summaryrefslogtreecommitdiff
path: root/fs/overlayfs/readdir.c
blob: 0ca8af060b0c194e5824e59b59d9d2dc8b051355 (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
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
// SPDX-License-Identifier: GPL-2.0-only
/*
 *
 * Copyright (C) 2011 Novell Inc.
 */

#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/namei.h>
#include <linux/file.h>
#include <linux/xattr.h>
#include <linux/rbtree.h>
#include <linux/security.h>
#include <linux/cred.h>
#include <linux/ratelimit.h>
#include "overlayfs.h"

struct ovl_cache_entry {
	unsigned int len;
	unsigned int type;
	u64 real_ino;
	u64 ino;
	struct list_head l_node;
	struct rb_node node;
	struct ovl_cache_entry *next_maybe_whiteout;
	bool is_upper;
	bool is_whiteout;
	bool check_xwhiteout;
	char name[];
};

struct ovl_dir_cache {
	long refcount;
	u64 version;
	struct list_head entries;
	struct rb_root root;
};

struct ovl_readdir_data {
	struct dir_context ctx;
	struct dentry *dentry;
	bool is_lowest;
	struct rb_root *root;
	struct list_head *list;
	struct list_head middle;
	struct ovl_cache_entry *first_maybe_whiteout;
	int count;
	int err;
	bool is_upper;
	bool d_type_supported;
	bool in_xwhiteouts_dir;
};

struct ovl_dir_file {
	bool is_real;
	bool is_upper;
	struct ovl_dir_cache *cache;
	struct list_head *cursor;
	struct file *realfile;
	struct file *upperfile;
};

static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n)
{
	return rb_entry(n, struct ovl_cache_entry, node);
}

static bool ovl_cache_entry_find_link(const char *name, int len,
				      struct rb_node ***link,
				      struct rb_node **parent)
{
	bool found = false;
	struct rb_node **newp = *link;

	while (!found && *newp) {
		int cmp;
		struct ovl_cache_entry *tmp;

		*parent = *newp;
		tmp = ovl_cache_entry_from_node(*newp);
		cmp = strncmp(name, tmp->name, len);
		if (cmp > 0)
			newp = &tmp->node.rb_right;
		else if (cmp < 0 || len < tmp->len)
			newp = &tmp->node.rb_left;
		else
			found = true;
	}
	*link = newp;

	return found;
}

static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root,
						    const char *name, int len)
{
	struct rb_node *node = root->rb_node;
	int cmp;

	while (node) {
		struct ovl_cache_entry *p = ovl_cache_entry_from_node(node);

		cmp = strncmp(name, p->name, len);
		if (cmp > 0)
			node = p->node.rb_right;
		else if (cmp < 0 || len < p->len)
			node = p->node.rb_left;
		else
			return p;
	}

	return NULL;
}

static bool ovl_calc_d_ino(struct ovl_readdir_data *rdd,
			   struct ovl_cache_entry *p)
{
	/* Don't care if not doing ovl_iter() */
	if (!rdd->dentry)
		return false;

	/* Always recalc d_ino when remapping lower inode numbers */
	if (ovl_xino_bits(OVL_FS(rdd->dentry->d_sb)))
		return true;

	/* Always recalc d_ino for parent */
	if (strcmp(p->name, "..") == 0)
		return true;

	/* If this is lower, then native d_ino will do */
	if (!rdd->is_upper)
		return false;

	/*
	 * Recalc d_ino for '.' and for all entries if dir is impure (contains
	 * copied up entries)
	 */
	if ((p->name[0] == '.' && p->len == 1) ||
	    ovl_test_flag(OVL_IMPURE, d_inode(rdd->dentry)))
		return true;

	return false;
}

static struct ovl_cache_entry *ovl_cache_entry_new(struct ovl_readdir_data *rdd,
						   const char *name, int len,
						   u64 ino, unsigned int d_type)
{
	struct ovl_cache_entry *p;
	size_t size = offsetof(struct ovl_cache_entry, name[len + 1]);

	p = kmalloc(size, GFP_KERNEL);
	if (!p)
		return NULL;

	memcpy(p->name, name, len);
	p->name[len] = '\0';
	p->len = len;
	p->type = d_type;
	p->real_ino = ino;
	p->ino = ino;
	/* Defer setting d_ino for upper entry to ovl_iterate() */
	if (ovl_calc_d_ino(rdd, p))
		p->ino = 0;
	p->is_upper = rdd->is_upper;
	p->is_whiteout = false;
	/* Defer check for overlay.whiteout to ovl_iterate() */
	p->check_xwhiteout = rdd->in_xwhiteouts_dir && d_type == DT_REG;

