summaryrefslogtreecommitdiffstats
path: root/fs/overlayfs/inode.c
blob: c101ebbb7a7792efd9faaa1494c0233f7122e10f (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
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *
 * Copyright (C) 2011 Novell Inc.
 */

#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/ratelimit.h>
#include <linux/fiemap.h>
#include "overlayfs.h"


int ovl_setattr(struct dentry *dentry, struct iattr *attr)
{
	int err;
	bool full_copy_up = false;
	struct dentry *upperdentry;
	const struct cred *old_cred;

	err = setattr_prepare(dentry, attr);
	if (err)
		return err;

	err = ovl_want_write(dentry);
	if (err)
		goto out;

	if (attr->ia_valid & ATTR_SIZE) {
		struct inode *realinode = d_inode(ovl_dentry_real(dentry));

		err = -ETXTBSY;
		if (atomic_read(&realinode->i_writecount) < 0)
			goto out_drop_write;

		/* Truncate should trigger data copy up as well */
		full_copy_up = true;
	}

	if (!full_copy_up)
		err = ovl_copy_up(dentry);
	else
		err = ovl_copy_up_with_data(dentry);
	if (!err) {
		struct inode *winode = NULL;

		upperdentry = ovl_dentry_upper(dentry);

		if (attr->ia_valid & ATTR_SIZE) {
			winode = d_inode(upperdentry);
			err = get_write_access(winode);
			if (err)
				goto out_drop_write;
		}

		if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
			attr->ia_valid &= ~ATTR_MODE;

		/*
		 * We might have to translate ovl file into real file object
		 * once use cases emerge.  For now, simply don't let underlying
		 * filesystem rely on attr->ia_file
		 */
		attr->ia_valid &= ~ATTR_FILE;

		/*
		 * If open(O_TRUNC) is done, VFS calls ->setattr with ATTR_OPEN
		 * set.  Overlayfs does not pass O_TRUNC flag to underlying
		 * filesystem during open -> do not pass ATTR_OPEN.  This
		 * disables optimization in fuse which assumes open(O_TRUNC)
		 * already set file size to 0.  But we never passed O_TRUNC to
		 * fuse.  So by clearing ATTR_OPEN, fuse will be forced to send
		 * setattr request to server.
		 */
		attr->ia_valid &= ~ATTR_OPEN;

		inode_lock(upperdentry->d_inode);
		old_cred = ovl_override_creds(dentry->d_sb);
		err = notify_change(upperdentry, attr, NULL);
		revert_creds(old_cred);
		if (!err)
			ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
		inode_unlock(upperdentry->d_inode);

		if (winode)
			put_write_access(winode);
	}
out_drop_write:
	ovl_drop_write(dentry);
out:
	return err;
}

static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid)
{
	bool samefs = ovl_same_fs(dentry->d_sb);
	unsigned int xinobits = ovl_xino_bits(dentry->d_sb);
	unsigned int xinoshift = 64 - xinobits;

	if (samefs) {
		/*
		 * When all layers are on the same fs, all real inode
		 * number are unique, so we use the overlay st_dev,
		 * which is friendly to du -x.
		 */
		stat->dev = dentry->d_sb->s_dev;
		return 0;
	} else if (xinobits) {
		/*
		 * All inode numbers of underlying fs should not be using the
		 * high xinobits, so we use high xinobits to partition the
		 * overlay st_ino address space. The high bits holds the fsid
		 * (upper fsid is 0). The lowest xinobit is reserved for mapping
		 * the non-peresistent inode numbers range in case of overflow.
		 * This way all overlay inode numbers are unique and use the
		 * overlay st_dev.
		 */
		if (likely(!(stat->ino >> xinoshift))) {
			stat->ino |= ((u64)fsid) << (xinoshift + 1);
			stat->dev = dentry->d_sb->s_dev;
			return 0;
		} else if (ovl_xino_warn(dentry->d_sb)) {
			pr_warn_ratelimited("inode number too big (%pd2, ino=%llu, xinobits=%d)\n",
					    dentry, stat->ino, xinobits);
		}
	}

