forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
xfs_inode.c
3609 lines (3197 loc) · 97.6 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_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_inode.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_dir2.h"
#include "xfs_attr_sf.h"
#include "xfs_attr.h"
#include "xfs_trans_space.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_inode_item.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_filestream.h"
#include "xfs_cksum.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_symlink.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_bmap_btree.h"
#include "xfs_reflink.h"
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(struct xfs_inode *, struct xfs_buf *);
STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *);
/*
* 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;
}
/*
* Helper function to extract CoW extent size hint from inode.
* Between the extent size hint and the CoW extent size hint, we
* return the greater of the two. If the value is zero (automatic),
* use the default size.
*/
xfs_extlen_t
xfs_get_cowextsz_hint(
struct xfs_inode *ip)
{
xfs_extlen_t a, b;
a = 0;
if (ip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
a = ip->i_d.di_cowextsize;
b = xfs_get_extsz_hint(ip);
a = max(a, b);
if (a == 0)
return XFS_DEFAULT_COWEXTSZ_HINT;
return a;
}
/*
* These two are wrapper routines around the xfs_ilock() routine used to
* centralize some grungy code. They are used in places that wish to lock the
* inode solely for reading the extents. The reason these places can't just
* call xfs_ilock(ip, 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 functions return a value which should be given to the corresponding
* xfs_iunlock() call.
*/
uint
xfs_ilock_data_map_shared(
struct xfs_inode *ip)
{
uint lock_mode = XFS_ILOCK_SHARED;
if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
(ip->i_df.if_flags & XFS_IFEXTENTS) == 0)
lock_mode = XFS_ILOCK_EXCL;
xfs_ilock(ip, lock_mode);
return lock_mode;
}
uint
xfs_ilock_attr_map_shared(
struct xfs_inode *ip)
{
uint lock_mode = XFS_ILOCK_SHARED;
if (ip->i_d.di_aformat == XFS_DINODE_FMT_BTREE &&
(ip->i_afp->if_flags & XFS_IFEXTENTS) == 0)
lock_mode = XFS_ILOCK_EXCL;
xfs_ilock(ip, lock_mode);
return lock_mode;
}
/*
* In addition to i_rwsem in the VFS inode, the xfs inode contains 2
* multi-reader locks: i_mmap_lock and the i_lock. This routine allows
* various combinations of the locks to be obtained.
*
* The 3 locks should always be ordered so that the IO lock is obtained first,
* the mmap lock second and the ilock last in order to prevent deadlock.
*
* Basic locking order:
*
* i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
*
* mmap_sem locking order:
*
* i_rwsem -> page lock -> mmap_sem
* mmap_sem -> i_mmap_lock -> page_lock
*
* The difference in mmap_sem locking order mean that we cannot hold the
* i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
* fault in pages during copy in/out (for buffered IO) or require the mmap_sem
* in get_user_pages() to map the user pages into the kernel address space for
* direct IO. Similarly the i_rwsem cannot be taken inside a page fault because
* page faults already hold the mmap_sem.
*
* Hence to serialise fully against both syscall and mmap based IO, we need to
* take both the i_rwsem and the i_mmap_lock. These locks should *only* be both
* taken in places where we need to invalidate the page cache in a race
* free manner (e.g. truncate, hole punch and other extent manipulation
* functions).
