summaryrefslogtreecommitdiff
path: root/fs/overlayfs/namei.c
blob: 76ff6633917350672caa413964da6700811e9af1 (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
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2011 Novell Inc.
 * Copyright (C) 2016 Red Hat, Inc.
 */

#include <linux/fs.h>
#include <linux/cred.h>
#include <linux/ctype.h>
#include <linux/namei.h>
#include <linux/xattr.h>
#include <linux/ratelimit.h>
#include <linux/mount.h>
#include <linux/exportfs.h>
#include "overlayfs.h"

struct ovl_lookup_data {
	struct super_block *sb;
	struct qstr name;
	bool is_dir;
	bool opaque;
	bool stop;
	bool last;
	char *redirect;
	bool metacopy;
};

static int ovl_check_redirect(struct dentry *dentry, struct ovl_lookup_data *d,
			      size_t prelen, const char *post)
{
	int res;
	char *buf;

	buf = ovl_get_redirect_xattr(dentry, prelen + strlen(post));
	if (IS_ERR_OR_NULL(buf))
		return PTR_ERR(buf);

	if (buf[0] == '/') {
		/*
		 * One of the ancestor path elements in an absolute path
		 * lookup in ovl_lookup_layer() could have been opaque and
		 * that will stop further lookup in lower layers (d->stop=true)
		 * But we have found an absolute redirect in decendant path
		 * element and that should force continue lookup in lower
		 * layers (reset d->stop).
		 */
		d->stop = false;
	} else {
		res = strlen(buf) + 1;
		memmove(buf + prelen, buf, res);
		memcpy(buf, d->name.name, prelen);
	}

	strcat(buf, post);
	kfree(d->redirect);
	d->redirect = buf;
	d->name.name = d->redirect;
	d->name.len = strlen(d->redirect);

	return 0;
}

static int ovl_acceptable(void *ctx, struct dentry *dentry)
{
	/*
	 * A non-dir origin may be disconnected, which is fine, because
	 * we only need it for its unique inode number.
	 */
	if (!d_is_dir(dentry))
		return 1;

	/* Don't decode a deleted empty directory */
	if (d_unhashed(dentry))
		return 0;

	/* Check if directory belongs to the layer we are decoding from */
	return is_subdir(dentry, ((struct vfsmount *)ctx)->mnt_root);
}

/*
 * Check validity of an overlay file handle buffer.
 *
 * Return 0 for a valid file handle.
 * Return -ENODATA for "origin unknown".
 * Return <0 for an invalid file handle.
 */
int ovl_check_fb_len(struct ovl_fb *fb, int fb_len)
{
	if (fb_len < sizeof(struct ovl_fb) || fb_len < fb->len)
		return -EINVAL;

	if (fb->magic != OVL_FH_MAGIC)
		return -EINVAL;

	/* Treat larger version and unknown flags as "origin unknown" */
	if (fb->version > OVL_FH_VERSION || fb->flags & ~OVL_FH_FLAG_ALL)
		return -ENODATA;

	/* Treat endianness mismatch as "origin unknown" */
	if (!(fb->flags & OVL_FH_FLAG_ANY_ENDIAN) &&
	    (fb->flags & OVL_FH_FLAG_BIG_ENDIAN) != OVL_FH_FLAG_CPU_ENDIAN)
		return -ENODATA;

	return 0;
}

static struct ovl_fh *ovl_get_fh(struct dentry *dentry, const char *name)
{
	int res, err;
	struct ovl_fh *fh = NULL;

	res = vfs_getxattr(dentry, name, NULL, 0);
	if (res < 0) {
		if (res == -ENODATA || res == -EOPNOTSUPP)
			return NULL;
		goto fail;
	}
	/* Zero size value means "copied up but origin unknown" */
	if (res == 0)
		return NULL;

	fh = kzalloc(res + OVL_FH_WIRE_OFFSET, GFP_KERNEL);
	if (!fh)
		return ERR_PTR(-ENOMEM);

	res = vfs_getxattr(dentry, name, fh->buf, res);
	if (res < 0)
		goto fail;

	err = ovl_check_fb_len(&fh->fb, res);
	if (err < 0) {
		if (err == -ENODATA)
			goto out;
		goto invalid;
	}

	return fh;

out:
	kfree(fh);
	return NULL;

fail:
	pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res);
	goto out;
invalid:
	pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh);
	goto out;
}

struct dentry *ovl_decode_real_fh(struct ovl_fh *fh, struct vfsmount *mnt,
				  bool connected)
{
	struct dentry *real;
	int bytes;