	if (d_type == DT_CHR) {
		p->next_maybe_whiteout = rdd->first_maybe_whiteout;
		rdd->first_maybe_whiteout = p;
	}
	return p;
}

static bool ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd,
				  const char *name, int len, u64 ino,
				  unsigned int d_type)
{
	struct rb_node **newp = &rdd->root->rb_node;
	struct rb_node *parent = NULL;
	struct ovl_cache_entry *p;

	if (ovl_cache_entry_find_link(name, len, &newp, &parent))
		return true;

	p = ovl_cache_entry_new(rdd, name, len, ino, d_type);
	if (p == NULL) {
		rdd->err = -ENOMEM;
		return false;
	}

	list_add_tail(&p->l_node, rdd->list);
	rb_link_node(&p->node, parent, newp);
	rb_insert_color(&p->node, rdd->root);

	return true;
}

static bool ovl_fill_lowest(struct ovl_readdir_data *rdd,
			   const char *name, int namelen,
			   loff_t offset, u64 ino, unsigned int d_type)
{
	struct ovl_cache_entry *p;

	p = ovl_cache_entry_find(rdd->root, name, namelen);
	if (p) {
		list_move_tail(&p->l_node, &rdd->middle);
	} else {
		p = ovl_cache_entry_new(rdd, name, namelen, ino, d_type);
		if (p == NULL)
			rdd->err = -ENOMEM;
		else
			list_add_tail(&p->l_node, &rdd->middle);
	}

	return rdd->err == 0;
}

void ovl_cache_free(struct list_head *list)
{
	struct ovl_cache_entry *p;
	struct ovl_cache_entry *n;

	list_for_each_entry_safe(p, n, list, l_node)
		kfree(p);

	INIT_LIST_HEAD(list);
}

void ovl_dir_cache_free(struct inode *inode)
{
	struct ovl_dir_cache *cache = ovl_dir_cache(inode);

	if (cache) {
		ovl_cache_free(&cache->entries);
		kfree(cache);
	}
}

static void ovl_cache_put(struct ovl_dir_file *od, struct inode *inode)
{
	struct ovl_dir_cache *cache = od->cache;

	WARN_ON(cache->refcount <= 0);
	cache->refcount--;
	if (!cache->refcount) {
		if (ovl_dir_cache(inode) == cache)
			ovl_set_dir_cache(inode, NULL);

		ovl_cache_free(&cache->entries);
		kfree(cache);
	}
}

static bool ovl_fill_merge(struct dir_context *ctx, const char *name,
			  int namelen, loff_t offset, u64 ino,
			  unsigned int d_type)
{
	struct ovl_readdir_data *rdd =
		container_of(ctx, struct ovl_readdir_data, ctx);

	rdd->count++;
	if (!rdd->is_lowest)
		return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type);
	else
		return ovl_fill_lowest(rdd, name, namelen, offset, ino, d_type);
}

static int ovl_check_whiteouts(const struct path *path, struct ovl_readdir_data *rdd)
{
	int err;
	struct ovl_cache_entry *p;
	struct dentry *dentry, *dir = path->dentry;
	const struct cred *old_cred;

	old_cred = ovl_override_creds(rdd->dentry->d_sb);

	err = down_write_killable(&dir->d_inode->i_rwsem);
	if (!err) {
		while (rdd->first_maybe_whiteout) {
			p = rdd->first_maybe_whiteout;
			rdd->first_maybe_whiteout = p->next_maybe_whiteout;
			dentry = lookup_one(mnt_idmap(path->mnt), p->name, dir, p->len);
			if (!IS_ERR(dentry)) {
				p->is_whiteout = ovl_is_whiteout(dentry);
				dput(dentry);
			}
		}
		inode_unlock(dir->d_inode);
	}
	revert_creds(old_cred);

	return err;
}

static inline int ovl_dir_read(const struct path *realpath,
			       struct ovl_readdir_data *rdd)
{
	struct file *realfile;
	int err;

	realfile = ovl_path_open(realpath, O_RDONLY | O_LARGEFILE);
	if (IS_ERR(realfile))
		return PTR_ERR(realfile);

	rdd->first_maybe_whiteout = NULL;
	rdd->ctx.pos = 0;
	do {
		rdd->count = 0;
		rdd->err = 0;
		err = iterate_dir(realfile, &rdd->ctx);
		if (err >= 0)
			err = rdd->err;
	} while (!err && rdd->count);

