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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2011 Novell Inc.
* Copyright (C) 2016 Red Hat, Inc.
*/
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/xattr.h>
#include <linux/exportfs.h>
#include <linux/fileattr.h>
#include <linux/uuid.h>
#include <linux/namei.h>
#include <linux/ratelimit.h>
#include "overlayfs.h"
int ovl_want_write(struct dentry *dentry)
{
struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
return mnt_want_write(ovl_upper_mnt(ofs));
}
void ovl_drop_write(struct dentry *dentry)
{
struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
mnt_drop_write(ovl_upper_mnt(ofs));
}
struct dentry *ovl_workdir(struct dentry *dentry)
{
struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
return ofs->workdir;
}
const struct cred *ovl_override_creds(struct super_block *sb)
{
struct ovl_fs *ofs = sb->s_fs_info;
return override_creds(ofs->creator_cred);
}
/*
* Check if underlying fs supports file handles and try to determine encoding
* type, in order to deduce maximum inode number used by fs.
*
* Return 0 if file handles are not supported.
* Return 1 (FILEID_INO32_GEN) if fs uses the default 32bit inode encoding.
* Return -1 if fs uses a non default encoding with unknown inode size.
*/
int ovl_can_decode_fh(struct super_block *sb)
{
if (!capable(CAP_DAC_READ_SEARCH))
return 0;
if (!sb->s_export_op || !sb->s_export_op->fh_to_dentry)
return 0;
return sb->s_export_op->encode_fh ? -1 : FILEID_INO32_GEN;
}
struct dentry *ovl_indexdir(struct super_block *sb)
{
struct ovl_fs *ofs = sb->s_fs_info;
return ofs->indexdir;
}
/* Index all files on copy up. For now only enabled for NFS export */
bool ovl_index_all(struct super_block *sb)
{
struct ovl_fs *ofs = sb->s_fs_info;
return ofs->config.nfs_export && ofs->config.index;
}
/* Verify lower origin on lookup. For now only enabled for NFS export */
bool ovl_verify_lower(struct super_block *sb)
{
struct ovl_fs *ofs = sb->s_fs_info;
return ofs->config.nfs_export && ofs->config.index;
}
struct ovl_path *ovl_stack_alloc(unsigned int n)
{
return kcalloc(n, sizeof(struct ovl_path), GFP_KERNEL);
}
void ovl_stack_cpy(struct ovl_path *dst, struct ovl_path *src, unsigned int n)
{
unsigned int i;
memcpy(dst, src, sizeof(struct ovl_path) * n);
for (i = 0; i < n; i++)
dget(src[i].dentry);
}
void ovl_stack_put(struct ovl_path *stack, unsigned int n)
{
unsigned int i;
for (i = 0; stack && i < n; i++)
dput(stack[i].dentry);
}
void ovl_stack_free(struct ovl_path *stack, unsigned int n)
{
ovl_stack_put(stack, n);
kfree(stack);
}
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;
}
void ovl_free_entry(struct ovl_entry *oe)
{
ovl_stack_put(ovl_lowerstack(oe), ovl_numlower(oe));
kfree(oe);
}
#define OVL_D_REVALIDATE (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE)
bool ovl_dentry_remote(struct dentry *dentry)
{
return dentry->d_flags & OVL_D_REVALIDATE;
}
void ovl_dentry_update_reval(struct dentry *dentry, struct dentry *realdentry)
{
if (!ovl_dentry_remote(realdentry))
return;
spin_lock(&dentry->d_lock);
dentry->d_flags |= realdentry->d_flags & OVL_D_REVALIDATE;
spin_unlock(&dentry->d_lock);
}
void ovl_dentry_init_reval(struct dentry *dentry, struct dentry *upperdentry,
struct ovl_entry *oe)
{
return ovl_dentry_init_flags(dentry, upperdentry, oe, OVL_D_REVALIDATE);
}
void ovl_dentry_init_flags(struct dentry *dentry, struct dentry *upperdentry,
struct ovl_entry *oe, unsigned int mask)
{
struct ovl_path *lowerstack = ovl_lowerstack(oe);
unsigned int i, flags = 0;
if (upperdentry)
flags |= upperdentry->d_flags;
for (i = 0; i < ovl_numlower(oe); i++)
flags |= lowerstack[i].dentry->d_flags;
spin_lock(&dentry->d_lock);
dentry->d_flags &= ~mask;
dentry->d_flags |= flags & mask;
spin_unlock(&dentry->d_lock);
}
bool ovl_dentry_weird(struct dentry *dentry)
{
return dentry->d_flags & (DCACHE_NEED_AUTOMOUNT |
DCACHE_MANAGE_TRANSIT |
DCACHE_OP_HASH |
DCACHE_OP_COMPARE);
}
enum ovl_path_type ovl_path_type(struct dentry *dentry)
{
struct ovl_entry *oe = OVL_E(dentry);
enum ovl_path_type type = 0;
if (ovl_dentry_upper(dentry)) {
type = __OVL_PATH_UPPER;
/*
* Non-dir dentry can hold lower dentry of its copy up origin.
