aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/linux-2.6/xfs_iops.c
blob: 631d0137551e105d62f667fc6de35a62f4210337 (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
/*
 * 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_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_alloc.h"
#include "xfs_dmapi.h"
#include "xfs_quota.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_bmap.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_itable.h"
#include "xfs_rw.h"
#include "xfs_acl.h"
#include "xfs_attr.h"
#include "xfs_buf_item.h"
#include "xfs_utils.h"
#include "xfs_vnodeops.h"

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

/*
 * Bring the atime in the XFS inode uptodate.
 * Used before logging the inode to disk or when the Linux inode goes away.
 */
void
xfs_synchronize_atime(
	xfs_inode_t	*ip)
{
	struct inode	*inode = VFS_I(ip);

	if (!(inode->i_state & I_CLEAR)) {
		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;
	}
}

/*
 * If the linux inode is valid, mark it dirty.
 * Used when commiting a dirty inode into a transaction so that
 * the inode will get written back by the linux code
 */
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|I_CLEAR)))
		mark_inode_dirty_sync(inode);
}

/*
 * Change the requested timestamp in the given inode.
 * We don't lock across timestamp updates, and we don't log them but
 * we do record the fact that there is dirty information in core.
 */
void
xfs_ichgtime(
	xfs_inode_t	*ip,
	int		flags)
{
	struct inode	*inode = VFS_I(ip);
	timespec_t	tv;
	int		sync_it = 0;

	tv = current_fs_time(inode->i_sb);

	if ((flags & XFS_ICHGTIME_MOD) &&
	    !timespec_equal(&inode->i_mtime, &tv)) {
		inode->i_mtime = tv;
		ip->i_d.di_mtime.t_sec = (__int32_t)tv.tv_sec;
		ip->i_d.di_mtime.t_nsec = (__int32_t)tv.tv_nsec;
		sync_it = 1;
	}
	if ((flags & XFS_ICHGTIME_CHG) &&
	    !timespec_equal(&inode->i_ctime, &tv)) {
		inode->i_ctime = tv;
		ip->i_d.di_ctime.t_sec = (__int32_t)tv.tv_sec;
		ip->i_d.di_ctime.t_nsec = (__int32_t)tv.tv_nsec;
		sync_it = 1;
	}

	/*
	 * We update the i_update_core field _after_ changing
	 * the timestamps in order to coordinate properly with
	 * xfs_iflush() so that we don't lose timestamp updates.
	 * This keeps us from having to hold the inode lock
	 * while doing this.  We use the SYNCHRONIZE macro to
	 * ensure that the compiler does not reorder the update
	 * of i_update_core above the timestamp updates above.
	 */
	if (sync_it) {
		SYNCHRONIZE();
		ip->i_update_core = 1;
		xfs_mark_inode_dirty_sync(ip);
	}
}

/*
 * 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)
{
	struct xfs_inode *ip = XFS_I(inode);
	size_t		length;
	void		*value;
	char		*name;
	int		error;

	error = security_inode_init_security(inode, dir, &name,
					     &value, &length);
	if (error) {
		if (error == -EOPNOTSUPP)
			return 0;
		return -error;
	}

	error = xfs_attr_set(ip, name, value, length, ATTR_SECURE);

	kfree(name);
	kfree(value);
	return error;
}

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;
	xfs_acl_t	*default_acl = NULL;
	struct xfs_name	name;
	int (*test_default_acl)(struct inode *) = _ACL_DEFAULT_EXISTS;
	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 (test_default_acl && test_default_acl(dir)) {
		if (!_ACL_ALLOC(default_acl)) {
			return -ENOMEM;
		}
		if (!_ACL_GET_DEFAULT(dir, default_acl)) {
			_ACL_FREE(default_acl);
			default_acl = NULL;
		}
	}

	if (IS_POSIXACL(dir) && !default_acl)
		mode &= ~current->fs->umask;

	xfs_dentry_to_name(&name, dentry);
	error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip, NULL);
	if (unlikely(error))
		goto out_free_acl;

	inode = VFS_I(ip);

	error = xfs_init_security(inode, dir);
	if (unlikely(error))
		goto out_cleanup_inode;

	if (default_acl) {
		error = _ACL_INHERIT(inode, mode, default_acl);
		if (unlikely(error))
			goto out_cleanup_inode;
		_ACL_FREE(default_acl);
	}


	d_instantiate(dentry, inode);
	return -error;

 out_cleanup_inode:
	xfs_cleanup_inode(dir, inode, dentry);
 out_free_acl:
	if (default_acl)
		_ACL_FREE(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;

	atomic_inc(&inode->i_count);
	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->fs->umask : S_IRWXUGO);
	xfs_dentry_to_name(&name, dentry);

	error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip, NULL);
	if (unlikely(error))
		goto out;

	inode = VFS_I(cip);

	error = xfs_init_security(inode, dir);
	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);
}

