summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_iops.c
blob: 23ce927973a4a739e3472b68e9f7f6ef84de202a (plain) (blame)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_acl.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_alloc.h"
#include "xfs_quota.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_bmap.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_itable.h"
#include "xfs_rw.h"
#include "xfs_attr.h"
#include "xfs_buf_item.h"
#include "xfs_utils.h"
#include "xfs_vnodeops.h"
#include "xfs_inode_item.h"
#include "xfs_trace.h"

#include <linux/capability.h>
#include <linux/xattr.h>
#include <linux/namei.h>
#include <linux/posix_acl.h>
#include <linux/security.h>
#include <linux/fiemap.h>
#include <linux/slab.h>

/*
 * Bring the timestamps in the XFS inode uptodate.
 *
 * Used before writing the inode to disk.
 */
void
xfs_synchronize_times(
	xfs_inode_t	*ip)
{
	struct inode	*inode = VFS_I(ip);

	ip->i_d.di_atime.t_sec = (__int32_t)inode->i_atime.tv_sec;
	ip->i_d.di_atime.t_nsec = (__int32_t)inode->i_atime.tv_nsec;
	ip->i_d.di_ctime.t_sec = (__int32_t)inode->i_ctime.tv_sec;
	ip->i_d.di_ctime.t_nsec = (__int32_t)inode->i_ctime.tv_nsec;
	ip->i_d.di_mtime.t_sec = (__int32_t)inode->i_mtime.tv_sec;
	ip->i_d.di_mtime.t_nsec = (__int32_t)inode->i_mtime.tv_nsec;
}

/*
 * If the linux inode is valid, mark it dirty, else mark the dirty state
 * in the XFS inode to make sure we pick it up when reclaiming the inode.
 */
void
xfs_mark_inode_dirty_sync(
	xfs_inode_t	*ip)
{
	struct inode	*inode = VFS_I(ip);

	if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
		mark_inode_dirty_sync(inode);
	else {
		barrier();
		ip->i_update_core = 1;
	}
}

void
xfs_mark_inode_dirty(
	xfs_inode_t	*ip)
{
	struct inode	*inode = VFS_I(ip);

	if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
		mark_inode_dirty(inode);
	else {
		barrier();
		ip->i_update_core = 1;
	}

}


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++) {
		error = xfs_attr_set(ip, xattr->name, xattr->value,
				     xattr->value_len, ATTR_SECURE);
		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;
}

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));
	iput(inode);
}

STATIC int
xfs_vn_mknod(
	struct inode	*dir,
	struct dentry	*dentry,
	int		mode,
	dev_t		rdev)
{
	struct inode	*inode;
	struct xfs_inode *ip = NULL;
	struct posix_acl *default_acl = NULL;
	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;
		rdev = sysv_encode_dev(rdev);
	} else {
		rdev = 0;
	}

	if (IS_POSIXACL(dir)) {
		default_acl = xfs_get_acl(dir, ACL_TYPE_DEFAULT);
		if (IS_ERR(default_acl))
			return PTR_ERR(default_acl);

		if (!default_acl)
			mode &= ~current_umask();
	}

	xfs_dentry_to_name(&name, dentry);
	error = xfs_create(XFS_I(dir), &name, mode, rdev, &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;

	if (default_acl) {
		error = -xfs_inherit_acl(inode, default_acl);
		default_acl = NULL;
		if (unlikely(error))
			goto out_cleanup_inode;
	}


	d_instantiate(dentry, inode);
	return -error;

 out_cleanup_inode:
	xfs_cleanup_inode(dir, inode, dentry);
 out_free_acl:
	posix_acl_release(default_acl);
	return -error;
}

STATIC int
xfs_vn_create(
	struct inode	*dir,
	struct dentry	*dentry,
	int		mode,
	struct nameidata *nd)
{
	return xfs_vn_mknod(dir, dentry, mode, 0);
}

STATIC int
xfs_vn_mkdir(
	struct inode	*dir,
	struct dentry	*dentry,
	int		mode)
{
	return xfs_vn_mknod(dir, dentry, mode|S_IFDIR, 0);
}

STATIC struct dentry *
xfs_vn_lookup(
	struct inode	*dir,
	struct dentry	*dentry,
	struct nameidata *nd)
{
	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 (unlikely(error)) {
		if (unlikely(error != ENOENT))
			return ERR_PTR(-error);
		d_add(dentry, NULL);
		return NULL;
	}

	return d_splice_alias(VFS_I(cip), dentry);
}

STATIC struct dentry *
xfs_vn_ci_lookup(
	struct inode	*dir,
	struct dentry	*dentry,
	struct nameidata *nd)
{
	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 = old_dentry->d_inode;
	struct xfs_name	name;
	int		error;

	xfs_dentry_to_name(&name, dentry);