*/
if (ovl_numlower(oe)) {
if (ovl_test_flag(OVL_CONST_INO, d_inode(dentry)))
type |= __OVL_PATH_ORIGIN;
if (d_is_dir(dentry) ||
!ovl_has_upperdata(d_inode(dentry)))
type |= __OVL_PATH_MERGE;
}
} else {
if (ovl_numlower(oe) > 1)
type |= __OVL_PATH_MERGE;
}
return type;
}
void ovl_path_upper(struct dentry *dentry, struct path *path)
{
struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
path->mnt = ovl_upper_mnt(ofs);
path->dentry = ovl_dentry_upper(dentry);
}
void ovl_path_lower(struct dentry *dentry, struct path *path)
{
struct ovl_entry *oe = OVL_E(dentry);
struct ovl_path *lowerpath = ovl_lowerstack(oe);
if (ovl_numlower(oe)) {
path->mnt = lowerpath->layer->mnt;
path->dentry = lowerpath->dentry;
} else {
*path = (struct path) { };
}
}
void ovl_path_lowerdata(struct dentry *dentry, struct path *path)
{
struct ovl_entry *oe = OVL_E(dentry);
struct ovl_path *lowerstack = ovl_lowerstack(oe);
if (ovl_numlower(oe)) {
path->mnt = lowerstack[ovl_numlower(oe) - 1].layer->mnt;
path->dentry = lowerstack[ovl_numlower(oe) - 1].dentry;
} else {
*path = (struct path) { };
}
}
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;
}
enum ovl_path_type ovl_path_realdata(struct dentry *dentry, struct path *path)
{
enum ovl_path_type type = ovl_path_type(dentry);
WARN_ON_ONCE(d_is_dir(dentry));
if (!OVL_TYPE_UPPER(type) || OVL_TYPE_MERGE(type))
ovl_path_lowerdata(dentry, path);
else
ovl_path_upper(dentry, path);
return type;
}
struct dentry *ovl_dentry_upper(struct dentry *dentry)
{
return ovl_upperdentry_dereference(OVL_I(d_inode(dentry)));
}
struct dentry *ovl_dentry_lower(struct dentry *dentry)
{
struct ovl_entry *oe = OVL_E(dentry);
return ovl_numlower(oe) ? ovl_lowerstack(oe)->dentry : NULL;
}
const struct ovl_layer *ovl_layer_lower(struct dentry *dentry)
{
struct ovl_entry *oe = OVL_E(dentry);
return ovl_numlower(oe) ? ovl_lowerstack(oe)->layer : NULL;
}
/*
* ovl_dentry_lower() could return either a data dentry or metacopy dentry
* depending on what is stored in lowerstack[0]. At times we need to find
* lower dentry which has data (and not metacopy dentry). This helper
* returns the lower data dentry.
*/
struct dentry *ovl_dentry_lowerdata(struct dentry *dentry)
{
struct ovl_entry *oe = OVL_E(dentry);
return ovl_numlower(oe) ?
