forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathxfs_iops.c
1388 lines (1212 loc) · 34.7 KB
/
xfs_iops.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
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#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_mount.h"
#include "xfs_inode.h"
#include "xfs_acl.h"
#include "xfs_quota.h"
#include "xfs_attr.h"
#include "xfs_trans.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_symlink.h"
#include "xfs_dir2.h"
#include "xfs_iomap.h"
#include "xfs_error.h"
#include "xfs_ioctl.h"
#include <linux/posix_acl.h>
#include <linux/security.h>
#include <linux/iversion.h>
#include <linux/fiemap.h>
/*
* Directories have different lock order w.r.t. mmap_lock compared to regular
* files. This is due to readdir potentially triggering page faults on a user
* buffer inside filldir(), and this happens with the ilock on the directory
* held. For regular files, the lock order is the other way around - the
* mmap_lock is taken during the page fault, and then we lock the ilock to do
* block mapping. Hence we need a different class for the directory ilock so
* that lockdep can tell them apart.
*/
static struct lock_class_key xfs_nondir_ilock_class;
static struct lock_class_key xfs_dir_ilock_class;
static int
xfs_initxattrs(
struct inode *inode,
const struct xattr *xattr_array,
void *fs_info)
{
const struct xattr *xattr;
struct xfs_inode *ip = XFS_I(inode);
int error = 0;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
struct xfs_da_args args = {
.dp = ip,
.attr_filter = XFS_ATTR_SECURE,
.name = xattr->name,
.namelen = strlen(xattr->name),
.value = xattr->value,
.valuelen = xattr->value_len,
};
error = xfs_attr_set(&args);
if (error < 0)
break;
}
return error;
}
/*
* Hook in SELinux. This is not quite correct yet, what we really need
* here (as we do for default ACLs) is a mechanism by which creation of
* these attrs can be journalled at inode creation time (along with the
* inode, of course, such that log replay can't cause these to be lost).
*/
STATIC int
xfs_init_security(
struct inode *inode,
struct inode *dir,
const struct qstr *qstr)
{
return security_inode_init_security(inode, dir, qstr,
&xfs_initxattrs, NULL);
}
static void
xfs_dentry_to_name(
struct xfs_name *namep,
struct dentry *dentry)
{
namep->name = dentry->d_name.name;
namep->len = dentry->d_name.len;
namep->type = XFS_DIR3_FT_UNKNOWN;
}
static int
xfs_dentry_mode_to_name(
struct xfs_name *namep,
struct dentry *dentry,
int mode)
{
namep->name = dentry->d_name.name;
namep->len = dentry->d_name.len;
namep->type = xfs_mode_to_ftype(mode);
if (unlikely(namep->type == XFS_DIR3_FT_UNKNOWN))
return -EFSCORRUPTED;
return 0;
}
STATIC void
xfs_cleanup_inode(
struct inode *dir,
struct inode *inode,
struct dentry *dentry)
{
struct xfs_name teardown;
/* Oh, the horror.
* If we can't add the ACL or we fail in
* xfs_init_security we must back out.
* ENOSPC can hit here, among other things.
*/
xfs_dentry_to_name(&teardown, dentry);
xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
}
/*
* Check to see if we are likely to need an extended attribute to be added to
* the inode we are about to allocate. This allows the attribute fork to be
* created during the inode allocation, reducing the number of transactions we
* need to do in this fast path.
*
* The security checks are optimistic, but not guaranteed. The two LSMs that
* require xattrs to be added here (selinux and smack) are also the only two
* LSMs that add a sb->s_security structure to the superblock. Hence if security
* is enabled and sb->s_security is set, we have a pretty good idea that we are
* going to be asked to add a security xattr immediately after allocating the
* xfs inode and instantiating the VFS inode.