	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(dentry->d_inode));
	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_sb_version_hasasciici(&XFS_M(dir->i_sb)->m_sb))
		d_invalidate(dentry);
	return 0;
}

STATIC int
xfs_vn_symlink(
	struct inode	*dir,
	struct dentry	*dentry,
	const char	*symname)
{
	struct inode	*inode;
	struct xfs_inode *cip = NULL;
	struct xfs_name	name;
	int		error;
	mode_t		mode;

	mode = S_IFLNK |
		(irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO);
	xfs_dentry_to_name(&name, dentry);

	error = xfs_symlink(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;

	d_instantiate(dentry, inode);
	return 0;

 out_cleanup_inode:
	xfs_cleanup_inode(dir, inode, dentry);
 out:
	return -error;
}

STATIC int
xfs_vn_rename(
	struct inode	*odir,
	struct dentry	*odentry,
	struct inode	*ndir,
	struct dentry	*ndentry)
{
	struct inode	*new_inode = ndentry->d_inode;
	struct xfs_name	oname;
	struct xfs_name	nname;

	xfs_dentry_to_name(&oname, odentry);
	xfs_dentry_to_name(&nname, ndentry);

	return -xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode),
			   XFS_I(ndir), &nname, new_inode ?
			   			XFS_I(new_inode) : NULL);
}

/*
 * 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 void *
xfs_vn_follow_link(
	struct dentry		*dentry,
	struct nameidata	*nd)
{
	char			*link;
	int			error = -ENOMEM;

	link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
	if (!link)
		goto out_err;

	error = -xfs_readlink(XFS_I(dentry->d_inode), link);
	if (unlikely(error))
		goto out_kfree;

	nd_set_link(nd, link);
	return NULL;

 out_kfree:
	kfree(link);
 out_err:
	nd_set_link(nd, ERR_PTR(error));
	return NULL;
}

STATIC void
xfs_vn_put_link(
	struct dentry	*dentry,
	struct nameidata *nd,
	void		*p)
{
	char		*s = nd_get_link(nd);

	if (!IS_ERR(s))
		kfree(s);
}

STATIC int
xfs_vn_getattr(
	struct vfsmount		*mnt,
	struct dentry		*dentry,
	struct kstat		*stat)
{
	struct inode		*inode = dentry->d_inode;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;

	trace_xfs_getattr(ip);

	if (XFS_FORCED_SHUTDOWN(mp))
		return -XFS_ERROR(EIO);

	stat->size = XFS_ISIZE(ip);
	stat->dev = inode->i_sb->s_dev;
	stat->mode = ip->i_d.di_mode;
	stat->nlink = ip->i_d.di_nlink;
	stat->uid = ip->i_d.di_uid;
	stat->gid = ip->i_d.di_gid;
	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_d.di_nblocks + ip->i_delayed_blks);


	switch (inode->i_mode & S_IFMT) {
	case S_IFBLK:
	case S_IFCHR:
		stat->blksize = BLKDEV_IOSIZE;
		stat->rdev = MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
				   sysv_minor(ip->i_df.if_u2.if_rdev));
		break;
	default:
		if (XFS_IS_REALTIME_INODE(ip)) {
			/*
			 * If the file blocks are being allocated from a
			 * realtime volume, then return the inode's realtime
			 * extent size or the realtime volume's extent size.
			 */
			stat->blksize =
				xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
		} else
			stat->blksize = xfs_preferred_iosize(mp);
		stat->rdev = 0;
		break;
	}

	return 0;
}

int
xfs_setattr_nonsize(
	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			error;
	uid_t			uid = 0, iuid = 0;
	gid_t			gid = 0, igid = 0;
	struct xfs_dquot	*udqp = NULL, *gdqp = NULL;
	struct xfs_dquot	*olddquot1 = NULL, *olddquot2 = NULL;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	error = -inode_change_ok(inode, iattr);
	if (error)
		return XFS_ERROR(error);

	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 = 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);
		error = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip),
					 qflags, &udqp, &gdqp);
		if (error)
			return error;
	}

	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
	if (error)
		goto out_dqrele;

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	/*
	 * 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);
			error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
						capable(CAP_FOWNER) ?
						XFS_QMOPT_FORCE_RES : 0);
			if (error)	/* out of quota */
				goto out_trans_cancel;
		}
	}

	xfs_trans_ijoin(tp, ip, 0);

