aboutsummaryrefslogtreecommitdiff
path: root/fs/stat.c
blob: f43afe0081fed2237b5eed6c5a2a50cee9d75402 (plain)
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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/stat.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/blkdev.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/cred.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>
#include <linux/compat.h>
#include <linux/iversion.h>

#include <linux/uaccess.h>
#include <asm/unistd.h>

#include "internal.h"
#include "mount.h"

/**
 * generic_fillattr - Fill in the basic attributes from the inode struct
 * @mnt_userns:	user namespace of the mount the inode was found from
 * @inode:	Inode to use as the source
 * @stat:	Where to fill in the attributes
 *
 * Fill in the basic attributes in the kstat structure from data that's to be
 * found on the VFS inode structure.  This is the default if no getattr inode
 * operation is supplied.
 *
 * If the inode has been found through an idmapped mount the user namespace of
 * the vfsmount must be passed through @mnt_userns. This function will then
 * take care to map the inode according to @mnt_userns before filling in the
 * uid and gid filds. On non-idmapped mounts or if permission checking is to be
 * performed on the raw inode simply passs init_user_ns.
 */
void generic_fillattr(struct user_namespace *mnt_userns, struct inode *inode,
		      struct kstat *stat)
{
	vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
	vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode);

	stat->dev = inode->i_sb->s_dev;
	stat->ino = inode->i_ino;
	stat->mode = inode->i_mode;
	stat->nlink = inode->i_nlink;
	stat->uid = vfsuid_into_kuid(vfsuid);
	stat->gid = vfsgid_into_kgid(vfsgid);
	stat->rdev = inode->i_rdev;
	stat->size = i_size_read(inode);
	stat->atime = inode->i_atime;
	stat->mtime = inode->i_mtime;
	stat->ctime = inode->i_ctime;
	stat->blksize = i_blocksize(inode);
	stat->blocks = inode->i_blocks;
}
EXPORT_SYMBOL(generic_fillattr);

/**
 * generic_fill_statx_attr - Fill in the statx attributes from the inode flags
 * @inode:	Inode to use as the source
 * @stat:	Where to fill in the attribute flags
 *
 * Fill in the STATX_ATTR_* flags in the kstat structure for properties of the
 * inode that are published on i_flags and enforced by the VFS.
 */
void generic_fill_statx_attr(struct inode *inode, struct kstat *stat)
{
	if (inode->i_flags & S_IMMUTABLE)
		stat->attributes |= STATX_ATTR_IMMUTABLE;
	if (inode->i_flags & S_APPEND)
		stat->attributes |= STATX_ATTR_APPEND;
	stat->attributes_mask |= KSTAT_ATTR_VFS_FLAGS;
}
EXPORT_SYMBOL(generic_fill_statx_attr);

/**
 * vfs_getattr_nosec - getattr without security checks
 * @path: file to get attributes from
 * @stat: structure to return attributes in
 * @request_mask: STATX_xxx flags indicating what the caller wants
 * @query_flags: Query mode (AT_STATX_SYNC_TYPE)
 *
 * Get attributes without calling security_inode_getattr.
 *
 * Currently the only caller other than vfs_getattr is internal to the
 * filehandle lookup code, which uses only the inode number and returns no
 * attributes to any user.  Any other code probably wants vfs_getattr.
 */
int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
		      u32 request_mask, unsigned int query_flags)
{
	struct user_namespace *mnt_userns;
	struct inode *inode = d_backing_inode(path->dentry);

	memset(stat, 0, sizeof(*stat));
	stat->result_mask |= STATX_BASIC_STATS;
	query_flags &= AT_STATX_SYNC_TYPE;

	/* allow the fs to override these if it really wants to */
	/* SB_NOATIME means filesystem supplies dummy atime value */
	if (inode->i_sb->s_flags & SB_NOATIME)
		stat->result_mask &= ~STATX_ATIME;