	if (!err && rdd->first_maybe_whiteout && rdd->dentry)
		err = ovl_check_whiteouts(realpath, rdd);

	fput(realfile);

	return err;
}

static void ovl_dir_reset(struct file *file)
{
	struct ovl_dir_file *od = file->private_data;
	struct ovl_dir_cache *cache = od->cache;
	struct inode *inode = file_inode(file);
	bool is_real;

	if (cache && ovl_inode_version_get(inode) != cache->version) {
		ovl_cache_put(od, inode);
		od->cache = NULL;
		od->cursor = NULL;
	}
	is_real = ovl_dir_is_real(inode);
	if (od->is_real != is_real) {
		/* is_real can only become false when dir is copied up */
		if (WARN_ON(is_real))
			return;
		od->is_real = false;
	}
}

static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list,
	struct rb_root *root)
{
	int err;
	struct path realpath;
	struct ovl_readdir_data rdd = {
		.ctx.actor = ovl_fill_merge,
		.dentry = dentry,
		.list = list,
		.root = root,
		.is_lowest = false,
	};
	int idx, next;
	const struct ovl_layer *layer;

	for (idx = 0; idx != -1; idx = next) {
		next = ovl_path_next(idx, dentry, &realpath, &layer);
		rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry;
		rdd.in_xwhiteouts_dir = layer->has_xwhiteouts &&
					ovl_dentry_has_xwhiteouts(dentry);

		if (next != -1) {
			err = ovl_dir_read(&realpath, &rdd);
			if (err)
				break;
		} else {
			/*
			 * Insert lowest layer entries before upper ones, this
			 * allows offsets to be reasonably constant
			 */
			list_add(&rdd.middle, rdd.list);
			rdd.is_lowest = true;
			err = ovl_dir_read(&realpath, &rdd);
			list_del(&rdd.middle);
		}
	}
	return err;
}

static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
{
	struct list_head *p;
	loff_t off = 0;

	list_for_each(p, &od->cache->entries) {
		if (off >= pos)
			break;
		off++;
	}
	/* Cursor is safe since the cache is stable */
	od->cursor = p;
}

static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
{
	int res;
	struct ovl_dir_cache *cache;
	struct inode *inode = d_inode(dentry);

	cache = ovl_dir_cache(inode);
	if (cache && ovl_inode_version_get(inode) == cache->version) {
		WARN_ON(!cache->refcount);
		cache->refcount++;
		return cache;
	}
	ovl_set_dir_cache(d_inode(dentry), NULL);

	cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL);
	if (!cache)
		return ERR_PTR(-ENOMEM);

	cache->refcount = 1;
	INIT_LIST_HEAD(&cache->entries);
	cache->root = RB_ROOT;

	res = ovl_dir_read_merged(dentry, &cache->entries, &cache->root);
	if (res) {
		ovl_cache_free(&cache->entries);
		kfree(cache);
		return ERR_PTR(res);
	}

	cache->version = ovl_inode_version_get(inode);
	ovl_set_dir_cache(inode, cache);

	return cache;
}

/* Map inode number to lower fs unique range */
static u64 ovl_remap_lower_ino(u64 ino, int xinobits, int fsid,
			       const char *name, int namelen, bool warn)
{
	unsigned int xinoshift = 64 - xinobits;

	if (unlikely(ino >> xinoshift)) {
		if (warn) {
			pr_warn_ratelimited("d_ino too big (%.*s, ino=%llu, xinobits=%d)\n",
					    namelen, name, ino, xinobits);
		}
		return ino;
	}

	/*
	 * The lowest xinobit is reserved for mapping the non-peresistent inode
	 * numbers range, but this range is only exposed via st_ino, not here.
	 */
	return ino | ((u64)fsid) << (xinoshift + 1);
}

/*
 * Set d_ino for upper entries if needed. Non-upper entries should always report
 * the uppermost real inode ino and should not call this function.
 *
 * When not all layer are on same fs, report real ino also for upper.
 *
 * When all layers are on the same fs, and upper has a reference to
 * copy up origin, call vfs_getattr() on the overlay entry to make
 * sure that d_ino will be consistent with st_ino from stat(2).
 *
 * Also checks the overlay.whiteout xattr by doing a full lookup which will return
 * negative in this case.
 */
static int ovl_cache_update(const struct path *path, struct ovl_cache_entry *p, bool update_ino)

