summaryrefslogtreecommitdiffstats
path: root/fs/overlayfs/super.c
blob: 3d0b9dee2b76771a78179f4691f7bf294b6982b1 (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
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
/*
 *
 * Copyright (C) 2011 Novell Inc.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation.
 */

#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/slab.h>
#include <linux/parser.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/statfs.h>
#include <linux/seq_file.h>
#include <linux/posix_acl_xattr.h>
#include "overlayfs.h"

MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Overlay filesystem");
MODULE_LICENSE("GPL");

struct ovl_config {
	char *lowerdir;
	char *upperdir;
	char *workdir;
	bool default_permissions;
};

/* private information held for overlayfs's superblock */
struct ovl_fs {
	struct vfsmount *upper_mnt;
	unsigned numlower;
	struct vfsmount **lower_mnt;
	struct dentry *workdir;
	long lower_namelen;
	/* pathnames of lower and upper dirs, for show_options */
	struct ovl_config config;
	/* creds of process who forced instantiation of super block */
	const struct cred *creator_cred;
};

struct ovl_dir_cache;

/* private information held for every overlayfs dentry */
struct ovl_entry {
	struct dentry *__upperdentry;
	struct ovl_dir_cache *cache;
	union {
		struct {
			u64 version;
			bool opaque;
		};
		struct rcu_head rcu;
	};
	unsigned numlower;
	struct path lowerstack[];
};

#define OVL_MAX_STACK 500

static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe)
{
	return oe->numlower ? oe->lowerstack[0].dentry : NULL;
}

enum ovl_path_type ovl_path_type(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	enum ovl_path_type type = 0;

	if (oe->__upperdentry) {
		type = __OVL_PATH_UPPER;

		/*
		 * Non-dir dentry can hold lower dentry from previous
		 * location. Its purity depends only on opaque flag.
		 */
		if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode))
			type |= __OVL_PATH_MERGE;
		else if (!oe->opaque)
			type |= __OVL_PATH_PURE;
	} else {
		if (oe->numlower > 1)
			type |= __OVL_PATH_MERGE;
	}
	return type;
}

static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe)
{
	return lockless_dereference(oe->__upperdentry);
}

void ovl_path_upper(struct dentry *dentry, struct path *path)
{
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	struct ovl_entry *oe = dentry->d_fsdata;

	path->mnt = ofs->upper_mnt;
	path->dentry = ovl_upperdentry_dereference(oe);
}

enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
{
	enum ovl_path_type type = ovl_path_type(dentry);

	if (!OVL_TYPE_UPPER(type))
		ovl_path_lower(dentry, path);
	else
		ovl_path_upper(dentry, path);

	return type;
}

struct dentry *ovl_dentry_upper(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	return ovl_upperdentry_dereference(oe);
}

struct dentry *ovl_dentry_lower(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	return __ovl_dentry_lower(oe);
}

struct dentry *ovl_dentry_real(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	struct dentry *realdentry;

	realdentry = ovl_upperdentry_dereference(oe);
	if (!realdentry)
		realdentry = __ovl_dentry_lower(oe);

	return realdentry;
}

static void ovl_inode_init(struct inode *inode, struct inode *realinode,
			   bool is_upper)
{
	WRITE_ONCE(inode->i_private, (unsigned long) realinode |
		   (is_upper ? OVL_ISUPPER_MASK : 0));
}

struct vfsmount *ovl_entry_mnt_real(struct ovl_entry *oe, struct inode *inode,
				    bool is_upper)
{
	if (is_upper) {
		struct ovl_fs *ofs = inode->i_sb->s_fs_info;

		return ofs->upper_mnt;
	} else {
		return oe->numlower ? oe->lowerstack[0].mnt : NULL;
	}
}

struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	return oe->cache;
}

void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	oe->cache = cache;
}

void ovl_path_lower(struct dentry *dentry, struct path *path)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	*path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL };
}

int ovl_want_write(struct dentry *dentry)
{
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	return mnt_want_write(ofs->upper_mnt);
}

void ovl_drop_write(struct dentry *dentry)
{
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	mnt_drop_write(ofs->upper_mnt);
}

struct dentry *ovl_workdir(struct dentry *dentry)
{
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	return ofs->workdir;
}

bool ovl_dentry_is_opaque(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	return oe->opaque;
}

