-
Notifications
You must be signed in to change notification settings - Fork 55.4k
/
Copy pathxfs_vnodeops.c
2842 lines (2512 loc) · 69.9 KB
/
xfs_vnodeops.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 "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_mount.h"
#include "xfs_da_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_itable.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_acl.h"
#include "xfs_attr.h"
#include "xfs_rw.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_utils.h"
#include "xfs_rtalloc.h"
#include "xfs_trans_space.h"
#include "xfs_log_priv.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"
#include "xfs_trace.h"
int
xfs_setattr(
struct xfs_inode *ip,
struct iattr *iattr,
int flags)
{
xfs_mount_t *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
xfs_trans_t *tp;
int code;
uint lock_flags;
uint commit_flags=0;
uid_t uid=0, iuid=0;
gid_t gid=0, igid=0;
struct xfs_dquot *udqp, *gdqp, *olddquot1, *olddquot2;
int need_iolock = 1;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
code = -inode_change_ok(inode, iattr);
if (code)
return code;
olddquot1 = olddquot2 = NULL;
udqp = gdqp = NULL;
/*
* If disk quotas is on, we make sure that the dquots do exist on disk,
* before we start any other transactions. Trying to do this later
* is messy. We don't care to take a readlock to look at the ids
* in inode here, because we can't hold it across the trans_reserve.
* If the IDs do change before we take the ilock, we're covered
* because the i_*dquot fields will get updated anyway.
*/
if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) {
uint qflags = 0;
if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
uid = iattr->ia_uid;
qflags |= XFS_QMOPT_UQUOTA;
} else {
uid = ip->i_d.di_uid;
}
if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
gid = iattr->ia_gid;
qflags |= XFS_QMOPT_GQUOTA;
} else {
gid = ip->i_d.di_gid;
}
/*
* We take a reference when we initialize udqp and gdqp,
* so it is important that we never blindly double trip on
* the same variable. See xfs_create() for an example.
*/
ASSERT(udqp == NULL);
ASSERT(gdqp == NULL);
code = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip),
qflags, &udqp, &gdqp);
if (code)
return code;
}
/*
* For the other attributes, we acquire the inode lock and
* first do an error checking pass.
*/
tp = NULL;
lock_flags = XFS_ILOCK_EXCL;
if (flags & XFS_ATTR_NOLOCK)
need_iolock = 0;
if (!(mask & ATTR_SIZE)) {
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
commit_flags = 0;
code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp),
0, 0, 0);
if (code) {
lock_flags = 0;
goto error_return;
}
} else {
if (need_iolock)
lock_flags |= XFS_IOLOCK_EXCL;
}
xfs_ilock(ip, lock_flags);
/*
* Change file ownership. Must be the owner or privileged.
*/
if (mask & (ATTR_UID|ATTR_GID)) {
/*
* These IDs could have changed since we last looked at them.
* But, we're assured that if the ownership did change
* while we didn't have the inode locked, inode's dquot(s)
* would have changed also.
*/
iuid = ip->i_d.di_uid;
igid = ip->i_d.di_gid;
gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;
/*
* Do a quota reservation only if uid/gid is actually
* going to change.
*/
if (XFS_IS_QUOTA_RUNNING(mp) &&
((XFS_IS_UQUOTA_ON(mp) && iuid != uid) ||
(XFS_IS_GQUOTA_ON(mp) && igid != gid))) {
ASSERT(tp);
code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
capable(CAP_FOWNER) ?
XFS_QMOPT_FORCE_RES : 0);
if (code) /* out of quota */
goto error_return;
}
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
if (mask & ATTR_SIZE) {
/* Short circuit the truncate case for zero length files */
if (iattr->ia_size == 0 &&
ip->i_size == 0 && ip->i_d.di_nextents == 0) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
lock_flags &= ~XFS_ILOCK_EXCL;
if (mask & ATTR_CTIME) {
inode->i_mtime = inode->i_ctime =
current_fs_time(inode->i_sb);
xfs_mark_inode_dirty_sync(ip);
}
code = 0;
goto error_return;
}
if (S_ISDIR(ip->i_d.di_mode)) {
code = XFS_ERROR(EISDIR);
goto error_return;
} else if (!S_ISREG(ip->i_d.di_mode)) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
/*
* Make sure that the dquots are attached to the inode.