*/
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_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) !=
(XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
if (lock_flags & XFS_IOLOCK_EXCL) {
down_write_nested(&VFS_I(ip)->i_rwsem,
XFS_IOLOCK_DEP(lock_flags));
} else if (lock_flags & XFS_IOLOCK_SHARED) {
down_read_nested(&VFS_I(ip)->i_rwsem,
XFS_IOLOCK_DEP(lock_flags));
}
if (lock_flags & XFS_MMAPLOCK_EXCL)
mrupdate_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags));
else if (lock_flags & XFS_MMAPLOCK_SHARED)
mraccess_nested(&ip->i_mmaplock, XFS_MMAPLOCK_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_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) !=
(XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
if (lock_flags & XFS_IOLOCK_EXCL) {
if (!down_write_trylock(&VFS_I(ip)->i_rwsem))
goto out;
} else if (lock_flags & XFS_IOLOCK_SHARED) {
if (!down_read_trylock(&VFS_I(ip)->i_rwsem))
goto out;
}
if (lock_flags & XFS_MMAPLOCK_EXCL) {
if (!mrtryupdate(&ip->i_mmaplock))
goto out_undo_iolock;
} else if (lock_flags & XFS_MMAPLOCK_SHARED) {
if (!mrtryaccess(&ip->i_mmaplock))
goto out_undo_iolock;
}
if (lock_flags & XFS_ILOCK_EXCL) {
if (!mrtryupdate(&ip->i_lock))
goto out_undo_mmaplock;
} else if (lock_flags & XFS_ILOCK_SHARED) {
if (!mrtryaccess(&ip->i_lock))
goto out_undo_mmaplock;
}
return 1;
out_undo_mmaplock:
if (lock_flags & XFS_MMAPLOCK_EXCL)
mrunlock_excl(&ip->i_mmaplock);
else if (lock_flags & XFS_MMAPLOCK_SHARED)
mrunlock_shared(&ip->i_mmaplock);
out_undo_iolock:
if (lock_flags & XFS_IOLOCK_EXCL)
up_write(&VFS_I(ip)->i_rwsem);
else if (lock_flags & XFS_IOLOCK_SHARED)
up_read(&VFS_I(ip)->i_rwsem);
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_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) !=
(XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
ASSERT(lock_flags != 0);
if (lock_flags & XFS_IOLOCK_EXCL)
up_write(&VFS_I(ip)->i_rwsem);
else if (lock_flags & XFS_IOLOCK_SHARED)
up_read(&VFS_I(ip)->i_rwsem);
if (lock_flags & XFS_MMAPLOCK_EXCL)
mrunlock_excl(&ip->i_mmaplock);
else if (lock_flags & XFS_MMAPLOCK_SHARED)
mrunlock_shared(&ip->i_mmaplock);
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_MMAPLOCK_EXCL|XFS_ILOCK_EXCL));
ASSERT((lock_flags &
~(XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)) == 0);
if (lock_flags & XFS_ILOCK_EXCL)
mrdemote(&ip->i_lock);
if (lock_flags & XFS_MMAPLOCK_EXCL)
mrdemote(&ip->i_mmaplock);
if (lock_flags & XFS_IOLOCK_EXCL)
downgrade_write(&VFS_I(ip)->i_rwsem);
trace_xfs_ilock_demote(ip, lock_flags, _RET_IP_);
}
#if defined(DEBUG) || defined(XFS_WARN)
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_MMAPLOCK_EXCL|XFS_MMAPLOCK_SHARED)) {
if (!(lock_flags & XFS_MMAPLOCK_SHARED))
return !!ip->i_mmaplock.mr_writer;
return rwsem_is_locked(&ip->i_mmaplock.mr_lock);
}
if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) {
if (!(lock_flags & XFS_IOLOCK_SHARED))
return !debug_locks ||
lockdep_is_held_type(&VFS_I(ip)->i_rwsem, 0);
return rwsem_is_locked(&VFS_I(ip)->i_rwsem);
}
ASSERT(0);
return 0;
}
#endif
#ifdef DEBUG
int xfs_locked_n;
int xfs_small_retries;
int xfs_middle_retries;
int xfs_lots_retries;
int xfs_lock_delays;
#endif
/*
* xfs_lockdep_subclass_ok() is only used in an ASSERT, so is only called when
* DEBUG or XFS_WARN is set. And MAX_LOCKDEP_SUBCLASSES is then only defined
* when CONFIG_LOCKDEP is set. Hence the complex define below to avoid build
* errors and warnings.
*/
#if (defined(DEBUG) || defined(XFS_WARN)) && defined(CONFIG_LOCKDEP)
static bool
xfs_lockdep_subclass_ok(
int subclass)
{
return subclass < MAX_LOCKDEP_SUBCLASSES;
}
#else
#define xfs_lockdep_subclass_ok(subclass) (true)
#endif
/*
* Bump the subclass so xfs_lock_inodes() acquires each lock with a different
* value. This can be called for any type of inode lock combination, including
* parent locking. Care must be taken to ensure we don't overrun the subclass
* storage fields in the class mask we build.
