summaryrefslogtreecommitdiff
path: root/fs/overlayfs/super.c
blob: cc51d2f9b7ad24321669f128843d50938fb778ce (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
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
// SPDX-License-Identifier: GPL-2.0-only
/*
 *
 * Copyright (C) 2011 Novell Inc.
 */

#include <uapi/linux/magic.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/xattr.h>
#include <linux/mount.h>
#include <linux/parser.h>
#include <linux/module.h>
#include <linux/statfs.h>
#include <linux/seq_file.h>
#include <linux/posix_acl_xattr.h>
#include <linux/exportfs.h>
#include "overlayfs.h"

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


struct ovl_dir_cache;

#define OVL_MAX_STACK 500

static bool ovl_redirect_dir_def = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_DIR);
module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644);
MODULE_PARM_DESC(ovl_redirect_dir_def,
		 "Default to on or off for the redirect_dir feature");

static bool ovl_redirect_always_follow =
	IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW);
module_param_named(redirect_always_follow, ovl_redirect_always_follow,
		   bool, 0644);
MODULE_PARM_DESC(ovl_redirect_always_follow,
		 "Follow redirects even if redirect_dir feature is turned off");

static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX);
module_param_named(index, ovl_index_def, bool, 0644);
MODULE_PARM_DESC(ovl_index_def,
		 "Default to on or off for the inodes index feature");

static bool ovl_nfs_export_def = IS_ENABLED(CONFIG_OVERLAY_FS_NFS_EXPORT);
module_param_named(nfs_export, ovl_nfs_export_def, bool, 0644);
MODULE_PARM_DESC(ovl_nfs_export_def,
		 "Default to on or off for the NFS export feature");

static bool ovl_xino_auto_def = IS_ENABLED(CONFIG_OVERLAY_FS_XINO_AUTO);
module_param_named(xino_auto, ovl_xino_auto_def, bool, 0644);
MODULE_PARM_DESC(ovl_xino_auto_def,
		 "Auto enable xino feature");

static void ovl_entry_stack_free(struct ovl_entry *oe)
{
	unsigned int i;

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

static bool ovl_metacopy_def = IS_ENABLED(CONFIG_OVERLAY_FS_METACOPY);
module_param_named(metacopy, ovl_metacopy_def, bool, 0644);
MODULE_PARM_DESC(ovl_metacopy_def,
		 "Default to on or off for the metadata only copy up feature");

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

	if (oe) {
		ovl_entry_stack_free(oe);
		kfree_rcu(oe, rcu);
	}
}

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

	/* It's an overlay file */
	if (inode && d_inode(dentry) == inode)
		return dentry;

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

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

	if (real && !inode && ovl_has_upperdata(d_inode(dentry)))
		return real;

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

	/* Handle recursion */
	real = d_real(real, inode);

	if (!inode || inode == d_inode(real))
		return real;
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 kmem_cache *ovl_inode_cachep;

static struct inode *ovl_alloc_inode(struct super_block *sb)
{
	struct ovl_inode *oi = kmem_cache_alloc(ovl_inode_cachep, GFP_KERNEL);

	if (!oi)
		return NULL;

	oi->cache = NULL;
	oi->redirect = NULL;
	oi->version = 0;
	oi->flags = 0;
	oi->__upperdentry = NULL;
	oi->lower = NULL;
	oi->lowerdata = NULL;
	mutex_init(&oi->lock);

	return &oi->vfs_inode;
}

static void ovl_free_inode(struct inode *inode)
{
	struct ovl_inode *oi = OVL_I(inode);

	kfree(oi->redirect);
	mutex_destroy(&oi->lock);
	kmem_cache_free(ovl_inode_cachep, oi);
}

static void ovl_destroy_inode(struct inode *inode)
{
	struct ovl_inode *oi = OVL_I(inode);

	dput(oi->__upperdentry);
	iput(oi->lower);
	if (S_ISDIR(inode->i_mode))
		ovl_dir_cache_free(inode);
	else
		iput(oi->lowerdata);
}

static void ovl_free_fs(struct ovl_fs *ofs)
{
	unsigned i;

	iput(ofs->indexdir_trap);
	iput(ofs->workdir_trap);
	iput(ofs->upperdir_trap);
	dput(ofs->indexdir);
	dput(ofs->workdir);
	if (ofs->workdir_locked)
		ovl_inuse_unlock(ofs->workbasedir);
	dput(ofs->workbasedir);
	if (ofs->upperdir_locked)
		ovl_inuse_unlock(ofs->upper_mnt->mnt_root);
	mntput(ofs->upper_mnt);
	for (i = 0; i < ofs->numlower; i++) {
		iput(ofs->lower_layers[i].trap);
		mntput(ofs->lower_layers[i].mnt);
	}
	for (i = 0; i < ofs->numlowerfs; i++)
		free_anon_bdev(ofs->lower_fs[i].pseudo_dev);
	kfree(ofs->lower_layers);
	kfree(ofs->lower_fs);

	kfree(ofs->config.lowerdir);
	kfree(ofs->config.upperdir);
	kfree(ofs->config.workdir);
	kfree(ofs->config.redirect_mode);
	if (ofs->creator_cred)
		put_cred(ofs->creator_cred);
	kfree(ofs);
}