	/*
	 * Note: If you add another clause to set an attribute flag, please
	 * update attributes_mask below.
	 */
	if (IS_AUTOMOUNT(inode))
		stat->attributes |= STATX_ATTR_AUTOMOUNT;

	if (IS_DAX(inode))
		stat->attributes |= STATX_ATTR_DAX;

	stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT |
				  STATX_ATTR_DAX);

	if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) {
		stat->result_mask |= STATX_CHANGE_COOKIE;
		stat->change_cookie = inode_query_iversion(inode);
	}

	mnt_userns = mnt_user_ns(path->mnt);
	if (inode->i_op->getattr)
		return inode->i_op->getattr(mnt_userns, path, stat,
					    request_mask, query_flags);

	generic_fillattr(mnt_userns, inode, stat);
	return 0;
}
EXPORT_SYMBOL(vfs_getattr_nosec);

/*
 * vfs_getattr - Get the enhanced basic attributes of a file
 * @path: The file of interest
 * @stat: Where to return the statistics
 * @request_mask: STATX_xxx flags indicating what the caller wants
 * @query_flags: Query mode (AT_STATX_SYNC_TYPE)
 *
 * Ask the filesystem for a file's attributes.  The caller must indicate in
 * request_mask and query_flags to indicate what they want.
 *
 * If the file is remote, the filesystem can be forced to update the attributes
 * from the backing store by passing AT_STATX_FORCE_SYNC in query_flags or can
 * suppress the update by passing AT_STATX_DONT_SYNC.
 *
 * Bits must have been set in request_mask to indicate which attributes the
 * caller wants retrieving.  Any such attribute not requested may be returned
 * anyway, but the value may be approximate, and, if remote, may not have been
 * synchronised with the server.
 *
 * 0 will be returned on success, and a -ve error code if unsuccessful.
 */
int vfs_getattr(const struct path *path, struct kstat *stat,
		u32 request_mask, unsigned int query_flags)
{
	int retval;

	retval = security_inode_getattr(path);
	if (retval)
		return retval;
	return vfs_getattr_nosec(path, stat, request_mask, query_flags);
}
EXPORT_SYMBOL(vfs_getattr);

/**
 * vfs_fstat - Get the basic attributes by file descriptor
 * @fd: The file descriptor referring to the file of interest
 * @stat: The result structure to fill in.
 *
 * This function is a wrapper around vfs_getattr().  The main difference is
 * that it uses a file descriptor to determine the file location.
 *
 * 0 will be returned on success, and a -ve error code if unsuccessful.
 */
int vfs_fstat(int fd, struct kstat *stat)
{
	struct fd f;
	int error;

	f = fdget_raw(fd);
	if (!f.file)
		return -EBADF;
	error = vfs_getattr(&f.file->f_path, stat, STATX_BASIC_STATS, 0);
	fdput(f);
	return error;
}

int getname_statx_lookup_flags(int flags)
{
	int lookup_flags = 0;

	if (!(flags & AT_SYMLINK_NOFOLLOW))
		lookup_flags |= LOOKUP_FOLLOW;
	if (!(flags & AT_NO_AUTOMOUNT))
		lookup_flags |= LOOKUP_AUTOMOUNT;
	if (flags & AT_EMPTY_PATH)
		lookup_flags |= LOOKUP_EMPTY;

	return lookup_flags;
}

/**
 * vfs_statx - Get basic and extra attributes by filename
 * @dfd: A file descriptor representing the base dir for a relative filename
 * @filename: The name of the file of interest
 * @flags: Flags to control the query
 * @stat: The result structure to fill in.
 * @request_mask: STATX_xxx flags indicating what the caller wants
 *
 * This function is a wrapper around vfs_getattr().  The main difference is
 * that it uses a filename and base directory to determine the file location.
 * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink
 * at the given name from being referenced.
 *
 * 0 will be returned on success, and a -ve error code if unsuccessful.
 */
static int vfs_statx(int dfd, struct filename *filename, int flags,
	      struct kstat *stat, u32 request_mask)
{
	struct path path;
	unsigned int lookup_flags = getname_statx_lookup_flags(flags);
	int error;

	if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH |
		      AT_STATX_SYNC_TYPE))
		return -EINVAL;

retry:
	error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
	if (error)
		goto out;

	error = vfs_getattr(&path, stat, request_mask, flags);

	stat->mnt_id = real_mount(path.mnt)->mnt_id;
	stat->result_mask |= STATX_MNT_ID;

	if (path.mnt->mnt_root == path.dentry)
		stat->attributes |= STATX_ATTR_MOUNT_ROOT;
	stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;