	/*
	 * Make sure that the stored uuid matches the uuid of the lower
	 * layer where file handle will be decoded.
	 */
	if (!uuid_equal(&fh->fb.uuid, &mnt->mnt_sb->s_uuid))
		return NULL;

	bytes = (fh->fb.len - offsetof(struct ovl_fb, fid));
	real = exportfs_decode_fh(mnt, (struct fid *)fh->fb.fid,
				  bytes >> 2, (int)fh->fb.type,
				  connected ? ovl_acceptable : NULL, mnt);
	if (IS_ERR(real)) {
		/*
		 * Treat stale file handle to lower file as "origin unknown".
		 * upper file handle could become stale when upper file is
		 * unlinked and this information is needed to handle stale
		 * index entries correctly.
		 */
		if (real == ERR_PTR(-ESTALE) &&
		    !(fh->fb.flags & OVL_FH_FLAG_PATH_UPPER))
			real = NULL;
		return real;
	}

	if (ovl_dentry_weird(real)) {
		dput(real);
		return NULL;
	}

	return real;
}

static bool ovl_is_opaquedir(struct dentry *dentry)
{
	return ovl_check_dir_xattr(dentry, OVL_XATTR_OPAQUE);
}

static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
			     const char *name, unsigned int namelen,
			     size_t prelen, const char *post,
			     struct dentry **ret)
{
	struct dentry *this;
	int err;
	bool last_element = !post[0];

	this = lookup_positive_unlocked(name, base, namelen);
	if (IS_ERR(this)) {
		err = PTR_ERR(this);
		this = NULL;
		if (err == -ENOENT || err == -ENAMETOOLONG)
			goto out;
		goto out_err;
	}

	if (ovl_dentry_weird(this)) {
		/* Don't support traversing automounts and other weirdness */
		err = -EREMOTE;
		goto out_err;
	}
	if (ovl_is_whiteout(this)) {
		d->stop = d->opaque = true;
		goto put_and_out;
	}
	/*
	 * This dentry should be a regular file if previous layer lookup
	 * found a metacopy dentry.
	 */
	if (last_element && d->metacopy && !d_is_reg(this)) {
		d->stop = true;
		goto put_and_out;
	}
	if (!d_can_lookup(this)) {
		if (d->is_dir || !last_element) {
			d->stop = true;
			goto put_and_out;
		}
		err = ovl_check_metacopy_xattr(this);
		if (err < 0)
			goto out_err;

		d->metacopy = err;
		d->stop = !d->metacopy;
		if (!d->metacopy || d->last)
			goto out;
	} else {
		if (ovl_lookup_trap_inode(d->sb, this)) {
			/* Caught in a trap of overlapping layers */
			err = -ELOOP;
			goto out_err;
		}

		if (last_element)
			d->is_dir = true;
		if (d->last)
			goto out;

		if (ovl_is_opaquedir(this)) {
			d->stop = true;
			if (last_element)
				d->opaque = true;
			goto out;
		}
	}
	err = ovl_check_redirect(this, d, prelen, post);
	if (err)
		goto out_err;
out:
	*ret = this;
	return 0;

put_and_out:
	dput(this);
	this = NULL;
	goto out;

out_err:
	dput(this);
	return err;
}

static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
			    struct dentry **ret)
{
	/* Counting down from the end, since the prefix can change */
	size_t rem = d->name.len - 1;
	struct dentry *dentry = NULL;
	int err;

	if (d->name.name[0] != '/')
		return ovl_lookup_single(base, d, d->name.name, d->name.len,
					 0, "", ret);

	while (!IS_ERR_OR_NULL(base) && d_can_lookup(base)) {
		const char *s = d->name.name + d->name.len - rem;
		const char *next = strchrnul(s, '/');
		size_t thislen = next - s;
		bool end = !next[0];