void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	oe->opaque = opaque;
}

void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	WARN_ON(!inode_is_locked(upperdentry->d_parent->d_inode));
	WARN_ON(oe->__upperdentry);
	/*
	 * Make sure upperdentry is consistent before making it visible to
	 * ovl_upperdentry_dereference().
	 */
	smp_wmb();
	oe->__upperdentry = upperdentry;
}

void ovl_inode_update(struct inode *inode, struct inode *upperinode)
{
	WARN_ON(!upperinode);
	WARN_ON(!inode_unhashed(inode));
	WRITE_ONCE(inode->i_private,
		   (unsigned long) upperinode | OVL_ISUPPER_MASK);
	if (!S_ISDIR(upperinode->i_mode))
		__insert_inode_hash(inode, (unsigned long) upperinode);
}

void ovl_dentry_version_inc(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	WARN_ON(!inode_is_locked(dentry->d_inode));
	oe->version++;
}

u64 ovl_dentry_version_get(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	WARN_ON(!inode_is_locked(dentry->d_inode));
	return oe->version;
}

bool ovl_is_whiteout(struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;

	return inode && IS_WHITEOUT(inode);
}

const struct cred *ovl_override_creds(struct super_block *sb)
{
	struct ovl_fs *ofs = sb->s_fs_info;

	return override_creds(ofs->creator_cred);
}

static bool ovl_is_opaquedir(struct dentry *dentry)
{
	int res;
	char val;
	struct inode *inode = dentry->d_inode;

	if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr)
		return false;

	res = inode->i_op->getxattr(dentry, inode, OVL_XATTR_OPAQUE, &val, 1);
	if (res == 1 && val == 'y')
		return true;

	return false;
}

static void ovl_dentry_release(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	if (oe) {
		unsigned int i;

		dput(oe->__upperdentry);
		for (i = 0; i < oe->numlower; i++)
			dput(oe->lowerstack[i].dentry);
		kfree_rcu(oe, rcu);
	}
}

static struct dentry *ovl_d_real(struct dentry *dentry,
				 const struct inode *inode,
				 unsigned int open_flags)
{
	struct dentry *real;

	if (d_is_dir(dentry)) {
		if (!inode || inode == d_inode(dentry))
			return dentry;
		goto bug;
	}

	if (d_is_negative(dentry))
		return dentry;

	if (open_flags) {
		int err = ovl_open_maybe_copy_up(dentry, open_flags);

		if (err)
			return ERR_PTR(err);
	}

	real = ovl_dentry_upper(dentry);
	if (real && (!inode || inode == d_inode(real)))
		return real;

	real = ovl_dentry_lower(dentry);
	if (!real)
		goto bug;

	if (!inode || inode == d_inode(real))
		return real;

	/* Handle recursion */
	return d_real(real, inode, open_flags);
bug:
	WARN(1, "ovl_d_real(%pd4, %s:%lu): real dentry not found\n", dentry,
	     inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0);
	return dentry;
}

static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	unsigned int i;
	int ret = 1;

	for (i = 0; i < oe->numlower; i++) {
		struct dentry *d = oe->lowerstack[i].dentry;

		if (d->d_flags & DCACHE_OP_REVALIDATE) {
			ret = d->d_op->d_revalidate(d, flags);
			if (ret < 0)
				return ret;
			if (!ret) {
				if (!(flags & LOOKUP_RCU))
					d_invalidate(d);
				return -ESTALE;
			}
		}
	}
	return 1;
}

static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	unsigned int i;
	int ret = 1;

	for (i = 0; i < oe->numlower; i++) {
		struct dentry *d = oe->lowerstack[i].dentry;

		if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE) {
			ret = d->d_op->d_weak_revalidate(d, flags);
			if (ret <= 0)
				break;
		}
	}
	return ret;
}

static const struct dentry_operations ovl_dentry_operations = {
	.d_release = ovl_dentry_release,
	.d_real = ovl_d_real,
};

static const struct dentry_operations ovl_reval_dentry_operations = {
	.d_release = ovl_dentry_release,
	.d_real = ovl_d_real,
	.d_revalidate = ovl_dentry_revalidate,
	.d_weak_revalidate = ovl_dentry_weak_revalidate,
};

static struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
{
	size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
	struct ovl_entry *oe = kzalloc(size, GFP_KERNEL);

	if (oe)
		oe->numlower = numlower;

	return oe;
}

static bool ovl_dentry_remote(struct dentry *dentry)
{
	return dentry->d_flags &
		(DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE |
		 DCACHE_OP_REAL);
}

