xfs_iops.c 29.2 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
/*
2
3
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
Linus Torvalds's avatar
Linus Torvalds committed
4
 *
5
6
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
Linus Torvalds's avatar
Linus Torvalds committed
7
8
 * published by the Free Software Foundation.
 *
9
10
11
12
 * 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.
Linus Torvalds's avatar
Linus Torvalds committed
13
 *
14
15
16
 * 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
Linus Torvalds's avatar
Linus Torvalds committed
17
18
19
 */
#include "xfs.h"
#include "xfs_fs.h"
20
#include "xfs_acl.h"
21
#include "xfs_bit.h"
Linus Torvalds's avatar
Linus Torvalds committed
22
#include "xfs_log.h"
23
#include "xfs_inum.h"
Linus Torvalds's avatar
Linus Torvalds committed
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
#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"
41
#include "xfs_vnodeops.h"
Christoph Hellwig's avatar
Christoph Hellwig committed
42
#include "xfs_inode_item.h"
Christoph Hellwig's avatar
Christoph Hellwig committed
43
#include "xfs_trace.h"
Linus Torvalds's avatar
Linus Torvalds committed
44

45
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
46
47
#include <linux/xattr.h>
#include <linux/namei.h>
48
#include <linux/posix_acl.h>
49
#include <linux/security.h>
Eric Sandeen's avatar
Eric Sandeen committed
50
#include <linux/fiemap.h>
51
#include <linux/slab.h>
Linus Torvalds's avatar
Linus Torvalds committed
52

53
/*
54
55
56
 * Bring the timestamps in the XFS inode uptodate.
 *
 * Used before writing the inode to disk.
57
58
 */
void
59
xfs_synchronize_times(
60
61
	xfs_inode_t	*ip)
{
62
	struct inode	*inode = VFS_I(ip);
63

64
65
66
67
68
69
	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;
70
71
}

72
/*
73
 * If the linux inode is valid, mark it dirty.
Lucas De Marchi's avatar
Lucas De Marchi committed
74
 * Used when committing a dirty inode into a transaction so that
75
76
77
78
79
80
 * the inode will get written back by the linux code
 */
void
xfs_mark_inode_dirty_sync(
	xfs_inode_t	*ip)
{
81
	struct inode	*inode = VFS_I(ip);
82

83
	if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
84
		mark_inode_dirty_sync(inode);
85
86
}

87
88
89
90
91
92
void
xfs_mark_inode_dirty(
	xfs_inode_t	*ip)
{
	struct inode	*inode = VFS_I(ip);

93
	if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
94
95
96
		mark_inode_dirty(inode);
}

97
98
99
100
101
102
103
/*
 * 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
104
xfs_init_security(
105
	struct inode	*inode,
106
107
	struct inode	*dir,
	const struct qstr *qstr)
108
{
109
	struct xfs_inode *ip = XFS_I(inode);
110
111
	size_t		length;
	void		*value;
112
	unsigned char	*name;
113
114
	int		error;

115
	error = security_inode_init_security(inode, dir, qstr, (char **)&name,
116
					     &value, &length);
117
118
119
120
121
122
	if (error) {
		if (error == -EOPNOTSUPP)
			return 0;
		return -error;
	}

123
	error = xfs_attr_set(ip, name, value, length, ATTR_SECURE);
124
125
126
127
128
129

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

130
131
132
133
134
135
136
137
138
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;
}

139
STATIC void
140
xfs_cleanup_inode(
141
	struct inode	*dir,
142
	struct inode	*inode,
143
	struct dentry	*dentry)
144
{
145
	struct xfs_name	teardown;
146
147

	/* Oh, the horror.
148
	 * If we can't add the ACL or we fail in
149
	 * xfs_init_security we must back out.
150
151
	 * ENOSPC can hit here, among other things.
	 */
152
	xfs_dentry_to_name(&teardown, dentry);
153

154
	xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
155
	iput(inode);
156
157
}