ovl_lowerstack(oe)[ovl_numlower(oe) - 1].dentry : NULL;
}
struct dentry *ovl_dentry_real(struct dentry *dentry)
{
return ovl_dentry_upper(dentry) ?: ovl_dentry_lower(dentry);
}
struct dentry *ovl_i_dentry_upper(struct inode *inode)
{
return ovl_upperdentry_dereference(OVL_I(inode));
}
struct inode *ovl_i_path_real(struct inode *inode, struct path *path)
{
struct ovl_path *lowerpath = ovl_lowerpath(OVL_I_E(inode));
path->dentry = ovl_i_dentry_upper(inode);
if (!path->dentry) {
path->dentry = lowerpath->dentry;
path->mnt = lowerpath->layer->mnt;
} else {
path->mnt = ovl_upper_mnt(OVL_FS(inode->i_sb));
}
return path->dentry ? d_inode_rcu(path->dentry) : NULL;
}
struct inode *ovl_inode_upper(struct inode *inode)
{
struct dentry *upperdentry = ovl_i_dentry_upper(inode);
return upperdentry ? d_inode(upperdentry) : NULL;
}
struct inode *ovl_inode_lower(struct inode *inode)
{
struct ovl_path *lowerpath = ovl_lowerpath(OVL_I_E(inode));
return lowerpath ? d_inode(lowerpath->dentry) : NULL;
}
struct inode *ovl_inode_real(struct inode *inode)
{
return ovl_inode_upper(inode) ?: ovl_inode_lower(inode);
}
/* Return inode which contains lower data. Do not return metacopy */
struct inode *ovl_inode_lowerdata(struct inode *inode)
{
if (WARN_ON(!S_ISREG(inode->i_mode)))
return NULL;
return OVL_I(inode)->lowerdata ?: ovl_inode_lower(inode);
}
/* Return real inode which contains data. Does not return metacopy inode */
struct inode *ovl_inode_realdata(struct inode *inode)
{
struct inode *upperinode;
upperinode = ovl_inode_upper(inode);
if (upperinode && ovl_has_upperdata(inode))
return upperinode;
return ovl_inode_lowerdata(inode);
}
struct ovl_dir_cache *ovl_dir_cache(struct inode *inode)
{
return OVL_I(inode)->cache;
}
void ovl_set_dir_cache(struct inode *inode, struct ovl_dir_cache *cache)
{
OVL_I(inode)->cache = cache;
}
void ovl_dentry_set_flag(unsigned long flag, struct dentry *dentry)
{
set_bit(flag, OVL_E_FLAGS(dentry));
}
void ovl_dentry_clear_flag(unsigned long flag, struct dentry *dentry)
{
clear_bit(flag, OVL_E_FLAGS(dentry));
}
bool ovl_dentry_test_flag(unsigned long flag, struct dentry *dentry)
{
return test_bit(flag, OVL_E_FLAGS(dentry));
}
bool ovl_dentry_is_opaque(struct dentry *dentry)
{
return ovl_dentry_test_flag(OVL_E_OPAQUE, dentry);
}
bool ovl_dentry_is_whiteout(struct dentry *dentry)
{
return !dentry->d_inode && ovl_dentry_is_opaque(dentry);
}
void ovl_dentry_set_opaque(struct dentry *dentry)
{
ovl_dentry_set_flag(OVL_E_OPAQUE, dentry);
}
/*
* For hard links and decoded file handles, it's possible for ovl_dentry_upper()
* to return positive, while there's no actual upper alias for the inode.
* Copy up code needs to know about the existence of the upper alias, so it
* can't use ovl_dentry_upper().
*/
bool ovl_dentry_has_upper_alias(struct dentry *dentry)
{
return ovl_dentry_test_flag(OVL_E_UPPER_ALIAS, dentry);
}
void ovl_dentry_set_upper_alias(struct dentry *dentry)
{
ovl_dentry_set_flag(OVL_E_UPPER_ALIAS, dentry);
}
static bool ovl_should_check_upperdata(struct inode *inode)
{
if (!S_ISREG(inode->i_mode))
return false;
if (!ovl_inode_lower(inode))
return false;
return true;
}
bool ovl_has_upperdata(struct inode *inode)
{
if (!ovl_should_check_upperdata(inode))
return true;
if (!ovl_test_flag(OVL_UPPERDATA, inode))
return false;
/*
* Pairs with smp_wmb() in ovl_set_upperdata(). Main user of
* ovl_has_upperdata() is ovl_copy_up_meta_inode_data(). Make sure
* if setting of OVL_UPPERDATA is visible, then effects of writes
* before that are visible too.
*/
smp_rmb();
return true;
}
void ovl_set_upperdata(struct inode *inode)
{
/*
* Pairs with smp_rmb() in ovl_has_upperdata(). Make sure
* if OVL_UPPERDATA flag is visible, then effects of write operations
* before it are visible as well.