static bool ovl_dentry_weird(struct dentry *dentry)
{
	return dentry->d_flags & (DCACHE_NEED_AUTOMOUNT |
				  DCACHE_MANAGE_TRANSIT |
				  DCACHE_OP_HASH |
				  DCACHE_OP_COMPARE);
}

static inline struct dentry *ovl_lookup_real(struct super_block *ovl_sb,
					     struct dentry *dir,
					     const struct qstr *name)
{
	const struct cred *old_cred;
	struct dentry *dentry;

	old_cred = ovl_override_creds(ovl_sb);
	dentry = lookup_one_len_unlocked(name->name, dir, name->len);
	revert_creds(old_cred);

	if (IS_ERR(dentry)) {
		if (PTR_ERR(dentry) == -ENOENT)
			dentry = NULL;
	} else if (!dentry->d_inode) {
		dput(dentry);
		dentry = NULL;
	} else if (ovl_dentry_weird(dentry)) {
		dput(dentry);
		/* Don't support traversing automounts and other weirdness */
		dentry = ERR_PTR(-EREMOTE);
	}
	return dentry;
}

/*
 * 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 = oe->lowerstack[idx - 1];

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

struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
			  unsigned int flags)
{
	struct ovl_entry *oe;
	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
	struct path *stack = NULL;
	struct dentry *upperdir, *upperdentry = NULL;
	unsigned int ctr = 0;
	struct inode *inode = NULL;
	bool upperopaque = false;
	struct dentry *this, *prev = NULL;
	unsigned int i;
	int err;

	upperdir = ovl_upperdentry_dereference(poe);
	if (upperdir) {
		this = ovl_lookup_real(dentry->d_sb, upperdir, &dentry->d_name);
		err = PTR_ERR(this);
		if (IS_ERR(this))
			goto out;

		if (this) {
			if (unlikely(ovl_dentry_remote(this))) {
				dput(this);
				err = -EREMOTE;
				goto out;
			}
			if (ovl_is_whiteout(this)) {
				dput(this);
				this = NULL;
				upperopaque = true;
			} else if (poe->numlower && ovl_is_opaquedir(this)) {
				upperopaque = true;
			}
		}
		upperdentry = prev = this;
	}

	if (!upperopaque && poe->numlower) {
		err = -ENOMEM;
		stack = kcalloc(poe->numlower, sizeof(struct path), GFP_KERNEL);
		if (!stack)
			goto out_put_upper;
	}

	for (i = 0; !upperopaque && i < poe->numlower; i++) {
		bool opaque = false;
		struct path lowerpath = poe->lowerstack[i];

		this = ovl_lookup_real(dentry->d_sb,
				       lowerpath.dentry, &dentry->d_name);
		err = PTR_ERR(this);
		if (IS_ERR(this)) {
			/*
			 * If it's positive, then treat ENAMETOOLONG as ENOENT.
			 */
			if (err == -ENAMETOOLONG && (upperdentry || ctr))
				continue;
			goto out_put;
		}
		if (!this)
			continue;
		if (ovl_is_whiteout(this)) {
			dput(this);
			break;
		}
		/*
		 * Only makes sense to check opaque dir if this is not the
		 * lowermost layer.
		 */
		if (i < poe->numlower - 1 && ovl_is_opaquedir(this))
			opaque = true;

		if (prev && (!S_ISDIR(prev->d_inode->i_mode) ||
			     !S_ISDIR(this->d_inode->i_mode))) {
			/*
			 * FIXME: check for upper-opaqueness maybe better done
			 * in remove code.
			 */
			if (prev == upperdentry)
				upperopaque = true;
			dput(this);
			break;
		}
		/*
		 * If this is a non-directory then stop here.
		 */
		if (!S_ISDIR(this->d_inode->i_mode))
			opaque = true;

		stack[ctr].dentry = this;
		stack[ctr].mnt = lowerpath.mnt;
		ctr++;
		prev = this;
		if (opaque)
			break;
	}