*/
static inline bool
xfs_create_need_xattr(
struct inode *dir,
struct posix_acl *default_acl,
struct posix_acl *acl)
{
if (acl)
return true;
if (default_acl)
return true;
#if IS_ENABLED(CONFIG_SECURITY)
if (dir->i_sb->s_security)
return true;
#endif
return false;
}
STATIC int
xfs_generic_create(
struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
umode_t mode,
dev_t rdev,
bool tmpfile) /* unnamed file */
{
struct inode *inode;
struct xfs_inode *ip = NULL;
struct posix_acl *default_acl, *acl;
struct xfs_name name;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (S_ISCHR(mode) || S_ISBLK(mode)) {
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
} else {
rdev = 0;
}
error = posix_acl_create(dir, &mode, &default_acl, &acl);
if (error)
return error;
/* Verify mode is valid also for tmpfile case */
error = xfs_dentry_mode_to_name(&name, dentry, mode);
if (unlikely(error))
goto out_free_acl;
if (!tmpfile) {
error = xfs_create(mnt_userns, XFS_I(dir), &name, mode, rdev,
xfs_create_need_xattr(dir, default_acl, acl),
&ip);
} else {
error = xfs_create_tmpfile(mnt_userns, XFS_I(dir), mode, &ip);
}
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
#ifdef CONFIG_XFS_POSIX_ACL
if (default_acl) {
error = __xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
if (error)
goto out_cleanup_inode;
}
if (acl) {
error = __xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
if (error)
goto out_cleanup_inode;
}
#endif
xfs_setup_iops(ip);
if (tmpfile) {
/*
* The VFS requires that any inode fed to d_tmpfile must have
* nlink == 1 so that it can decrement the nlink in d_tmpfile.
* However, we created the temp file with nlink == 0 because
* we're not allowed to put an inode with nlink > 0 on the
* unlinked list. Therefore we have to set nlink to 1 so that
* d_tmpfile can immediately set it back to zero.
*/
set_nlink(inode, 1);
d_tmpfile(dentry, inode);
} else
d_instantiate(dentry, inode);
xfs_finish_inode_setup(ip);
out_free_acl:
posix_acl_release(default_acl);
posix_acl_release(acl);
return error;
out_cleanup_inode:
xfs_finish_inode_setup(ip);
if (!tmpfile)
xfs_cleanup_inode(dir, inode, dentry);
xfs_irele(ip);
goto out_free_acl;
}
STATIC int
xfs_vn_mknod(
struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
umode_t mode,
dev_t rdev)
{
return xfs_generic_create(mnt_userns, dir, dentry, mode, rdev, false);
}
STATIC int
xfs_vn_create(
struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
umode_t mode,
bool flags)
{
return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, false);
}
STATIC int
xfs_vn_mkdir(
struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
umode_t mode)
{
return xfs_generic_create(mnt_userns, dir, dentry, mode | S_IFDIR, 0,
false);
}
STATIC struct dentry *
xfs_vn_lookup(
struct inode *dir,
struct dentry *dentry,
unsigned int flags)
{
struct inode *inode;
struct xfs_inode *cip;
struct xfs_name name;
int error;
if (dentry->d_name.len >= MAXNAMELEN)
return ERR_PTR(-ENAMETOOLONG);
xfs_dentry_to_name(&name, dentry);
error = xfs_lookup(XFS_I(dir), &name, &cip, NULL);
if (likely(!error))
inode = VFS_I(cip);
else if (likely(error == -ENOENT))
inode = NULL;
else
inode = ERR_PTR(error);
return d_splice_alias(inode, dentry);
}
STATIC struct dentry *
xfs_vn_ci_lookup(
struct inode *dir,
struct dentry *dentry,
unsigned int flags)
{
struct xfs_inode *ip;
struct xfs_name xname;
struct xfs_name ci_name;
struct qstr dname;
int error;
if (dentry->d_name.len >= MAXNAMELEN)
return ERR_PTR(-ENAMETOOLONG);
xfs_dentry_to_name(&xname, dentry);
error = xfs_lookup(XFS_I(dir), &xname, &ip, &ci_name);
if (unlikely(error)) {
if (unlikely(error != -ENOENT))
return ERR_PTR(error);
/*
* call d_add(dentry, NULL) here when d_drop_negative_children
* is called in xfs_vn_mknod (ie. allow negative dentries
* with CI filesystems).