*/
smp_wmb();
ovl_set_flag(OVL_UPPERDATA, inode);
}
/* Caller should hold ovl_inode->lock */
bool ovl_dentry_needs_data_copy_up_locked(struct dentry *dentry, int flags)
{
if (!ovl_open_flags_need_copy_up(flags))
return false;
return !ovl_test_flag(OVL_UPPERDATA, d_inode(dentry));
}
bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags)
{
if (!ovl_open_flags_need_copy_up(flags))
return false;
return !ovl_has_upperdata(d_inode(dentry));
}
bool ovl_redirect_dir(struct super_block *sb)
{
struct ovl_fs *ofs = sb->s_fs_info;
return ofs->config.redirect_dir && !ofs->noxattr;
}
const char *ovl_dentry_get_redirect(struct dentry *dentry)
{
return OVL_I(d_inode(dentry))->redirect;
}
void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect)
{
struct ovl_inode *oi = OVL_I(d_inode(dentry));
kfree(oi->redirect);
oi->redirect = redirect;
}
void ovl_inode_update(struct inode *inode, struct dentry *upperdentry)
{
struct inode *upperinode = d_inode(upperdentry);
WARN_ON(OVL_I(inode)->__upperdentry);
/*
* Make sure upperdentry is consistent before making it visible
*/
smp_wmb();
OVL_I(inode)->__upperdentry = upperdentry;
if (inode_unhashed(inode)) {
inode->i_private = upperinode;
__insert_inode_hash(inode, (unsigned long) upperinode);
}
}
static void ovl_dir_version_inc(struct dentry *dentry, bool impurity)
{
struct inode *inode = d_inode(dentry);
WARN_ON(!inode_is_locked(inode));
WARN_ON(!d_is_dir(dentry));
/*
* Version is used by readdir code to keep cache consistent.
* For merge dirs (or dirs with origin) all changes need to be noted.
* For non-merge dirs, cache contains only impure entries (i.e. ones
* which have been copied up and have origins), so only need to note
* changes to impure entries.
*/
if (!ovl_dir_is_real(inode) || impurity)
OVL_I(inode)->version++;
}
void ovl_dir_modified(struct dentry *dentry, bool impurity)
{
/* Copy mtime/ctime */
ovl_copyattr(d_inode(dentry));
ovl_dir_version_inc(dentry, impurity);
}
u64 ovl_inode_version_get(struct inode *inode)
{
WARN_ON(!inode_is_locked(inode));
return OVL_I(inode)->version;
}
bool ovl_is_whiteout(struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
return inode && IS_WHITEOUT(inode);
}
struct file *ovl_path_open(const struct path *path, int flags)
{
struct inode *inode = d_inode(path->dentry);
struct mnt_idmap *real_idmap = mnt_idmap(path->mnt);
int err, acc_mode;
if (flags & ~(O_ACCMODE | O_LARGEFILE))
BUG();
switch (flags & O_ACCMODE) {
case O_RDONLY:
acc_mode = MAY_READ;
break;
case O_WRONLY:
acc_mode = MAY_WRITE;
break;
default:
BUG();
}
err = inode_permission(real_idmap, inode, acc_mode | MAY_OPEN);
if (err)
return ERR_PTR(err);
/* O_NOATIME is an optimization, don't fail if not permitted */
if (inode_owner_or_capable(real_idmap, inode))
flags |= O_NOATIME;
return dentry_open(path, flags, current_cred());
}
/* Caller should hold ovl_inode->lock */
static bool ovl_already_copied_up_locked(struct dentry *dentry, int flags)
{
bool disconnected = dentry->d_flags & DCACHE_DISCONNECTED;
if (ovl_dentry_upper(dentry) &&
(ovl_dentry_has_upper_alias(dentry) || disconnected) &&
!ovl_dentry_needs_data_copy_up_locked(dentry, flags))
return true;
return false;
}
bool ovl_already_copied_up(struct dentry *dentry, int flags)
{
bool disconnected = dentry->d_flags & DCACHE_DISCONNECTED;
/*
* Check if copy-up has happened as well as for upper alias (in
* case of hard links) is there.
*
* Both checks are lockless:
* - false negatives: will recheck under oi->lock
* - false positives:
* + ovl_dentry_upper() uses memory barriers to ensure the
* upper dentry is up-to-date
* + ovl_dentry_has_upper_alias() relies on locking of
* upper parent i_rwsem to prevent reordering copy-up
* with rename.