Linus Torvalds's avatar
Linus Torvalds committed
158
STATIC int
159
xfs_vn_mknod(
Linus Torvalds's avatar
Linus Torvalds committed
160
161
162
163
164
	struct inode	*dir,
	struct dentry	*dentry,
	int		mode,
	dev_t		rdev)
{
Christoph Hellwig's avatar
Christoph Hellwig committed
165
	struct inode	*inode;
166
	struct xfs_inode *ip = NULL;
167
	struct posix_acl *default_acl = NULL;
168
	struct xfs_name	name;
Linus Torvalds's avatar
Linus Torvalds committed
169
170
171
172
173
174
	int		error;

	/*
	 * Irix uses Missed'em'V split, but doesn't want to see
	 * the upper 5 bits of (14bit) major.
	 */
175
176
177
178
179
180
181
	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;
	}
Linus Torvalds's avatar
Linus Torvalds committed
182

183
184
185
	if (IS_POSIXACL(dir)) {
		default_acl = xfs_get_acl(dir, ACL_TYPE_DEFAULT);
		if (IS_ERR(default_acl))
186
			return PTR_ERR(default_acl);
Linus Torvalds's avatar
Linus Torvalds committed
187

188
189
		if (!default_acl)
			mode &= ~current_umask();
190
	}
Linus Torvalds's avatar
Linus Torvalds committed
191

192
	xfs_dentry_to_name(&name, dentry);
Christoph Hellwig's avatar
Christoph Hellwig committed
193
	error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
Christoph Hellwig's avatar
Christoph Hellwig committed
194
195
	if (unlikely(error))
		goto out_free_acl;
196

197
	inode = VFS_I(ip);
198

199
	error = xfs_init_security(inode, dir, &dentry->d_name);
Christoph Hellwig's avatar
Christoph Hellwig committed
200
201
202
203
	if (unlikely(error))
		goto out_cleanup_inode;

	if (default_acl) {
204
		error = -xfs_inherit_acl(inode, default_acl);
Christoph Hellwig's avatar
Christoph Hellwig committed
205
206
		if (unlikely(error))
			goto out_cleanup_inode;
207
		posix_acl_release(default_acl);
Linus Torvalds's avatar
Linus Torvalds committed
208
209
210
	}


Christoph Hellwig's avatar
Christoph Hellwig committed
211
212
213
214
	d_instantiate(dentry, inode);
	return -error;

 out_cleanup_inode:
215
	xfs_cleanup_inode(dir, inode, dentry);
Christoph Hellwig's avatar
Christoph Hellwig committed
216
 out_free_acl:
217
	posix_acl_release(default_acl);
Linus Torvalds's avatar
Linus Torvalds committed
218
219
220
221
	return -error;
}

STATIC int
222
xfs_vn_create(
Linus Torvalds's avatar
Linus Torvalds committed
223
224
225
226
227
	struct inode	*dir,
	struct dentry	*dentry,
	int		mode,
	struct nameidata *nd)
{
228
	return xfs_vn_mknod(dir, dentry, mode, 0);
Linus Torvalds's avatar
Linus Torvalds committed
229
230
231
}

STATIC int
232
xfs_vn_mkdir(
Linus Torvalds's avatar
Linus Torvalds committed
233
234
235
236
	struct inode	*dir,
	struct dentry	*dentry,
	int		mode)
{
237
	return xfs_vn_mknod(dir, dentry, mode|S_IFDIR, 0);
Linus Torvalds's avatar
Linus Torvalds committed
238
239
240
}

STATIC struct dentry *
241
xfs_vn_lookup(
Linus Torvalds's avatar
Linus Torvalds committed
242
243
244
245
	struct inode	*dir,
	struct dentry	*dentry,
	struct nameidata *nd)
{
246
	struct xfs_inode *cip;
247
	struct xfs_name	name;
Linus Torvalds's avatar
Linus Torvalds committed
248
249
250
251
252
	int		error;

	if (dentry->d_name.len >= MAXNAMELEN)
		return ERR_PTR(-ENAMETOOLONG);

253
	xfs_dentry_to_name(&name, dentry);
254
	error = xfs_lookup(XFS_I(dir), &name, &cip, NULL);
255
	if (unlikely(error)) {
Linus Torvalds's avatar
Linus Torvalds committed
256
257
258
259
260
261
		if (unlikely(error != ENOENT))
			return ERR_PTR(-error);
		d_add(dentry, NULL);
		return NULL;
	}