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

	ovl_free_fs(ofs);
}

/* Sync real dirty inodes in upper filesystem (if it exists) */
static int ovl_sync_fs(struct super_block *sb, int wait)
{
	struct ovl_fs *ofs = sb->s_fs_info;
	struct super_block *upper_sb;
	int ret;

	if (!ofs->upper_mnt)
		return 0;

	/*
	 * If this is a sync(2) call or an emergency sync, all the super blocks
	 * will be iterated, including upper_sb, so no need to do anything.
	 *
	 * If this is a syncfs(2) call, then we do need to call
	 * sync_filesystem() on upper_sb, but enough if we do it when being
	 * called with wait == 1.
	 */
	if (!wait)
		return 0;

	upper_sb = ofs->upper_mnt->mnt_sb;

	down_read(&upper_sb->s_umount);
	ret = sync_filesystem(upper_sb);
	up_read(&upper_sb->s_umount);

	return ret;
}

/**
 * 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 = ofs->namelen;
		buf->f_type = OVERLAYFS_SUPER_MAGIC;
	}

	return err;
}

/* Will this overlay be forced to mount/remount ro? */
static bool ovl_force_readonly(struct ovl_fs *ofs)
{
	return (!ofs->upper_mnt || !ofs->workdir);
}

static const char *ovl_redirect_mode_def(void)
{
	return ovl_redirect_dir_def ? "on" : "off";
}

enum {
	OVL_XINO_OFF,
	OVL_XINO_AUTO,
	OVL_XINO_ON,
};

static const char * const ovl_xino_str[] = {
	"off",
	"auto",
	"on",
};

static inline int ovl_xino_def(void)
{
	return ovl_xino_auto_def ? OVL_XINO_AUTO : OVL_XINO_OFF;
}

/**
 * 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 *ofs = sb->s_fs_info;

	seq_show_option(m, "lowerdir", ofs->config.lowerdir);
	if (ofs->config.upperdir) {
		seq_show_option(m, "upperdir", ofs->config.upperdir);
		seq_show_option(m, "workdir", ofs->config.workdir);
	}
	if (ofs->config.default_permissions)
		seq_puts(m, ",default_permissions");
	if (strcmp(ofs->config.redirect_mode, ovl_redirect_mode_def()) != 0)
		seq_printf(m, ",redirect_dir=%s", ofs->config.redirect_mode);
	if (ofs->config.index != ovl_index_def)
		seq_printf(m, ",index=%s", ofs->config.index ? "on" : "off");
	if (ofs->config.nfs_export != ovl_nfs_export_def)
		seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ?
						"on" : "off");
	if (ofs->config.xino != ovl_xino_def())
		seq_printf(m, ",xino=%s", ovl_xino_str[ofs->config.xino]);
	if (ofs->config.metacopy != ovl_metacopy_def)
		seq_printf(m, ",metacopy=%s",
			   ofs->config.metacopy ? "on" : "off");
	return 0;
}

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

	if (!(*flags & SB_RDONLY) && ovl_force_readonly(ofs))
		return -EROFS;

	return 0;
}

static const struct super_operations ovl_super_operations = {
	.alloc_inode	= ovl_alloc_inode,
	.free_inode	= ovl_free_inode,
	.destroy_inode	= ovl_destroy_inode,
	.drop_inode	= generic_delete_inode,
	.put_super	= ovl_put_super,
	.sync_fs	= ovl_sync_fs,
	.statfs		= ovl_statfs,
	.show_options	= ovl_show_options,
	.remount_fs	= ovl_remount,
};