*/
static inline int
xfs_lock_inumorder(int lock_mode, int subclass)
{
int class = 0;
ASSERT(!(lock_mode & (XFS_ILOCK_PARENT | XFS_ILOCK_RTBITMAP |
XFS_ILOCK_RTSUM)));
ASSERT(xfs_lockdep_subclass_ok(subclass));
if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) {
ASSERT(subclass <= XFS_IOLOCK_MAX_SUBCLASS);
class += subclass << XFS_IOLOCK_SHIFT;
}
if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) {
ASSERT(subclass <= XFS_MMAPLOCK_MAX_SUBCLASS);
class += subclass << XFS_MMAPLOCK_SHIFT;
}
if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) {
ASSERT(subclass <= XFS_ILOCK_MAX_SUBCLASS);
class += subclass << XFS_ILOCK_SHIFT;
}
return (lock_mode & ~XFS_LOCK_SUBCLASS_MASK) | class;
}
/*
* The following routine will lock n inodes in exclusive mode. We assume the
* caller calls us with the inodes in i_ino order.
*
* We need to detect deadlock where an inode that we lock is in the AIL and we
* start waiting for another inode that is locked by a thread in a long running
* transaction (such as truncate). This can result in deadlock since the long
* running trans might need to wait for the inode we just locked in order to
* push the tail and free space in the log.
*
* xfs_lock_inodes() can only be used to lock one type of lock at a time -
* the iolock, the mmaplock or the ilock, but not more than one at a time. If we
* lock more than one at a time, lockdep will report false positives saying we
* have violated locking orders.
*/
static void
xfs_lock_inodes(
xfs_inode_t **ips,
int inodes,
uint lock_mode)
{
int attempts = 0, i, j, try_lock;
xfs_log_item_t *lp;
/*
* Currently supports between 2 and 5 inodes with exclusive locking. We
* support an arbitrary depth of locking here, but absolute limits on
* inodes depend on the the type of locking and the limits placed by
* lockdep annotations in xfs_lock_inumorder. These are all checked by
* the asserts.
*/
ASSERT(ips && inodes >= 2 && inodes <= 5);
ASSERT(lock_mode & (XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL |
XFS_ILOCK_EXCL));
ASSERT(!(lock_mode & (XFS_IOLOCK_SHARED | XFS_MMAPLOCK_SHARED |
XFS_ILOCK_SHARED)));
ASSERT(!(lock_mode & XFS_MMAPLOCK_EXCL) ||
inodes <= XFS_MMAPLOCK_MAX_SUBCLASS + 1);
ASSERT(!(lock_mode & XFS_ILOCK_EXCL) ||
inodes <= XFS_ILOCK_MAX_SUBCLASS + 1);
if (lock_mode & XFS_IOLOCK_EXCL) {
ASSERT(!(lock_mode & (XFS_MMAPLOCK_EXCL | XFS_ILOCK_EXCL)));
} else if (lock_mode & XFS_MMAPLOCK_EXCL)
ASSERT(!(lock_mode & XFS_ILOCK_EXCL));
try_lock = 0;
i = 0;
again:
for (; i < inodes; i++) {
ASSERT(ips[i]);
if (i && (ips[i] == ips[i - 1])) /* Already locked */
continue;
/*
* If try_lock is not set yet, make sure all locked inodes are
* not in the AIL. If any are, set try_lock to be used later.
*/
if (!try_lock) {
for (j = (i - 1); j >= 0 && !try_lock; j--) {
lp = (xfs_log_item_t *)ips[j]->i_itemp;
if (lp && (lp->li_flags & XFS_LI_IN_AIL))
try_lock++;
}
}
/*
* If any of the previous locks we have locked is in the AIL,
* we must TRY to get the second and subsequent locks. If
* we can't get any, we must release all we have
* and try again.
*/
if (!try_lock) {
xfs_ilock(ips[i], xfs_lock_inumorder(lock_mode, i));
continue;
}
/* try_lock means we have an inode locked that is in the AIL. */
ASSERT(i != 0);
if (xfs_ilock_nowait(ips[i], xfs_lock_inumorder(lock_mode, i)))
continue;
/*
* Unlock all previous guys and try again. xfs_iunlock will try
* to push the tail if the inode is in the AIL.
*/
attempts++;
for (j = i - 1; j >= 0; j--) {
/*
* Check to see if we've already unlocked this one. Not
* the first one going back, and the inode ptr is the
* same.