262
	return d_splice_alias(VFS_I(cip), dentry);
Linus Torvalds's avatar
Linus Torvalds committed
263
264
}

265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
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);
285
286
287
288
289
		/*
		 * call d_add(dentry, NULL) here when d_drop_negative_children
		 * is called in xfs_vn_mknod (ie. allow negative dentries
		 * with CI filesystems).
		 */
290
291
292
293
294
		return NULL;
	}

	/* if exact match, just splice and exit */
	if (!ci_name.name)
295
		return d_splice_alias(VFS_I(ip), dentry);
296
297
298
299

	/* else case-insensitive match... */
	dname.name = ci_name.name;
	dname.len = ci_name.len;
300
	dentry = d_add_ci(dentry, VFS_I(ip), &dname);
301
302
303
304
	kmem_free(ci_name.name);
	return dentry;
}

Linus Torvalds's avatar
Linus Torvalds committed
305
STATIC int
306
xfs_vn_link(
Linus Torvalds's avatar
Linus Torvalds committed
307
308
309
310
	struct dentry	*old_dentry,
	struct inode	*dir,
	struct dentry	*dentry)
{
311
	struct inode	*inode = old_dentry->d_inode;
312
	struct xfs_name	name;
Linus Torvalds's avatar
Linus Torvalds committed
313
314
	int		error;

315
	xfs_dentry_to_name(&name, dentry);
Linus Torvalds's avatar
Linus Torvalds committed
316

317
	error = xfs_link(XFS_I(dir), XFS_I(inode), &name);
318
	if (unlikely(error))
319
320
		return -error;

Al Viro's avatar
Al Viro committed
321
	ihold(inode);
322
323
	d_instantiate(dentry, inode);
	return 0;
Linus Torvalds's avatar
Linus Torvalds committed
324
325
326
}

STATIC int
327
xfs_vn_unlink(
Linus Torvalds's avatar
Linus Torvalds committed
328
329
330
	struct inode	*dir,
	struct dentry	*dentry)
{
331
	struct xfs_name	name;
Linus Torvalds's avatar
Linus Torvalds committed
332
333
	int		error;

334
	xfs_dentry_to_name(&name, dentry);
Linus Torvalds's avatar
Linus Torvalds committed
335

336
337
338
339
340
341
342
343
344
345
346
347
	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;
Linus Torvalds's avatar
Linus Torvalds committed
348
349
350
}

STATIC int
351
xfs_vn_symlink(
Linus Torvalds's avatar
Linus Torvalds committed
352
353
354
355
	struct inode	*dir,
	struct dentry	*dentry,
	const char	*symname)
{
356
357
	struct inode	*inode;
	struct xfs_inode *cip = NULL;
358
	struct xfs_name	name;
Linus Torvalds's avatar
Linus Torvalds committed
359
	int		error;
360
	mode_t		mode;
Linus Torvalds's avatar
Linus Torvalds committed
361

362
	mode = S_IFLNK |
Al Viro's avatar
Al Viro committed
363
		(irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO);
364
	xfs_dentry_to_name(&name, dentry);
Linus Torvalds's avatar
Linus Torvalds committed
365

Christoph Hellwig's avatar
Christoph Hellwig committed
366
	error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip);
367
368
369
	if (unlikely(error))
		goto out;

370
	inode = VFS_I(cip);
371

372
	error = xfs_init_security(inode, dir, &dentry->d_name);
373
374
375
376
377
378
379
	if (unlikely(error))
		goto out_cleanup_inode;

	d_instantiate(dentry, inode);
	return 0;

 out_cleanup_inode:
380
	xfs_cleanup_inode(dir, inode, dentry);
381
 out:
Linus Torvalds's avatar
Linus Torvalds committed
382
383
384
385
	return -error;
}

STATIC int
386
xfs_vn_rename(
Linus Torvalds's avatar
Linus Torvalds committed
387
388
389
390
391
392
	struct inode	*odir,
	struct dentry	*odentry,
	struct inode	*ndir,
	struct dentry	*ndentry)
{
	struct inode	*new_inode = ndentry->d_inode;
393
394
	struct xfs_name	oname;
	struct xfs_name	nname;
Linus Torvalds's avatar
Linus Torvalds committed
395