	/* The inode could not be mapped to a unified st_ino address space */
	if (S_ISDIR(dentry->d_inode->i_mode)) {
		/*
		 * Always use the overlay st_dev for directories, so 'find
		 * -xdev' will scan the entire overlay mount and won't cross the
		 * overlay mount boundaries.
		 *
		 * If not all layers are on the same fs the pair {real st_ino;
		 * overlay st_dev} is not unique, so use the non persistent
		 * overlay st_ino for directories.
		 */
		stat->dev = dentry->d_sb->s_dev;
		stat->ino = dentry->d_inode->i_ino;
	} else {
		/*
		 * For non-samefs setup, if we cannot map all layers st_ino
		 * to a unified address space, we need to make sure that st_dev
		 * is unique per underlying fs, so we use the unique anonymous
		 * bdev assigned to the underlying fs.
		 */
		stat->dev = OVL_FS(dentry->d_sb)->fs[fsid].pseudo_dev;
	}

	return 0;
}

int ovl_getattr(const struct path *path, struct kstat *stat,
		u32 request_mask, unsigned int flags)
{
	struct dentry *dentry = path->dentry;
	enum ovl_path_type type;
	struct path realpath;
	const struct cred *old_cred;
	bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
	int fsid = 0;
	int err;
	bool metacopy_blocks = false;

	metacopy_blocks = ovl_is_metacopy_dentry(dentry);

	type = ovl_path_real(dentry, &realpath);
	old_cred = ovl_override_creds(dentry->d_sb);
	err = vfs_getattr(&realpath, stat, request_mask, flags);
	if (err)
		goto out;

	/*
	 * For non-dir or same fs, we use st_ino of the copy up origin.
	 * This guaranties constant st_dev/st_ino across copy up.
	 * With xino feature and non-samefs, we use st_ino of the copy up
	 * origin masked with high bits that represent the layer id.
	 *
	 * If lower filesystem supports NFS file handles, this also guaranties
	 * persistent st_ino across mount cycle.
	 */
	if (!is_dir || ovl_same_dev(dentry->d_sb)) {
		if (!OVL_TYPE_UPPER(type)) {
			fsid = ovl_layer_lower(dentry)->fsid;
		} else if (OVL_TYPE_ORIGIN(type)) {
			struct kstat lowerstat;
			u32 lowermask = STATX_INO | STATX_BLOCKS |
					(!is_dir ? STATX_NLINK : 0);

			ovl_path_lower(dentry, &realpath);
			err = vfs_getattr(&realpath, &lowerstat,
					  lowermask, flags);
			if (err)
				goto out;

			/*
			 * Lower hardlinks may be broken on copy up to different
			 * upper files, so we cannot use the lower origin st_ino
			 * for those different files, even for the same fs case.
			 *
			 * Similarly, several redirected dirs can point to the
			 * same dir on a lower layer. With the "verify_lower"
			 * feature, we do not use the lower origin st_ino, if
			 * we haven't verified that this redirect is unique.
			 *
			 * With inodes index enabled, it is safe to use st_ino
			 * of an indexed origin. The index validates that the
			 * upper hardlink is not broken and that a redirected
			 * dir is the only redirect to that origin.
			 */
			if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) ||
			    (!ovl_verify_lower(dentry->d_sb) &&
			     (is_dir || lowerstat.nlink == 1))) {
				fsid = ovl_layer_lower(dentry)->fsid;
				stat->ino = lowerstat.ino;
			}

			/*
			 * If we are querying a metacopy dentry and lower
			 * dentry is data dentry, then use the blocks we
			 * queried just now. We don't have to do additional
			 * vfs_getattr(). If lower itself is metacopy, then
			 * additional vfs_getattr() is unavoidable.
			 */
			if (metacopy_blocks &&
			    realpath.dentry == ovl_dentry_lowerdata(dentry)) {
				stat->blocks = lowerstat.blocks;
				metacopy_blocks = false;
			}
		}

		if (metacopy_blocks) {
			/*
			 * If lower is not same as lowerdata or if there was
			 * no origin on upper, we can end up here.
			 */
			struct kstat lowerdatastat;
			u32 lowermask = STATX_BLOCKS;

			ovl_path_lowerdata(dentry, &realpath);
			err = vfs_getattr(&realpath, &lowerdatastat,
					  lowermask, flags);
			if (err)
				goto out;
			stat->blocks = lowerdatastat.blocks;
		}
	}

	err = ovl_map_dev_ino(dentry, stat, fsid);
	if (err)
		goto out;