		/* Verify we did not go off the rails */
		if (WARN_ON(s[-1] != '/'))
			return -EIO;

		err = ovl_lookup_single(base, d, s, thislen,
					d->name.len - rem, next, &base);
		dput(dentry);
		if (err)
			return err;
		dentry = base;
		if (end)
			break;

		rem -= thislen + 1;

		if (WARN_ON(rem >= d->name.len))
			return -EIO;
	}
	*ret = dentry;
	return 0;
}


int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected,
			struct dentry *upperdentry, struct ovl_path **stackp)
{
	struct dentry *origin = NULL;
	int i;

	for (i = 0; i < ofs->numlower; i++) {
		/*
		 * If lower fs uuid is not unique among lower fs we cannot match
		 * fh->uuid to layer.
		 */
		if (ofs->lower_layers[i].fsid &&
		    ofs->lower_layers[i].fs->bad_uuid)
			continue;

		origin = ovl_decode_real_fh(fh, ofs->lower_layers[i].mnt,
					    connected);
		if (origin)
			break;
	}

	if (!origin)
		return -ESTALE;
	else if (IS_ERR(origin))
		return PTR_ERR(origin);

	if (upperdentry && !ovl_is_whiteout(upperdentry) &&
	    ((d_inode(origin)->i_mode ^ d_inode(upperdentry)->i_mode) & S_IFMT))
		goto invalid;

	if (!*stackp)
		*stackp = kmalloc(sizeof(struct ovl_path), GFP_KERNEL);
	if (!*stackp) {
		dput(origin);
		return -ENOMEM;
	}
	**stackp = (struct ovl_path){
		.dentry = origin,
		.layer = &ofs->lower_layers[i]
	};

	return 0;

invalid:
	pr_warn_ratelimited("overlayfs: invalid origin (%pd2, ftype=%x, origin ftype=%x).\n",
			    upperdentry, d_inode(upperdentry)->i_mode & S_IFMT,
			    d_inode(origin)->i_mode & S_IFMT);
	dput(origin);
	return -EIO;
}

static int ovl_check_origin(struct ovl_fs *ofs, struct dentry *upperdentry,
			    struct ovl_path **stackp, unsigned int *ctrp)
{
	struct ovl_fh *fh = ovl_get_fh(upperdentry, OVL_XATTR_ORIGIN);
	int err;

	if (IS_ERR_OR_NULL(fh))
		return PTR_ERR(fh);

	err = ovl_check_origin_fh(ofs, fh, false, upperdentry, stackp);
	kfree(fh);

	if (err) {
		if (err == -ESTALE)
			return 0;
		return err;
	}

	if (WARN_ON(*ctrp))
		return -EIO;

	*ctrp = 1;
	return 0;
}

/*
 * Verify that @fh matches the file handle stored in xattr @name.
 * Return 0 on match, -ESTALE on mismatch, < 0 on error.
 */
static int ovl_verify_fh(struct dentry *dentry, const char *name,
			 const struct ovl_fh *fh)
{
	struct ovl_fh *ofh = ovl_get_fh(dentry, name);
	int err = 0;

	if (!ofh)
		return -ENODATA;

	if (IS_ERR(ofh))
		return PTR_ERR(ofh);

	if (fh->fb.len != ofh->fb.len || memcmp(&fh->fb, &ofh->fb, fh->fb.len))
		err = -ESTALE;

	kfree(ofh);
	return err;
}

/*
 * Verify that @real dentry matches the file handle stored in xattr @name.
 *
 * If @set is true and there is no stored file handle, encode @real and store
 * file handle in xattr @name.
 *
 * Return 0 on match, -ESTALE on mismatch, -ENODATA on no xattr, < 0 on error.
 */
int ovl_verify_set_fh(struct dentry *dentry, const char *name,
		      struct dentry *real, bool is_upper, bool set)
{
	struct inode *inode;
	struct ovl_fh *fh;
	int err;

	fh = ovl_encode_real_fh(real, is_upper);
	err = PTR_ERR(fh);
	if (IS_ERR(fh)) {
		fh = NULL;
		goto fail;
	}

	err = ovl_verify_fh(dentry, name, fh);
	if (set && err == -ENODATA)
		err = ovl_do_setxattr(dentry, name, fh->buf, fh->fb.len, 0);
	if (err)
		goto fail;

out:
	kfree(fh);
	return err;

fail:
	inode = d_inode(real);
	pr_warn_ratelimited("overlayfs: failed to verify %s (%pd2, ino=%lu, err=%i)\n",
			    is_upper ? "upper" : "origin", real,
			    inode ? inode->i_ino : 0, err);
	goto out;
}