	/*
	 * 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;
	}

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	XFS_STATS_INC(xs_ig_attrchg);

	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);
	error = xfs_trans_commit(tp, 0);

	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	/*
	 * 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 XFS_ERROR(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) && !(flags & XFS_ATTR_NOACL)) {
		error = -xfs_acl_chmod(inode);
		if (error)
			return XFS_ERROR(error);
	}

	return 0;

out_trans_cancel:
	xfs_trans_cancel(tp, 0);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_dqrele:
	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	return error;
}

/*
 * Truncate file.  Must have write permission and not be a directory.
 */
int
xfs_setattr_size(
	struct xfs_inode	*ip,
	struct iattr		*iattr,
	int			flags)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	int			mask = iattr->ia_valid;
	struct xfs_trans	*tp;
	int			error;
	uint			lock_flags;
	uint			commit_flags = 0;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	error = -inode_change_ok(inode, iattr);
	if (error)
		return XFS_ERROR(error);

	ASSERT(S_ISREG(ip->i_d.di_mode));
	ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
			ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
			ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);

	lock_flags = XFS_ILOCK_EXCL;
	if (!(flags & XFS_ATTR_NOLOCK))
		lock_flags |= XFS_IOLOCK_EXCL;
	xfs_ilock(ip, lock_flags);

	/*
	 * Short circuit the truncate case for zero length files.
	 */
	if (iattr->ia_size == 0 &&
	    ip->i_size == 0 && ip->i_d.di_nextents == 0) {
		if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
			goto out_unlock;

		/*
		 * Use the regular setattr path to update the timestamps.
		 */
		xfs_iunlock(ip, lock_flags);
		iattr->ia_valid &= ~ATTR_SIZE;
		return xfs_setattr_nonsize(ip, iattr, 0);
	}

	/*
	 * Make sure that the dquots are attached to the inode.
	 */
	error = xfs_qm_dqattach_locked(ip, 0);
	if (error)
		goto out_unlock;

	/*
	 * Now we can make the changes.  Before we join the inode to the
	 * transaction, 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
		 * i_size.
		 */
		error = xfs_zero_eof(ip, iattr->ia_size, ip->i_size);
		if (error)
			goto out_unlock;
	}
	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) {
		error = xfs_flush_pages(ip, ip->i_d.di_size, iattr->ia_size, 0,
					FI_NONE);
		if (error)
			goto out_unlock;
	}

	/*
	 * Wait for all direct I/O to complete.
	 */
	inode_dio_wait(inode);

	error = -block_truncate_page(inode->i_mapping, iattr->ia_size,
				     xfs_get_blocks);
	if (error)
		goto out_unlock;

	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
	error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
				 XFS_TRANS_PERM_LOG_RES,
				 XFS_ITRUNCATE_LOG_COUNT);
	if (error)
		goto out_trans_cancel;

	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, 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 (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;
	} else if (iattr->ia_size <= ip->i_size ||
		   (iattr->ia_size == 0 && ip->i_d.di_nextents)) {
		error = xfs_itruncate_data(&tp, ip, iattr->ia_size);
		if (error)
			goto out_trans_abort;

		/*
		 * 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,
		 * and do not wait the usual (long) time for writeout.
		 */
		xfs_iflags_set(ip, XFS_ITRUNCATED);
	}

	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;
	}

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	XFS_STATS_INC(xs_ig_attrchg);

	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);

	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
	return error;

out_trans_abort:
	commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
	xfs_trans_cancel(tp, commit_flags);
	goto out_unlock;
}

STATIC int
xfs_vn_setattr(
	struct dentry	*dentry,
	struct iattr	*iattr)
{
	if (iattr->ia_valid & ATTR_SIZE)
		return -xfs_setattr_size(XFS_I(dentry->d_inode), iattr, 0);
	return -xfs_setattr_nonsize(XFS_I(dentry->d_inode), iattr, 0);
}

#define XFS_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)

/*
 * Call fiemap helper to fill in user data.
 * Returns positive errors to xfs_getbmap.
 */
STATIC int
xfs_fiemap_format(
	void			**arg,
	struct getbmapx		*bmv,
	int			*full)
{
	int			error;
	struct fiemap_extent_info *fieinfo = *arg;
	u32			fiemap_flags = 0;
	u64			logical, physical, length;