	/*
	 * It's probably not worth it to count subdirs to get the
	 * correct link count.  nlink=1 seems to pacify 'find' and
	 * other utilities.
	 */
	if (is_dir && OVL_TYPE_MERGE(type))
		stat->nlink = 1;

	/*
	 * Return the overlay inode nlinks for indexed upper inodes.
	 * Overlay inode nlink counts the union of the upper hardlinks
	 * and non-covered lower hardlinks. It does not include the upper
	 * index hardlink.
	 */
	if (!is_dir && ovl_test_flag(OVL_INDEX, d_inode(dentry)))
		stat->nlink = dentry->d_inode->i_nlink;

out:
	revert_creds(old_cred);

	return err;
}

int ovl_permission(struct inode *inode, int mask)
{
	struct inode *upperinode = ovl_inode_upper(inode);
	struct inode *realinode = upperinode ?: ovl_inode_lower(inode);
	const struct cred *old_cred;
	int err;

	/* Careful in RCU walk mode */
	if (!realinode) {
		WARN_ON(!(mask & MAY_NOT_BLOCK));
		return -ECHILD;
	}

	/*
	 * Check overlay inode with the creds of task and underlying inode
	 * with creds of mounter
	 */
	err = generic_permission(&init_user_ns, inode, mask);
	if (err)
		return err;

	old_cred = ovl_override_creds(inode->i_sb);
	if (!upperinode &&
	    !special_file(realinode->i_mode) && mask & MAY_WRITE) {
		mask &= ~(MAY_WRITE | MAY_APPEND);
		/* Make sure mounter can read file for copy up later */
		mask |= MAY_READ;
	}
	err = inode_permission(&init_user_ns, realinode, mask);
	revert_creds(old_cred);

	return err;
}

static const char *ovl_get_link(struct dentry *dentry,
				struct inode *inode,
				struct delayed_call *done)
{
	const struct cred *old_cred;
	const char *p;

	if (!dentry)
		return ERR_PTR(-ECHILD);

	old_cred = ovl_override_creds(dentry->d_sb);
	p = vfs_get_link(ovl_dentry_real(dentry), done);
	revert_creds(old_cred);
	return p;
}

bool ovl_is_private_xattr(struct super_block *sb, const char *name)
{
	struct ovl_fs *ofs = sb->s_fs_info;

	if (ofs->config.userxattr)
		return strncmp(name, OVL_XATTR_USER_PREFIX,
			       sizeof(OVL_XATTR_USER_PREFIX) - 1) == 0;
	else
		return strncmp(name, OVL_XATTR_TRUSTED_PREFIX,
			       sizeof(OVL_XATTR_TRUSTED_PREFIX) - 1) == 0;
}

int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
		  const void *value, size_t size, int flags)
{
	int err;
	struct dentry *upperdentry = ovl_i_dentry_upper(inode);
	struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry);
	const struct cred *old_cred;

	err = ovl_want_write(dentry);
	if (err)
		goto out;

	if (!value && !upperdentry) {
		err = vfs_getxattr(realdentry, name, NULL, 0);
		if (err < 0)
			goto out_drop_write;
	}

	if (!upperdentry) {
		err = ovl_copy_up(dentry);
		if (err)
			goto out_drop_write;

		realdentry = ovl_dentry_upper(dentry);
	}

	old_cred = ovl_override_creds(dentry->d_sb);
	if (value)
		err = vfs_setxattr(realdentry, name, value, size, flags);
	else {
		WARN_ON(flags != XATTR_REPLACE);
		err = vfs_removexattr(realdentry, name);
	}
	revert_creds(old_cred);

	/* copy c/mtime */
	ovl_copyattr(d_inode(realdentry), inode);

out_drop_write:
	ovl_drop_write(dentry);
out:
	return err;
}

int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
		  void *value, size_t size)
{
	ssize_t res;
	const struct cred *old_cred;
	struct dentry *realdentry =
		ovl_i_dentry_upper(inode) ?: ovl_dentry_lower(dentry);

	old_cred = ovl_override_creds(dentry->d_sb);
	res = vfs_getxattr(realdentry, name, value, size);
	revert_creds(old_cred);
	return res;
}

static bool ovl_can_list(struct super_block *sb, const char *s)
{
	/* Never list private (.overlay) */
	if (ovl_is_private_xattr(sb, s))
		return false;