/* Get upper dentry from index */
struct dentry *ovl_index_upper(struct ovl_fs *ofs, struct dentry *index)
{
	struct ovl_fh *fh;
	struct dentry *upper;

	if (!d_is_dir(index))
		return dget(index);

	fh = ovl_get_fh(index, OVL_XATTR_UPPER);
	if (IS_ERR_OR_NULL(fh))
		return ERR_CAST(fh);

	upper = ovl_decode_real_fh(fh, ofs->upper_mnt, true);
	kfree(fh);

	if (IS_ERR_OR_NULL(upper))
		return upper ?: ERR_PTR(-ESTALE);

	if (!d_is_dir(upper)) {
		pr_warn_ratelimited("overlayfs: invalid index upper (%pd2, upper=%pd2).\n",
				    index, upper);
		dput(upper);
		return ERR_PTR(-EIO);
	}

	return upper;
}

/* Is this a leftover from create/whiteout of directory index entry? */
static bool ovl_is_temp_index(struct dentry *index)
{
	return index->d_name.name[0] == '#';
}

/*
 * Verify that an index entry name matches the origin file handle stored in
 * OVL_XATTR_ORIGIN and that origin file handle can be decoded to lower path.
 * Return 0 on match, -ESTALE on mismatch or stale origin, < 0 on error.
 */
int ovl_verify_index(struct ovl_fs *ofs, struct dentry *index)
{
	struct ovl_fh *fh = NULL;
	size_t len;
	struct ovl_path origin = { };
	struct ovl_path *stack = &origin;
	struct dentry *upper = NULL;
	int err;

	if (!d_inode(index))
		return 0;

	/* Cleanup leftover from index create/cleanup attempt */
	err = -ESTALE;
	if (ovl_is_temp_index(index))
		goto fail;

	err = -EINVAL;
	if (index->d_name.len < sizeof(struct ovl_fb)*2)
		goto fail;

	err = -ENOMEM;
	len = index->d_name.len / 2;
	fh = kzalloc(len + OVL_FH_WIRE_OFFSET, GFP_KERNEL);
	if (!fh)
		goto fail;

	err = -EINVAL;
	if (hex2bin(fh->buf, index->d_name.name, len))
		goto fail;

	err = ovl_check_fb_len(&fh->fb, len);
	if (err)
		goto fail;

	/*
	 * Whiteout index entries are used as an indication that an exported
	 * overlay file handle should be treated as stale (i.e. after unlink
	 * of the overlay inode). These entries contain no origin xattr.
	 */
	if (ovl_is_whiteout(index))
		goto out;

	/*
	 * Verifying directory index entries are not stale is expensive, so
	 * only verify stale dir index if NFS export is enabled.
	 */
	if (d_is_dir(index) && !ofs->config.nfs_export)
		goto out;

	/*
	 * Directory index entries should have 'upper' xattr pointing to the
	 * real upper dir. Non-dir index entries are hardlinks to the upper
	 * real inode. For non-dir index, we can read the copy up origin xattr
	 * directly from the index dentry, but for dir index we first need to
	 * decode the upper directory.
	 */
	upper = ovl_index_upper(ofs, index);
	if (IS_ERR_OR_NULL(upper)) {
		err = PTR_ERR(upper);
		/*
		 * Directory index entries with no 'upper' xattr need to be
		 * removed. When dir index entry has a stale 'upper' xattr,
		 * we assume that upper dir was removed and we treat the dir
		 * index as orphan entry that needs to be whited out.
		 */
		if (err == -ESTALE)
			goto orphan;
		else if (!err)
			err = -ESTALE;
		goto fail;
	}

	err = ovl_verify_fh(upper, OVL_XATTR_ORIGIN, fh);
	dput(upper);
	if (err)
		goto fail;

