forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathsuper.c
1619 lines (1358 loc) · 38.8 KB
/
super.c
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
/*
*
* 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 <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 <[email protected]>");
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_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(ovl_inode_cachep, OVL_I(inode));
}
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);
kfree(oi->redirect);
mutex_destroy(&oi->lock);
call_rcu(&inode->i_rcu, ovl_i_callback);
}
static void ovl_free_fs(struct ovl_fs *ofs)
{
unsigned i;
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++)
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,
.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_get_upper(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;