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

	if (upperdentry || ctr) {
		struct dentry *realdentry;
		struct inode *realinode;

		realdentry = upperdentry ? upperdentry : stack[0].dentry;
		realinode = d_inode(realdentry);

		err = -ENOMEM;
		if (upperdentry && !d_is_dir(upperdentry)) {
			inode = ovl_get_inode(dentry->d_sb, realinode);
		} else {
			inode = ovl_new_inode(dentry->d_sb, realinode->i_mode);
			if (inode)
				ovl_inode_init(inode, realinode, !!upperdentry);
		}
		if (!inode)
			goto out_free_oe;
		ovl_copyattr(realdentry->d_inode, inode);
	}

	oe->opaque = upperopaque;
	oe->__upperdentry = upperdentry;
	memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
	kfree(stack);
	dentry->d_fsdata = oe;
	d_add(dentry, inode);

	return NULL;

out_free_oe:
	kfree(oe);
out_put:
	for (i = 0; i < ctr; i++)
		dput(stack[i].dentry);
	kfree(stack);
out_put_upper:
	dput(upperdentry);
out:
	return ERR_PTR(err);
}

struct file *ovl_path_open(struct path *path, int flags)
{
	return dentry_open(path, flags | O_NOATIME, current_cred());
}

static void ovl_put_super(struct super_block *sb)
{
	struct ovl_fs *ufs = sb->s_fs_info;
	unsigned i;

	dput(ufs->workdir);
	mntput(ufs->upper_mnt);
	for (i = 0; i < ufs->numlower; i++)
		mntput(ufs->lower_mnt[i]);
	kfree(ufs->lower_mnt);

	kfree(ufs->config.lowerdir);
	kfree(ufs->config.upperdir);
	kfree(ufs->config.workdir);
	put_cred(ufs->creator_cred);
	kfree(ufs);
}

/**
 * ovl_statfs
 * @sb: The overlayfs super block
 * @buf: The struct kstatfs to fill in with stats
 *
 * Get the filesystem statistics.  As writes always target the upper layer
 * filesystem pass the statfs to the upper filesystem (if it exists)
 */
static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	struct dentry *root_dentry = dentry->d_sb->s_root;
	struct path path;
	int err;

	ovl_path_real(root_dentry, &path);

	err = vfs_statfs(&path, buf);
	if (!err) {
		buf->f_namelen = max(buf->f_namelen, ofs->lower_namelen);
		buf->f_type = OVERLAYFS_SUPER_MAGIC;
	}

	return err;
}

/**
 * ovl_show_options
 *
 * Prints the mount options for a given superblock.
 * Returns zero; does not fail.
 */
static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
{
	struct super_block *sb = dentry->d_sb;
	struct ovl_fs *ufs = sb->s_fs_info;

	seq_show_option(m, "lowerdir", ufs->config.lowerdir);
	if (ufs->config.upperdir) {
		seq_show_option(m, "upperdir", ufs->config.upperdir);
		seq_show_option(m, "workdir", ufs->config.workdir);
	}
	if (ufs->config.default_permissions)
		seq_puts(m, ",default_permissions");
	return 0;
}

static int ovl_remount(struct super_block *sb, int *flags, char *data)
{
	struct ovl_fs *ufs = sb->s_fs_info;

	if (!(*flags & MS_RDONLY) && (!ufs->upper_mnt || !ufs->workdir))
		return -EROFS;

	return 0;
}

static const struct super_operations ovl_super_operations = {
	.put_super	= ovl_put_super,
	.statfs		= ovl_statfs,
	.show_options	= ovl_show_options,
	.remount_fs	= ovl_remount,
	.drop_inode	= generic_delete_inode,
};

enum {
	OPT_LOWERDIR,
	OPT_UPPERDIR,
	OPT_WORKDIR,
	OPT_DEFAULT_PERMISSIONS,
	OPT_ERR,
};

static const match_table_t ovl_tokens = {
	{OPT_LOWERDIR,			"lowerdir=%s"},
	{OPT_UPPERDIR,			"upperdir=%s"},
	{OPT_WORKDIR,			"workdir=%s"},
	{OPT_DEFAULT_PERMISSIONS,	"default_permissions"},
	{OPT_ERR,			NULL}
};

static char *ovl_next_opt(char **s)
{
	char *sbegin = *s;
	char *p;

	if (sbegin == NULL)
		return NULL;

	for (p = sbegin; *p; p++) {
		if (*p == '\\') {
			p++;
			if (!*p)
				break;
		} else if (*p == ',') {
			*p = '\0';
			*s = p + 1;
			return sbegin;
		}
	}
	*s = NULL;
	return sbegin;
}

static int ovl_parse_opt(char *opt, struct ovl_config *config)
{
	char *p;

	while ((p = ovl_next_opt(&opt)) != NULL) {
		int token;
		substring_t args[MAX_OPT_ARGS];

		if (!*p)
			continue;

