forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
dir.c
1318 lines (1123 loc) · 30.5 KB
/
dir.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
// SPDX-License-Identifier: GPL-2.0-only
/*
*
* Copyright (C) 2011 Novell Inc.
*/
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/cred.h>
#include <linux/module.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/atomic.h>
#include <linux/ratelimit.h>
#include "overlayfs.h"
static unsigned short ovl_redirect_max = 256;
module_param_named(redirect_max, ovl_redirect_max, ushort, 0644);
MODULE_PARM_DESC(redirect_max,
"Maximum length of absolute redirect xattr value");
static int ovl_set_redirect(struct dentry *dentry, bool samedir);
int ovl_cleanup(struct ovl_fs *ofs, struct inode *wdir, struct dentry *wdentry)
{
int err;
dget(wdentry);
if (d_is_dir(wdentry))
err = ovl_do_rmdir(ofs, wdir, wdentry);
else
err = ovl_do_unlink(ofs, wdir, wdentry);
dput(wdentry);
if (err) {
pr_err("cleanup of '%pd2' failed (%i)\n",
wdentry, err);
}
return err;
}
struct dentry *ovl_lookup_temp(struct ovl_fs *ofs, struct dentry *workdir)
{
struct dentry *temp;
char name[20];
static atomic_t temp_id = ATOMIC_INIT(0);
/* counter is allowed to wrap, since temp dentries are ephemeral */
snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id));
temp = ovl_lookup_upper(ofs, name, workdir, strlen(name));
if (!IS_ERR(temp) && temp->d_inode) {
pr_err("workdir/%s already exists\n", name);
dput(temp);
temp = ERR_PTR(-EIO);
}
return temp;
}
/* caller holds i_mutex on workdir */
static struct dentry *ovl_whiteout(struct ovl_fs *ofs)
{
int err;
struct dentry *whiteout;
struct dentry *workdir = ofs->workdir;
struct inode *wdir = workdir->d_inode;
if (!ofs->whiteout) {
whiteout = ovl_lookup_temp(ofs, workdir);
if (IS_ERR(whiteout))
goto out;
err = ovl_do_whiteout(ofs, wdir, whiteout);
if (err) {
dput(whiteout);
whiteout = ERR_PTR(err);
goto out;
}
ofs->whiteout = whiteout;
}
if (ofs->share_whiteout) {
whiteout = ovl_lookup_temp(ofs, workdir);
if (IS_ERR(whiteout))
goto out;
err = ovl_do_link(ofs, ofs->whiteout, wdir, whiteout);
if (!err)
goto out;
if (err != -EMLINK) {
pr_warn("Failed to link whiteout - disabling whiteout inode sharing(nlink=%u, err=%i)\n",
ofs->whiteout->d_inode->i_nlink, err);
ofs->share_whiteout = false;
}
dput(whiteout);
}
whiteout = ofs->whiteout;
ofs->whiteout = NULL;
out:
return whiteout;
}
/* Caller must hold i_mutex on both workdir and dir */
int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir,
struct dentry *dentry)
{
struct inode *wdir = ofs->workdir->d_inode;
struct dentry *whiteout;
int err;
int flags = 0;
whiteout = ovl_whiteout(ofs);
err = PTR_ERR(whiteout);
if (IS_ERR(whiteout))
return err;
if (d_is_dir(dentry))
flags = RENAME_EXCHANGE;
err = ovl_do_rename(ofs, wdir, whiteout, dir, dentry, flags);
if (err)
goto kill_whiteout;
if (flags)
ovl_cleanup(ofs, wdir, dentry);
out:
dput(whiteout);
return err;
kill_whiteout:
ovl_cleanup(ofs, wdir, whiteout);
goto out;
}
int ovl_mkdir_real(struct ovl_fs *ofs, struct inode *dir,
struct dentry **newdentry, umode_t mode)
{
int err;
struct dentry *d, *dentry = *newdentry;
err = ovl_do_mkdir(ofs, dir, dentry, mode);
if (err)
return err;
if (likely(!d_unhashed(dentry)))
return 0;
/*
* vfs_mkdir() may succeed and leave the dentry passed
* to it unhashed and negative. If that happens, try to
* lookup a new hashed and positive dentry.