	/* List all non-trusted xatts */
	if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0)
		return true;

	/* list other trusted for superuser only */
	return ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN);
}

ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
{
	struct dentry *realdentry = ovl_dentry_real(dentry);
	ssize_t res;
	size_t len;
	char *s;
	const struct cred *old_cred;

	old_cred = ovl_override_creds(dentry->d_sb);
	res = vfs_listxattr(realdentry, list, size);
	revert_creds(old_cred);
	if (res <= 0 || size == 0)
		return res;

	/* filter out private xattrs */
	for (s = list, len = res; len;) {
		size_t slen = strnlen(s, len) + 1;

		/* underlying fs providing us with an broken xattr list? */
		if (WARN_ON(slen > len))
			return -EIO;

		len -= slen;
		if (!ovl_can_list(dentry->d_sb, s)) {
			res -= slen;
			memmove(s, s + slen, len);
		} else {
			s += slen;
		}
	}

	return res;
}

struct posix_acl *ovl_get_acl(struct inode *inode, int type)
{
	struct inode *realinode = ovl_inode_real(inode);
	const struct cred *old_cred;
	struct posix_acl *acl;

	if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
		return NULL;

	old_cred = ovl_override_creds(inode->i_sb);
	acl = get_acl(realinode, type);
	revert_creds(old_cred);

	return acl;
}

int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags)
{
	if (flags & S_ATIME) {
		struct ovl_fs *ofs = inode->i_sb->s_fs_info;
		struct path upperpath = {
			.mnt = ovl_upper_mnt(ofs),
			.dentry = ovl_upperdentry_dereference(OVL_I(inode)),
		};

		if (upperpath.dentry) {
			touch_atime(&upperpath);
			inode->i_atime = d_inode(upperpath.dentry)->i_atime;
		}
	}
	return 0;
}

static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		      u64 start, u64 len)
{
	int err;
	struct inode *realinode = ovl_inode_realdata(inode);
	const struct cred *old_cred;

	if (!realinode->i_op->fiemap)
		return -EOPNOTSUPP;

	old_cred = ovl_override_creds(inode->i_sb);
	err = realinode->i_op->fiemap(realinode, fieinfo, start, len);
	revert_creds(old_cred);

	return err;
}

static const struct inode_operations ovl_file_inode_operations = {
	.setattr	= ovl_setattr,
	.permission	= ovl_permission,
	.getattr	= ovl_getattr,
	.listxattr	= ovl_listxattr,
	.get_acl	= ovl_get_acl,
	.update_time	= ovl_update_time,
	.fiemap		= ovl_fiemap,
};

static const struct inode_operations ovl_symlink_inode_operations = {
	.setattr	= ovl_setattr,
	.get_link	= ovl_get_link,
	.getattr	= ovl_getattr,
	.listxattr	= ovl_listxattr,
	.update_time	= ovl_update_time,
};

static const struct inode_operations ovl_special_inode_operations = {
	.setattr	= ovl_setattr,
	.permission	= ovl_permission,
	.getattr	= ovl_getattr,
	.listxattr	= ovl_listxattr,
	.get_acl	= ovl_get_acl,
	.update_time	= ovl_update_time,
};

static const struct address_space_operations ovl_aops = {
	/* For O_DIRECT dentry_open() checks f_mapping->a_ops->direct_IO */
	.direct_IO		= noop_direct_IO,
};