		token = match_token(p, ovl_tokens, args);
		switch (token) {
		case OPT_UPPERDIR:
			kfree(config->upperdir);
			config->upperdir = match_strdup(&args[0]);
			if (!config->upperdir)
				return -ENOMEM;
			break;

		case OPT_LOWERDIR:
			kfree(config->lowerdir);
			config->lowerdir = match_strdup(&args[0]);
			if (!config->lowerdir)
				return -ENOMEM;
			break;

		case OPT_WORKDIR:
			kfree(config->workdir);
			config->workdir = match_strdup(&args[0]);
			if (!config->workdir)
				return -ENOMEM;
			break;

		case OPT_DEFAULT_PERMISSIONS:
			config->default_permissions = true;
			break;

		default:
			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
			return -EINVAL;
		}
	}

	/* Workdir is useless in non-upper mount */
	if (!config->upperdir && config->workdir) {
		pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
			config->workdir);
		kfree(config->workdir);
		config->workdir = NULL;
	}

	return 0;
}

#define OVL_WORKDIR_NAME "work"

static struct dentry *ovl_workdir_create(struct vfsmount *mnt,
					 struct dentry *dentry)
{
	struct inode *dir = dentry->d_inode;
	struct dentry *work;
	int err;
	bool retried = false;

	err = mnt_want_write(mnt);
	if (err)
		return ERR_PTR(err);

	inode_lock_nested(dir, I_MUTEX_PARENT);
retry:
	work = lookup_one_len(OVL_WORKDIR_NAME, dentry,
			      strlen(OVL_WORKDIR_NAME));

	if (!IS_ERR(work)) {
		struct kstat stat = {
			.mode = S_IFDIR | 0,
		};
		struct iattr attr = {
			.ia_valid = ATTR_MODE,
			.ia_mode = stat.mode,
		};

		if (work->d_inode) {
			err = -EEXIST;
			if (retried)
				goto out_dput;

			retried = true;
			ovl_workdir_cleanup(dir, mnt, work, 0);
			dput(work);
			goto retry;
		}

		err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
		if (err)
			goto out_dput;

		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
		if (err && err != -ENODATA && err != -EOPNOTSUPP)
			goto out_dput;

		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
		if (err && err != -ENODATA && err != -EOPNOTSUPP)
			goto out_dput;

		/* Clear any inherited mode bits */
		inode_lock(work->d_inode);
		err = notify_change(work, &attr, NULL);
		inode_unlock(work->d_inode);
		if (err)
			goto out_dput;
	}
out_unlock:
	inode_unlock(dir);
	mnt_drop_write(mnt);

	return work;

out_dput:
	dput(work);
	work = ERR_PTR(err);
	goto out_unlock;
}

static void ovl_unescape(char *s)
{
	char *d = s;

	for (;; s++, d++) {
		if (*s == '\\')
			s++;
		*d = *s;
		if (!*s)
			break;
	}
}

static int ovl_mount_dir_noesc(const char *name, struct path *path)
{
	int err = -EINVAL;

	if (!*name) {
		pr_err("overlayfs: empty lowerdir\n");
		goto out;
	}
	err = kern_path(name, LOOKUP_FOLLOW, path);
	if (err) {
		pr_err("overlayfs: failed to resolve '%s': %i\n", name, err);
		goto out;
	}
	err = -EINVAL;
	if (ovl_dentry_weird(path->dentry)) {
		pr_err("overlayfs: filesystem on '%s' not supported\n", name);
		goto out_put;
	}
	if (!S_ISDIR(path->dentry->d_inode->i_mode)) {
		pr_err("overlayfs: '%s' not a directory\n", name);
		goto out_put;
	}
	return 0;

out_put:
	path_put(path);
out:
	return err;
}

static int ovl_mount_dir(const char *name, struct path *path)
{
	int err = -ENOMEM;
	char *tmp = kstrdup(name, GFP_KERNEL);

	if (tmp) {
		ovl_unescape(tmp);
		err = ovl_mount_dir_noesc(tmp, path);

		if (!err)
			if (ovl_dentry_remote(path->dentry)) {
				pr_err("overlayfs: filesystem on '%s' not supported as upperdir\n",
				       tmp);
				path_put(path);
				err = -EINVAL;
			}
		kfree(tmp);
	}
	return err;
}

static int ovl_lower_dir(const char *name, struct path *path, long *namelen,
			 int *stack_depth, bool *remote)
{
	int err;
	struct kstatfs statfs;