enum {
	OPT_LOWERDIR,
	OPT_UPPERDIR,
	OPT_WORKDIR,
	OPT_DEFAULT_PERMISSIONS,
	OPT_REDIRECT_DIR,
	OPT_INDEX_ON,
	OPT_INDEX_OFF,
	OPT_NFS_EXPORT_ON,
	OPT_NFS_EXPORT_OFF,
	OPT_XINO_ON,
	OPT_XINO_OFF,
	OPT_XINO_AUTO,
	OPT_METACOPY_ON,
	OPT_METACOPY_OFF,
	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_REDIRECT_DIR,		"redirect_dir=%s"},
	{OPT_INDEX_ON,			"index=on"},
	{OPT_INDEX_OFF,			"index=off"},
	{OPT_NFS_EXPORT_ON,		"nfs_export=on"},
	{OPT_NFS_EXPORT_OFF,		"nfs_export=off"},
	{OPT_XINO_ON,			"xino=on"},
	{OPT_XINO_OFF,			"xino=off"},
	{OPT_XINO_AUTO,			"xino=auto"},
	{OPT_METACOPY_ON,		"metacopy=on"},
	{OPT_METACOPY_OFF,		"metacopy=off"},
	{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_redirect_mode(struct ovl_config *config, const char *mode)
{
	if (strcmp(mode, "on") == 0) {
		config->redirect_dir = true;
		/*
		 * Does not make sense to have redirect creation without
		 * redirect following.
		 */
		config->redirect_follow = true;
	} else if (strcmp(mode, "follow") == 0) {
		config->redirect_follow = true;
	} else if (strcmp(mode, "off") == 0) {
		if (ovl_redirect_always_follow)
			config->redirect_follow = true;
	} else if (strcmp(mode, "nofollow") != 0) {
		pr_err("overlayfs: bad mount option \"redirect_dir=%s\"\n",
		       mode);
		return -EINVAL;
	}

	return 0;
}

static int ovl_parse_opt(char *opt, struct ovl_config *config)
{
	char *p;
	int err;
	bool metacopy_opt = false, redirect_opt = false;

	config->redirect_mode = kstrdup(ovl_redirect_mode_def(), GFP_KERNEL);
	if (!config->redirect_mode)
		return -ENOMEM;

	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;

		case OPT_REDIRECT_DIR:
			kfree(config->redirect_mode);
			config->redirect_mode = match_strdup(&args[0]);
			if (!config->redirect_mode)
				return -ENOMEM;
			redirect_opt = true;
			break;

		case OPT_INDEX_ON:
			config->index = true;
			break;

		case OPT_INDEX_OFF:
			config->index = false;
			break;

		case OPT_NFS_EXPORT_ON:
			config->nfs_export = true;
			break;

		case OPT_NFS_EXPORT_OFF:
			config->nfs_export = false;
			break;

		case OPT_XINO_ON:
			config->xino = OVL_XINO_ON;
			break;

		case OPT_XINO_OFF:
			config->xino = OVL_XINO_OFF;
			break;

		case OPT_XINO_AUTO:
			config->xino = OVL_XINO_AUTO;
			break;

		case OPT_METACOPY_ON:
			config->metacopy = true;
			metacopy_opt = true;
			break;

		case OPT_METACOPY_OFF:
			config->metacopy = false;
			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;
	}

	err = ovl_parse_redirect_mode(config, config->redirect_mode);
	if (err)
		return err;

	/*
	 * This is to make the logic below simpler.  It doesn't make any other
	 * difference, since config->redirect_dir is only used for upper.
	 */
	if (!config->upperdir && config->redirect_follow)
		config->redirect_dir = true;

	/* Resolve metacopy -> redirect_dir dependency */
	if (config->metacopy && !config->redirect_dir) {
		if (metacopy_opt && redirect_opt) {
			pr_err("overlayfs: conflicting options: metacopy=on,redirect_dir=%s\n",
			       config->redirect_mode);
			return -EINVAL;
		}
		if (redirect_opt) {
			/*
			 * There was an explicit redirect_dir=... that resulted
			 * in this conflict.
			 */
			pr_info("overlayfs: disabling metacopy due to redirect_dir=%s\n",
				config->redirect_mode);
			config->metacopy = false;
		} else {
			/* Automatically enable redirect otherwise. */
			config->redirect_follow = config->redirect_dir = true;
		}
	}

	return 0;
}

#define OVL_WORKDIR_NAME "work"
#define OVL_INDEXDIR_NAME "index"

static struct dentry *ovl_workdir_create(struct ovl_fs *ofs,
					 const char *name, bool persist)
{
	struct inode *dir =  ofs->workbasedir->d_inode;
	struct vfsmount *mnt = ofs->upper_mnt;
	struct dentry *work;
	int err;
	bool retried = false;
	bool locked = false;

	inode_lock_nested(dir, I_MUTEX_PARENT);
	locked = true;

retry:
	work = lookup_one_len(name, ofs->workbasedir, strlen(name));

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

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

			if (persist)
				goto out_unlock;

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

		work = ovl_create_real(dir, work, OVL_CATTR(attr.ia_mode));
		err = PTR_ERR(work);
		if (IS_ERR(work))
			goto out_err;