/*
 * It is possible to stack overlayfs instance on top of another
 * overlayfs instance as lower layer. We need to annotate the
 * stackable i_mutex locks according to stack level of the super
 * block instance. An overlayfs instance can never be in stack
 * depth 0 (there is always a real fs below it).  An overlayfs
 * inode lock will use the lockdep annotaion ovl_i_mutex_key[depth].
 *
 * For example, here is a snip from /proc/lockdep_chains after
 * dir_iterate of nested overlayfs:
 *
 * [...] &ovl_i_mutex_dir_key[depth]   (stack_depth=2)
 * [...] &ovl_i_mutex_dir_key[depth]#2 (stack_depth=1)
 * [...] &type->i_mutex_dir_key        (stack_depth=0)
 *
 * Locking order w.r.t ovl_want_write() is important for nested overlayfs.
 *
 * This chain is valid:
 * - inode->i_rwsem			(inode_lock[2])
 * - upper_mnt->mnt_sb->s_writers	(ovl_want_write[0])
 * - OVL_I(inode)->lock			(ovl_inode_lock[2])
 * - OVL_I(lowerinode)->lock		(ovl_inode_lock[1])
 *
 * And this chain is valid:
 * - inode->i_rwsem			(inode_lock[2])
 * - OVL_I(inode)->lock			(ovl_inode_lock[2])
 * - lowerinode->i_rwsem		(inode_lock[1])
 * - OVL_I(lowerinode)->lock		(ovl_inode_lock[1])
 *
 * But lowerinode->i_rwsem SHOULD NOT be acquired while ovl_want_write() is
 * held, because it is in reverse order of the non-nested case using the same
 * upper fs:
 * - inode->i_rwsem			(inode_lock[1])
 * - upper_mnt->mnt_sb->s_writers	(ovl_want_write[0])
 * - OVL_I(inode)->lock			(ovl_inode_lock[1])
 */
#define OVL_MAX_NESTING FILESYSTEM_MAX_STACK_DEPTH

static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode)
{
#ifdef CONFIG_LOCKDEP
	static struct lock_class_key ovl_i_mutex_key[OVL_MAX_NESTING];
	static struct lock_class_key ovl_i_mutex_dir_key[OVL_MAX_NESTING];
	static struct lock_class_key ovl_i_lock_key[OVL_MAX_NESTING];

	int depth = inode->i_sb->s_stack_depth - 1;

	if (WARN_ON_ONCE(depth < 0 || depth >= OVL_MAX_NESTING))
		depth = 0;

	if (S_ISDIR(inode->i_mode))
		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_dir_key[depth]);
	else
		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_key[depth]);

	lockdep_set_class(&OVL_I(inode)->lock, &ovl_i_lock_key[depth]);
#endif
}

static void ovl_next_ino(struct inode *inode)
{
	struct ovl_fs *ofs = inode->i_sb->s_fs_info;

	inode->i_ino = atomic_long_inc_return(&ofs->last_ino);
	if (unlikely(!inode->i_ino))
		inode->i_ino = atomic_long_inc_return(&ofs->last_ino);
}

static void ovl_map_ino(struct inode *inode, unsigned long ino, int fsid)
{
	int xinobits = ovl_xino_bits(inode->i_sb);
	unsigned int xinoshift = 64 - xinobits;

	/*
	 * When d_ino is consistent with st_ino (samefs or i_ino has enough
	 * bits to encode layer), set the same value used for st_ino to i_ino,
	 * so inode number exposed via /proc/locks and a like will be
	 * consistent with d_ino and st_ino values. An i_ino value inconsistent
	 * with d_ino also causes nfsd readdirplus to fail.
	 */
	inode->i_ino = ino;
	if (ovl_same_fs(inode->i_sb)) {
		return;
	} else if (xinobits && likely(!(ino >> xinoshift))) {
		inode->i_ino |= (unsigned long)fsid << (xinoshift + 1);
		return;
	}

	/*
	 * For directory inodes on non-samefs with xino disabled or xino
	 * overflow, we allocate a non-persistent inode number, to be used for
	 * resolving st_ino collisions in ovl_map_dev_ino().
	 *
	 * To avoid ino collision with legitimate xino values from upper
	 * layer (fsid 0), use the lowest xinobit to map the non
	 * persistent inode numbers to the unified st_ino address space.
	 */
	if (S_ISDIR(inode->i_mode)) {
		ovl_next_ino(inode);
		if (xinobits) {
			inode->i_ino &= ~0UL >> xinobits;
			inode->i_ino |= 1UL << xinoshift;
		}
	}
}

void ovl_inode_init(struct inode *inode, struct ovl_inode_params *oip,
		    unsigned long ino, int fsid)
{
	struct inode *realinode;

	if (oip->upperdentry)
		OVL_I(inode)->__upperdentry = oip->upperdentry;
	if (oip->lowerpath && oip->lowerpath->dentry)
		OVL_I(inode)->lower = igrab(d_inode(oip->lowerpath->dentry));
	if (oip->lowerdata)
		OVL_I(inode)->lowerdata = igrab(d_inode(oip->lowerdata));