	err = ovl_mount_dir_noesc(name, path);
	if (err)
		goto out;

	err = vfs_statfs(path, &statfs);
	if (err) {
		pr_err("overlayfs: statfs failed on '%s'\n", name);
		goto out_put;
	}
	*namelen = max(*namelen, statfs.f_namelen);
	*stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);

	if (ovl_dentry_remote(path->dentry))
		*remote = true;

	return 0;

out_put:
	path_put(path);
out:
	return err;
}

/* Workdir should not be subdir of upperdir and vice versa */
static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir)
{
	bool ok = false;

	if (workdir != upperdir) {
		ok = (lock_rename(workdir, upperdir) == NULL);
		unlock_rename(workdir, upperdir);
	}
	return ok;
}

static unsigned int ovl_split_lowerdirs(char *str)
{
	unsigned int ctr = 1;
	char *s, *d;

	for (s = d = str;; s++, d++) {
		if (*s == '\\') {
			s++;
		} else if (*s == ':') {
			*d = '\0';
			ctr++;
			continue;
		}
		*d = *s;
		if (!*s)
			break;
	}
	return ctr;
}

static int __maybe_unused
ovl_posix_acl_xattr_get(const struct xattr_handler *handler,
			struct dentry *dentry, struct inode *inode,
			const char *name, void *buffer, size_t size)
{
	return ovl_xattr_get(dentry, handler->name, buffer, size);
}

static int __maybe_unused
ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
			struct dentry *dentry, struct inode *inode,
			const char *name, const void *value,
			size_t size, int flags)
{
	struct dentry *workdir = ovl_workdir(dentry);
	struct inode *realinode = ovl_inode_real(inode, NULL);
	struct posix_acl *acl = NULL;
	int err;

	/* Check that everything is OK before copy-up */
	if (value) {
		acl = posix_acl_from_xattr(&init_user_ns, value, size);
		if (IS_ERR(acl))
			return PTR_ERR(acl);
	}
	err = -EOPNOTSUPP;
	if (!IS_POSIXACL(d_inode(workdir)))
		goto out_acl_release;
	if (!realinode->i_op->set_acl)
		goto out_acl_release;
	if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) {
		err = acl ? -EACCES : 0;
		goto out_acl_release;
	}
	err = -EPERM;
	if (!inode_owner_or_capable(inode))
		goto out_acl_release;

	posix_acl_release(acl);

	err = ovl_xattr_set(dentry, handler->name, value, size, flags);
	if (!err)
		ovl_copyattr(ovl_inode_real(inode, NULL), inode);

	return err;

out_acl_release:
	posix_acl_release(acl);
	return err;
}

static int ovl_own_xattr_get(const struct xattr_handler *handler,
			     struct dentry *dentry, struct inode *inode,
			     const char *name, void *buffer, size_t size)
{
	return -EPERM;
}

static int ovl_own_xattr_set(const struct xattr_handler *handler,
			     struct dentry *dentry, struct inode *inode,
			     const char *name, const void *value,
			     size_t size, int flags)
{
	return -EPERM;
}

static int ovl_other_xattr_get(const struct xattr_handler *handler,
			       struct dentry *dentry, struct inode *inode,
			       const char *name, void *buffer, size_t size)
{
	return ovl_xattr_get(dentry, name, buffer, size);
}

static int ovl_other_xattr_set(const struct xattr_handler *handler,
			       struct dentry *dentry, struct inode *inode,
			       const char *name, const void *value,
			       size_t size, int flags)
{
	return ovl_xattr_set(dentry, name, value, size, flags);
}

static const struct xattr_handler __maybe_unused
ovl_posix_acl_access_xattr_handler = {
	.name = XATTR_NAME_POSIX_ACL_ACCESS,
	.flags = ACL_TYPE_ACCESS,
	.get = ovl_posix_acl_xattr_get,
	.set = ovl_posix_acl_xattr_set,
};

static const struct xattr_handler __maybe_unused
ovl_posix_acl_default_xattr_handler = {
	.name = XATTR_NAME_POSIX_ACL_DEFAULT,
	.flags = ACL_TYPE_DEFAULT,
	.get = ovl_posix_acl_xattr_get,
	.set = ovl_posix_acl_xattr_set,
};

static const struct xattr_handler ovl_own_xattr_handler = {
	.prefix	= OVL_XATTR_PREFIX,
	.get = ovl_own_xattr_get,
	.set = ovl_own_xattr_set,
};