*/
code = xfs_qm_dqattach_locked(ip, 0);
if (code)
goto error_return;
/*
* Now we can make the changes. Before we join the inode
* to the transaction, if ATTR_SIZE is set then take care of
* the part of the truncation that must be done without the
* inode lock. This needs to be done before joining the inode
* to the transaction, because the inode cannot be unlocked
* once it is a part of the transaction.
*/
if (iattr->ia_size > ip->i_size) {
/*
* Do the first part of growing a file: zero any data
* in the last block that is beyond the old EOF. We
* need to do this before the inode is joined to the
* transaction to modify the i_size.
*/
code = xfs_zero_eof(ip, iattr->ia_size, ip->i_size);
if (code)
goto error_return;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
lock_flags &= ~XFS_ILOCK_EXCL;
/*
* We are going to log the inode size change in this
* transaction so any previous writes that are beyond the on
* disk EOF and the new EOF that have not been written out need
* to be written here. If we do not write the data out, we
* expose ourselves to the null files problem.
*
* Only flush from the on disk size to the smaller of the in
* memory file size or the new size as that's the range we
* really care about here and prevents waiting for other data
* not within the range we care about here.
*/
if (ip->i_size != ip->i_d.di_size &&
iattr->ia_size > ip->i_d.di_size) {
code = xfs_flush_pages(ip,
ip->i_d.di_size, iattr->ia_size,
XBF_ASYNC, FI_NONE);
if (code)
goto error_return;
}
/* wait for all I/O to complete */
xfs_ioend_wait(ip);
code = -block_truncate_page(inode->i_mapping, iattr->ia_size,
xfs_get_blocks);
if (code)
goto error_return;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
code = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
if (code)
goto error_return;
truncate_setsize(inode, iattr->ia_size);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip);
/*
* Only change the c/mtime if we are changing the size
* or we are explicitly asked to change it. This handles
* the semantic difference between truncate() and ftruncate()
* as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME
* is a special case where we need to update the times despite
* not having these flags set. For all other operations the
* VFS set these flags explicitly if it wants a timestamp
* update.
*/
if (iattr->ia_size != ip->i_size &&
(!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
mask |= ATTR_CTIME | ATTR_MTIME;
}
if (iattr->ia_size > ip->i_size) {
ip->i_d.di_size = iattr->ia_size;
ip->i_size = iattr->ia_size;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
} else if (iattr->ia_size <= ip->i_size ||
(iattr->ia_size == 0 && ip->i_d.di_nextents)) {
/*
* signal a sync transaction unless
* we're truncating an already unlinked
* file on a wsync filesystem
*/
code = xfs_itruncate_finish(&tp, ip, iattr->ia_size,
XFS_DATA_FORK,
((ip->i_d.di_nlink != 0 ||
!(mp->m_flags & XFS_MOUNT_WSYNC))
? 1 : 0));
if (code)
goto abort_return;
/*
* Truncated "down", so we're removing references
* to old data here - if we now delay flushing for
* a long time, we expose ourselves unduly to the
* notorious NULL files problem. So, we mark this
* vnode and flush it when the file is closed, and
* do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
}
} else if (tp) {
xfs_trans_ijoin(tp, ip);
}
/*
* Change file ownership. Must be the owner or privileged.
*/
if (mask & (ATTR_UID|ATTR_GID)) {
/*
* CAP_FSETID overrides the following restrictions:
*
* The set-user-ID and set-group-ID bits of a file will be
* cleared upon successful return from chown()
*/
if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
!capable(CAP_FSETID)) {
ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
}
/*
* Change the ownerships and register quota modifications
* in the transaction.
