mount, "corrupt inode %Lu (btree).",
(unsigned long long) ip->i_ino);
XFS_CORRUPTION_ERROR("xfs_iformat_btree", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return XFS_ERROR(EFSCORRUPTED);
}
ifp->if_broot_bytes = size;
ifp->if_broot = kmem_alloc(size, KM_SLEEP | KM_NOFS);
ASSERT(ifp->if_broot != NULL);
/*
* Copy and convert from the on-disk structure
* to the in-memory structure.
*/
xfs_bmdr_to_bmbt(ip->i_mount, dfp,
XFS_DFORK_SIZE(dip, ip->i_mount, whichfork),
ifp->if_broot, size);
ifp->if_flags &= ~XFS_IFEXTENTS;
ifp->if_flags |= XFS_IFBROOT;
return 0;
}
STATIC void
xfs_dinode_from_disk(
xfs_icdinode_t *to,
xfs_dinode_t *from)
{
to->di_magic = be16_to_cpu(from->di_magic);
to->di_mode = be16_to_cpu(from->di_mode);
to->di_version = from ->di_version;
to->di_format = from->di_format;
to->di_onlink = be16_to_cpu(from->di_onlink);
to->di_uid = be32_to_cpu(from->di_uid);
to->di_gid = be32_to_cpu(from->di_gid);
to->di_nlink = be32_to_cpu(from->di_nlink);
to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
to->di_flushiter = be16_to_cpu(from->di_flushiter);
to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec);
to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec);
to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec);
to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec);
to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec);
to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec);
to->di_size = be64_to_cpu(from->di_size);
to->di_nblocks = be64_to_cpu(from->di_nblocks);
to->di_extsize = be32_to_cpu(from->di_extsize);
to->di_nextents = be32_to_cpu(from->di_nextents);
to->di_anextents = be16_to_cpu(from->di_anextents);
to->di_forkoff = from->di_forkoff;
to->di_aformat = from->di_aformat;
to->di_dmevmask = be32_to_cpu(from->di_dmevmask);
to->di_dmstate = be16_to_cpu(from->di_dmstate);
to->di_flags = be16_to_cpu(from->di_flags);
to->di_gen = be32_to_cpu(from->di_gen);
}
void
xfs_dinode_to_disk(
xfs_dinode_t *to,
xfs_icdinode_t *from)
{
to->di_magic = cpu_to_be16(from->di_magic);
to->di_mode = cpu_to_be16(from->di_mode);
to->di_version = from ->di_version;
to->di_format = from->di_format;
to->di_onlink = cpu_to_be16(from->di_onlink);
to->di_uid = cpu_to_be32(from->di_uid);
to->di_gid = cpu_to_be32(from->di_gid);
to->di_nlink = cpu_to_be32(from->di_nlink);
to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
to->di_flushiter = cpu_to_be16(from->di_flushiter);
to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);
to->di_size = cpu_to_be64(from->di_size);
to->di_nblocks = cpu_to_be64(from->di_nblocks);
to->di_extsize = cpu_to_be32(from->di_extsize);
to->di_nextents = cpu_to_be32(from->di_nextents);
to->di_anextents = cpu_to_be16(from->di_anextents);
to->di_forkoff = from->di_forkoff;
to->di_aformat = from->di_aformat;
to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
to->di_dmstate = cpu_to_be16(from->di_dmstate);
to->di_flags = cpu_to_be16(from->di_flags);
to->di_gen = cpu_to_be32(from->di_gen);
}
STATIC uint
_xfs_dic2xflags(
__uint16_t di_flags)
{
uint flags = 0;
if (di_flags & XFS_DIFLAG_ANY) {
if (di_flags & XFS_DIFLAG_REALTIME)
flags |= XFS_XFLAG_REALTIME;
if (di_flags & XFS_DIFLAG_PREALLOC)
flags |= XFS_XFLAG_PREALLOC;
if (di_flags & XFS_DIFLAG_IMMUTABLE)
flags |= XFS_XFLAG_IMMUTABLE;
if (di_flags & XFS_DIFLAG_APPEND)
flags |= XFS_XFLAG_APPEND;
if (di_flags & XFS_DIFLAG_SYNC)
flags |= XFS_XFLAG_SYNC;
if (di_flags & XFS_DIFLAG_NOATIME)
flags |= XFS_XFLAG_NOATIME;
if (di_flags & XFS_DIFLAG_NODUMP)
flags |= XFS_XFLAG_NODUMP;
if (di_flags & XFS_DIFLAG_RTINHERIT)
flags |= XFS_XFLAG_RTINHERIT;
if (di_flags & XFS_DIFLAG_PROJINHERIT)
flags |= XFS_XFLAG_PROJINHERIT;
if (di_flags & XFS_DIFLAG_NOSYMLINKS)
flags |= XFS_XFLAG_NOSYMLINKS;
if (di_flags & XFS_DIFLAG_EXTSIZE)
flags |= XFS_XFLAG_EXTSIZE;
if (di_flags & XFS_DIFLAG_EXTSZINHERIT)
flags |= XFS_XFLAG_EXTSZINHERIT;
if (di_flags & XFS_DIFLAG_NODEFRAG)
flags |= XFS_XFLAG_NODEFRAG;
if (di_flags & XFS_DIFLAG_FILESTREAM)
flags |= XFS_XFLAG_FILESTREAM;
}
return flags;
}
uint
xfs_ip2xflags(
xfs_inode_t *ip)
{
xfs_icdinode_t *dic = &ip->i_d;
return _xfs_dic2xflags(dic->di_flags) |
(XFS_IFORK_Q(ip) ? XFS_XFLAG_HASATTR : 0);
}
uint
xfs_dic2xflags(
xfs_dinode_t *dip)
{
return _xfs_dic2xflags(be16_to_cpu(dip->di_flags)) |
(XFS_DFORK_Q(dip) ? XFS_XFLAG_HASATTR : 0);
}
/*
* Read the disk inode attributes into the in-core inode structure.
*/
int
xfs_iread(
xfs_mount_t *mp,
xfs_trans_t *tp,
xfs_inode_t *ip,
uint iget_flags)
{
xfs_buf_t *bp;
xfs_dinode_t *dip;
int error;
/*
* Fill in the location information in the in-core inode.
*/
error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags);
if (error)
return error;
/*
* Get pointers to the on-disk inode and the buffer containing it.
*/
error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0, iget_flags);
if (error)
return error;
/*
* If we got something that isn't an inode it means someone
* (nfs or dmi) has a stale handle.
*/
if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC)) {
#ifdef DEBUG
xfs_alert(mp,
"%s: dip->di_magic (0x%x) != XFS_DINODE_MAGIC (0x%x)",