*/
d = ovl_lookup_upper(ofs, dentry->d_name.name, dentry->d_parent,
dentry->d_name.len);
if (IS_ERR(d)) {
pr_warn("failed lookup after mkdir (%pd2, err=%i).\n",
dentry, err);
return PTR_ERR(d);
}
dput(dentry);
*newdentry = d;
return 0;
}
struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir,
struct dentry *newdentry, struct ovl_cattr *attr)
{
int err;
if (IS_ERR(newdentry))
return newdentry;
err = -ESTALE;
if (newdentry->d_inode)
goto out;
if (attr->hardlink) {
err = ovl_do_link(ofs, attr->hardlink, dir, newdentry);
} else {
switch (attr->mode & S_IFMT) {
case S_IFREG:
err = ovl_do_create(ofs, dir, newdentry, attr->mode);
break;
case S_IFDIR:
/* mkdir is special... */
err = ovl_mkdir_real(ofs, dir, &newdentry, attr->mode);
break;
case S_IFCHR:
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
err = ovl_do_mknod(ofs, dir, newdentry, attr->mode,
attr->rdev);
break;
case S_IFLNK:
err = ovl_do_symlink(ofs, dir, newdentry, attr->link);
break;
default:
err = -EPERM;
}
}
if (!err && WARN_ON(!newdentry->d_inode)) {
/*
* Not quite sure if non-instantiated dentry is legal or not.
* VFS doesn't seem to care so check and warn here.
*/
err = -EIO;
}
out:
if (err) {
dput(newdentry);
return ERR_PTR(err);
}
return newdentry;
}
struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir,
struct ovl_cattr *attr)
{
return ovl_create_real(ofs, d_inode(workdir),
ovl_lookup_temp(ofs, workdir), attr);
}
static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper,
int xerr)
{
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
int err;
err = ovl_check_setxattr(ofs, upper, OVL_XATTR_OPAQUE, "y", 1, xerr);
if (!err)
ovl_dentry_set_opaque(dentry);
return err;
}
static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry)
{
/*
* Fail with -EIO when trying to create opaque dir and upper doesn't
* support xattrs. ovl_rename() calls ovl_set_opaque_xerr(-EXDEV) to
* return a specific error for noxattr case.
*/
return ovl_set_opaque_xerr(dentry, upperdentry, -EIO);
}
/*
* Common operations required to be done after creation of file on upper.
* If @hardlink is false, then @inode is a pre-allocated inode, we may or
* may not use to instantiate the new dentry.
*/
static int ovl_instantiate(struct dentry *dentry, struct inode *inode,
struct dentry *newdentry, bool hardlink)
{
struct ovl_inode_params oip = {
.upperdentry = newdentry,
.newinode = inode,
};
ovl_dir_modified(dentry->d_parent, false);
ovl_dentry_set_upper_alias(dentry);
ovl_dentry_update_reval(dentry, newdentry,
DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE);
if (!hardlink) {
/*
* ovl_obtain_alias() can be called after ovl_create_real()
* and before we get here, so we may get an inode from cache
* with the same real upperdentry that is not the inode we
* pre-allocated. In this case we will use the cached inode
* to instantiate the new dentry.
*
* XXX: if we ever use ovl_obtain_alias() to decode directory
* file handles, need to use ovl_get_inode_locked() and
* d_instantiate_new() here to prevent from creating two
* hashed directory inode aliases.