*/
return NULL;
}
/* if exact match, just splice and exit */
if (!ci_name.name)
return d_splice_alias(VFS_I(ip), dentry);
/* else case-insensitive match... */
dname.name = ci_name.name;
dname.len = ci_name.len;
dentry = d_add_ci(dentry, VFS_I(ip), &dname);
kmem_free(ci_name.name);
return dentry;
}
STATIC int
xfs_vn_link(
struct dentry *old_dentry,
struct inode *dir,
struct dentry *dentry)
{
struct inode *inode = d_inode(old_dentry);
struct xfs_name name;
int error;
error = xfs_dentry_mode_to_name(&name, dentry, inode->i_mode);
if (unlikely(error))
return error;
error = xfs_link(XFS_I(dir), XFS_I(inode), &name);
if (unlikely(error))
return error;
ihold(inode);
d_instantiate(dentry, inode);
return 0;
}
STATIC int
xfs_vn_unlink(
struct inode *dir,
struct dentry *dentry)
{
struct xfs_name name;
int error;
xfs_dentry_to_name(&name, dentry);
error = xfs_remove(XFS_I(dir), &name, XFS_I(d_inode(dentry)));
if (error)
return error;
/*
* With unlink, the VFS makes the dentry "negative": no inode,
* but still hashed. This is incompatible with case-insensitive
* mode, so invalidate (unhash) the dentry in CI-mode.
*/
if (xfs_has_asciici(XFS_M(dir->i_sb)))
d_invalidate(dentry);
return 0;
}
STATIC int
xfs_vn_symlink(
struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
const char *symname)
{
struct inode *inode;
struct xfs_inode *cip = NULL;
struct xfs_name name;
int error;
umode_t mode;
mode = S_IFLNK |
(irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO);
error = xfs_dentry_mode_to_name(&name, dentry, mode);
if (unlikely(error))
goto out;
error = xfs_symlink(mnt_userns, XFS_I(dir), &name, symname, mode, &cip);
if (unlikely(error))
goto out;
inode = VFS_I(cip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
xfs_setup_iops(cip);
d_instantiate(dentry, inode);
xfs_finish_inode_setup(cip);
return 0;
out_cleanup_inode:
xfs_finish_inode_setup(cip);
xfs_cleanup_inode(dir, inode, dentry);
xfs_irele(cip);
out:
return error;
}
STATIC int
xfs_vn_rename(
struct user_namespace *mnt_userns,
struct inode *odir,
struct dentry *odentry,
struct inode *ndir,
struct dentry *ndentry,
unsigned int flags)
{
struct inode *new_inode = d_inode(ndentry);
int omode = 0;
int error;
struct xfs_name oname;
struct xfs_name nname;
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
/* if we are exchanging files, we need to set i_mode of both files */
if (flags & RENAME_EXCHANGE)
omode = d_inode(ndentry)->i_mode;
error = xfs_dentry_mode_to_name(&oname, odentry, omode);
if (omode && unlikely(error))
return error;
error = xfs_dentry_mode_to_name(&nname, ndentry,
d_inode(odentry)->i_mode);
if (unlikely(error))
return error;
return xfs_rename(mnt_userns, XFS_I(odir), &oname,
XFS_I(d_inode(odentry)), XFS_I(ndir), &nname,
new_inode ? XFS_I(new_inode) : NULL, flags);
}
/*
* careful here - this function can get called recursively, so
* we need to be very careful about how much stack we use.
* uio is kmalloced for this reason...
*/
STATIC const char *
xfs_vn_get_link(
struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
char *link;
int error = -ENOMEM;
if (!dentry)
return ERR_PTR(-ECHILD);
link = kmalloc(XFS_SYMLINK_MAXLEN+1, GFP_KERNEL);
if (!link)
goto out_err;
error = xfs_readlink(XFS_I(d_inode(dentry)), link);
if (unlikely(error))
goto out_kfree;
set_delayed_call(done, kfree_link, link);
return link;
out_kfree:
kfree(link);
out_err:
return ERR_PTR(error);
}
static uint32_t
xfs_stat_blksize(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
/*
* If the file blocks are being allocated from a realtime volume, then
* always return the realtime extent size.
*/
if (XFS_IS_REALTIME_INODE(ip))
return XFS_FSB_TO_B(mp, xfs_get_extsz_hint(ip));
/*
* Allow large block sizes to be reported to userspace programs if the
* "largeio" mount option is used.
*
* If compatibility mode is specified, simply return the basic unit of
* caching so that we don't get inefficient read/modify/write I/O from
* user apps. Otherwise....