*/
if (ovl_dentry_upper(dentry) &&
(ovl_dentry_has_upper_alias(dentry) || disconnected) &&
!ovl_dentry_needs_data_copy_up(dentry, flags))
return true;
return false;
}
int ovl_copy_up_start(struct dentry *dentry, int flags)
{
struct inode *inode = d_inode(dentry);
int err;
err = ovl_inode_lock_interruptible(inode);
if (!err && ovl_already_copied_up_locked(dentry, flags)) {
err = 1; /* Already copied up */
ovl_inode_unlock(inode);
}
return err;
}
void ovl_copy_up_end(struct dentry *dentry)
{
ovl_inode_unlock(d_inode(dentry));
}
bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path)
{
int res;
res = ovl_path_getxattr(ofs, path, OVL_XATTR_ORIGIN, NULL, 0);
/* Zero size value means "copied up but origin unknown" */
if (res >= 0)
return true;
return false;
}
bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
enum ovl_xattr ox)
{
int res;
char val;
if (!d_is_dir(path->dentry))
return false;
res = ovl_path_getxattr(ofs, path, ox, &val, 1);
if (res == 1 && val == 'y')
return true;
return false;
}
#define OVL_XATTR_OPAQUE_POSTFIX "opaque"
#define OVL_XATTR_REDIRECT_POSTFIX "redirect"
#define OVL_XATTR_ORIGIN_POSTFIX "origin"
#define OVL_XATTR_IMPURE_POSTFIX "impure"
#define OVL_XATTR_NLINK_POSTFIX "nlink"
#define OVL_XATTR_UPPER_POSTFIX "upper"
#define OVL_XATTR_METACOPY_POSTFIX "metacopy"
#define OVL_XATTR_PROTATTR_POSTFIX "protattr"
#define OVL_XATTR_TAB_ENTRY(x) \
[x] = { [false] = OVL_XATTR_TRUSTED_PREFIX x ## _POSTFIX, \
[true] = OVL_XATTR_USER_PREFIX x ## _POSTFIX }
const char *const ovl_xattr_table[][2] = {
OVL_XATTR_TAB_ENTRY(OVL_XATTR_OPAQUE),
OVL_XATTR_TAB_ENTRY(OVL_XATTR_REDIRECT),
OVL_XATTR_TAB_ENTRY(OVL_XATTR_ORIGIN),
OVL_XATTR_TAB_ENTRY(OVL_XATTR_IMPURE),
OVL_XATTR_TAB_ENTRY(OVL_XATTR_NLINK),
OVL_XATTR_TAB_ENTRY(OVL_XATTR_UPPER),
OVL_XATTR_TAB_ENTRY(OVL_XATTR_METACOPY),
OVL_XATTR_TAB_ENTRY(OVL_XATTR_PROTATTR),
};
int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry,
enum ovl_xattr ox, const void *value, size_t size,
int xerr)
{
int err;
if (ofs->noxattr)
return xerr;
err = ovl_setxattr(ofs, upperdentry, ox, value, size);
if (err == -EOPNOTSUPP) {
pr_warn("cannot set %s xattr on upper\n", ovl_xattr(ofs, ox));
ofs->noxattr = true;
return xerr;
}
return err;
}
int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry)
{
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
int err;
if (ovl_test_flag(OVL_IMPURE, d_inode(dentry)))
return 0;
/*
* Do not fail when upper doesn't support xattrs.
* Upper inodes won't have origin nor redirect xattr anyway.
*/
err = ovl_check_setxattr(ofs, upperdentry, OVL_XATTR_IMPURE, "y", 1, 0);
if (!err)
ovl_set_flag(OVL_IMPURE, d_inode(dentry));
return err;
}
#define OVL_PROTATTR_MAX 32 /* Reserved for future flags */
void ovl_check_protattr(struct inode *inode, struct dentry *upper)
{
struct ovl_fs *ofs = OVL_FS(inode->i_sb);
u32 iflags = inode->i_flags & OVL_PROT_I_FLAGS_MASK;
char buf[OVL_PROTATTR_MAX+1];
int res, n;
res = ovl_getxattr_upper(ofs, upper, OVL_XATTR_PROTATTR, buf,
OVL_PROTATTR_MAX);
if (res < 0)
return;
/*
* Initialize inode flags from overlay.protattr xattr and upper inode
* flags. If upper inode has those fileattr flags set (i.e. from old
* kernel), we do not clear them on ovl_get_inode(), but we will clear
* them on next fileattr_set().