*/
if (iuid != uid) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) {
ASSERT(mask & ATTR_UID);
ASSERT(udqp);
olddquot1 = xfs_qm_vop_chown(tp, ip,
&ip->i_udquot, udqp);
}
ip->i_d.di_uid = uid;
inode->i_uid = uid;
}
if (igid != gid) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
ASSERT(!XFS_IS_PQUOTA_ON(mp));
ASSERT(mask & ATTR_GID);
ASSERT(gdqp);
olddquot2 = xfs_qm_vop_chown(tp, ip,
&ip->i_gdquot, gdqp);
}
ip->i_d.di_gid = gid;
inode->i_gid = gid;
}
}
/*
* Change file access modes.
*/
if (mask & ATTR_MODE) {
umode_t mode = iattr->ia_mode;
if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
mode &= ~S_ISGID;
ip->i_d.di_mode &= S_IFMT;
ip->i_d.di_mode |= mode & ~S_IFMT;
inode->i_mode &= S_IFMT;
inode->i_mode |= mode & ~S_IFMT;
}
/*
* Change file access or modified times.
*/
if (mask & ATTR_ATIME) {
inode->i_atime = iattr->ia_atime;
ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
ip->i_update_core = 1;
}
if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
ip->i_update_core = 1;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
ip->i_update_core = 1;
}
/*
* And finally, log the inode core if any attribute in it
* has been changed.
*/
if (mask & (ATTR_UID|ATTR_GID|ATTR_MODE|
ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
* This is slightly sub-optimal in that truncates require
* two sync transactions instead of one for wsync filesystems.
* One for the truncate and one for the timestamps since we
* don't want to change the timestamps unless we're sure the
* truncate worked. Truncates are less than 1% of the laddis
* mix so this probably isn't worth the trouble to optimize.
*/
code = 0;
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
code = xfs_trans_commit(tp, commit_flags);
xfs_iunlock(ip, lock_flags);
/*
* Release any dquot(s) the inode had kept before chown.
*/
xfs_qm_dqrele(olddquot1);
xfs_qm_dqrele(olddquot2);
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
if (code)
return code;
/*
* XXX(hch): Updating the ACL entries is not atomic vs the i_mode
* update. We could avoid this with linked transactions
* and passing down the transaction pointer all the way
* to attr_set. No previous user of the generic
* Posix ACL code seems to care about this issue either.
*/
if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) {
code = -xfs_acl_chmod(inode);
if (code)
return XFS_ERROR(code);
}
return 0;
abort_return:
commit_flags |= XFS_TRANS_ABORT;
error_return:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
if (tp) {
xfs_trans_cancel(tp, commit_flags);
}
if (lock_flags != 0) {
xfs_iunlock(ip, lock_flags);
}
return code;
}
/*
* The maximum pathlen is 1024 bytes. Since the minimum file system
* blocksize is 512 bytes, we can get a max of 2 extents back from
* bmapi.
*/
#define SYMLINK_MAPS 2
STATIC int
xfs_readlink_bmap(
xfs_inode_t *ip,
char *link)
{
xfs_mount_t *mp = ip->i_mount;
int pathlen = ip->i_d.di_size;
int nmaps = SYMLINK_MAPS;
xfs_bmbt_irec_t mval[SYMLINK_MAPS];
xfs_daddr_t d;
int byte_cnt;
int n;
xfs_buf_t *bp;
int error = 0;
error = xfs_bmapi(NULL, ip, 0, XFS_B_TO_FSB(mp, pathlen), 0, NULL, 0,
mval, &nmaps, NULL);
if (error)
goto out;
for (n = 0; n < nmaps; n++) {
d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt),
XBF_LOCK | XBF_MAPPED | XBF_DONT_BLOCK);
error = XFS_BUF_GETERROR(bp);
if (error) {
xfs_ioerror_alert("xfs_readlink",
ip->i_mount, bp, XFS_BUF_ADDR(bp));
xfs_buf_relse(bp);
goto out;
}
if (pathlen < byte_cnt)
byte_cnt = pathlen;
pathlen -= byte_cnt;
memcpy(link, XFS_BUF_PTR(bp), byte_cnt);
xfs_buf_relse(bp);
}
link[ip->i_d.di_size] = '\0';
error = 0;
out:
return error;
}
int
xfs_readlink(
xfs_inode_t *ip,
char *link)
{
xfs_mount_t *mp = ip->i_mount;
int pathlen;
int error = 0;
trace_xfs_readlink(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
xfs_ilock(ip, XFS_ILOCK_SHARED);
ASSERT((ip->i_d.di_mode & S_IFMT) == S_IFLNK);
ASSERT(ip->i_d.di_size <= MAXPATHLEN);
pathlen = ip->i_d.di_size;
if (!pathlen)
goto out;
if (ip->i_df.if_flags & XFS_IFINLINE) {
memcpy(link, ip->i_df.if_u1.if_data, pathlen);
link[pathlen] = '\0';
} else {
error = xfs_readlink_bmap(ip, link);
}
out:
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return error;
}
/*
* Flags for xfs_free_eofblocks
*/
#define XFS_FREE_EOF_TRYLOCK (1<<0)
/*
* This is called by xfs_inactive to free any blocks beyond eof
* when the link count isn't zero and by xfs_dm_punch_hole() when
* punching a hole to EOF.