*/
inode = ovl_get_inode(dentry->d_sb, &oip);
if (IS_ERR(inode))
return PTR_ERR(inode);
if (inode == oip.newinode)
ovl_set_flag(OVL_UPPERDATA, inode);
} else {
WARN_ON(ovl_inode_real(inode) != d_inode(newdentry));
dput(newdentry);
inc_nlink(inode);
}
d_instantiate(dentry, inode);
if (inode != oip.newinode) {
pr_warn_ratelimited("newly created inode found in cache (%pd2)\n",
dentry);
}
/* Force lookup of new upper hardlink to find its lower */
if (hardlink)
d_drop(dentry);
return 0;
}
static bool ovl_type_merge(struct dentry *dentry)
{
return OVL_TYPE_MERGE(ovl_path_type(dentry));
}
static bool ovl_type_origin(struct dentry *dentry)
{
return OVL_TYPE_ORIGIN(ovl_path_type(dentry));
}
static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
struct ovl_cattr *attr)
{
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct dentry *newdentry;
int err;
if (!attr->hardlink && !IS_POSIXACL(udir))
attr->mode &= ~current_umask();
inode_lock_nested(udir, I_MUTEX_PARENT);
newdentry = ovl_create_real(ofs, udir,
ovl_lookup_upper(ofs, dentry->d_name.name,
upperdir, dentry->d_name.len),
attr);
err = PTR_ERR(newdentry);
if (IS_ERR(newdentry))
goto out_unlock;
if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry) &&
!ovl_allow_offline_changes(ofs)) {
/* Setting opaque here is just an optimization, allow to fail */
ovl_set_opaque(dentry, newdentry);
}
err = ovl_instantiate(dentry, inode, newdentry, !!attr->hardlink);
if (err)
goto out_cleanup;
out_unlock:
inode_unlock(udir);
return err;
out_cleanup:
ovl_cleanup(ofs, udir, newdentry);
dput(newdentry);
goto out_unlock;
}
static struct dentry *ovl_clear_empty(struct dentry *dentry,
struct list_head *list)
{
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
struct dentry *workdir = ovl_workdir(dentry);
struct inode *wdir = workdir->d_inode;
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct path upperpath;
struct dentry *upper;
struct dentry *opaquedir;
struct kstat stat;
int err;
if (WARN_ON(!workdir))
return ERR_PTR(-EROFS);
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
ovl_path_upper(dentry, &upperpath);
err = vfs_getattr(&upperpath, &stat,
STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
if (err)
goto out_unlock;
err = -ESTALE;
if (!S_ISDIR(stat.mode))
goto out_unlock;
upper = upperpath.dentry;
if (upper->d_parent->d_inode != udir)
goto out_unlock;
opaquedir = ovl_create_temp(ofs, workdir, OVL_CATTR(stat.mode));
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir))
goto out_unlock;
err = ovl_copy_xattr(dentry->d_sb, &upperpath, opaquedir);
if (err)
goto out_cleanup;
err = ovl_set_opaque(dentry, opaquedir);
if (err)
goto out_cleanup;
inode_lock(opaquedir->d_inode);
err = ovl_set_attr(ofs, opaquedir, &stat);
inode_unlock(opaquedir->d_inode);
if (err)
goto out_cleanup;
err = ovl_do_rename(ofs, wdir, opaquedir, udir, upper, RENAME_EXCHANGE);
if (err)
goto out_cleanup;
ovl_cleanup_whiteouts(ofs, upper, list);
ovl_cleanup(ofs, wdir, upper);
unlock_rename(workdir, upperdir);
/* dentry's upper doesn't match now, get rid of it */
d_drop(dentry);
return opaquedir;
out_cleanup:
ovl_cleanup(ofs, wdir, opaquedir);
dput(opaquedir);
out_unlock:
unlock_rename(workdir, upperdir);
out:
return ERR_PTR(err);
}
static int ovl_set_upper_acl(struct ovl_fs *ofs, struct dentry *upperdentry,
const char *acl_name, struct posix_acl *acl)
{
if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !acl)
return 0;
return ovl_do_set_acl(ofs, upperdentry, acl_name, acl);
}
static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
struct ovl_cattr *cattr)
{
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
struct dentry *workdir = ovl_workdir(dentry);
struct inode *wdir = workdir->d_inode;
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct dentry *upper;
struct dentry *newdentry;
int err;
struct posix_acl *acl, *default_acl;
bool hardlink = !!cattr->hardlink;
if (WARN_ON(!workdir))
return -EROFS;
if (!hardlink) {
err = posix_acl_create(dentry->d_parent->d_inode,
&cattr->mode, &default_acl, &acl);
if (err)
return err;
}
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
upper = ovl_lookup_upper(ofs, dentry->d_name.name, upperdir,
dentry->d_name.len);
err = PTR_ERR(upper);
if (IS_ERR(upper))
goto out_unlock;
err = -ESTALE;
if (d_is_negative(upper) || !IS_WHITEOUT(d_inode(upper)))