		/*
		 * Try to remove POSIX ACL xattrs from workdir.  We are good if:
		 *
		 * a) success (there was a POSIX ACL xattr and was removed)
		 * b) -ENODATA (there was no POSIX ACL xattr)
		 * c) -EOPNOTSUPP (POSIX ACL xattrs are not supported)
		 *
		 * There are various other error values that could effectively
		 * mean that the xattr doesn't exist (e.g. -ERANGE is returned
		 * if the xattr name is too long), but the set of filesystems
		 * allowed as upper are limited to "normal" ones, where checking
		 * for the above two errors is sufficient.
		 */
		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;
	} else {
		err = PTR_ERR(work);
		goto out_err;
	}
out_unlock:
	if (locked)
		inode_unlock(dir);

	return work;

out_dput:
	dput(work);
out_err:
	pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
		ofs->config.workdir, name, -err);
	work = NULL;
	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 (!d_is_dir(path->dentry)) {
		pr_err("overlayfs: '%s' not a directory\n", name);
		goto out_put;
	}
	return 0;

out_put:
	path_put_init(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_init(path);
				err = -EINVAL;
			}
		kfree(tmp);
	}
	return err;
}

static int ovl_check_namelen(struct path *path, struct ovl_fs *ofs,
			     const char *name)
{
	struct kstatfs statfs;
	int err = vfs_statfs(path, &statfs);

	if (err)
		pr_err("overlayfs: statfs failed on '%s'\n", name);
	else
		ofs->namelen = max(ofs->namelen, statfs.f_namelen);

	return err;
}

static int ovl_lower_dir(const char *name, struct path *path,
			 struct ovl_fs *ofs, int *stack_depth, bool *remote)
{
	int fh_type;
	int err;

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

	err = ovl_check_namelen(path, ofs, name);
	if (err)
		goto out_put;

	*stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);

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

	/*
	 * The inodes index feature and NFS export need to encode and decode
	 * file handles, so they require that all layers support them.
	 */
	fh_type = ovl_can_decode_fh(path->dentry->d_sb);
	if ((ofs->config.nfs_export ||
	     (ofs->config.index && ofs->config.upperdir)) && !fh_type) {
		ofs->config.index = false;
		ofs->config.nfs_export = false;
		pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n",
			name);
	}

	/* Check if lower fs has 32bit inode numbers */
	if (fh_type != FILEID_INO32_GEN)
		ofs->xino_bits = 0;

	return 0;

out_put:
	path_put_init(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, inode, 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);
	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);

	/*
	 * Check if sgid bit needs to be cleared (actual setacl operation will
	 * be done with mounter's capabilities and so that won't do it for us).
	 */
	if (unlikely(inode->i_mode & S_ISGID) &&
	    handler->flags == ACL_TYPE_ACCESS &&
	    !in_group_p(inode->i_gid) &&
	    !capable_wrt_inode_uidgid(inode, CAP_FSETID)) {
		struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };

		err = ovl_setattr(dentry, &iattr);
		if (err)
			return err;
	}

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

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 -EOPNOTSUPP;
}

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, inode, 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, inode, 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_setup_trap(struct super_block *sb, struct dentry *dir,
			  struct inode **ptrap, const char *name)
{
	struct inode *trap;
	int err;

	trap = ovl_get_trap_inode(sb, dir);
	err = PTR_ERR(trap);
	if (IS_ERR(trap)) {
		if (err == -ELOOP)
			pr_err("overlayfs: conflicting %s path\n", name);
		return err;
	}

	*ptrap = trap;
	return 0;
}

static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs,
			 struct path *upperpath)
{
	struct vfsmount *upper_mnt;
	int err;

	err = ovl_mount_dir(ofs->config.upperdir, upperpath);
	if (err)
		goto out;

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

	err = ovl_check_namelen(upperpath, ofs, ofs->config.upperdir);
	if (err)
		goto out;

	err = ovl_setup_trap(sb, upperpath->dentry, &ofs->upperdir_trap,
			     "upperdir");
	if (err)
		goto out;

	upper_mnt = clone_private_mount(upperpath);
	err = PTR_ERR(upper_mnt);
	if (IS_ERR(upper_mnt)) {
		pr_err("overlayfs: failed to clone upperpath\n");
		goto out;
	}

	/* Don't inherit atime flags */
	upper_mnt->mnt_flags &= ~(MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME);
	ofs->upper_mnt = upper_mnt;

	err = -EBUSY;
	if (ovl_inuse_trylock(ofs->upper_mnt->mnt_root)) {
		ofs->upperdir_locked = true;
	} else if (ofs->config.index) {
		pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n");
		goto out;
	} else {
		pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
	}

	err = 0;
out:
	return err;
}

static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
			    struct path *workpath)
{
	struct vfsmount *mnt = ofs->upper_mnt;
	struct dentry *temp;
	int fh_type;
	int err;