*/
STATIC int
xfs_free_eofblocks(
xfs_mount_t *mp,
xfs_inode_t *ip,
int flags)
{
xfs_trans_t *tp;
int error;
xfs_fileoff_t end_fsb;
xfs_fileoff_t last_fsb;
xfs_filblks_t map_len;
int nimaps;
xfs_bmbt_irec_t imap;
/*
* Figure out if there are any blocks beyond the end
* of the file. If not, then there is nothing to do.
*/
end_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)ip->i_size));
last_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
if (last_fsb <= end_fsb)
return 0;
map_len = last_fsb - end_fsb;
nimaps = 1;
xfs_ilock(ip, XFS_ILOCK_SHARED);
error = xfs_bmapi(NULL, ip, end_fsb, map_len, 0,
NULL, 0, &imap, &nimaps, NULL);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!error && (nimaps != 0) &&
(imap.br_startblock != HOLESTARTBLOCK ||
ip->i_delayed_blks)) {
/*
* Attach the dquots to the inode up front.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* There are blocks after the end of file.
* Free them up now by truncating the file to
* its current size.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
/*
* Do the xfs_itruncate_start() call before
* reserving any log space because
* itruncate_start will call into the buffer
* cache and we can't
* do that within a transaction.
*/
if (flags & XFS_FREE_EOF_TRYLOCK) {
if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
xfs_trans_cancel(tp, 0);
return 0;
}
} else {
xfs_ilock(ip, XFS_IOLOCK_EXCL);
}
error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE,
ip->i_size);
if (error) {
xfs_trans_cancel(tp, 0);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}
error = xfs_trans_reserve(tp, 0,
XFS_ITRUNCATE_LOG_RES(mp),
0, XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip);
error = xfs_itruncate_finish(&tp, ip,
ip->i_size,
XFS_DATA_FORK,
0);
/*
* If we get an error at this point we
* simply don't bother truncating the file.
*/
if (error) {
xfs_trans_cancel(tp,
(XFS_TRANS_RELEASE_LOG_RES |
XFS_TRANS_ABORT));
} else {
error = xfs_trans_commit(tp,
XFS_TRANS_RELEASE_LOG_RES);
}
xfs_iunlock(ip, XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL);
}
return error;
}
/*
* Free a symlink that has blocks associated with it.
*/
STATIC int
xfs_inactive_symlink_rmt(
xfs_inode_t *ip,
xfs_trans_t **tpp)
{
xfs_buf_t *bp;
int committed;
int done;
int error;
xfs_fsblock_t first_block;
xfs_bmap_free_t free_list;
int i;
xfs_mount_t *mp;
xfs_bmbt_irec_t mval[SYMLINK_MAPS];
int nmaps;
xfs_trans_t *ntp;
int size;
xfs_trans_t *tp;
tp = *tpp;
mp = ip->i_mount;
ASSERT(ip->i_d.di_size > XFS_IFORK_DSIZE(ip));
/*
* We're freeing a symlink that has some
* blocks allocated to it. Free the
* blocks here. We know that we've got
* either 1 or 2 extents and that we can
* free them all in one bunmapi call.