*/
for (n = 0; n < res; n++) {
if (buf[n] == 'a')
iflags |= S_APPEND;
else if (buf[n] == 'i')
iflags |= S_IMMUTABLE;
else
break;
}
if (!res || n < res) {
pr_warn_ratelimited("incompatible overlay.protattr format (%pd2, len=%d)\n",
upper, res);
} else {
inode_set_flags(inode, iflags, OVL_PROT_I_FLAGS_MASK);
}
}
int ovl_set_protattr(struct inode *inode, struct dentry *upper,
struct fileattr *fa)
{
struct ovl_fs *ofs = OVL_FS(inode->i_sb);
char buf[OVL_PROTATTR_MAX];
int len = 0, err = 0;
u32 iflags = 0;
BUILD_BUG_ON(HWEIGHT32(OVL_PROT_FS_FLAGS_MASK) > OVL_PROTATTR_MAX);
if (fa->flags & FS_APPEND_FL) {
buf[len++] = 'a';
iflags |= S_APPEND;
}
if (fa->flags & FS_IMMUTABLE_FL) {
buf[len++] = 'i';
iflags |= S_IMMUTABLE;
}
/*
* Do not allow to set protection flags when upper doesn't support
* xattrs, because we do not set those fileattr flags on upper inode.
* Remove xattr if it exist and all protection flags are cleared.
*/
if (len) {
err = ovl_check_setxattr(ofs, upper, OVL_XATTR_PROTATTR,
buf, len, -EPERM);
} else if (inode->i_flags & OVL_PROT_I_FLAGS_MASK) {
err = ovl_removexattr(ofs, upper, OVL_XATTR_PROTATTR);
if (err == -EOPNOTSUPP || err == -ENODATA)
err = 0;
}
if (err)
return err;
inode_set_flags(inode, iflags, OVL_PROT_I_FLAGS_MASK);
/* Mask out the fileattr flags that should not be set in upper inode */
fa->flags &= ~OVL_PROT_FS_FLAGS_MASK;
fa->fsx_xflags &= ~OVL_PROT_FSX_FLAGS_MASK;
return 0;
}
/**
* Caller must hold a reference to inode to prevent it from being freed while
* it is marked inuse.
*/
bool ovl_inuse_trylock(struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
bool locked = false;
spin_lock(&inode->i_lock);
if (!(inode->i_state & I_OVL_INUSE)) {
inode->i_state |= I_OVL_INUSE;
locked = true;
}
spin_unlock(&inode->i_lock);
return locked;
}
void ovl_inuse_unlock(struct dentry *dentry)
{
if (dentry) {
struct inode *inode = d_inode(dentry);
spin_lock(&inode->i_lock);
WARN_ON(!(inode->i_state & I_OVL_INUSE));
inode->i_state &= ~I_OVL_INUSE;
spin_unlock(&inode->i_lock);
}
}
bool ovl_is_inuse(struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
bool inuse;
spin_lock(&inode->i_lock);
inuse = (inode->i_state & I_OVL_INUSE);
spin_unlock(&inode->i_lock);
return inuse;
}
/*
* Does this overlay dentry need to be indexed on copy up?
*/
bool ovl_need_index(struct dentry *dentry)
{
struct dentry *lower = ovl_dentry_lower(dentry);
if (!lower || !ovl_indexdir(dentry->d_sb))
return false;
/* Index all files for NFS export and consistency verification */
if (ovl_index_all(dentry->d_sb))
return true;
/* Index only lower hardlinks on copy up */
if (!d_is_dir(lower) && d_inode(lower)->i_nlink > 1)
return true;
return false;
}
/* Caller must hold OVL_I(inode)->lock */
static void ovl_cleanup_index(struct dentry *dentry)
{
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
struct dentry *indexdir = ovl_indexdir(dentry->d_sb);
struct inode *dir = indexdir->d_inode;
struct dentry *lowerdentry = ovl_dentry_lower(dentry);
struct dentry *upperdentry = ovl_dentry_upper(dentry);
struct dentry *index = NULL;
struct inode *inode;
struct qstr name = { };
int err;
err = ovl_get_index_name(ofs, lowerdentry, &name);
if (err)
goto fail;
inode = d_inode(upperdentry);
if (!S_ISDIR(inode->i_mode) && inode->i_nlink != 1) {
pr_warn_ratelimited("cleanup linked index (%pd2, ino=%lu, nlink=%u)\n",
upperdentry, inode->i_ino, inode->i_nlink);
/*
* We either have a bug with persistent union nlink or a lower
* hardlink was added while overlay is mounted. Adding a lower
* hardlink and then unlinking all overlay hardlinks would drop
* overlay nlink to zero before all upper inodes are unlinked.