static const struct xattr_handler ovl_other_xattr_handler = {
	.prefix	= "", /* catch all */
	.get = ovl_other_xattr_get,
	.set = ovl_other_xattr_set,
};

static const struct xattr_handler *ovl_xattr_handlers[] = {
#ifdef CONFIG_FS_POSIX_ACL
	&ovl_posix_acl_access_xattr_handler,
	&ovl_posix_acl_default_xattr_handler,
#endif
	&ovl_own_xattr_handler,
	&ovl_other_xattr_handler,
	NULL
};

static int ovl_fill_super(struct super_block *sb, void *data, int silent)
{
	struct path upperpath = { NULL, NULL };
	struct path workpath = { NULL, NULL };
	struct dentry *root_dentry;
	struct inode *realinode;
	struct ovl_entry *oe;
	struct ovl_fs *ufs;
	struct path *stack = NULL;
	char *lowertmp;
	char *lower;
	unsigned int numlower;
	unsigned int stacklen = 0;
	unsigned int i;
	bool remote = false;
	int err;

	err = -ENOMEM;
	ufs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL);
	if (!ufs)
		goto out;

	err = ovl_parse_opt((char *) data, &ufs->config);
	if (err)
		goto out_free_config;

	err = -EINVAL;
	if (!ufs->config.lowerdir) {
		if (!silent)
			pr_err("overlayfs: missing 'lowerdir'\n");
		goto out_free_config;
	}

	sb->s_stack_depth = 0;
	sb->s_maxbytes = MAX_LFS_FILESIZE;
	if (ufs->config.upperdir) {
		if (!ufs->config.workdir) {
			pr_err("overlayfs: missing 'workdir'\n");
			goto out_free_config;
		}

		err = ovl_mount_dir(ufs->config.upperdir, &upperpath);
		if (err)
			goto out_free_config;

		/* Upper fs should not be r/o */
		if (upperpath.mnt->mnt_sb->s_flags & MS_RDONLY) {
			pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n");
			err = -EINVAL;
			goto out_put_upperpath;
		}

		err = ovl_mount_dir(ufs->config.workdir, &workpath);
		if (err)
			goto out_put_upperpath;

		err = -EINVAL;
		if (upperpath.mnt != workpath.mnt) {
			pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
			goto out_put_workpath;
		}
		if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) {
			pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
			goto out_put_workpath;
		}
		sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth;
	}
	err = -ENOMEM;
	lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL);
	if (!lowertmp)
		goto out_put_workpath;

	err = -EINVAL;
	stacklen = ovl_split_lowerdirs(lowertmp);
	if (stacklen > OVL_MAX_STACK) {
		pr_err("overlayfs: too many lower directories, limit is %d\n",
		       OVL_MAX_STACK);
		goto out_free_lowertmp;
	} else if (!ufs->config.upperdir && stacklen == 1) {
		pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
		goto out_free_lowertmp;
	}

	stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL);
	if (!stack)
		goto out_free_lowertmp;

	lower = lowertmp;
	for (numlower = 0; numlower < stacklen; numlower++) {
		err = ovl_lower_dir(lower, &stack[numlower],
				    &ufs->lower_namelen, &sb->s_stack_depth,
				    &remote);
		if (err)
			goto out_put_lowerpath;

		lower = strchr(lower, '\0') + 1;
	}

	err = -EINVAL;
	sb->s_stack_depth++;
	if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
		pr_err("overlayfs: maximum fs stacking depth exceeded\n");
		goto out_put_lowerpath;
	}

	if (ufs->config.upperdir) {
		ufs->upper_mnt = clone_private_mount(&upperpath);
		err = PTR_ERR(ufs->upper_mnt);
		if (IS_ERR(ufs->upper_mnt)) {
			pr_err("overlayfs: failed to clone upperpath\n");
			goto out_put_lowerpath;
		}
		/* Don't inherit atime flags */
		ufs->upper_mnt->mnt_flags &= ~(MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME);

		sb->s_time_gran = ufs->upper_mnt->mnt_sb->s_time_gran;

		ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry);
		err = PTR_ERR(ufs->workdir);
		if (IS_ERR(ufs->workdir)) {
			pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
				ufs->config.workdir, OVL_WORKDIR_NAME, -err);
			sb->s_flags |= MS_RDONLY;
			ufs->workdir = NULL;
		}