*
* If the underlying volume is a stripe, then return the stripe width in
* bytes as the recommended I/O size. It is not a stripe and we've set a
* default buffered I/O size, return that, otherwise return the compat
* default.
*/
if (xfs_has_large_iosize(mp)) {
if (mp->m_swidth)
return XFS_FSB_TO_B(mp, mp->m_swidth);
if (xfs_has_allocsize(mp))
return 1U << mp->m_allocsize_log;
}
return PAGE_SIZE;
}
STATIC int
xfs_vn_getattr(
struct user_namespace *mnt_userns,
const struct path *path,
struct kstat *stat,
u32 request_mask,
unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
trace_xfs_getattr(ip);
if (xfs_is_shutdown(mp))
return -EIO;
stat->size = XFS_ISIZE(ip);
stat->dev = inode->i_sb->s_dev;
stat->mode = inode->i_mode;
stat->nlink = inode->i_nlink;
stat->uid = i_uid_into_mnt(mnt_userns, inode);
stat->gid = i_gid_into_mnt(mnt_userns, inode);
stat->ino = ip->i_ino;
stat->atime = inode->i_atime;
stat->mtime = inode->i_mtime;
stat->ctime = inode->i_ctime;
stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks);
if (xfs_has_v3inodes(mp)) {
if (request_mask & STATX_BTIME) {
stat->result_mask |= STATX_BTIME;
stat->btime = ip->i_crtime;
}
}
/*
* Note: If you add another clause to set an attribute flag, please
* update attributes_mask below.
*/
if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (ip->i_diflags & XFS_DIFLAG_APPEND)
stat->attributes |= STATX_ATTR_APPEND;
if (ip->i_diflags & XFS_DIFLAG_NODUMP)
stat->attributes |= STATX_ATTR_NODUMP;
stat->attributes_mask |= (STATX_ATTR_IMMUTABLE |
STATX_ATTR_APPEND |
STATX_ATTR_NODUMP);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
stat->blksize = BLKDEV_IOSIZE;
stat->rdev = inode->i_rdev;
break;
default:
stat->blksize = xfs_stat_blksize(ip);
stat->rdev = 0;
break;
}
return 0;
}
static void
xfs_setattr_mode(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct inode *inode = VFS_I(ip);
umode_t mode = iattr->ia_mode;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
inode->i_mode &= S_IFMT;
inode->i_mode |= mode & ~S_IFMT;
}
void
xfs_setattr_time(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct inode *inode = VFS_I(ip);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
if (iattr->ia_valid & ATTR_ATIME)
inode->i_atime = iattr->ia_atime;
if (iattr->ia_valid & ATTR_CTIME)
inode->i_ctime = iattr->ia_ctime;
if (iattr->ia_valid & ATTR_MTIME)
inode->i_mtime = iattr->ia_mtime;
}
static int
xfs_vn_change_ok(
struct user_namespace *mnt_userns,
struct dentry *dentry,
struct iattr *iattr)
{
struct xfs_mount *mp = XFS_I(d_inode(dentry))->i_mount;
if (xfs_is_readonly(mp))
return -EROFS;
if (xfs_is_shutdown(mp))
return -EIO;
return setattr_prepare(mnt_userns, dentry, iattr);
}
/*
* Set non-size attributes of an inode.
*
* Caution: The caller of this function is responsible for calling
* setattr_prepare() or otherwise verifying the change is fine.
*/
static int
xfs_setattr_nonsize(
struct user_namespace *mnt_userns,
struct xfs_inode *ip,
struct iattr *iattr)
{
xfs_mount_t *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
xfs_trans_t *tp;
int error;
kuid_t uid = GLOBAL_ROOT_UID, iuid = GLOBAL_ROOT_UID;
kgid_t gid = GLOBAL_ROOT_GID, igid = GLOBAL_ROOT_GID;
struct xfs_dquot *udqp = NULL, *gdqp = NULL;
struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL;
ASSERT((mask & ATTR_SIZE) == 0);
/*
* 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 = inode->i_uid;
}
if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
gid = iattr->ia_gid;
qflags |= XFS_QMOPT_GQUOTA;
} else {
gid = inode->i_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);
error = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_projid,
qflags, &udqp, &gdqp, NULL);
if (error)
return error;
}
error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL,
capable(CAP_FOWNER), &tp);
if (error)
goto out_dqrele;
/*
* 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 = inode->i_uid;
igid = inode->i_gid;
gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;
/*
* 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 ((inode->i_mode & (S_ISUID|S_ISGID)) &&
!capable(CAP_FSETID))
inode->i_mode &= ~(S_ISUID|S_ISGID);
/*
* Change the ownerships and register quota modifications
* in the transaction.