#ifdef CONFIG_XFS_POSIX_ACL
STATIC int
xfs_check_acl(
	struct inode		*inode,
	int			mask)
{
	struct xfs_inode	*ip = XFS_I(inode);
	int			error;

	xfs_itrace_entry(ip);

	if (XFS_IFORK_Q(ip)) {
		error = xfs_acl_iaccess(ip, mask, NULL);
		if (error != -1)
			return -error;
	}

	return -EAGAIN;
}

STATIC int
xfs_vn_permission(
	struct inode		*inode,
	int			mask)
{
	return generic_permission(inode, mask, xfs_check_acl);
}
#else
#define xfs_vn_permission NULL
#endif

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;

	xfs_itrace_entry(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.tv_sec = ip->i_d.di_mtime.t_sec;
	stat->mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
	stat->ctime.tv_sec = ip->i_d.di_ctime.t_sec;
	stat->ctime.tv_nsec = ip->i_d.di_ctime.t_nsec;
	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;
}

STATIC int
xfs_vn_setattr(
	struct dentry	*dentry,
	struct iattr	*iattr)
{
	return -xfs_setattr(XFS_I(dentry->d_inode), iattr, 0);
}

/*
 * block_truncate_page can return an error, but we can't propagate it
 * at all here. Leave a complaint + stack trace in the syslog because
 * this could be bad. If it is bad, we need to propagate the error further.
 */
STATIC void
xfs_vn_truncate(
	struct inode	*inode)
{
	int	error;
	error = block_truncate_page(inode->i_mapping, inode->i_size,
							xfs_get_blocks);
	WARN_ON(error);
}

STATIC long
xfs_vn_fallocate(
	struct inode	*inode,
	int		mode,
	loff_t		offset,
	loff_t		len)
{
	long		error;
	loff_t		new_size = 0;
	xfs_flock64_t	bf;
	xfs_inode_t	*ip = XFS_I(inode);

	/* preallocation on directories not yet supported */
	error = -ENODEV;
	if (S_ISDIR(inode->i_mode))
		goto out_error;

	bf.l_whence = 0;
	bf.l_start = offset;
	bf.l_len = len;

	xfs_ilock(ip, XFS_IOLOCK_EXCL);
	error = xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
				      0, XFS_ATTR_NOLOCK);
	if (!error && !(mode & FALLOC_FL_KEEP_SIZE) &&
	    offset + len > i_size_read(inode))
		new_size = offset + len;

	/* Change file size if needed */
	if (new_size) {
		struct iattr iattr;

		iattr.ia_valid = ATTR_SIZE;
		iattr.ia_size = new_size;
		error = xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
	}

	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
out_error:
	return error;
}

#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);

	/* our formatter will tell xfs_getbmap when to stop. */
	bm.bmv_count = MAXEXTNUM;
	bm.bmv_iflags = BMV_IF_PREALLOC;
	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 = {
	.permission		= xfs_vn_permission,
	.truncate		= xfs_vn_truncate,
	.getattr		= xfs_vn_getattr,
	.setattr		= xfs_vn_setattr,
	.setxattr		= generic_setxattr,
	.getxattr		= generic_getxattr,
	.removexattr		= generic_removexattr,
	.listxattr		= xfs_vn_listxattr,
	.fallocate		= xfs_vn_fallocate,
	.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,
	.permission		= xfs_vn_permission,
	.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,
	.permission		= xfs_vn_permission,
	.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,
	.permission		= xfs_vn_permission,
	.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|I_LOCK;
	inode_add_to_lists(ip->i_mount->m_super, inode);

	inode->i_mode	= ip->i_d.di_mode;
	inode->i_nlink	= 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;
	}

	xfs_iflags_clear(ip, XFS_INEW);
	barrier();

	unlock_new_inode(inode);
}