		/*
		 * Upper should support d_type, else whiteouts are visible.
		 * Given workdir and upper are on same fs, we can do
		 * iterate_dir() on workdir. This check requires successful
		 * creation of workdir in previous step.
		 */
		if (ufs->workdir) {
			err = ovl_check_d_type_supported(&workpath);
			if (err < 0)
				goto out_put_workdir;

			/*
			 * We allowed this configuration and don't want to
			 * break users over kernel upgrade. So warn instead
			 * of erroring out.
			 */
			if (!err)
				pr_warn("overlayfs: upper fs needs to support d_type.\n");
		}
	}

	err = -ENOMEM;
	ufs->lower_mnt = kcalloc(numlower, sizeof(struct vfsmount *), GFP_KERNEL);
	if (ufs->lower_mnt == NULL)
		goto out_put_workdir;
	for (i = 0; i < numlower; i++) {
		struct vfsmount *mnt = clone_private_mount(&stack[i]);

		err = PTR_ERR(mnt);
		if (IS_ERR(mnt)) {
			pr_err("overlayfs: failed to clone lowerpath\n");
			goto out_put_lower_mnt;
		}
		/*
		 * Make lower_mnt R/O.  That way fchmod/fchown on lower file
		 * will fail instead of modifying lower fs.
		 */
		mnt->mnt_flags |= MNT_READONLY | MNT_NOATIME;

		ufs->lower_mnt[ufs->numlower] = mnt;
		ufs->numlower++;
	}

	/* If the upper fs is nonexistent, we mark overlayfs r/o too */
	if (!ufs->upper_mnt)
		sb->s_flags |= MS_RDONLY;

	if (remote)
		sb->s_d_op = &ovl_reval_dentry_operations;
	else
		sb->s_d_op = &ovl_dentry_operations;

	ufs->creator_cred = prepare_creds();
	if (!ufs->creator_cred)
		goto out_put_lower_mnt;

	err = -ENOMEM;
	oe = ovl_alloc_entry(numlower);
	if (!oe)
		goto out_put_cred;

	root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR));
	if (!root_dentry)
		goto out_free_oe;

	mntput(upperpath.mnt);
	for (i = 0; i < numlower; i++)
		mntput(stack[i].mnt);
	path_put(&workpath);
	kfree(lowertmp);

	oe->__upperdentry = upperpath.dentry;
	for (i = 0; i < numlower; i++) {
		oe->lowerstack[i].dentry = stack[i].dentry;
		oe->lowerstack[i].mnt = ufs->lower_mnt[i];
	}
	kfree(stack);

	root_dentry->d_fsdata = oe;

	realinode = d_inode(ovl_dentry_real(root_dentry));
	ovl_inode_init(d_inode(root_dentry), realinode, !!upperpath.dentry);
	ovl_copyattr(realinode, d_inode(root_dentry));

	sb->s_magic = OVERLAYFS_SUPER_MAGIC;
	sb->s_op = &ovl_super_operations;
	sb->s_xattr = ovl_xattr_handlers;
	sb->s_root = root_dentry;
	sb->s_fs_info = ufs;
	sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK;

	return 0;

out_free_oe:
	kfree(oe);
out_put_cred:
	put_cred(ufs->creator_cred);
out_put_lower_mnt:
	for (i = 0; i < ufs->numlower; i++)
		mntput(ufs->lower_mnt[i]);
	kfree(ufs->lower_mnt);
out_put_workdir:
	dput(ufs->workdir);
	mntput(ufs->upper_mnt);
out_put_lowerpath:
	for (i = 0; i < numlower; i++)
		path_put(&stack[i]);
	kfree(stack);
out_free_lowertmp:
	kfree(lowertmp);
out_put_workpath:
	path_put(&workpath);
out_put_upperpath:
	path_put(&upperpath);
out_free_config:
	kfree(ufs->config.lowerdir);
	kfree(ufs->config.upperdir);
	kfree(ufs->config.workdir);
	kfree(ufs);
out:
	return err;
}

static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags,
				const char *dev_name, void *raw_data)
{
	return mount_nodev(fs_type, flags, raw_data, ovl_fill_super);
}

static struct file_system_type ovl_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "overlay",
	.mount		= ovl_mount,
	.kill_sb	= kill_anon_super,
};
MODULE_ALIAS_FS("overlay");

static int __init ovl_init(void)
{
	return register_filesystem(&ovl_fs_type);
}

static void __exit ovl_exit(void)
{
	unregister_filesystem(&ovl_fs_type);
}

module_init(ovl_init);
module_exit(ovl_exit);