	/* Do nothing for a hole */
	if (bmv->bmv_block == -1LL)
		return 0;

	logical = BBTOB(bmv->bmv_offset);
	physical = BBTOB(bmv->bmv_block);
	length = BBTOB(bmv->bmv_length);

	if (bmv->bmv_oflags & BMV_OF_PREALLOC)
		fiemap_flags |= FIEMAP_EXTENT_UNWRITTEN;
	else if (bmv->bmv_oflags & BMV_OF_DELALLOC) {
		fiemap_flags |= FIEMAP_EXTENT_DELALLOC;
		physical = 0;   /* no block yet */
	}
	if (bmv->bmv_oflags & BMV_OF_LAST)
		fiemap_flags |= FIEMAP_EXTENT_LAST;

	error = fiemap_fill_next_extent(fieinfo, logical, physical,
					length, fiemap_flags);
	if (error > 0) {
		error = 0;
		*full = 1;	/* user array now full */
	}

	return -error;
}

STATIC int
xfs_vn_fiemap(
	struct inode		*inode,
	struct fiemap_extent_info *fieinfo,
	u64			start,
	u64			length)
{
	xfs_inode_t		*ip = XFS_I(inode);
	struct getbmapx		bm;
	int			error;

	error = fiemap_check_flags(fieinfo, XFS_FIEMAP_FLAGS);
	if (error)
		return error;

	/* Set up bmap header for xfs internal routine */
	bm.bmv_offset = BTOBB(start);
	/* Special case for whole file */
	if (length == FIEMAP_MAX_OFFSET)
		bm.bmv_length = -1LL;
	else
		bm.bmv_length = BTOBB(length);

	/* We add one because in getbmap world count includes the header */
	bm.bmv_count = !fieinfo->fi_extents_max ? MAXEXTNUM :
					fieinfo->fi_extents_max + 1;
	bm.bmv_count = min_t(__s32, bm.bmv_count,
			     (PAGE_SIZE * 16 / sizeof(struct getbmapx)));
	bm.bmv_iflags = BMV_IF_PREALLOC | BMV_IF_NO_HOLES;
	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
		bm.bmv_iflags |= BMV_IF_ATTRFORK;
	if (!(fieinfo->fi_flags & FIEMAP_FLAG_SYNC))
		bm.bmv_iflags |= BMV_IF_DELALLOC;

	error = xfs_getbmap(ip, &bm, xfs_fiemap_format, fieinfo);
	if (error)
		return -error;

	return 0;
}

static const struct inode_operations xfs_inode_operations = {
	.get_acl		= xfs_get_acl,
	.getattr		= xfs_vn_getattr,
	.setattr		= xfs_vn_setattr,
	.setxattr		= generic_setxattr,
	.getxattr		= generic_getxattr,
	.removexattr		= generic_removexattr,
	.listxattr		= xfs_vn_listxattr,
	.fiemap			= xfs_vn_fiemap,
};

static const struct inode_operations xfs_dir_inode_operations = {
	.create			= xfs_vn_create,
	.lookup			= xfs_vn_lookup,
	.link			= xfs_vn_link,
	.unlink			= xfs_vn_unlink,
	.symlink		= xfs_vn_symlink,
	.mkdir			= xfs_vn_mkdir,
	/*
	 * Yes, XFS uses the same method for rmdir and unlink.
	 *
	 * There are some subtile differences deeper in the code,
	 * but we use S_ISDIR to check for those.
	 */
	.rmdir			= xfs_vn_unlink,
	.mknod			= xfs_vn_mknod,
	.rename			= xfs_vn_rename,
	.get_acl		= xfs_get_acl,
	.getattr		= xfs_vn_getattr,
	.setattr		= xfs_vn_setattr,
	.setxattr		= generic_setxattr,
	.getxattr		= generic_getxattr,
	.removexattr		= generic_removexattr,
	.listxattr		= xfs_vn_listxattr,
};

static const struct inode_operations xfs_dir_ci_inode_operations = {
	.create			= xfs_vn_create,
	.lookup			= xfs_vn_ci_lookup,
	.link			= xfs_vn_link,
	.unlink			= xfs_vn_unlink,
	.symlink		= xfs_vn_symlink,
	.mkdir			= xfs_vn_mkdir,
	/*
	 * Yes, XFS uses the same method for rmdir and unlink.
	 *
	 * There are some subtile differences deeper in the code,
	 * but we use S_ISDIR to check for those.
	 */
	.rmdir			= xfs_vn_unlink,
	.mknod			= xfs_vn_mknod,
	.rename			= xfs_vn_rename,
	.get_acl		= xfs_get_acl,
	.getattr		= xfs_vn_getattr,
	.setattr		= xfs_vn_setattr,
	.setxattr		= generic_setxattr,
	.getxattr		= generic_getxattr,
	.removexattr		= generic_removexattr,
	.listxattr		= xfs_vn_listxattr,
};

static const struct inode_operations xfs_symlink_inode_operations = {
	.readlink		= generic_readlink,
	.follow_link		= xfs_vn_follow_link,
	.put_link		= xfs_vn_put_link,
	.get_acl		= xfs_get_acl,
	.getattr		= xfs_vn_getattr,
	.setattr		= xfs_vn_setattr,
	.setxattr		= generic_setxattr,
	.getxattr		= generic_getxattr,
	.removexattr		= generic_removexattr,
	.listxattr		= xfs_vn_listxattr,
};