*/
if (j != (i - 1) && ips[j] == ips[j + 1])
continue;
xfs_iunlock(ips[j], lock_mode);
}
if ((attempts % 5) == 0) {
delay(1); /* Don't just spin the CPU */
#ifdef DEBUG
xfs_lock_delays++;
#endif
}
i = 0;
try_lock = 0;
goto again;
}
#ifdef DEBUG
if (attempts) {
if (attempts < 5) xfs_small_retries++;
else if (attempts < 100) xfs_middle_retries++;
else xfs_lots_retries++;
} else {
xfs_locked_n++;
}
#endif
}
/*
* xfs_lock_two_inodes() can only be used to lock one type of lock at a time -
* the iolock, the mmaplock or the ilock, but not more than one at a time. If we
* lock more than one at a time, lockdep will report false positives saying we
* have violated locking orders.
*/
void
xfs_lock_two_inodes(
xfs_inode_t *ip0,
xfs_inode_t *ip1,
uint lock_mode)
{
xfs_inode_t *temp;
int attempts = 0;
xfs_log_item_t *lp;
ASSERT(!(lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL))
ASSERT(!(lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
ASSERT(ip0->i_ino != ip1->i_ino);
if (ip0->i_ino > ip1->i_ino) {
temp = ip0;
ip0 = ip1;
ip1 = temp;
}
again:
xfs_ilock(ip0, xfs_lock_inumorder(lock_mode, 0));
/*
* If the first lock we have locked is in the AIL, we must TRY to get
* the second lock. If we can't get it, we must release the first one
* and try again.
*/
lp = (xfs_log_item_t *)ip0->i_itemp;
if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(lock_mode, 1))) {
xfs_iunlock(ip0, lock_mode);
if ((++attempts % 5) == 0)
delay(1); /* Don't just spin the CPU */
goto again;
}
} else {
xfs_ilock(ip1, xfs_lock_inumorder(lock_mode, 1));
}
}
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);
}
STATIC uint
_xfs_dic2xflags(
__uint16_t di_flags,
uint64_t di_flags2,
bool has_attr)
{
uint flags = 0;
if (di_flags & XFS_DIFLAG_ANY) {
if (di_flags & XFS_DIFLAG_REALTIME)
flags |= FS_XFLAG_REALTIME;
if (di_flags & XFS_DIFLAG_PREALLOC)
flags |= FS_XFLAG_PREALLOC;
if (di_flags & XFS_DIFLAG_IMMUTABLE)
flags |= FS_XFLAG_IMMUTABLE;
if (di_flags & XFS_DIFLAG_APPEND)
flags |= FS_XFLAG_APPEND;
if (di_flags & XFS_DIFLAG_SYNC)
flags |= FS_XFLAG_SYNC;
if (di_flags & XFS_DIFLAG_NOATIME)
flags |= FS_XFLAG_NOATIME;
if (di_flags & XFS_DIFLAG_NODUMP)
flags |= FS_XFLAG_NODUMP;
if (di_flags & XFS_DIFLAG_RTINHERIT)
flags |= FS_XFLAG_RTINHERIT;
if (di_flags & XFS_DIFLAG_PROJINHERIT)
flags |= FS_XFLAG_PROJINHERIT;
if (di_flags & XFS_DIFLAG_NOSYMLINKS)
flags |= FS_XFLAG_NOSYMLINKS;
if (di_flags & XFS_DIFLAG_EXTSIZE)
flags |= FS_XFLAG_EXTSIZE;
if (di_flags & XFS_DIFLAG_EXTSZINHERIT)
flags |= FS_XFLAG_EXTSZINHERIT;
if (di_flags & XFS_DIFLAG_NODEFRAG)
flags |= FS_XFLAG_NODEFRAG;
if (di_flags & XFS_DIFLAG_FILESTREAM)
flags |= FS_XFLAG_FILESTREAM;
}
if (di_flags2 & XFS_DIFLAG2_ANY) {
if (di_flags2 & XFS_DIFLAG2_DAX)
flags |= FS_XFLAG_DAX;
if (di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
flags |= FS_XFLAG_COWEXTSIZE;
}
if (has_attr)
flags |= FS_XFLAG_HASATTR;
return flags;
}
uint
xfs_ip2xflags(
struct xfs_inode *ip)
{
struct xfs_icdinode *dic = &ip->i_d;
return _xfs_dic2xflags(dic->di_flags, dic->di_flags2, XFS_IFORK_Q(ip));
}
/*
* Lookups up an inode from "name". If ci_name is not NULL, then a CI match
* is allowed, otherwise it has to be an exact match. If a CI match is found,
* ci_name->name will point to a the actual name (caller must free) or
* will be set to NULL if an exact match is found.