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

	ofs->workdir = ovl_workdir_create(ofs, OVL_WORKDIR_NAME, false);
	if (!ofs->workdir)
		goto out;

	err = ovl_setup_trap(sb, ofs->workdir, &ofs->workdir_trap, "workdir");
	if (err)
		goto out;

	/*
	 * 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.
	 */
	err = ovl_check_d_type_supported(workpath);
	if (err < 0)
		goto out;

	/*
	 * 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");

	/* Check if upper/work fs supports O_TMPFILE */
	temp = ovl_do_tmpfile(ofs->workdir, S_IFREG | 0);
	ofs->tmpfile = !IS_ERR(temp);
	if (ofs->tmpfile)
		dput(temp);
	else
		pr_warn("overlayfs: upper fs does not support tmpfile.\n");

	/*
	 * Check if upper/work fs supports trusted.overlay.* xattr
	 */
	err = ovl_do_setxattr(ofs->workdir, OVL_XATTR_OPAQUE, "0", 1, 0);
	if (err) {
		ofs->noxattr = true;
		ofs->config.index = false;
		ofs->config.metacopy = false;
		pr_warn("overlayfs: upper fs does not support xattr, falling back to index=off and metacopy=off.\n");
		err = 0;
	} else {
		vfs_removexattr(ofs->workdir, OVL_XATTR_OPAQUE);
	}

	/* Check if upper/work fs supports file handles */
	fh_type = ovl_can_decode_fh(ofs->workdir->d_sb);
	if (ofs->config.index && !fh_type) {
		ofs->config.index = false;
		pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n");
	}

	/* Check if upper fs has 32bit inode numbers */
	if (fh_type != FILEID_INO32_GEN)
		ofs->xino_bits = 0;

	/* NFS export of r/w mount depends on index */
	if (ofs->config.nfs_export && !ofs->config.index) {
		pr_warn("overlayfs: NFS export requires \"index=on\", falling back to nfs_export=off.\n");
		ofs->config.nfs_export = false;
	}
out:
	mnt_drop_write(mnt);
	return err;
}

static int ovl_get_workdir(struct super_block *sb, struct ovl_fs *ofs,
			   struct path *upperpath)
{
	int err;
	struct path workpath = { };

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

	err = -EINVAL;
	if (upperpath->mnt != workpath.mnt) {
		pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
		goto out;
	}
	if (!ovl_workdir_ok(workpath.dentry, upperpath->dentry)) {
		pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
		goto out;
	}

	ofs->workbasedir = dget(workpath.dentry);

	err = -EBUSY;
	if (ovl_inuse_trylock(ofs->workbasedir)) {
		ofs->workdir_locked = true;
	} else if (ofs->config.index) {
		pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n");
		goto out;
	} else {
		pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
	}

	err = ovl_make_workdir(sb, ofs, &workpath);

out:
	path_put(&workpath);

	return err;
}

static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
			    struct ovl_entry *oe, struct path *upperpath)
{
	struct vfsmount *mnt = ofs->upper_mnt;
	int err;

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

	/* Verify lower root is upper root origin */
	err = ovl_verify_origin(upperpath->dentry, oe->lowerstack[0].dentry,
				true);
	if (err) {
		pr_err("overlayfs: failed to verify upper root origin\n");
		goto out;
	}

	ofs->indexdir = ovl_workdir_create(ofs, OVL_INDEXDIR_NAME, true);
	if (ofs->indexdir) {
		err = ovl_setup_trap(sb, ofs->indexdir, &ofs->indexdir_trap,
				     "indexdir");
		if (err)
			goto out;

		/*
		 * Verify upper root is exclusively associated with index dir.
		 * Older kernels stored upper fh in "trusted.overlay.origin"
		 * xattr. If that xattr exists, verify that it is a match to
		 * upper dir file handle. In any case, verify or set xattr
		 * "trusted.overlay.upper" to indicate that index may have
		 * directory entries.
		 */
		if (ovl_check_origin_xattr(ofs->indexdir)) {
			err = ovl_verify_set_fh(ofs->indexdir, OVL_XATTR_ORIGIN,
						upperpath->dentry, true, false);
			if (err)
				pr_err("overlayfs: failed to verify index dir 'origin' xattr\n");
		}
		err = ovl_verify_upper(ofs->indexdir, upperpath->dentry, true);
		if (err)
			pr_err("overlayfs: failed to verify index dir 'upper' xattr\n");