{
	struct dentry *dir = path->dentry;
	struct ovl_fs *ofs = OVL_FS(dir->d_sb);
	struct dentry *this = NULL;
	enum ovl_path_type type;
	u64 ino = p->real_ino;
	int xinobits = ovl_xino_bits(ofs);
	int err = 0;

	if (!ovl_same_dev(ofs) && !p->check_xwhiteout)
		goto out;

	if (p->name[0] == '.') {
		if (p->len == 1) {
			this = dget(dir);
			goto get;
		}
		if (p->len == 2 && p->name[1] == '.') {
			/* we shall not be moved */
			this = dget(dir->d_parent);
			goto get;
		}
	}
	/* This checks also for xwhiteouts */
	this = lookup_one(mnt_idmap(path->mnt), p->name, dir, p->len);
	if (IS_ERR_OR_NULL(this) || !this->d_inode) {
		/* Mark a stale entry */
		p->is_whiteout = true;
		if (IS_ERR(this)) {
			err = PTR_ERR(this);
			this = NULL;
			goto fail;
		}
		goto out;
	}

get:
	if (!ovl_same_dev(ofs) || !update_ino)
		goto out;

	type = ovl_path_type(this);
	if (OVL_TYPE_ORIGIN(type)) {
		struct kstat stat;
		struct path statpath = *path;

		statpath.dentry = this;
		err = vfs_getattr(&statpath, &stat, STATX_INO, 0);
		if (err)
			goto fail;

		/*
		 * Directory inode is always on overlay st_dev.
		 * Non-dir with ovl_same_dev() could be on pseudo st_dev in case
		 * of xino bits overflow.
		 */
		WARN_ON_ONCE(S_ISDIR(stat.mode) &&
			     dir->d_sb->s_dev != stat.dev);
		ino = stat.ino;
	} else if (xinobits && !OVL_TYPE_UPPER(type)) {
		ino = ovl_remap_lower_ino(ino, xinobits,
					  ovl_layer_lower(this)->fsid,
					  p->name, p->len,
					  ovl_xino_warn(ofs));
	}

out:
	p->ino = ino;
	dput(this);
	return err;

fail:
	pr_warn_ratelimited("failed to look up (%s) for ino (%i)\n",
			    p->name, err);
	goto out;
}

static bool ovl_fill_plain(struct dir_context *ctx, const char *name,
			  int namelen, loff_t offset, u64 ino,
			  unsigned int d_type)
{
	struct ovl_cache_entry *p;
	struct ovl_readdir_data *rdd =
		container_of(ctx, struct ovl_readdir_data, ctx);

	rdd->count++;
	p = ovl_cache_entry_new(rdd, name, namelen, ino, d_type);
	if (p == NULL) {
		rdd->err = -ENOMEM;
		return false;
	}
	list_add_tail(&p->l_node, rdd->list);

	return true;
}

static int ovl_dir_read_impure(const struct path *path,  struct list_head *list,
			       struct rb_root *root)
{
	int err;
	struct path realpath;
	struct ovl_cache_entry *p, *n;
	struct ovl_readdir_data rdd = {
		.ctx.actor = ovl_fill_plain,
		.list = list,
		.root = root,
	};

	INIT_LIST_HEAD(list);
	*root = RB_ROOT;
	ovl_path_upper(path->dentry, &realpath);

	err = ovl_dir_read(&realpath, &rdd);
	if (err)
		return err;

	list_for_each_entry_safe(p, n, list, l_node) {
		if (strcmp(p->name, ".") != 0 &&
		    strcmp(p->name, "..") != 0) {
			err = ovl_cache_update(path, p, true);
			if (err)
				return err;
		}
		if (p->ino == p->real_ino) {
			list_del(&p->l_node);
			kfree(p);
		} else {
			struct rb_node **newp = &root->rb_node;
			struct rb_node *parent = NULL;

			if (WARN_ON(ovl_cache_entry_find_link(p->name, p->len,
							      &newp, &parent)))
				return -EIO;

			rb_link_node(&p->node, parent, newp);
			rb_insert_color(&p->node, root);
		}
	}
	return 0;
}

static struct ovl_dir_cache *ovl_cache_get_impure(const struct path *path)
{
	int res;
	struct dentry *dentry = path->dentry;
	struct inode *inode = d_inode(dentry);
	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
	struct ovl_dir_cache *cache;

	cache = ovl_dir_cache(inode);
	if (cache && ovl_inode_version_get(inode) == cache->version)
		return cache;