* As a safety measure, when that situation is detected, set
* the overlay nlink to the index inode nlink minus one for the
* index entry itself.
*/
set_nlink(d_inode(dentry), inode->i_nlink - 1);
ovl_set_nlink_upper(dentry);
goto out;
}
inode_lock_nested(dir, I_MUTEX_PARENT);
index = ovl_lookup_upper(ofs, name.name, indexdir, name.len);
err = PTR_ERR(index);
if (IS_ERR(index)) {
index = NULL;
} else if (ovl_index_all(dentry->d_sb)) {
/* Whiteout orphan index to block future open by handle */
err = ovl_cleanup_and_whiteout(OVL_FS(dentry->d_sb),
dir, index);
} else {
/* Cleanup orphan index entries */
err = ovl_cleanup(ofs, dir, index);
}
inode_unlock(dir);
if (err)
goto fail;
out:
kfree(name.name);
dput(index);
return;
fail:
pr_err("cleanup index of '%pd2' failed (%i)\n", dentry, err);
goto out;
}
/*
* Operations that change overlay inode and upper inode nlink need to be
* synchronized with copy up for persistent nlink accounting.
*/
int ovl_nlink_start(struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
const struct cred *old_cred;
int err;
if (WARN_ON(!inode))
return -ENOENT;
/*
* With inodes index is enabled, we store the union overlay nlink
* in an xattr on the index inode. When whiting out an indexed lower,
* we need to decrement the overlay persistent nlink, but before the
* first copy up, we have no upper index inode to store the xattr.
*
* As a workaround, before whiteout/rename over an indexed lower,
* copy up to create the upper index. Creating the upper index will
* initialize the overlay nlink, so it could be dropped if unlink
* or rename succeeds.
*
* TODO: implement metadata only index copy up when called with
* ovl_copy_up_flags(dentry, O_PATH).
*/
if (ovl_need_index(dentry) && !ovl_dentry_has_upper_alias(dentry)) {
err = ovl_copy_up(dentry);
if (err)
return err;
}
err = ovl_inode_lock_interruptible(inode);
if (err)
return err;
if (d_is_dir(dentry) || !ovl_test_flag(OVL_INDEX, inode))
goto out;
old_cred = ovl_override_creds(dentry->d_sb);
/*
* The overlay inode nlink should be incremented/decremented IFF the
* upper operation succeeds, along with nlink change of upper inode.
* Therefore, before link/unlink/rename, we store the union nlink
* value relative to the upper inode nlink in an upper inode xattr.
*/
err = ovl_set_nlink_upper(dentry);
revert_creds(old_cred);
out:
if (err)
ovl_inode_unlock(inode);
return err;
}
void ovl_nlink_end(struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
if (ovl_test_flag(OVL_INDEX, inode) && inode->i_nlink == 0) {
const struct cred *old_cred;
old_cred = ovl_override_creds(dentry->d_sb);
ovl_cleanup_index(dentry);
revert_creds(old_cred);
}
ovl_inode_unlock(inode);
}
int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir)
{
/* Workdir should not be the same as upperdir */
if (workdir == upperdir)
goto err;
/* Workdir should not be subdir of upperdir and vice versa */
if (lock_rename(workdir, upperdir) != NULL)
goto err_unlock;
return 0;
err_unlock:
unlock_rename(workdir, upperdir);
err:
pr_err("failed to lock workdir+upperdir\n");
return -EIO;
}
/* err < 0, 0 if no metacopy xattr, 1 if metacopy xattr found */
int ovl_check_metacopy_xattr(struct ovl_fs *ofs, const struct path *path)
{
int res;
/* Only regular files can have metacopy xattr */
if (!S_ISREG(d_inode(path->dentry)->i_mode))
return 0;
res = ovl_path_getxattr(ofs, path, OVL_XATTR_METACOPY, NULL, 0);
if (res < 0) {
if (res == -ENODATA || res == -EOPNOTSUPP)
return 0;
/*
* getxattr on user.* may fail with EACCES in case there's no
* read permission on the inode. Not much we can do, other than
* tell the caller that this is not a metacopy inode.