		/* Cleanup bad/stale/orphan index entries */
		if (!err)
			err = ovl_indexdir_cleanup(ofs);
	}
	if (err || !ofs->indexdir)
		pr_warn("overlayfs: try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");

out:
	mnt_drop_write(mnt);
	return err;
}

static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid)
{
	unsigned int i;

	if (!ofs->config.nfs_export && !(ofs->config.index && ofs->upper_mnt))
		return true;

	for (i = 0; i < ofs->numlowerfs; i++) {
		/*
		 * We use uuid to associate an overlay lower file handle with a
		 * lower layer, so we can accept lower fs with null uuid as long
		 * as all lower layers with null uuid are on the same fs.
		 */
		if (uuid_equal(&ofs->lower_fs[i].sb->s_uuid, uuid))
			return false;
	}
	return true;
}

/* Get a unique fsid for the layer */
static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path)
{
	struct super_block *sb = path->mnt->mnt_sb;
	unsigned int i;
	dev_t dev;
	int err;

	/* fsid 0 is reserved for upper fs even with non upper overlay */
	if (ofs->upper_mnt && ofs->upper_mnt->mnt_sb == sb)
		return 0;

	for (i = 0; i < ofs->numlowerfs; i++) {
		if (ofs->lower_fs[i].sb == sb)
			return i + 1;
	}

	if (!ovl_lower_uuid_ok(ofs, &sb->s_uuid)) {
		ofs->config.index = false;
		ofs->config.nfs_export = false;
		pr_warn("overlayfs: %s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n",
			uuid_is_null(&sb->s_uuid) ? "null" : "conflicting",
			path->dentry);
	}

	err = get_anon_bdev(&dev);
	if (err) {
		pr_err("overlayfs: failed to get anonymous bdev for lowerpath\n");
		return err;
	}

	ofs->lower_fs[ofs->numlowerfs].sb = sb;
	ofs->lower_fs[ofs->numlowerfs].pseudo_dev = dev;
	ofs->numlowerfs++;

	return ofs->numlowerfs;
}

static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs,
				struct path *stack, unsigned int numlower)
{
	int err;
	unsigned int i;

	err = -ENOMEM;
	ofs->lower_layers = kcalloc(numlower, sizeof(struct ovl_layer),
				    GFP_KERNEL);
	if (ofs->lower_layers == NULL)
		goto out;

	ofs->lower_fs = kcalloc(numlower, sizeof(struct ovl_sb),
				GFP_KERNEL);
	if (ofs->lower_fs == NULL)
		goto out;

	for (i = 0; i < numlower; i++) {
		struct vfsmount *mnt;
		struct inode *trap;
		int fsid;

		err = fsid = ovl_get_fsid(ofs, &stack[i]);
		if (err < 0)
			goto out;

		err = -EBUSY;
		if (ovl_is_inuse(stack[i].dentry)) {
			pr_err("overlayfs: lowerdir is in-use as upperdir/workdir\n");
			goto out;
		}

		err = ovl_setup_trap(sb, stack[i].dentry, &trap, "lowerdir");
		if (err)
			goto out;

		mnt = clone_private_mount(&stack[i]);
		err = PTR_ERR(mnt);
		if (IS_ERR(mnt)) {
			pr_err("overlayfs: failed to clone lowerpath\n");
			iput(trap);
			goto out;
		}

		/*
		 * Make lower layers R/O.  That way fchmod/fchown on lower file
		 * will fail instead of modifying lower fs.
		 */
		mnt->mnt_flags |= MNT_READONLY | MNT_NOATIME;

		ofs->lower_layers[ofs->numlower].trap = trap;
		ofs->lower_layers[ofs->numlower].mnt = mnt;
		ofs->lower_layers[ofs->numlower].idx = i + 1;
		ofs->lower_layers[ofs->numlower].fsid = fsid;
		if (fsid) {
			ofs->lower_layers[ofs->numlower].fs =
				&ofs->lower_fs[fsid - 1];
		}
		ofs->numlower++;
	}

	/*
	 * When all layers on same fs, overlay can use real inode numbers.
	 * With mount option "xino=on", mounter declares that there are enough
	 * free high bits in underlying fs to hold the unique fsid.
	 * If overlayfs does encounter underlying inodes using the high xino
	 * bits reserved for fsid, it emits a warning and uses the original
	 * inode number.
	 */
	if (!ofs->numlowerfs || (ofs->numlowerfs == 1 && !ofs->upper_mnt)) {
		ofs->xino_bits = 0;
		ofs->config.xino = OVL_XINO_OFF;
	} else if (ofs->config.xino == OVL_XINO_ON && !ofs->xino_bits) {
		/*
		 * This is a roundup of number of bits needed for numlowerfs+1
		 * (i.e. ilog2(numlowerfs+1 - 1) + 1). fsid 0 is reserved for
		 * upper fs even with non upper overlay.
		 */
		BUILD_BUG_ON(ilog2(OVL_MAX_STACK) > 31);
		ofs->xino_bits = ilog2(ofs->numlowerfs) + 1;
	}