*/
ASSERT(ip->i_d.di_nextents > 0 && ip->i_d.di_nextents <= 2);
if ((error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES, XFS_ITRUNCATE_LOG_COUNT))) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
*tpp = NULL;
return error;
}
/*
* Lock the inode, fix the size, and join it to the transaction.
* Hold it so in the normal path, we still have it locked for
* the second transaction. In the error paths we need it
* held so the cancel won't rele it, see below.
*/
xfs_ilock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
size = (int)ip->i_d.di_size;
ip->i_d.di_size = 0;
xfs_trans_ijoin(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
* Find the block(s) so we can inval and unmap them.
*/
done = 0;
xfs_bmap_init(&free_list, &first_block);
nmaps = ARRAY_SIZE(mval);
if ((error = xfs_bmapi(tp, ip, 0, XFS_B_TO_FSB(mp, size),
XFS_BMAPI_METADATA, &first_block, 0, mval, &nmaps,
&free_list)))
goto error0;
/*
* Invalidate the block(s).
*/
for (i = 0; i < nmaps; i++) {
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, mval[i].br_startblock),
XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0);
xfs_trans_binval(tp, bp);
}
/*
* Unmap the dead block(s) to the free_list.
*/
if ((error = xfs_bunmapi(tp, ip, 0, size, XFS_BMAPI_METADATA, nmaps,
&first_block, &free_list, &done)))
goto error1;
ASSERT(done);
/*
* Commit the first transaction. This logs the EFI and the inode.
*/
if ((error = xfs_bmap_finish(&tp, &free_list, &committed)))
goto error1;
/*
* The transaction must have been committed, since there were
* actually extents freed by xfs_bunmapi. See xfs_bmap_finish.
* The new tp has the extent freeing and EFDs.
*/
ASSERT(committed);
/*
* The first xact was committed, so add the inode to the new one.
* Mark it dirty so it will be logged and moved forward in the log as
* part of every commit.
*/
xfs_trans_ijoin(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
* Get a new, empty transaction to return to our caller.
*/
ntp = xfs_trans_dup(tp);
/*
* Commit the transaction containing extent freeing and EFDs.
* If we get an error on the commit here or on the reserve below,
* we need to unlock the inode since the new transaction doesn't
* have the inode attached.
*/
error = xfs_trans_commit(tp, 0);
tp = ntp;
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
goto error0;
}
/*
* transaction commit worked ok so we can drop the extra ticket
* reference that we gained in xfs_trans_dup()
*/
xfs_log_ticket_put(tp->t_ticket);
/*
* Remove the memory for extent descriptions (just bookkeeping).
*/
if (ip->i_df.if_bytes)
xfs_idata_realloc(ip, -ip->i_df.if_bytes, XFS_DATA_FORK);
ASSERT(ip->i_df.if_bytes == 0);
/*
* Put an itruncate log reservation in the new transaction
* for our caller.
*/
if ((error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES, XFS_ITRUNCATE_LOG_COUNT))) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
goto error0;
}
/*
* Return with the inode locked but not joined to the transaction.
*/
*tpp = tp;
return 0;
error1:
xfs_bmap_cancel(&free_list);
error0:
/*
* Have to come here with the inode locked and either
* (held and in the transaction) or (not in the transaction).
* If the inode isn't held then cancel would iput it, but
* that's wrong since this is inactive and the vnode ref
* count is 0 already.
* Cancel won't do anything to the inode if held, but it still
* needs to be locked until the cancel is done, if it was
* joined to the transaction.
*/
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
*tpp = NULL;
return error;
}
STATIC int
xfs_inactive_symlink_local(
xfs_inode_t *ip,
xfs_trans_t **tpp)
{
int error;
ASSERT(ip->i_d.di_size <= XFS_IFORK_DSIZE(ip));
/*
* We're freeing a symlink which fit into
* the inode. Just free the memory used
* to hold the old symlink.