	/* Check if non-dir index is orphan and don't warn before cleaning it */
	if (!d_is_dir(index) && d_inode(index)->i_nlink == 1) {
		err = ovl_check_origin_fh(ofs, fh, false, index, &stack);
		if (err)
			goto fail;

		if (ovl_get_nlink(origin.dentry, index, 0) == 0)
			goto orphan;
	}

out:
	dput(origin.dentry);
	kfree(fh);
	return err;

fail:
	pr_warn_ratelimited("overlayfs: failed to verify index (%pd2, ftype=%x, err=%i)\n",
			    index, d_inode(index)->i_mode & S_IFMT, err);
	goto out;

orphan:
	pr_warn_ratelimited("overlayfs: orphan index entry (%pd2, ftype=%x, nlink=%u)\n",
			    index, d_inode(index)->i_mode & S_IFMT,
			    d_inode(index)->i_nlink);
	err = -ENOENT;
	goto out;
}

static int ovl_get_index_name_fh(struct ovl_fh *fh, struct qstr *name)
{
	char *n, *s;

	n = kcalloc(fh->fb.len, 2, GFP_KERNEL);
	if (!n)
		return -ENOMEM;

	s  = bin2hex(n, fh->buf, fh->fb.len);
	*name = (struct qstr) QSTR_INIT(n, s - n);

	return 0;

}

/*
 * Lookup in indexdir for the index entry of a lower real inode or a copy up
 * origin inode. The index entry name is the hex representation of the lower
 * inode file handle.
 *
 * If the index dentry in negative, then either no lower aliases have been
 * copied up yet, or aliases have been copied up in older kernels and are
 * not indexed.
 *
 * If the index dentry for a copy up origin inode is positive, but points
 * to an inode different than the upper inode, then either the upper inode
 * has been copied up and not indexed or it was indexed, but since then
 * index dir was cleared. Either way, that index cannot be used to indentify
 * the overlay inode.
 */
int ovl_get_index_name(struct dentry *origin, struct qstr *name)
{
	struct ovl_fh *fh;
	int err;

	fh = ovl_encode_real_fh(origin, false);
	if (IS_ERR(fh))
		return PTR_ERR(fh);

	err = ovl_get_index_name_fh(fh, name);

	kfree(fh);
	return err;
}

/* Lookup index by file handle for NFS export */
struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh)
{
	struct dentry *index;
	struct qstr name;
	int err;

	err = ovl_get_index_name_fh(fh, &name);
	if (err)
		return ERR_PTR(err);

	index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len);
	kfree(name.name);
	if (IS_ERR(index)) {
		if (PTR_ERR(index) == -ENOENT)
			index = NULL;
		return index;
	}

	if (ovl_is_whiteout(index))
		err = -ESTALE;
	else if (ovl_dentry_weird(index))
		err = -EIO;
	else
		return index;

	dput(index);
	return ERR_PTR(err);
}

struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
				struct dentry *origin, bool verify)
{
	struct dentry *index;
	struct inode *inode;
	struct qstr name;
	bool is_dir = d_is_dir(origin);
	int err;

	err = ovl_get_index_name(origin, &name);
	if (err)
		return ERR_PTR(err);

	index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len);
	if (IS_ERR(index)) {
		err = PTR_ERR(index);
		if (err == -ENOENT) {
			index = NULL;
			goto out;
		}
		pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%.*s, err=%i);\n"
				    "overlayfs: mount with '-o index=off' to disable inodes index.\n",
				    d_inode(origin)->i_ino, name.len, name.name,
				    err);
		goto out;
	}

	inode = d_inode(index);
	if (ovl_is_whiteout(index) && !verify) {
		/*
		 * When index lookup is called with !verify for decoding an
		 * overlay file handle, a whiteout index implies that decode
		 * should treat file handle as stale and no need to print a
		 * warning about it.
		 */
		dput(index);
		index = ERR_PTR(-ESTALE);
		goto out;
	} else if (ovl_dentry_weird(index) || ovl_is_whiteout(index) ||
		   ((inode->i_mode ^ d_inode(origin)->i_mode) & S_IFMT)) {
		/*
		 * Index should always be of the same file type as origin
		 * except for the case of a whiteout index. A whiteout
		 * index should only exist if all lower aliases have been
		 * unlinked, which means that finding a lower origin on lookup
		 * whose index is a whiteout should be treated as an error.
		 */
		pr_warn_ratelimited("overlayfs: bad index found (index=%pd2, ftype=%x, origin ftype=%x).\n",
				    index, d_inode(index)->i_mode & S_IFMT,
				    d_inode(origin)->i_mode & S_IFMT);
		goto fail;
	} else if (is_dir && verify) {
		if (!upper) {
			pr_warn_ratelimited("overlayfs: suspected uncovered redirected dir found (origin=%pd2, index=%pd2).\n",
					    origin, index);
			goto fail;
		}