	realinode = ovl_inode_real(inode);
	ovl_copyattr(realinode, inode);
	ovl_copyflags(realinode, inode);
	ovl_map_ino(inode, ino, fsid);
}

static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
{
	inode->i_mode = mode;
	inode->i_flags |= S_NOCMTIME;
#ifdef CONFIG_FS_POSIX_ACL
	inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
#endif

	ovl_lockdep_annotate_inode_mutex_key(inode);

	switch (mode & S_IFMT) {
	case S_IFREG:
		inode->i_op = &ovl_file_inode_operations;
		inode->i_fop = &ovl_file_operations;
		inode->i_mapping->a_ops = &ovl_aops;
		break;

	case S_IFDIR:
		inode->i_op = &ovl_dir_inode_operations;
		inode->i_fop = &ovl_dir_operations;
		break;

	case S_IFLNK:
		inode->i_op = &ovl_symlink_inode_operations;
		break;

	default:
		inode->i_op = &ovl_special_inode_operations;
		init_special_inode(inode, mode, rdev);
		break;
	}
}

/*
 * With inodes index enabled, an overlay inode nlink counts the union of upper
 * hardlinks and non-covered lower hardlinks. During the lifetime of a non-pure
 * upper inode, the following nlink modifying operations can happen:
 *
 * 1. Lower hardlink copy up
 * 2. Upper hardlink created, unlinked or renamed over
 * 3. Lower hardlink whiteout or renamed over
 *
 * For the first, copy up case, the union nlink does not change, whether the
 * operation succeeds or fails, but the upper inode nlink may change.
 * Therefore, before copy up, we store the union nlink value relative to the
 * lower inode nlink in the index inode xattr .overlay.nlink.
 *
 * For the second, upper hardlink case, the union nlink should be incremented
 * or decremented IFF the operation succeeds, aligned with nlink change of the
 * upper inode. Therefore, before link/unlink/rename, we store the union nlink
 * value relative to the upper inode nlink in the index inode.
 *
 * For the last, lower cover up case, we simplify things by preceding the
 * whiteout or cover up with copy up. This makes sure that there is an index
 * upper inode where the nlink xattr can be stored before the copied up upper
 * entry is unlink.
 */
#define OVL_NLINK_ADD_UPPER	(1 << 0)

/*
 * On-disk format for indexed nlink:
 *
 * nlink relative to the upper inode - "U[+-]NUM"
 * nlink relative to the lower inode - "L[+-]NUM"
 */

static int ovl_set_nlink_common(struct dentry *dentry,
				struct dentry *realdentry, const char *format)
{
	struct inode *inode = d_inode(dentry);
	struct inode *realinode = d_inode(realdentry);
	char buf[13];
	int len;

	len = snprintf(buf, sizeof(buf), format,
		       (int) (inode->i_nlink - realinode->i_nlink));

	if (WARN_ON(len >= sizeof(buf)))
		return -EIO;

	return ovl_do_setxattr(OVL_FS(inode->i_sb), ovl_dentry_upper(dentry),
			       OVL_XATTR_NLINK, buf, len);
}

int ovl_set_nlink_upper(struct dentry *dentry)
{
	return ovl_set_nlink_common(dentry, ovl_dentry_upper(dentry), "U%+i");
}

int ovl_set_nlink_lower(struct dentry *dentry)
{
	return ovl_set_nlink_common(dentry, ovl_dentry_lower(dentry), "L%+i");
}

unsigned int ovl_get_nlink(struct ovl_fs *ofs, struct dentry *lowerdentry,
			   struct dentry *upperdentry,
			   unsigned int fallback)
{
	int nlink_diff;
	int nlink;
	char buf[13];
	int err;

	if (!lowerdentry || !upperdentry || d_inode(lowerdentry)->i_nlink == 1)
		return fallback;

	err = ovl_do_getxattr(ofs, upperdentry, OVL_XATTR_NLINK,
			      &buf, sizeof(buf) - 1);
	if (err < 0)
		goto fail;

	buf[err] = '\0';
	if ((buf[0] != 'L' && buf[0] != 'U') ||
	    (buf[1] != '+' && buf[1] != '-'))
		goto fail;