	/* Impure cache is not refcounted, free it here */
	ovl_dir_cache_free(inode);
	ovl_set_dir_cache(inode, NULL);

	cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL);
	if (!cache)
		return ERR_PTR(-ENOMEM);

	res = ovl_dir_read_impure(path, &cache->entries, &cache->root);
	if (res) {
		ovl_cache_free(&cache->entries);
		kfree(cache);
		return ERR_PTR(res);
	}
	if (list_empty(&cache->entries)) {
		/*
		 * A good opportunity to get rid of an unneeded "impure" flag.
		 * Removing the "impure" xattr is best effort.
		 */
		if (!ovl_want_write(dentry)) {
			ovl_removexattr(ofs, ovl_dentry_upper(dentry),
					OVL_XATTR_IMPURE);
			ovl_drop_write(dentry);
		}
		ovl_clear_flag(OVL_IMPURE, inode);
		kfree(cache);
		return NULL;
	}

	cache->version = ovl_inode_version_get(inode);
	ovl_set_dir_cache(inode, cache);

	return cache;
}

struct ovl_readdir_translate {
	struct dir_context *orig_ctx;
	struct ovl_dir_cache *cache;
	struct dir_context ctx;
	u64 parent_ino;
	int fsid;
	int xinobits;
	bool xinowarn;
};

static bool ovl_fill_real(struct dir_context *ctx, const char *name,
			   int namelen, loff_t offset, u64 ino,
			   unsigned int d_type)
{
	struct ovl_readdir_translate *rdt =
		container_of(ctx, struct ovl_readdir_translate, ctx);
	struct dir_context *orig_ctx = rdt->orig_ctx;

	if (rdt->parent_ino && strcmp(name, "..") == 0) {
		ino = rdt->parent_ino;
	} else if (rdt->cache) {
		struct ovl_cache_entry *p;

		p = ovl_cache_entry_find(&rdt->cache->root, name, namelen);
		if (p)
			ino = p->ino;
	} else if (rdt->xinobits) {
		ino = ovl_remap_lower_ino(ino, rdt->xinobits, rdt->fsid,
					  name, namelen, rdt->xinowarn);
	}

	return orig_ctx->actor(orig_ctx, name, namelen, offset, ino, d_type);
}

static bool ovl_is_impure_dir(struct file *file)
{
	struct ovl_dir_file *od = file->private_data;
	struct inode *dir = file_inode(file);

	/*
	 * Only upper dir can be impure, but if we are in the middle of
	 * iterating a lower real dir, dir could be copied up and marked
	 * impure. We only want the impure cache if we started iterating
	 * a real upper dir to begin with.
	 */
	return od->is_upper && ovl_test_flag(OVL_IMPURE, dir);

}

static int ovl_iterate_real(struct file *file, struct dir_context *ctx)
{
	int err;
	struct ovl_dir_file *od = file->private_data;
	struct dentry *dir = file->f_path.dentry;
	struct ovl_fs *ofs = OVL_FS(dir->d_sb);
	const struct ovl_layer *lower_layer = ovl_layer_lower(dir);
	struct ovl_readdir_translate rdt = {
		.ctx.actor = ovl_fill_real,
		.orig_ctx = ctx,
		.xinobits = ovl_xino_bits(ofs),
		.xinowarn = ovl_xino_warn(ofs),
	};

	if (rdt.xinobits && lower_layer)
		rdt.fsid = lower_layer->fsid;

	if (OVL_TYPE_MERGE(ovl_path_type(dir->d_parent))) {
		struct kstat stat;
		struct path statpath = file->f_path;

		statpath.dentry = dir->d_parent;
		err = vfs_getattr(&statpath, &stat, STATX_INO, 0);
		if (err)
			return err;

		WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev);
		rdt.parent_ino = stat.ino;
	}

	if (ovl_is_impure_dir(file)) {
		rdt.cache = ovl_cache_get_impure(&file->f_path);
		if (IS_ERR(rdt.cache))
			return PTR_ERR(rdt.cache);
	}

	err = iterate_dir(od->realfile, &rdt.ctx);
	ctx->pos = rdt.ctx.pos;

	return err;
}


static int ovl_iterate(struct file *file, struct dir_context *ctx)
{
	struct ovl_dir_file *od = file->private_data;
	struct dentry *dentry = file->f_path.dentry;
	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
	struct ovl_cache_entry *p;
	const struct cred *old_cred;
	int err;

	old_cred = ovl_override_creds(dentry->d_sb);
	if (!ctx->pos)
		ovl_dir_reset(file);