		/* Verify that dir index 'upper' xattr points to upper dir */
		err = ovl_verify_upper(index, upper, false);
		if (err) {
			if (err == -ESTALE) {
				pr_warn_ratelimited("overlayfs: suspected multiply redirected dir found (upper=%pd2, origin=%pd2, index=%pd2).\n",
						    upper, origin, index);
			}
			goto fail;
		}
	} else if (upper && d_inode(upper) != inode) {
		goto out_dput;
	}
out:
	kfree(name.name);
	return index;

out_dput:
	dput(index);
	index = NULL;
	goto out;

fail:
	dput(index);
	index = ERR_PTR(-EIO);
	goto out;
}

/*
 * Returns next layer in stack starting from top.
 * Returns -1 if this is the last layer.
 */
int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	BUG_ON(idx < 0);
	if (idx == 0) {
		ovl_path_upper(dentry, path);
		if (path->dentry)
			return oe->numlower ? 1 : -1;
		idx++;
	}
	BUG_ON(idx > oe->numlower);
	path->dentry = oe->lowerstack[idx - 1].dentry;
	path->mnt = oe->lowerstack[idx - 1].layer->mnt;

	return (idx < oe->numlower) ? idx + 1 : -1;
}

/* Fix missing 'origin' xattr */
static int ovl_fix_origin(struct dentry *dentry, struct dentry *lower,
			  struct dentry *upper)
{
	int err;

	if (ovl_check_origin_xattr(upper))
		return 0;

	err = ovl_want_write(dentry);
	if (err)
		return err;

	err = ovl_set_origin(dentry, lower, upper);
	if (!err)
		err = ovl_set_impure(dentry->d_parent, upper->d_parent);

	ovl_drop_write(dentry);
	return err;
}

struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
			  unsigned int flags)
{
	struct ovl_entry *oe;
	const struct cred *old_cred;
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
	struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata;
	struct ovl_path *stack = NULL, *origin_path = NULL;
	struct dentry *upperdir, *upperdentry = NULL;
	struct dentry *origin = NULL;
	struct dentry *index = NULL;
	unsigned int ctr = 0;
	struct inode *inode = NULL;
	bool upperopaque = false;
	char *upperredirect = NULL;
	struct dentry *this;
	unsigned int i;
	int err;
	bool metacopy = false;
	struct ovl_lookup_data d = {
		.sb = dentry->d_sb,
		.name = dentry->d_name,
		.is_dir = false,
		.opaque = false,
		.stop = false,
		.last = ofs->config.redirect_follow ? false : !poe->numlower,
		.redirect = NULL,
		.metacopy = false,
	};

	if (dentry->d_name.len > ofs->namelen)
		return ERR_PTR(-ENAMETOOLONG);

	old_cred = ovl_override_creds(dentry->d_sb);
	upperdir = ovl_dentry_upper(dentry->d_parent);
	if (upperdir) {
		err = ovl_lookup_layer(upperdir, &d, &upperdentry);
		if (err)
			goto out;

		if (upperdentry && unlikely(ovl_dentry_remote(upperdentry))) {
			dput(upperdentry);
			err = -EREMOTE;
			goto out;
		}
		if (upperdentry && !d.is_dir) {
			unsigned int origin_ctr = 0;