	if (ofs->xino_bits) {
		pr_info("overlayfs: \"xino\" feature enabled using %d upper inode bits.\n",
			ofs->xino_bits);
	}

	err = 0;
out:
	return err;
}

static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
					    struct ovl_fs *ofs)
{
	int err;
	char *lowertmp, *lower;
	struct path *stack = NULL;
	unsigned int stacklen, numlower = 0, i;
	bool remote = false;
	struct ovl_entry *oe;

	err = -ENOMEM;
	lowertmp = kstrdup(ofs->config.lowerdir, GFP_KERNEL);
	if (!lowertmp)
		goto out_err;

	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_err;
	} else if (!ofs->config.upperdir && stacklen == 1) {
		pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
		goto out_err;
	} else if (!ofs->config.upperdir && ofs->config.nfs_export &&
		   ofs->config.redirect_follow) {
		pr_warn("overlayfs: NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
		ofs->config.nfs_export = false;
	}

	err = -ENOMEM;
	stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL);
	if (!stack)
		goto out_err;

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

		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_err;
	}

	err = ovl_get_lower_layers(sb, ofs, stack, numlower);
	if (err)
		goto out_err;

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

	for (i = 0; i < numlower; i++) {
		oe->lowerstack[i].dentry = dget(stack[i].dentry);
		oe->lowerstack[i].layer = &ofs->lower_layers[i];
	}

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

out:
	for (i = 0; i < numlower; i++)
		path_put(&stack[i]);
	kfree(stack);
	kfree(lowertmp);

	return oe;

out_err:
	oe = ERR_PTR(err);
	goto out;
}

/*
 * Check if this layer root is a descendant of:
 * - another layer of this overlayfs instance
 * - upper/work dir of any overlayfs instance
 * - a disconnected dentry (detached root)
 */
static int ovl_check_layer(struct super_block *sb, struct dentry *dentry,
			   const char *name)
{
	struct dentry *next, *parent;
	bool is_root = false;
	int err = 0;

	if (!dentry || dentry == dentry->d_sb->s_root)
		return 0;

	next = dget(dentry);
	/* Walk back ancestors to fs root (inclusive) looking for traps */
	do {
		parent = dget_parent(next);
		is_root = (parent == next);
		if (ovl_is_inuse(parent)) {
			err = -EBUSY;
			pr_err("overlayfs: %s path overlapping in-use upperdir/workdir\n",
			       name);
		} else if (ovl_lookup_trap_inode(sb, parent)) {
			err = -ELOOP;
			pr_err("overlayfs: overlapping %s path\n", name);
		}
		dput(next);
		next = parent;
	} while (!err && !is_root);

	/* Did we really walk to fs root or found a detached root? */
	if (!err && next != dentry->d_sb->s_root) {
		err = -ESTALE;
		pr_err("overlayfs: disconnected %s path\n", name);
	}

	dput(next);

	return err;
}

/*
 * Check if any of the layers or work dirs overlap.
 */
static int ovl_check_overlapping_layers(struct super_block *sb,
					struct ovl_fs *ofs)
{
	int i, err;

	if (ofs->upper_mnt) {
		err = ovl_check_layer(sb, ofs->upper_mnt->mnt_root, "upperdir");
		if (err)
			return err;

		/*
		 * Checking workbasedir avoids hitting ovl_is_inuse(parent) of
		 * this instance and covers overlapping work and index dirs,
		 * unless work or index dir have been moved since created inside
		 * workbasedir.  In that case, we already have their traps in
		 * inode cache and we will catch that case on lookup.
		 */
		err = ovl_check_layer(sb, ofs->workbasedir, "workdir");
		if (err)
			return err;
	}

	for (i = 0; i < ofs->numlower; i++) {
		err = ovl_check_layer(sb, ofs->lower_layers[i].mnt->mnt_root,
				      "lowerdir");
		if (err)
			return err;
	}

	return 0;
}

static int ovl_fill_super(struct super_block *sb, void *data, int silent)
{
	struct path upperpath = { };
	struct dentry *root_dentry;
	struct ovl_entry *oe;
	struct ovl_fs *ofs;
	struct cred *cred;
	int err;

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

	ofs->creator_cred = cred = prepare_creds();
	if (!cred)
		goto out_err;

	ofs->config.index = ovl_index_def;
	ofs->config.nfs_export = ovl_nfs_export_def;
	ofs->config.xino = ovl_xino_def();
	ofs->config.metacopy = ovl_metacopy_def;
	err = ovl_parse_opt((char *) data, &ofs->config);
	if (err)
		goto out_err;