*/
int
xfs_lookup(
xfs_inode_t *dp,
struct xfs_name *name,
xfs_inode_t **ipp,
struct xfs_name *ci_name)
{
xfs_ino_t inum;
int error;
trace_xfs_lookup(dp, name);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
if (error)
goto out_unlock;
error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp);
if (error)
goto out_free_name;
return 0;
out_free_name:
if (ci_name)
kmem_free(ci_name->name);
out_unlock:
*ipp = NULL;
return error;
}
/*
* Allocate an inode on disk and return a copy of its in-core version.
* The in-core inode is locked exclusively. Set mode, nlink, and rdev
* appropriately within the inode. The uid and gid for the inode are
* set according to the contents of the given cred structure.
*
* Use xfs_dialloc() to allocate the on-disk inode. If xfs_dialloc()
* has a free inode available, call xfs_iget() to obtain the in-core
* version of the allocated inode. Finally, fill in the inode and
* log its initial contents. In this case, ialloc_context would be
* set to NULL.
*
* If xfs_dialloc() does not have an available inode, it will replenish
* its supply by doing an allocation. Since we can only do one
* allocation within a transaction without deadlocks, we must commit
* the current transaction before returning the inode itself.
* In this case, therefore, we will set ialloc_context and return.
* The caller should then commit the current transaction, start a new
* transaction, and call xfs_ialloc() again to actually get the inode.
*
* To ensure that some other process does not grab the inode that
* was allocated during the first call to xfs_ialloc(), this routine
* also returns the [locked] bp pointing to the head of the freelist
* as ialloc_context. The caller should hold this buffer across
* the commit and pass it back into this routine on the second call.
*
* If we are allocating quota inodes, we do not have a parent inode
* to attach to or associate with (i.e. pip == NULL) because they
* are not linked into the directory structure - they are attached
* directly to the superblock - and so have no parent.
*/
static int
xfs_ialloc(
xfs_trans_t *tp,
xfs_inode_t *pip,
umode_t mode,
xfs_nlink_t nlink,
xfs_dev_t rdev,
prid_t prid,
int okalloc,
xfs_buf_t **ialloc_context,
xfs_inode_t **ipp)
{
struct xfs_mount *mp = tp->t_mountp;
xfs_ino_t ino;
xfs_inode_t *ip;
uint flags;
int error;
struct timespec tv;
struct inode *inode;
/*
* Call the space management code to pick
* the on-disk inode to be allocated.
*/
error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc,
ialloc_context, &ino);
if (error)
return error;
if (*ialloc_context || ino == NULLFSINO) {
*ipp = NULL;
return 0;
}
ASSERT(*ialloc_context == NULL);
/*
* Get the in-core inode with the lock held exclusively.
* This is because we're setting fields here we need
* to prevent others from looking at until we're done.
*/
error = xfs_iget(mp, tp, ino, XFS_IGET_CREATE,
XFS_ILOCK_EXCL, &ip);
if (error)
return error;
ASSERT(ip != NULL);
inode = VFS_I(ip);
/*
* We always convert v1 inodes to v2 now - we only support filesystems
* with >= v2 inode capability, so there is no reason for ever leaving
* an inode in v1 format.
*/
if (ip->i_d.di_version == 1)
ip->i_d.di_version = 2;
inode->i_mode = mode;
set_nlink(inode, nlink);
ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid());
ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid());
xfs_set_projid(ip, prid);
if (pip && XFS_INHERIT_GID(pip)) {
ip->i_d.di_gid = pip->i_d.di_gid;
if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode))
inode->i_mode |= S_ISGID;
}
/*
* If the group ID of the new file does not match the effective group
* ID or one of the supplementary group IDs, the S_ISGID bit is cleared
* (and only if the irix_sgid_inherit compatibility variable is set).