*/
if (!uid_eq(iuid, uid)) {
if (XFS_IS_UQUOTA_ON(mp)) {
ASSERT(mask & ATTR_UID);
ASSERT(udqp);
olddquot1 = xfs_qm_vop_chown(tp, ip,
&ip->i_udquot, udqp);
}
inode->i_uid = uid;
}
if (!gid_eq(igid, gid)) {
if (XFS_IS_GQUOTA_ON(mp)) {
ASSERT(xfs_has_pquotino(mp) ||
!XFS_IS_PQUOTA_ON(mp));
ASSERT(mask & ATTR_GID);
ASSERT(gdqp);
olddquot2 = xfs_qm_vop_chown(tp, ip,
&ip->i_gdquot, gdqp);
}
inode->i_gid = gid;
}
}
if (mask & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(mp, xs_ig_attrchg);
if (xfs_has_wsync(mp))
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
/*
* 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 (error)
return error;
/*
* 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) {
error = posix_acl_chmod(mnt_userns, inode, inode->i_mode);
if (error)
return error;
}
return 0;
out_dqrele:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
return error;
}
/*
* Truncate file. Must have write permission and not be a directory.
*
* Caution: The caller of this function is responsible for calling
* setattr_prepare() or otherwise verifying the change is fine.
*/
STATIC int
xfs_setattr_size(
struct user_namespace *mnt_userns,
struct xfs_inode *ip,
struct iattr *iattr)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags = 0;
bool did_zeroing = false;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
ASSERT(S_ISREG(inode->i_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
/*
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_df.if_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(mnt_userns, ip, iattr);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip);
if (error)
return error;
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
/*
* File data changes must be complete before we start the transaction to
* modify the inode. 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.
*
* Start with zeroing any data beyond EOF that we may expose on file
* extension, or zeroing out the rest of the block on a downward
* truncate.
*/
if (newsize > oldsize) {
trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
error = xfs_zero_range(ip, oldsize, newsize - oldsize,
&did_zeroing);
} else {
/*
* iomap won't detect a dirty page over an unwritten block (or a
* cow block over a hole) and subsequently skips zeroing the
* newly post-EOF portion of the page. Flush the new EOF to
* convert the block before the pagecache truncate.
*/
error = filemap_write_and_wait_range(inode->i_mapping, newsize,
newsize);
if (error)
return error;
error = xfs_truncate_page(ip, newsize, &did_zeroing);
}
if (error)
return error;
/*
* We've already locked out new page faults, so now we can safely remove
* pages from the page cache knowing they won't get refaulted until we
* drop the XFS_MMAP_EXCL lock after the extent manipulations are
* complete. The truncate_setsize() call also cleans partial EOF page
* PTEs on extending truncates and hence ensures sub-page block size
* filesystems are correctly handled, too.
*
* We have to do all the page cache truncate work outside the
* transaction context as the "lock" order is page lock->log space
* reservation as defined by extent allocation in the writeback path.
* Hence a truncate can fail with ENOMEM from xfs_trans_alloc(), but
* having already truncated the in-memory version of the file (i.e. made
* user visible changes). There's not much we can do about this, except
* to hope that the caller sees ENOMEM and retries the truncate
* operation.
*
* And we update in-core i_size and truncate page cache beyond newsize
* before writeback the [i_disk_size, newsize] range, so we're
* guaranteed not to write stale data past the new EOF on truncate down.
*/
truncate_setsize(inode, newsize);
/*
* 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. Note that this includes any block zeroing we did above;
* otherwise those blocks may not be zeroed after a crash.
*/
if (did_zeroing ||
(newsize > ip->i_disk_size && oldsize != ip->i_disk_size)) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_disk_size, newsize - 1);
if (error)
return error;
}
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
return error;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* 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 (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_time(inode);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_disk_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_cancel;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,