	if (od->is_real) {
		/*
		 * If parent is merge, then need to adjust d_ino for '..', if
		 * dir is impure then need to adjust d_ino for copied up
		 * entries.
		 */
		if (ovl_xino_bits(ofs) ||
		    (ovl_same_fs(ofs) &&
		     (ovl_is_impure_dir(file) ||
		      OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))))) {
			err = ovl_iterate_real(file, ctx);
		} else {
			err = iterate_dir(od->realfile, ctx);
		}
		goto out;
	}

	if (!od->cache) {
		struct ovl_dir_cache *cache;

		cache = ovl_cache_get(dentry);
		err = PTR_ERR(cache);
		if (IS_ERR(cache))
			goto out;

		od->cache = cache;
		ovl_seek_cursor(od, ctx->pos);
	}

	while (od->cursor != &od->cache->entries) {
		p = list_entry(od->cursor, struct ovl_cache_entry, l_node);
		if (!p->is_whiteout) {
			if (!p->ino || p->check_xwhiteout) {
				err = ovl_cache_update(&file->f_path, p, !p->ino);
				if (err)
					goto out;
			}
		}
		/* ovl_cache_update() sets is_whiteout on stale entry */
		if (!p->is_whiteout) {
			if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
				break;
		}
		od->cursor = p->l_node.next;
		ctx->pos++;
	}
	err = 0;
out:
	revert_creds(old_cred);
	return err;
}

static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin)
{
	loff_t res;
	struct ovl_dir_file *od = file->private_data;

	inode_lock(file_inode(file));
	if (!file->f_pos)
		ovl_dir_reset(file);

	if (od->is_real) {
		res = vfs_llseek(od->realfile, offset, origin);
		file->f_pos = od->realfile->f_pos;
	} else {
		res = -EINVAL;

		switch (origin) {
		case SEEK_CUR:
			offset += file->f_pos;
			break;
		case SEEK_SET:
			break;
		default:
			goto out_unlock;
		}
		if (offset < 0)
			goto out_unlock;

		if (offset != file->f_pos) {
			file->f_pos = offset;
			if (od->cache)
				ovl_seek_cursor(od, offset);
		}
		res = offset;
	}
out_unlock:
	inode_unlock(file_inode(file));

	return res;
}

static struct file *ovl_dir_open_realfile(const struct file *file,
					  const struct path *realpath)
{
	struct file *res;
	const struct cred *old_cred;

	old_cred = ovl_override_creds(file_inode(file)->i_sb);
	res = ovl_path_open(realpath, O_RDONLY | (file->f_flags & O_LARGEFILE));
	revert_creds(old_cred);

	return res;
}

/*
 * Like ovl_real_fdget(), returns upperfile if dir was copied up since open.
 * Unlike ovl_real_fdget(), this caches upperfile in file->private_data.
 *
 * TODO: use same abstract type for file->private_data of dir and file so
 * upperfile could also be cached for files as well.
 */
struct file *ovl_dir_real_file(const struct file *file, bool want_upper)
{

	struct ovl_dir_file *od = file->private_data;
	struct dentry *dentry = file->f_path.dentry;
	struct file *old, *realfile = od->realfile;

	if (!OVL_TYPE_UPPER(ovl_path_type(dentry)))
		return want_upper ? NULL : realfile;

	/*
	 * Need to check if we started out being a lower dir, but got copied up
	 */
	if (!od->is_upper) {
		realfile = READ_ONCE(od->upperfile);
		if (!realfile) {
			struct path upperpath;

			ovl_path_upper(dentry, &upperpath);
			realfile = ovl_dir_open_realfile(file, &upperpath);
			if (IS_ERR(realfile))
				return realfile;

			old = cmpxchg_release(&od->upperfile, NULL, realfile);
			if (old) {
				fput(realfile);
				realfile = old;
			}
		}
	}

	return realfile;
}

static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
			 int datasync)
{
	struct file *realfile;
	int err;

	err = ovl_sync_status(OVL_FS(file_inode(file)->i_sb));
	if (err <= 0)
		return err;

	realfile = ovl_dir_real_file(file, true);
	err = PTR_ERR_OR_ZERO(realfile);