*/
if ((irix_sgid_inherit) &&
(inode->i_mode & S_ISGID) &&
(!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid))))
inode->i_mode &= ~S_ISGID;
ip->i_d.di_size = 0;
ip->i_d.di_nextents = 0;
ASSERT(ip->i_d.di_nblocks == 0);
tv = current_time(inode);
inode->i_mtime = tv;
inode->i_atime = tv;
inode->i_ctime = tv;
ip->i_d.di_extsize = 0;
ip->i_d.di_dmevmask = 0;
ip->i_d.di_dmstate = 0;
ip->i_d.di_flags = 0;
if (ip->i_d.di_version == 3) {
inode->i_version = 1;
ip->i_d.di_flags2 = 0;
ip->i_d.di_cowextsize = 0;
ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec;
ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec;
}
flags = XFS_ILOG_CORE;
switch (mode & S_IFMT) {
case S_IFIFO:
case S_IFCHR:
case S_IFBLK:
case S_IFSOCK:
ip->i_d.di_format = XFS_DINODE_FMT_DEV;
ip->i_df.if_u2.if_rdev = rdev;
ip->i_df.if_flags = 0;
flags |= XFS_ILOG_DEV;
break;
case S_IFREG:
case S_IFDIR:
if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
uint64_t di_flags2 = 0;
uint di_flags = 0;
if (S_ISDIR(mode)) {
if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_RTINHERIT;
if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSZINHERIT;
ip->i_d.di_extsize = pip->i_d.di_extsize;
}
if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
di_flags |= XFS_DIFLAG_PROJINHERIT;
} else if (S_ISREG(mode)) {
if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_REALTIME;
if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSIZE;
ip->i_d.di_extsize = pip->i_d.di_extsize;
}
}
if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
xfs_inherit_noatime)
di_flags |= XFS_DIFLAG_NOATIME;
if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
xfs_inherit_nodump)
di_flags |= XFS_DIFLAG_NODUMP;
if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
xfs_inherit_sync)
di_flags |= XFS_DIFLAG_SYNC;
if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
xfs_inherit_nosymlinks)
di_flags |= XFS_DIFLAG_NOSYMLINKS;
if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
xfs_inherit_nodefrag)
di_flags |= XFS_DIFLAG_NODEFRAG;
if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
di_flags |= XFS_DIFLAG_FILESTREAM;
if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
di_flags2 |= XFS_DIFLAG2_DAX;
ip->i_d.di_flags |= di_flags;
ip->i_d.di_flags2 |= di_flags2;
}
if (pip &&
(pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) &&
pip->i_d.di_version == 3 &&
ip->i_d.di_version == 3) {
if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
}
}
/* FALLTHROUGH */
case S_IFLNK:
ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
ip->i_df.if_flags = XFS_IFEXTENTS;
ip->i_df.if_bytes = ip->i_df.if_real_bytes = 0;
ip->i_df.if_u1.if_extents = NULL;
break;
default:
ASSERT(0);
}
/*
* Attribute fork settings for new inode.
*/
ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
ip->i_d.di_anextents = 0;
/*
* Log the new values stuffed into the inode.
*/
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, flags);
/* now that we have an i_mode we can setup the inode structure */
xfs_setup_inode(ip);
*ipp = ip;
return 0;
}
/*
* Allocates a new inode from disk and return a pointer to the
* incore copy. This routine will internally commit the current
* transaction and allocate a new one if the Space Manager needed
* to do an allocation to replenish the inode free-list.
*
* This routine is designed to be called from xfs_create and
* xfs_create_dir.
*
*/
int
xfs_dir_ialloc(
xfs_trans_t **tpp, /* input: current transaction;
output: may be a new transaction. */
xfs_inode_t *dp, /* directory within whose allocate
the inode. */
umode_t mode,
xfs_nlink_t nlink,
xfs_dev_t rdev,
prid_t prid, /* project id */
int okalloc, /* ok to allocate new space */
xfs_inode_t **ipp, /* pointer to inode; it will be
locked. */
int *committed)
{
xfs_trans_t *tp;
xfs_inode_t *ip;
xfs_buf_t *ialloc_context = NULL;
int code;
void *dqinfo;
uint tflags;
tp = *tpp;
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
/*
* xfs_ialloc will return a pointer to an incore inode if
* the Space Manager has an available inode on the free
* list. Otherwise, it will do an allocation and replenish
* the freelist. Since we can only do one allocation per
* transaction without deadlocks, we will need to commit the
* current transaction and start a new one. We will then
* need to call xfs_ialloc again to get the inode.