	err = kstrtoint(buf + 1, 10, &nlink_diff);
	if (err < 0)
		goto fail;

	nlink = d_inode(buf[0] == 'L' ? lowerdentry : upperdentry)->i_nlink;
	nlink += nlink_diff;

	if (nlink <= 0)
		goto fail;

	return nlink;

fail:
	pr_warn_ratelimited("failed to get index nlink (%pd2, err=%i)\n",
			    upperdentry, err);
	return fallback;
}

struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev)
{
	struct inode *inode;

	inode = new_inode(sb);
	if (inode)
		ovl_fill_inode(inode, mode, rdev);

	return inode;
}

static int ovl_inode_test(struct inode *inode, void *data)
{
	return inode->i_private == data;
}

static int ovl_inode_set(struct inode *inode, void *data)
{
	inode->i_private = data;
	return 0;
}

static bool ovl_verify_inode(struct inode *inode, struct dentry *lowerdentry,
			     struct dentry *upperdentry, bool strict)
{
	/*
	 * For directories, @strict verify from lookup path performs consistency
	 * checks, so NULL lower/upper in dentry must match NULL lower/upper in
	 * inode. Non @strict verify from NFS handle decode path passes NULL for
	 * 'unknown' lower/upper.
	 */
	if (S_ISDIR(inode->i_mode) && strict) {
		/* Real lower dir moved to upper layer under us? */
		if (!lowerdentry && ovl_inode_lower(inode))
			return false;

		/* Lookup of an uncovered redirect origin? */
		if (!upperdentry && ovl_inode_upper(inode))
			return false;
	}

	/*
	 * Allow non-NULL lower inode in ovl_inode even if lowerdentry is NULL.
	 * This happens when finding a copied up overlay inode for a renamed
	 * or hardlinked overlay dentry and lower dentry cannot be followed
	 * by origin because lower fs does not support file handles.
	 */
	if (lowerdentry && ovl_inode_lower(inode) != d_inode(lowerdentry))
		return false;

	/*
	 * Allow non-NULL __upperdentry in inode even if upperdentry is NULL.
	 * This happens when finding a lower alias for a copied up hard link.
	 */
	if (upperdentry && ovl_inode_upper(inode) != d_inode(upperdentry))
		return false;

	return true;
}

struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real,
			       bool is_upper)
{
	struct inode *inode, *key = d_inode(real);

	inode = ilookup5(sb, (unsigned long) key, ovl_inode_test, key);
	if (!inode)
		return NULL;

	if (!ovl_verify_inode(inode, is_upper ? NULL : real,
			      is_upper ? real : NULL, false)) {
		iput(inode);
		return ERR_PTR(-ESTALE);
	}

	return inode;
}

bool ovl_lookup_trap_inode(struct super_block *sb, struct dentry *dir)
{
	struct inode *key = d_inode(dir);
	struct inode *trap;
	bool res;

	trap = ilookup5(sb, (unsigned long) key, ovl_inode_test, key);
	if (!trap)
		return false;

	res = IS_DEADDIR(trap) && !ovl_inode_upper(trap) &&
				  !ovl_inode_lower(trap);

	iput(trap);
	return res;
}

/*
 * Create an inode cache entry for layer root dir, that will intentionally
 * fail ovl_verify_inode(), so any lookup that will find some layer root
 * will fail.
 */
struct inode *ovl_get_trap_inode(struct super_block *sb, struct dentry *dir)
{
	struct inode *key = d_inode(dir);
	struct inode *trap;

	if (!d_is_dir(dir))
		return ERR_PTR(-ENOTDIR);

	trap = iget5_locked(sb, (unsigned long) key, ovl_inode_test,
			    ovl_inode_set, key);
	if (!trap)
		return ERR_PTR(-ENOMEM);

	if (!(trap->i_state & I_NEW)) {
		/* Conflicting layer roots? */
		iput(trap);
		return ERR_PTR(-ELOOP);
	}

	trap->i_mode = S_IFDIR;
	trap->i_flags = S_DEAD;
	unlock_new_inode(trap);

	return trap;
}

/*
 * Does overlay inode need to be hashed by lower inode?
 */
static bool ovl_hash_bylower(struct super_block *sb, struct dentry *upper,
			     struct dentry *lower, bool index)
{
	struct ovl_fs *ofs = sb->s_fs_info;