			/*
			 * Lookup copy up origin by decoding origin file handle.
			 * We may get a disconnected dentry, which is fine,
			 * because we only need to hold the origin inode in
			 * cache and use its inode number.  We may even get a
			 * connected dentry, that is not under any of the lower
			 * layers root.  That is also fine for using it's inode
			 * number - it's the same as if we held a reference
			 * to a dentry in lower layer that was moved under us.
			 */
			err = ovl_check_origin(ofs, upperdentry, &origin_path,
					       &origin_ctr);
			if (err)
				goto out_put_upper;

			if (d.metacopy)
				metacopy = true;
		}

		if (d.redirect) {
			err = -ENOMEM;
			upperredirect = kstrdup(d.redirect, GFP_KERNEL);
			if (!upperredirect)
				goto out_put_upper;
			if (d.redirect[0] == '/')
				poe = roe;
		}
		upperopaque = d.opaque;
	}

	if (!d.stop && poe->numlower) {
		err = -ENOMEM;
		stack = kcalloc(ofs->numlower, sizeof(struct ovl_path),
				GFP_KERNEL);
		if (!stack)
			goto out_put_upper;
	}

	for (i = 0; !d.stop && i < poe->numlower; i++) {
		struct ovl_path lower = poe->lowerstack[i];

		if (!ofs->config.redirect_follow)
			d.last = i == poe->numlower - 1;
		else
			d.last = lower.layer->idx == roe->numlower;

		err = ovl_lookup_layer(lower.dentry, &d, &this);
		if (err)
			goto out_put;

		if (!this)
			continue;

		/*
		 * If no origin fh is stored in upper of a merge dir, store fh
		 * of lower dir and set upper parent "impure".
		 */
		if (upperdentry && !ctr && !ofs->noxattr && d.is_dir) {
			err = ovl_fix_origin(dentry, this, upperdentry);
			if (err) {
				dput(this);
				goto out_put;
			}
		}

		/*
		 * When "verify_lower" feature is enabled, do not merge with a
		 * lower dir that does not match a stored origin xattr. In any
		 * case, only verified origin is used for index lookup.
		 *
		 * For non-dir dentry, if index=on, then ensure origin
		 * matches the dentry found using path based lookup,
		 * otherwise error out.
		 */
		if (upperdentry && !ctr &&
		    ((d.is_dir && ovl_verify_lower(dentry->d_sb)) ||
		     (!d.is_dir && ofs->config.index && origin_path))) {
			err = ovl_verify_origin(upperdentry, this, false);
			if (err) {
				dput(this);
				if (d.is_dir)
					break;
				goto out_put;
			}
			origin = this;
		}

		if (d.metacopy)
			metacopy = true;
		/*
		 * Do not store intermediate metacopy dentries in chain,
		 * except top most lower metacopy dentry
		 */
		if (d.metacopy && ctr) {
			dput(this);
			continue;
		}

		stack[ctr].dentry = this;
		stack[ctr].layer = lower.layer;
		ctr++;

		/*
		 * Following redirects can have security consequences: it's like
		 * a symlink into the lower layer without the permission checks.
		 * This is only a problem if the upper layer is untrusted (e.g
		 * comes from an USB drive).  This can allow a non-readable file
		 * or directory to become readable.
		 *
		 * Only following redirects when redirects are enabled disables
		 * this attack vector when not necessary.
		 */
		err = -EPERM;
		if (d.redirect && !ofs->config.redirect_follow) {
			pr_warn_ratelimited("overlayfs: refusing to follow redirect for (%pd2)\n",
					    dentry);
			goto out_put;
		}

		if (d.stop)
			break;

		if (d.redirect && d.redirect[0] == '/' && poe != roe) {
			poe = roe;
			/* Find the current layer on the root dentry */
			i = lower.layer->idx - 1;
		}
	}

	if (metacopy) {
		/*
		 * Found a metacopy dentry but did not find corresponding
		 * data dentry
		 */
		if (d.metacopy) {
			err = -EIO;
			goto out_put;
		}

		err = -EPERM;
		if (!ofs->config.metacopy) {
			pr_warn_ratelimited("overlay: refusing to follow metacopy origin for (%pd2)\n",
					    dentry);
			goto out_put;
		}
	} else if (!d.is_dir && upperdentry && !ctr && origin_path) {
		if (WARN_ON(stack != NULL)) {
			err = -EIO;
			goto out_put;
		}
		stack = origin_path;
		ctr = 1;
		origin_path = NULL;
	}