STATIC void
xfs_diflags_to_iflags(
	struct inode		*inode,
	struct xfs_inode	*ip)
{
	if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
		inode->i_flags |= S_IMMUTABLE;
	else
		inode->i_flags &= ~S_IMMUTABLE;
	if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
		inode->i_flags |= S_APPEND;
	else
		inode->i_flags &= ~S_APPEND;
	if (ip->i_d.di_flags & XFS_DIFLAG_SYNC)
		inode->i_flags |= S_SYNC;
	else
		inode->i_flags &= ~S_SYNC;
	if (ip->i_d.di_flags & XFS_DIFLAG_NOATIME)
		inode->i_flags |= S_NOATIME;
	else
		inode->i_flags &= ~S_NOATIME;
}

/*
 * Initialize the Linux inode, set up the operation vectors and
 * unlock the inode.
 *
 * When reading existing inodes from disk this is called directly
 * from xfs_iget, when creating a new inode it is called from
 * xfs_ialloc after setting up the inode.
 *
 * We are always called with an uninitialised linux inode here.
 * We need to initialise the necessary fields and take a reference
 * on it.
 */
void
xfs_setup_inode(
	struct xfs_inode	*ip)
{
	struct inode		*inode = &ip->i_vnode;

	inode->i_ino = ip->i_ino;
	inode->i_state = I_NEW;

	inode_sb_list_add(inode);
	/* make the inode look hashed for the writeback code */
	hlist_add_fake(&inode->i_hash);

	inode->i_mode	= ip->i_d.di_mode;
	set_nlink(inode, ip->i_d.di_nlink);
	inode->i_uid	= ip->i_d.di_uid;
	inode->i_gid	= ip->i_d.di_gid;

	switch (inode->i_mode & S_IFMT) {
	case S_IFBLK:
	case S_IFCHR:
		inode->i_rdev =
			MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
			      sysv_minor(ip->i_df.if_u2.if_rdev));
		break;
	default:
		inode->i_rdev = 0;
		break;
	}

	inode->i_generation = ip->i_d.di_gen;
	i_size_write(inode, ip->i_d.di_size);
	inode->i_atime.tv_sec	= ip->i_d.di_atime.t_sec;
	inode->i_atime.tv_nsec	= ip->i_d.di_atime.t_nsec;
	inode->i_mtime.tv_sec	= ip->i_d.di_mtime.t_sec;
	inode->i_mtime.tv_nsec	= ip->i_d.di_mtime.t_nsec;
	inode->i_ctime.tv_sec	= ip->i_d.di_ctime.t_sec;
	inode->i_ctime.tv_nsec	= ip->i_d.di_ctime.t_nsec;
	xfs_diflags_to_iflags(inode, ip);

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		inode->i_op = &xfs_inode_operations;
		inode->i_fop = &xfs_file_operations;
		inode->i_mapping->a_ops = &xfs_address_space_operations;
		break;
	case S_IFDIR:
		if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
			inode->i_op = &xfs_dir_ci_inode_operations;
		else
			inode->i_op = &xfs_dir_inode_operations;
		inode->i_fop = &xfs_dir_file_operations;
		break;
	case S_IFLNK:
		inode->i_op = &xfs_symlink_inode_operations;
		if (!(ip->i_df.if_flags & XFS_IFINLINE))
			inode->i_mapping->a_ops = &xfs_address_space_operations;
		break;
	default:
		inode->i_op = &xfs_inode_operations;
		init_special_inode(inode, inode->i_mode, inode->i_rdev);
		break;
	}

	/*
	 * If there is no attribute fork no ACL can exist on this inode,
	 * and it can't have any file capabilities attached to it either.
	 */
	if (!XFS_IFORK_Q(ip)) {
		inode_has_no_xattr(inode);
		cache_no_acl(inode);
	}

	xfs_iflags_clear(ip, XFS_INEW);
	barrier();

	unlock_new_inode(inode);
}