	/* Handle STATX_DIOALIGN for block devices. */
	if (request_mask & STATX_DIOALIGN) {
		struct inode *inode = d_backing_inode(path.dentry);

		if (S_ISBLK(inode->i_mode))
			bdev_statx_dioalign(inode, stat);
	}

	path_put(&path);
	if (retry_estale(error, lookup_flags)) {
		lookup_flags |= LOOKUP_REVAL;
		goto retry;
	}
out:
	return error;
}

int vfs_fstatat(int dfd, const char __user *filename,
			      struct kstat *stat, int flags)
{
	int ret;
	int statx_flags = flags | AT_NO_AUTOMOUNT;
	struct filename *name;

	name = getname_flags(filename, getname_statx_lookup_flags(statx_flags), NULL);
	ret = vfs_statx(dfd, name, statx_flags, stat, STATX_BASIC_STATS);
	putname(name);

	return ret;
}

#ifdef __ARCH_WANT_OLD_STAT

/*
 * For backward compatibility?  Maybe this should be moved
 * into arch/i386 instead?
 */
static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * statbuf)
{
	static int warncount = 5;
	struct __old_kernel_stat tmp;

	if (warncount > 0) {
		warncount--;
		printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n",
			current->comm);
	} else if (warncount < 0) {
		/* it's laughable, but... */
		warncount = 0;
	}

	memset(&tmp, 0, sizeof(struct __old_kernel_stat));
	tmp.st_dev = old_encode_dev(stat->dev);
	tmp.st_ino = stat->ino;
	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
		return -EOVERFLOW;
	tmp.st_mode = stat->mode;
	tmp.st_nlink = stat->nlink;
	if (tmp.st_nlink != stat->nlink)
		return -EOVERFLOW;
	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
	tmp.st_rdev = old_encode_dev(stat->rdev);
#if BITS_PER_LONG == 32
	if (stat->size > MAX_NON_LFS)
		return -EOVERFLOW;
#endif
	tmp.st_size = stat->size;
	tmp.st_atime = stat->atime.tv_sec;
	tmp.st_mtime = stat->mtime.tv_sec;
	tmp.st_ctime = stat->ctime.tv_sec;
	return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}

SYSCALL_DEFINE2(stat, const char __user *, filename,
		struct __old_kernel_stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_stat(filename, &stat);
	if (error)
		return error;

	return cp_old_stat(&stat, statbuf);
}

SYSCALL_DEFINE2(lstat, const char __user *, filename,
		struct __old_kernel_stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_lstat(filename, &stat);
	if (error)
		return error;

	return cp_old_stat(&stat, statbuf);
}

SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_fstat(fd, &stat);

	if (!error)
		error = cp_old_stat(&stat, statbuf);

	return error;
}

#endif /* __ARCH_WANT_OLD_STAT */

#ifdef __ARCH_WANT_NEW_STAT

#if BITS_PER_LONG == 32
#  define choose_32_64(a,b) a
#else
#  define choose_32_64(a,b) b
#endif

#ifndef INIT_STRUCT_STAT_PADDING
#  define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st))
#endif

static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
{
	struct stat tmp;

	if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev))
		return -EOVERFLOW;
	if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev))
		return -EOVERFLOW;
#if BITS_PER_LONG == 32
	if (stat->size > MAX_NON_LFS)
		return -EOVERFLOW;
#endif