	/*
	 * Lookup index by lower inode and verify it matches upper inode.
	 * We only trust dir index if we verified that lower dir matches
	 * origin, otherwise dir index entries may be inconsistent and we
	 * ignore them.
	 *
	 * For non-dir upper metacopy dentry, we already set "origin" if we
	 * verified that lower matched upper origin. If upper origin was
	 * not present (because lower layer did not support fh encode/decode),
	 * or indexing is not enabled, do not set "origin" and skip looking up
	 * index. This case should be handled in same way as a non-dir upper
	 * without ORIGIN is handled.
	 *
	 * Always lookup index of non-dir non-metacopy and non-upper.
	 */
	if (ctr && (!upperdentry || (!d.is_dir && !metacopy)))
		origin = stack[0].dentry;

	if (origin && ovl_indexdir(dentry->d_sb) &&
	    (!d.is_dir || ovl_index_all(dentry->d_sb))) {
		index = ovl_lookup_index(ofs, upperdentry, origin, true);
		if (IS_ERR(index)) {
			err = PTR_ERR(index);
			index = NULL;
			goto out_put;
		}
	}

	oe = ovl_alloc_entry(ctr);
	err = -ENOMEM;
	if (!oe)
		goto out_put;

	memcpy(oe->lowerstack, stack, sizeof(struct ovl_path) * ctr);
	dentry->d_fsdata = oe;

	if (upperopaque)
		ovl_dentry_set_opaque(dentry);

	if (upperdentry)
		ovl_dentry_set_upper_alias(dentry);
	else if (index) {
		upperdentry = dget(index);
		upperredirect = ovl_get_redirect_xattr(upperdentry, 0);
		if (IS_ERR(upperredirect)) {
			err = PTR_ERR(upperredirect);
			upperredirect = NULL;
			goto out_free_oe;
		}
	}

	if (upperdentry || ctr) {
		struct ovl_inode_params oip = {
			.upperdentry = upperdentry,
			.lowerpath = stack,
			.index = index,
			.numlower = ctr,
			.redirect = upperredirect,
			.lowerdata = (ctr > 1 && !d.is_dir) ?
				      stack[ctr - 1].dentry : NULL,
		};

		inode = ovl_get_inode(dentry->d_sb, &oip);
		err = PTR_ERR(inode);
		if (IS_ERR(inode))
			goto out_free_oe;
	}

	revert_creds(old_cred);
	if (origin_path) {
		dput(origin_path->dentry);
		kfree(origin_path);
	}
	dput(index);
	kfree(stack);
	kfree(d.redirect);
	return d_splice_alias(inode, dentry);

out_free_oe:
	dentry->d_fsdata = NULL;
	kfree(oe);
out_put:
	dput(index);
	for (i = 0; i < ctr; i++)
		dput(stack[i].dentry);
	kfree(stack);
out_put_upper:
	if (origin_path) {
		dput(origin_path->dentry);
		kfree(origin_path);
	}
	dput(upperdentry);
	kfree(upperredirect);
out:
	kfree(d.redirect);
	revert_creds(old_cred);
	return ERR_PTR(err);
}

bool ovl_lower_positive(struct dentry *dentry)
{
	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
	const struct qstr *name = &dentry->d_name;
	const struct cred *old_cred;
	unsigned int i;
	bool positive = false;
	bool done = false;

	/*
	 * If dentry is negative, then lower is positive iff this is a
	 * whiteout.
	 */
	if (!dentry->d_inode)
		return ovl_dentry_is_opaque(dentry);

	/* Negative upper -> positive lower */
	if (!ovl_dentry_upper(dentry))
		return true;

	old_cred = ovl_override_creds(dentry->d_sb);
	/* Positive upper -> have to look up lower to see whether it exists */
	for (i = 0; !done && !positive && i < poe->numlower; i++) {
		struct dentry *this;
		struct dentry *lowerdir = poe->lowerstack[i].dentry;

		this = lookup_positive_unlocked(name->name, lowerdir,
					       name->len);
		if (IS_ERR(this)) {
			switch (PTR_ERR(this)) {
			case -ENOENT:
			case -ENAMETOOLONG:
				break;

			default:
				/*
				 * Assume something is there, we just couldn't
				 * access it.
				 */
				positive = true;
				break;
			}
		} else {
			positive = !ovl_is_whiteout(this);
			done = true;
			dput(this);
		}
	}
	revert_creds(old_cred);

	return positive;
}