	/* No, if pure upper */
	if (!lower)
		return false;

	/* Yes, if already indexed */
	if (index)
		return true;

	/* Yes, if won't be copied up */
	if (!ovl_upper_mnt(ofs))
		return true;

	/* No, if lower hardlink is or will be broken on copy up */
	if ((upper || !ovl_indexdir(sb)) &&
	    !d_is_dir(lower) && d_inode(lower)->i_nlink > 1)
		return false;

	/* No, if non-indexed upper with NFS export */
	if (sb->s_export_op && upper)
		return false;

	/* Otherwise, hash by lower inode for fsnotify */
	return true;
}

static struct inode *ovl_iget5(struct super_block *sb, struct inode *newinode,
			       struct inode *key)
{
	return newinode ? inode_insert5(newinode, (unsigned long) key,
					 ovl_inode_test, ovl_inode_set, key) :
			  iget5_locked(sb, (unsigned long) key,
				       ovl_inode_test, ovl_inode_set, key);
}

struct inode *ovl_get_inode(struct super_block *sb,
			    struct ovl_inode_params *oip)
{
	struct ovl_fs *ofs = OVL_FS(sb);
	struct dentry *upperdentry = oip->upperdentry;
	struct ovl_path *lowerpath = oip->lowerpath;
	struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL;
	struct inode *inode;
	struct dentry *lowerdentry = lowerpath ? lowerpath->dentry : NULL;
	bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry,
					oip->index);
	int fsid = bylower ? lowerpath->layer->fsid : 0;
	bool is_dir;
	unsigned long ino = 0;
	int err = oip->newinode ? -EEXIST : -ENOMEM;

	if (!realinode)
		realinode = d_inode(lowerdentry);

	/*
	 * Copy up origin (lower) may exist for non-indexed upper, but we must
	 * not use lower as hash key if this is a broken hardlink.
	 */
	is_dir = S_ISDIR(realinode->i_mode);
	if (upperdentry || bylower) {
		struct inode *key = d_inode(bylower ? lowerdentry :
						      upperdentry);
		unsigned int nlink = is_dir ? 1 : realinode->i_nlink;

		inode = ovl_iget5(sb, oip->newinode, key);
		if (!inode)
			goto out_err;
		if (!(inode->i_state & I_NEW)) {
			/*
			 * Verify that the underlying files stored in the inode
			 * match those in the dentry.
			 */
			if (!ovl_verify_inode(inode, lowerdentry, upperdentry,
					      true)) {
				iput(inode);
				err = -ESTALE;
				goto out_err;
			}

			dput(upperdentry);
			kfree(oip->redirect);
			goto out;
		}

		/* Recalculate nlink for non-dir due to indexing */
		if (!is_dir)
			nlink = ovl_get_nlink(ofs, lowerdentry, upperdentry,
					      nlink);
		set_nlink(inode, nlink);
		ino = key->i_ino;
	} else {
		/* Lower hardlink that will be broken on copy up */
		inode = new_inode(sb);
		if (!inode) {
			err = -ENOMEM;
			goto out_err;
		}
		ino = realinode->i_ino;
		fsid = lowerpath->layer->fsid;
	}
	ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev);
	ovl_inode_init(inode, oip, ino, fsid);

	if (upperdentry && ovl_is_impuredir(sb, upperdentry))
		ovl_set_flag(OVL_IMPURE, inode);

	if (oip->index)
		ovl_set_flag(OVL_INDEX, inode);

	OVL_I(inode)->redirect = oip->redirect;

	if (bylower)
		ovl_set_flag(OVL_CONST_INO, inode);

	/* Check for non-merge dir that may have whiteouts */
	if (is_dir) {
		if (((upperdentry && lowerdentry) || oip->numlower > 1) ||
		    ovl_check_origin_xattr(ofs, upperdentry ?: lowerdentry)) {
			ovl_set_flag(OVL_WHITEOUTS, inode);
		}
	}

	if (inode->i_state & I_NEW)
		unlock_new_inode(inode);
out:
	return inode;

out_err:
	pr_warn_ratelimited("failed to get inode (%i)\n", err);
	inode = ERR_PTR(err);
	goto out;
}