	INIT_STRUCT_STAT_PADDING(tmp);
	tmp.st_dev = new_encode_dev(stat->dev);
	tmp.st_ino = stat->ino;
	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
		return -EOVERFLOW;
	tmp.st_mode = stat->mode;
	tmp.st_nlink = stat->nlink;
	if (tmp.st_nlink != stat->nlink)
		return -EOVERFLOW;
	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
	tmp.st_rdev = new_encode_dev(stat->rdev);
	tmp.st_size = stat->size;
	tmp.st_atime = stat->atime.tv_sec;
	tmp.st_mtime = stat->mtime.tv_sec;
	tmp.st_ctime = stat->ctime.tv_sec;
#ifdef STAT_HAVE_NSEC
	tmp.st_atime_nsec = stat->atime.tv_nsec;
	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
#endif
	tmp.st_blocks = stat->blocks;
	tmp.st_blksize = stat->blksize;
	return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}

SYSCALL_DEFINE2(newstat, const char __user *, filename,
		struct stat __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_stat(filename, &stat);

	if (error)
		return error;
	return cp_new_stat(&stat, statbuf);
}

SYSCALL_DEFINE2(newlstat, const char __user *, filename,
		struct stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_lstat(filename, &stat);
	if (error)
		return error;

	return cp_new_stat(&stat, statbuf);
}

#if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT)
SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename,
		struct stat __user *, statbuf, int, flag)
{
	struct kstat stat;
	int error;

	error = vfs_fstatat(dfd, filename, &stat, flag);
	if (error)
		return error;
	return cp_new_stat(&stat, statbuf);
}
#endif

SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_fstat(fd, &stat);

	if (!error)
		error = cp_new_stat(&stat, statbuf);

	return error;
}
#endif

static int do_readlinkat(int dfd, const char __user *pathname,
			 char __user *buf, int bufsiz)
{
	struct path path;
	int error;
	int empty = 0;
	unsigned int lookup_flags = LOOKUP_EMPTY;

	if (bufsiz <= 0)
		return -EINVAL;

retry:
	error = user_path_at_empty(dfd, pathname, lookup_flags, &path, &empty);
	if (!error) {
		struct inode *inode = d_backing_inode(path.dentry);

		error = empty ? -ENOENT : -EINVAL;
		/*
		 * AFS mountpoints allow readlink(2) but are not symlinks
		 */
		if (d_is_symlink(path.dentry) || inode->i_op->readlink) {
			error = security_inode_readlink(path.dentry);
			if (!error) {
				touch_atime(&path);
				error = vfs_readlink(path.dentry, buf, bufsiz);
			}
		}
		path_put(&path);
		if (retry_estale(error, lookup_flags)) {
			lookup_flags |= LOOKUP_REVAL;
			goto retry;
		}
	}
	return error;
}

SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
		char __user *, buf, int, bufsiz)
{
	return do_readlinkat(dfd, pathname, buf, bufsiz);
}

SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf,
		int, bufsiz)
{
	return do_readlinkat(AT_FDCWD, path, buf, bufsiz);
}


/* ---------- LFS-64 ----------- */
#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64)

#ifndef INIT_STRUCT_STAT64_PADDING
#  define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st))
#endif

static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf)
{
	struct stat64 tmp;

	INIT_STRUCT_STAT64_PADDING(tmp);
#ifdef CONFIG_MIPS
	/* mips has weird padding, so we don't get 64 bits there */
	tmp.st_dev = new_encode_dev(stat->dev);
	tmp.st_rdev = new_encode_dev(stat->rdev);
#else
	tmp.st_dev = huge_encode_dev(stat->dev);
	tmp.st_rdev = huge_encode_dev(stat->rdev);
#endif
	tmp.st_ino = stat->ino;
	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
		return -EOVERFLOW;
#ifdef STAT64_HAS_BROKEN_ST_INO
	tmp.__st_ino = stat->ino;
#endif
	tmp.st_mode = stat->mode;
	tmp.st_nlink = stat->nlink;
	tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid);
	tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid);
	tmp.st_atime = stat->atime.tv_sec;
	tmp.st_atime_nsec = stat->atime.tv_nsec;
	tmp.st_mtime = stat->mtime.tv_sec;
	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
	tmp.st_ctime = stat->ctime.tv_sec;
	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
	tmp.st_size = stat->size;
	tmp.st_blocks = stat->blocks;
	tmp.st_blksize = stat->blksize;
	return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}