396
397
398
	xfs_dentry_to_name(&oname, odentry);
	xfs_dentry_to_name(&nname, ndentry);

399
	return -xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode),
400
401
			   XFS_I(ndir), &nname, new_inode ?
			   			XFS_I(new_inode) : NULL);
Linus Torvalds's avatar
Linus Torvalds committed
402
403
404
405
406
407
408
}

/*
 * 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...
 */
409
STATIC void *
410
xfs_vn_follow_link(
Linus Torvalds's avatar
Linus Torvalds committed
411
412
413
414
	struct dentry		*dentry,
	struct nameidata	*nd)
{
	char			*link;
415
	int			error = -ENOMEM;
Linus Torvalds's avatar
Linus Torvalds committed
416

417
	link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
418
419
	if (!link)
		goto out_err;
Linus Torvalds's avatar
Linus Torvalds committed
420

421
	error = -xfs_readlink(XFS_I(dentry->d_inode), link);
422
423
	if (unlikely(error))
		goto out_kfree;
Linus Torvalds's avatar
Linus Torvalds committed
424
425

	nd_set_link(nd, link);
426
	return NULL;
427
428
429
430
431
432

 out_kfree:
	kfree(link);
 out_err:
	nd_set_link(nd, ERR_PTR(error));
	return NULL;
Linus Torvalds's avatar
Linus Torvalds committed
433
434
}

435
STATIC void
436
xfs_vn_put_link(
437
438
439
	struct dentry	*dentry,
	struct nameidata *nd,
	void		*p)
Linus Torvalds's avatar
Linus Torvalds committed
440
{
441
442
	char		*s = nd_get_link(nd);

Linus Torvalds's avatar
Linus Torvalds committed
443
444
445
446
447
	if (!IS_ERR(s))
		kfree(s);
}

STATIC int
448
xfs_vn_getattr(
449
450
451
	struct vfsmount		*mnt,
	struct dentry		*dentry,
	struct kstat		*stat)
Linus Torvalds's avatar
Linus Torvalds committed
452
{
453
454
455
456
	struct inode		*inode = dentry->d_inode;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;

457
	trace_xfs_getattr(ip);
458
459
460
461
462
463
464
465
466
467
468
469

	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;
470
471
	stat->mtime = inode->i_mtime;
	stat->ctime = inode->i_ctime;
472
473
474
475
476
477
478
479
480
481
482
483
	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:
484
		if (XFS_IS_REALTIME_INODE(ip)) {
485
486
487
488
489
490
491
492
493
494
495
			/*
			 * 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;
496
	}
497
498

	return 0;
Linus Torvalds's avatar
Linus Torvalds committed
499
500
}

Christoph Hellwig's avatar
Christoph Hellwig committed
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
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);

	/*
	 * 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) {
776
777
778
779
780
781
782
783
784
		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);
Christoph Hellwig's avatar
Christoph Hellwig committed
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
	}

	/*
	 * 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,
					XBF_ASYNC, FI_NONE);
		if (error)
			goto out_unlock;
	}

	/*
	 * Wait for all I/O to complete.
	 */
	xfs_ioend_wait(ip);

	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);

	/*
	 * 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)) {
		/*
		 * Signal a sync transaction unless we are truncating an
		 * already unlinked file on a wsync filesystem.
		 */
		error = 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 (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;
}

Linus Torvalds's avatar
Linus Torvalds committed
937
STATIC int
938
xfs_vn_setattr(
Linus Torvalds's avatar
Linus Torvalds committed
939
	struct dentry	*dentry,
940
	struct iattr	*iattr)
Linus Torvalds's avatar
Linus Torvalds committed
941
{
Christoph Hellwig's avatar
Christoph Hellwig committed
942
943
944
	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);
Linus Torvalds's avatar
Linus Torvalds committed
945
946
}

Eric Sandeen's avatar
Eric Sandeen committed
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
#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;
For faster browsing, not all history is shown. View entire blame