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

	sb->s_stack_depth = 0;
	sb->s_maxbytes = MAX_LFS_FILESIZE;
	/* Assume underlaying fs uses 32bit inodes unless proven otherwise */
	if (ofs->config.xino != OVL_XINO_OFF)
		ofs->xino_bits = BITS_PER_LONG - 32;

	/* alloc/destroy_inode needed for setting up traps in inode cache */
	sb->s_op = &ovl_super_operations;

	if (ofs->config.upperdir) {
		if (!ofs->config.workdir) {
			pr_err("overlayfs: missing 'workdir'\n");
			goto out_err;
		}

		err = ovl_get_upper(sb, ofs, &upperpath);
		if (err)
			goto out_err;

		err = ovl_get_workdir(sb, ofs, &upperpath);
		if (err)
			goto out_err;

		if (!ofs->workdir)
			sb->s_flags |= SB_RDONLY;

		sb->s_stack_depth = ofs->upper_mnt->mnt_sb->s_stack_depth;
		sb->s_time_gran = ofs->upper_mnt->mnt_sb->s_time_gran;

	}
	oe = ovl_get_lowerstack(sb, ofs);
	err = PTR_ERR(oe);
	if (IS_ERR(oe))
		goto out_err;

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

	if (!(ovl_force_readonly(ofs)) && ofs->config.index) {
		err = ovl_get_indexdir(sb, ofs, oe, &upperpath);
		if (err)
			goto out_free_oe;

		/* Force r/o mount with no index dir */
		if (!ofs->indexdir) {
			dput(ofs->workdir);
			ofs->workdir = NULL;
			sb->s_flags |= SB_RDONLY;
		}

	}

	err = ovl_check_overlapping_layers(sb, ofs);
	if (err)
		goto out_free_oe;

	/* Show index=off in /proc/mounts for forced r/o mount */
	if (!ofs->indexdir) {
		ofs->config.index = false;
		if (ofs->upper_mnt && ofs->config.nfs_export) {
			pr_warn("overlayfs: NFS export requires an index dir, falling back to nfs_export=off.\n");
			ofs->config.nfs_export = false;
		}
	}

	if (ofs->config.metacopy && ofs->config.nfs_export) {
		pr_warn("overlayfs: NFS export is not supported with metadata only copy up, falling back to nfs_export=off.\n");
		ofs->config.nfs_export = false;
	}

	if (ofs->config.nfs_export)
		sb->s_export_op = &ovl_export_operations;

	/* Never override disk quota limits or use reserved space */
	cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);

	sb->s_magic = OVERLAYFS_SUPER_MAGIC;
	sb->s_xattr = ovl_xattr_handlers;
	sb->s_fs_info = ofs;
	sb->s_flags |= SB_POSIXACL;

	err = -ENOMEM;
	root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, 0));
	if (!root_dentry)
		goto out_free_oe;

	root_dentry->d_fsdata = oe;

	mntput(upperpath.mnt);
	if (upperpath.dentry) {
		ovl_dentry_set_upper_alias(root_dentry);
		if (ovl_is_impuredir(upperpath.dentry))
			ovl_set_flag(OVL_IMPURE, d_inode(root_dentry));
	}

	/* Root is always merge -> can have whiteouts */
	ovl_set_flag(OVL_WHITEOUTS, d_inode(root_dentry));
	ovl_dentry_set_flag(OVL_E_CONNECTED, root_dentry);
	ovl_set_upperdata(d_inode(root_dentry));
	ovl_inode_init(d_inode(root_dentry), upperpath.dentry,
		       ovl_dentry_lower(root_dentry), NULL);

	sb->s_root = root_dentry;

	return 0;

out_free_oe:
	ovl_entry_stack_free(oe);
	kfree(oe);
out_err:
	path_put(&upperpath);
	ovl_free_fs(ofs);
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 void ovl_inode_init_once(void *foo)
{
	struct ovl_inode *oi = foo;

	inode_init_once(&oi->vfs_inode);
}

static int __init ovl_init(void)
{
	int err;

	ovl_inode_cachep = kmem_cache_create("ovl_inode",
					     sizeof(struct ovl_inode), 0,
					     (SLAB_RECLAIM_ACCOUNT|
					      SLAB_MEM_SPREAD|SLAB_ACCOUNT),
					     ovl_inode_init_once);
	if (ovl_inode_cachep == NULL)
		return -ENOMEM;

	err = register_filesystem(&ovl_fs_type);
	if (err)
		kmem_cache_destroy(ovl_inode_cachep);

	return err;
}

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

	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy cache.
	 */
	rcu_barrier();
	kmem_cache_destroy(ovl_inode_cachep);

}

module_init(ovl_init);
module_exit(ovl_exit);