	/* Nothing to sync for lower */
	if (!realfile || err)
		return err;

	return vfs_fsync_range(realfile, start, end, datasync);
}

static int ovl_dir_release(struct inode *inode, struct file *file)
{
	struct ovl_dir_file *od = file->private_data;

	if (od->cache) {
		inode_lock(inode);
		ovl_cache_put(od, inode);
		inode_unlock(inode);
	}
	fput(od->realfile);
	if (od->upperfile)
		fput(od->upperfile);
	kfree(od);

	return 0;
}

static int ovl_dir_open(struct inode *inode, struct file *file)
{
	struct path realpath;
	struct file *realfile;
	struct ovl_dir_file *od;
	enum ovl_path_type type;

	od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL);
	if (!od)
		return -ENOMEM;

	type = ovl_path_real(file->f_path.dentry, &realpath);
	realfile = ovl_dir_open_realfile(file, &realpath);
	if (IS_ERR(realfile)) {
		kfree(od);
		return PTR_ERR(realfile);
	}
	od->realfile = realfile;
	od->is_real = ovl_dir_is_real(inode);
	od->is_upper = OVL_TYPE_UPPER(type);
	file->private_data = od;

	return 0;
}

WRAP_DIR_ITER(ovl_iterate) // FIXME!
const struct file_operations ovl_dir_operations = {
	.read		= generic_read_dir,
	.open		= ovl_dir_open,
	.iterate_shared	= shared_ovl_iterate,
	.llseek		= ovl_dir_llseek,
	.fsync		= ovl_dir_fsync,
	.release	= ovl_dir_release,
};

int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
{
	int err;
	struct ovl_cache_entry *p, *n;
	struct rb_root root = RB_ROOT;
	const struct cred *old_cred;

	old_cred = ovl_override_creds(dentry->d_sb);
	err = ovl_dir_read_merged(dentry, list, &root);
	revert_creds(old_cred);
	if (err)
		return err;

	err = 0;

	list_for_each_entry_safe(p, n, list, l_node) {
		/*
		 * Select whiteouts in upperdir, they should
		 * be cleared when deleting this directory.
		 */
		if (p->is_whiteout) {
			if (p->is_upper)
				continue;
			goto del_entry;
		}

		if (p->name[0] == '.') {
			if (p->len == 1)
				goto del_entry;
			if (p->len == 2 && p->name[1] == '.')
				goto del_entry;
		}
		err = -ENOTEMPTY;
		break;

del_entry:
		list_del(&p->l_node);
		kfree(p);
	}

	return err;
}

void ovl_cleanup_whiteouts(struct ovl_fs *ofs, struct dentry *upper,
			   struct list_head *list)
{
	struct ovl_cache_entry *p;

	inode_lock_nested(upper->d_inode, I_MUTEX_CHILD);
	list_for_each_entry(p, list, l_node) {
		struct dentry *dentry;

		if (WARN_ON(!p->is_whiteout || !p->is_upper))
			continue;

		dentry = ovl_lookup_upper(ofs, p->name, upper, p->len);
		if (IS_ERR(dentry)) {
			pr_err("lookup '%s/%.*s' failed (%i)\n",
			       upper->d_name.name, p->len, p->name,
			       (int) PTR_ERR(dentry));
			continue;
		}
		if (dentry->d_inode)
			ovl_cleanup(ofs, upper->d_inode, dentry);
		dput(dentry);
	}
	inode_unlock(upper->d_inode);
}

static bool ovl_check_d_type(struct dir_context *ctx, const char *name,
			  int namelen, loff_t offset, u64 ino,
			  unsigned int d_type)
{
	struct ovl_readdir_data *rdd =
		container_of(ctx, struct ovl_readdir_data, ctx);

	/* Even if d_type is not supported, DT_DIR is returned for . and .. */
	if (!strncmp(name, ".", namelen) || !strncmp(name, "..", namelen))
		return true;

	if (d_type != DT_UNKNOWN)
		rdd->d_type_supported = true;

	return true;
}

/*
 * Returns 1 if d_type is supported, 0 not supported/unknown. Negative values
 * if error is encountered.
 */
int ovl_check_d_type_supported(const struct path *realpath)
{
	int err;
	struct ovl_readdir_data rdd = {
		.ctx.actor = ovl_check_d_type,
		.d_type_supported = false,
	};

	err = ovl_dir_read(realpath, &rdd);
	if (err)
		return err;

	return rdd.d_type_supported;
}

#define OVL_INCOMPATDIR_NAME "incompat"

static int ovl_workdir_cleanup_recurse(struct ovl_fs *ofs, const struct path *path,
				       int level)
{
	int err;
	struct inode *dir = path->dentry->d_inode;
	LIST_HEAD(list);
	struct ovl_cache_entry *p;
	struct ovl_readdir_data rdd = {
		.ctx.actor = ovl_fill_plain,
		.list = &list,
	};
	bool incompat = false;