*/
if (ofs->config.userxattr && res == -EACCES)
return 0;
goto out;
}
return 1;
out:
pr_warn_ratelimited("failed to get metacopy (%i)\n", res);
return res;
}
bool ovl_is_metacopy_dentry(struct dentry *dentry)
{
struct ovl_entry *oe = OVL_E(dentry);
if (!d_is_reg(dentry))
return false;
if (ovl_dentry_upper(dentry)) {
if (!ovl_has_upperdata(d_inode(dentry)))
return true;
return false;
}
return (ovl_numlower(oe) > 1);
}
char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int padding)
{
int res;
char *s, *next, *buf = NULL;
res = ovl_path_getxattr(ofs, path, OVL_XATTR_REDIRECT, NULL, 0);
if (res == -ENODATA || res == -EOPNOTSUPP)
return NULL;
if (res < 0)
goto fail;
if (res == 0)
goto invalid;
buf = kzalloc(res + padding + 1, GFP_KERNEL);
if (!buf)
return ERR_PTR(-ENOMEM);
res = ovl_path_getxattr(ofs, path, OVL_XATTR_REDIRECT, buf, res);
if (res < 0)
goto fail;
if (res == 0)
goto invalid;
if (buf[0] == '/') {
for (s = buf; *s++ == '/'; s = next) {
next = strchrnul(s, '/');
if (s == next)
goto invalid;
}
} else {
if (strchr(buf, '/') != NULL)
goto invalid;
}
return buf;
invalid:
pr_warn_ratelimited("invalid redirect (%s)\n", buf);
res = -EINVAL;
goto err_free;
fail:
pr_warn_ratelimited("failed to get redirect (%i)\n", res);
err_free:
kfree(buf);
return ERR_PTR(res);
}
/*
* ovl_sync_status() - Check fs sync status for volatile mounts
*
* Returns 1 if this is not a volatile mount and a real sync is required.
*
* Returns 0 if syncing can be skipped because mount is volatile, and no errors
* have occurred on the upperdir since the mount.
*
* Returns -errno if it is a volatile mount, and the error that occurred since
* the last mount. If the error code changes, it'll return the latest error
* code.
*/
int ovl_sync_status(struct ovl_fs *ofs)
{
struct vfsmount *mnt;
if (ovl_should_sync(ofs))
return 1;
mnt = ovl_upper_mnt(ofs);
if (!mnt)
return 0;
return errseq_check(&mnt->mnt_sb->s_wb_err, ofs->errseq);
}
/*
* ovl_copyattr() - copy inode attributes from layer to ovl inode
*
* When overlay copies inode information from an upper or lower layer to the
* relevant overlay inode it will apply the idmapping of the upper or lower
* layer when doing so ensuring that the ovl inode ownership will correctly
* reflect the ownership of the idmapped upper or lower layer. For example, an
* idmapped upper or lower layer mapping id 1001 to id 1000 will take care to
* map any lower or upper inode owned by id 1001 to id 1000. These mapping
* helpers are nops when the relevant layer isn't idmapped.
*/
void ovl_copyattr(struct inode *inode)
{
struct path realpath;
struct inode *realinode;
struct mnt_idmap *real_idmap;
vfsuid_t vfsuid;
vfsgid_t vfsgid;
realinode = ovl_i_path_real(inode, &realpath);
real_idmap = mnt_idmap(realpath.mnt);
vfsuid = i_uid_into_vfsuid(real_idmap, realinode);
vfsgid = i_gid_into_vfsgid(real_idmap, realinode);
inode->i_uid = vfsuid_into_kuid(vfsuid);
inode->i_gid = vfsgid_into_kgid(vfsgid);
inode->i_mode = realinode->i_mode;
inode->i_atime = realinode->i_atime;
inode->i_mtime = realinode->i_mtime;
inode->i_ctime = realinode->i_ctime;
i_size_write(inode, i_size_read(realinode));
}
|