SYSCALL_DEFINE2(stat64, const char __user *, filename,
		struct stat64 __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_stat(filename, &stat);

	if (!error)
		error = cp_new_stat64(&stat, statbuf);

	return error;
}

SYSCALL_DEFINE2(lstat64, const char __user *, filename,
		struct stat64 __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_lstat(filename, &stat);

	if (!error)
		error = cp_new_stat64(&stat, statbuf);

	return error;
}

SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_fstat(fd, &stat);

	if (!error)
		error = cp_new_stat64(&stat, statbuf);

	return error;
}

SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
		struct stat64 __user *, statbuf, int, flag)
{
	struct kstat stat;
	int error;

	error = vfs_fstatat(dfd, filename, &stat, flag);
	if (error)
		return error;
	return cp_new_stat64(&stat, statbuf);
}
#endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */

static noinline_for_stack int
cp_statx(const struct kstat *stat, struct statx __user *buffer)
{
	struct statx tmp;

	memset(&tmp, 0, sizeof(tmp));

	/* STATX_CHANGE_COOKIE is kernel-only for now */
	tmp.stx_mask = stat->result_mask & ~STATX_CHANGE_COOKIE;
	tmp.stx_blksize = stat->blksize;
	/* STATX_ATTR_CHANGE_MONOTONIC is kernel-only for now */
	tmp.stx_attributes = stat->attributes & ~STATX_ATTR_CHANGE_MONOTONIC;
	tmp.stx_nlink = stat->nlink;
	tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid);
	tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid);
	tmp.stx_mode = stat->mode;
	tmp.stx_ino = stat->ino;
	tmp.stx_size = stat->size;
	tmp.stx_blocks = stat->blocks;
	tmp.stx_attributes_mask = stat->attributes_mask;
	tmp.stx_atime.tv_sec = stat->atime.tv_sec;
	tmp.stx_atime.tv_nsec = stat->atime.tv_nsec;
	tmp.stx_btime.tv_sec = stat->btime.tv_sec;
	tmp.stx_btime.tv_nsec = stat->btime.tv_nsec;
	tmp.stx_ctime.tv_sec = stat->ctime.tv_sec;
	tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec;
	tmp.stx_mtime.tv_sec = stat->mtime.tv_sec;
	tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec;
	tmp.stx_rdev_major = MAJOR(stat->rdev);
	tmp.stx_rdev_minor = MINOR(stat->rdev);
	tmp.stx_dev_major = MAJOR(stat->dev);
	tmp.stx_dev_minor = MINOR(stat->dev);
	tmp.stx_mnt_id = stat->mnt_id;
	tmp.stx_dio_mem_align = stat->dio_mem_align;
	tmp.stx_dio_offset_align = stat->dio_offset_align;

	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
}

int do_statx(int dfd, struct filename *filename, unsigned int flags,
	     unsigned int mask, struct statx __user *buffer)
{
	struct kstat stat;
	int error;

	if (mask & STATX__RESERVED)
		return -EINVAL;
	if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
		return -EINVAL;

	/* STATX_CHANGE_COOKIE is kernel-only for now. Ignore requests
	 * from userland.
	 */
	mask &= ~STATX_CHANGE_COOKIE;

	error = vfs_statx(dfd, filename, flags, &stat, mask);
	if (error)
		return error;

	return cp_statx(&stat, buffer);
}

/**
 * sys_statx - System call to get enhanced stats
 * @dfd: Base directory to pathwalk from *or* fd to stat.
 * @filename: File to stat or "" with AT_EMPTY_PATH
 * @flags: AT_* flags to control pathwalk.
 * @mask: Parts of statx struct actually required.
 * @buffer: Result buffer.
 *
 * Note that fstat() can be emulated by setting dfd to the fd of interest,
 * supplying "" as the filename and setting AT_EMPTY_PATH in the flags.
 */
SYSCALL_DEFINE5(statx,
		int, dfd, const char __user *, filename, unsigned, flags,
		unsigned int, mask,
		struct statx __user *, buffer)
{
	int ret;
	struct filename *name;