	/*
	 * The "work/incompat" directory is treated specially - if it is not
	 * empty, instead of printing a generic error and mounting read-only,
	 * we will error about incompat features and fail the mount.
	 *
	 * When called from ovl_indexdir_cleanup(), path->dentry->d_name.name
	 * starts with '#'.
	 */
	if (level == 2 &&
	    !strcmp(path->dentry->d_name.name, OVL_INCOMPATDIR_NAME))
		incompat = true;

	err = ovl_dir_read(path, &rdd);
	if (err)
		goto out;

	inode_lock_nested(dir, I_MUTEX_PARENT);
	list_for_each_entry(p, &list, l_node) {
		struct dentry *dentry;

		if (p->name[0] == '.') {
			if (p->len == 1)
				continue;
			if (p->len == 2 && p->name[1] == '.')
				continue;
		} else if (incompat) {
			pr_err("overlay with incompat feature '%s' cannot be mounted\n",
				p->name);
			err = -EINVAL;
			break;
		}
		dentry = ovl_lookup_upper(ofs, p->name, path->dentry, p->len);
		if (IS_ERR(dentry))
			continue;
		if (dentry->d_inode)
			err = ovl_workdir_cleanup(ofs, dir, path->mnt, dentry, level);
		dput(dentry);
		if (err)
			break;
	}
	inode_unlock(dir);
out:
	ovl_cache_free(&list);
	return err;
}

int ovl_workdir_cleanup(struct ovl_fs *ofs, struct inode *dir,
			struct vfsmount *mnt, struct dentry *dentry, int level)
{
	int err;

	if (!d_is_dir(dentry) || level > 1) {
		return ovl_cleanup(ofs, dir, dentry);
	}

	err = ovl_do_rmdir(ofs, dir, dentry);
	if (err) {
		struct path path = { .mnt = mnt, .dentry = dentry };

		inode_unlock(dir);
		err = ovl_workdir_cleanup_recurse(ofs, &path, level + 1);
		inode_lock_nested(dir, I_MUTEX_PARENT);
		if (!err)
			err = ovl_cleanup(ofs, dir, dentry);
	}

	return err;
}

int ovl_indexdir_cleanup(struct ovl_fs *ofs)
{
	int err;
	struct dentry *indexdir = ofs->workdir;
	struct dentry *index = NULL;
	struct inode *dir = indexdir->d_inode;
	struct path path = { .mnt = ovl_upper_mnt(ofs), .dentry = indexdir };
	LIST_HEAD(list);
	struct ovl_cache_entry *p;
	struct ovl_readdir_data rdd = {
		.ctx.actor = ovl_fill_plain,
		.list = &list,
	};

	err = ovl_dir_read(&path, &rdd);
	if (err)
		goto out;

	inode_lock_nested(dir, I_MUTEX_PARENT);
	list_for_each_entry(p, &list, l_node) {
		if (p->name[0] == '.') {
			if (p->len == 1)
				continue;
			if (p->len == 2 && p->name[1] == '.')
				continue;
		}
		index = ovl_lookup_upper(ofs, p->name, indexdir, p->len);
		if (IS_ERR(index)) {
			err = PTR_ERR(index);
			index = NULL;
			break;
		}
		/* Cleanup leftover from index create/cleanup attempt */
		if (index->d_name.name[0] == '#') {
			err = ovl_workdir_cleanup(ofs, dir, path.mnt, index, 1);
			if (err)
				break;
			goto next;
		}
		err = ovl_verify_index(ofs, index);
		if (!err) {
			goto next;
		} else if (err == -ESTALE) {
			/* Cleanup stale index entries */
			err = ovl_cleanup(ofs, dir, index);
		} else if (err != -ENOENT) {
			/*
			 * Abort mount to avoid corrupting the index if
			 * an incompatible index entry was found or on out
			 * of memory.
			 */
			break;
		} else if (ofs->config.nfs_export) {
			/*
			 * Whiteout orphan index to block future open by
			 * handle after overlay nlink dropped to zero.
			 */
			err = ovl_cleanup_and_whiteout(ofs, dir, index);
		} else {
			/* Cleanup orphan index entries */
			err = ovl_cleanup(ofs, dir, index);
		}

		if (err)
			break;

next:
		dput(index);
		index = NULL;
	}
	dput(index);
	inode_unlock(dir);
out:
	ovl_cache_free(&list);
	if (err)
		pr_err("failed index dir cleanup (%i)\n", err);
	return err;
}