*/
error = xfs_trans_reserve(*tpp, 0,
XFS_ITRUNCATE_LOG_RES(ip->i_mount),
0, XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
if (error) {
xfs_trans_cancel(*tpp, 0);
*tpp = NULL;
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
/*
* Zero length symlinks _can_ exist.
*/
if (ip->i_df.if_bytes > 0) {
xfs_idata_realloc(ip,
-(ip->i_df.if_bytes),
XFS_DATA_FORK);
ASSERT(ip->i_df.if_bytes == 0);
}
return 0;
}
STATIC int
xfs_inactive_attrs(
xfs_inode_t *ip,
xfs_trans_t **tpp)
{
xfs_trans_t *tp;
int error;
xfs_mount_t *mp;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
tp = *tpp;
mp = ip->i_mount;
ASSERT(ip->i_d.di_forkoff != 0);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
goto error_unlock;
error = xfs_attr_inactive(ip);
if (error)
goto error_unlock;
tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
error = xfs_trans_reserve(tp, 0,
XFS_IFREE_LOG_RES(mp),
0, XFS_TRANS_PERM_LOG_RES,
XFS_INACTIVE_LOG_COUNT);
if (error)
goto error_cancel;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip);
xfs_idestroy_fork(ip, XFS_ATTR_FORK);
ASSERT(ip->i_d.di_anextents == 0);
*tpp = tp;
return 0;
error_cancel:
ASSERT(XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
error_unlock:
*tpp = NULL;
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}
int
xfs_release(
xfs_inode_t *ip)
{
xfs_mount_t *mp = ip->i_mount;
int error;
if (!S_ISREG(ip->i_d.di_mode) || (ip->i_d.di_mode == 0))
return 0;
/* If this is a read-only mount, don't do this (would generate I/O) */
if (mp->m_flags & XFS_MOUNT_RDONLY)
return 0;
if (!XFS_FORCED_SHUTDOWN(mp)) {
int truncated;
/*
* If we are using filestreams, and we have an unlinked
* file that we are processing the last close on, then nothing
* will be able to reopen and write to this file. Purge this
* inode from the filestreams cache so that it doesn't delay
* teardown of the inode.
*/
if ((ip->i_d.di_nlink == 0) && xfs_inode_is_filestream(ip))
xfs_filestream_deassociate(ip);
/*
* If we previously truncated this file and removed old data
* in the process, we want to initiate "early" writeout on
* the last close. This is an attempt to combat the notorious
* NULL files problem which is particularly noticeable from a
* truncate down, buffered (re-)write (delalloc), followed by
* a crash. What we are effectively doing here is
* significantly reducing the time window where we'd otherwise
* be exposed to that problem.
*/
truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
if (truncated && VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0)
xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE);
}
if (ip->i_d.di_nlink == 0)
return 0;
if ((((ip->i_d.di_mode & S_IFMT) == S_IFREG) &&
((ip->i_size > 0) || (VN_CACHED(VFS_I(ip)) > 0 ||
ip->i_delayed_blks > 0)) &&
(ip->i_df.if_flags & XFS_IFEXTENTS)) &&
(!(ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))) {
/*
* If we can't get the iolock just skip truncating the blocks
* past EOF because we could deadlock with the mmap_sem
* otherwise. We'll get another chance to drop them once the
* last reference to the inode is dropped, so we'll never leak
* blocks permanently.
*
* Further, check if the inode is being opened, written and
* closed frequently and we have delayed allocation blocks
* outstanding (e.g. streaming writes from the NFS server),
* truncating the blocks past EOF will cause fragmentation to
* occur.
*
* In this case don't do the truncation, either, but we have to
* be careful how we detect this case. Blocks beyond EOF show
* up as i_delayed_blks even when the inode is clean, so we
* need to truncate them away first before checking for a dirty
* release. Hence on the first dirty close we will still remove
* the speculative allocation, but after that we will leave it
* in place.
*/
if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
return 0;
error = xfs_free_eofblocks(mp, ip,