	name = getname_flags(filename, getname_statx_lookup_flags(flags), NULL);
	ret = do_statx(dfd, name, flags, mask, buffer);
	putname(name);

	return ret;
}

#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_STAT)
static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
{
	struct compat_stat tmp;

	if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev))
		return -EOVERFLOW;
	if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev))
		return -EOVERFLOW;

	memset(&tmp, 0, sizeof(tmp));
	tmp.st_dev = new_encode_dev(stat->dev);
	tmp.st_ino = stat->ino;
	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
		return -EOVERFLOW;
	tmp.st_mode = stat->mode;
	tmp.st_nlink = stat->nlink;
	if (tmp.st_nlink != stat->nlink)
		return -EOVERFLOW;
	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
	tmp.st_rdev = new_encode_dev(stat->rdev);
	if ((u64) stat->size > MAX_NON_LFS)
		return -EOVERFLOW;
	tmp.st_size = stat->size;
	tmp.st_atime = stat->atime.tv_sec;
	tmp.st_atime_nsec = stat->atime.tv_nsec;
	tmp.st_mtime = stat->mtime.tv_sec;
	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
	tmp.st_ctime = stat->ctime.tv_sec;
	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
	tmp.st_blocks = stat->blocks;
	tmp.st_blksize = stat->blksize;
	return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
}

COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename,
		       struct compat_stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_stat(filename, &stat);
	if (error)
		return error;
	return cp_compat_stat(&stat, statbuf);
}

COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename,
		       struct compat_stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_lstat(filename, &stat);
	if (error)
		return error;
	return cp_compat_stat(&stat, statbuf);
}

#ifndef __ARCH_WANT_STAT64
COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd,
		       const char __user *, filename,
		       struct compat_stat __user *, statbuf, int, flag)
{
	struct kstat stat;
	int error;

	error = vfs_fstatat(dfd, filename, &stat, flag);
	if (error)
		return error;
	return cp_compat_stat(&stat, statbuf);
}
#endif

COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd,
		       struct compat_stat __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_fstat(fd, &stat);

	if (!error)
		error = cp_compat_stat(&stat, statbuf);
	return error;
}
#endif

/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
void __inode_add_bytes(struct inode *inode, loff_t bytes)
{
	inode->i_blocks += bytes >> 9;
	bytes &= 511;
	inode->i_bytes += bytes;
	if (inode->i_bytes >= 512) {
		inode->i_blocks++;
		inode->i_bytes -= 512;
	}
}
EXPORT_SYMBOL(__inode_add_bytes);

void inode_add_bytes(struct inode *inode, loff_t bytes)
{
	spin_lock(&inode->i_lock);
	__inode_add_bytes(inode, bytes);
	spin_unlock(&inode->i_lock);
}

EXPORT_SYMBOL(inode_add_bytes);

void __inode_sub_bytes(struct inode *inode, loff_t bytes)
{
	inode->i_blocks -= bytes >> 9;
	bytes &= 511;
	if (inode->i_bytes < bytes) {
		inode->i_blocks--;
		inode->i_bytes += 512;
	}
	inode->i_bytes -= bytes;
}

EXPORT_SYMBOL(__inode_sub_bytes);

void inode_sub_bytes(struct inode *inode, loff_t bytes)
{
	spin_lock(&inode->i_lock);
	__inode_sub_bytes(inode, bytes);
	spin_unlock(&inode->i_lock);
}

EXPORT_SYMBOL(inode_sub_bytes);

loff_t inode_get_bytes(struct inode *inode)
{
	loff_t ret;

	spin_lock(&inode->i_lock);
	ret = __inode_get_bytes(inode);
	spin_unlock(&inode->i_lock);
	return ret;
}

EXPORT_SYMBOL(inode_get_bytes);

void inode_set_bytes(struct inode *inode, loff_t bytes)
{
	/* Caller is here responsible for sufficient locking
	 * (ie. inode->i_lock) */
	inode->i_blocks = bytes >> 9;
	inode->i_bytes = bytes & 511;
}

EXPORT_SYMBOL(inode_set_bytes);