goto out_dput;
newdentry = ovl_create_temp(ofs, workdir, cattr);
err = PTR_ERR(newdentry);
if (IS_ERR(newdentry))
goto out_dput;
/*
* mode could have been mutilated due to umask (e.g. sgid directory)
*/
if (!hardlink &&
!S_ISLNK(cattr->mode) &&
newdentry->d_inode->i_mode != cattr->mode) {
struct iattr attr = {
.ia_valid = ATTR_MODE,
.ia_mode = cattr->mode,
};
inode_lock(newdentry->d_inode);
err = ovl_do_notify_change(ofs, newdentry, &attr);
inode_unlock(newdentry->d_inode);
if (err)
goto out_cleanup;
}
if (!hardlink) {
err = ovl_set_upper_acl(ofs, newdentry,
XATTR_NAME_POSIX_ACL_ACCESS, acl);
if (err)
goto out_cleanup;
err = ovl_set_upper_acl(ofs, newdentry,
XATTR_NAME_POSIX_ACL_DEFAULT, default_acl);
if (err)
goto out_cleanup;
}
if (!hardlink && S_ISDIR(cattr->mode)) {
err = ovl_set_opaque(dentry, newdentry);
if (err)
goto out_cleanup;
err = ovl_do_rename(ofs, wdir, newdentry, udir, upper,
RENAME_EXCHANGE);
if (err)
goto out_cleanup;
ovl_cleanup(ofs, wdir, upper);
} else {
err = ovl_do_rename(ofs, wdir, newdentry, udir, upper, 0);
if (err)
goto out_cleanup;
}
err = ovl_instantiate(dentry, inode, newdentry, hardlink);
if (err) {
ovl_cleanup(ofs, udir, newdentry);
dput(newdentry);
}
out_dput:
dput(upper);
out_unlock:
unlock_rename(workdir, upperdir);
out:
if (!hardlink) {
posix_acl_release(acl);
posix_acl_release(default_acl);
}
return err;
out_cleanup:
ovl_cleanup(ofs, wdir, newdentry);
dput(newdentry);
goto out_dput;
}
static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
struct ovl_cattr *attr, bool origin)
{
int err;
const struct cred *old_cred;
struct cred *override_cred;
struct dentry *parent = dentry->d_parent;
err = ovl_copy_up(parent);
if (err)
return err;
old_cred = ovl_override_creds(dentry->d_sb);
/*
* When linking a file with copy up origin into a new parent, mark the
* new parent dir "impure".
*/
if (origin) {
err = ovl_set_impure(parent, ovl_dentry_upper(parent));
if (err)
goto out_revert_creds;
}
if (!attr->hardlink) {
err = -ENOMEM;
override_cred = prepare_creds();
if (!override_cred)
goto out_revert_creds;
/*
* In the creation cases(create, mkdir, mknod, symlink),
* ovl should transfer current's fs{u,g}id to underlying
* fs. Because underlying fs want to initialize its new
* inode owner using current's fs{u,g}id. And in this
* case, the @inode is a new inode that is initialized
* in inode_init_owner() to current's fs{u,g}id. So use
* the inode's i_{u,g}id to override the cred's fs{u,g}id.
*
* But in the other hardlink case, ovl_link() does not
* create a new inode, so just use the ovl mounter's
* fs{u,g}id.
*/
override_cred->fsuid = inode->i_uid;
override_cred->fsgid = inode->i_gid;
err = security_dentry_create_files_as(dentry,
attr->mode, &dentry->d_name, old_cred,
override_cred);
if (err) {
put_cred(override_cred);
goto out_revert_creds;
}
put_cred(override_creds(override_cred));
put_cred(override_cred);
}
if (!ovl_dentry_is_whiteout(dentry))
err = ovl_create_upper(dentry, inode, attr);
else
err = ovl_create_over_whiteout(dentry, inode, attr);
out_revert_creds:
revert_creds(old_cred);
return err;
}
static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
const char *link)
{
int err;
struct inode *inode;
struct ovl_cattr attr = {
.rdev = rdev,
.link = link,
};
err = ovl_want_write(dentry);
if (err)
goto out;
/* Preallocate inode to be used by ovl_get_inode() */
err = -ENOMEM;
inode = ovl_new_inode(dentry->d_sb, mode, rdev);
if (!inode)
goto out_drop_write;
spin_lock(&inode->i_lock);
inode->i_state |= I_CREATING;
spin_unlock(&inode->i_lock);
inode_init_owner(&init_user_ns, inode, dentry->d_parent->d_inode, mode);
attr.mode = inode->i_mode;
err = ovl_create_or_link(dentry, inode, &attr, false);
/* Did we end up using the preallocated inode? */
if (inode != d_inode(dentry))
iput(inode);
out_drop_write:
ovl_drop_write(dentry);
out:
return err;
}
static int ovl_create(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode, bool excl)
{
return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL);
}
static int ovl_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode)
{
return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL);
}
static int ovl_mknod(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t rdev)
{
/* Don't allow creation of "whiteout" on overlay */
if (S_ISCHR(mode) && rdev == WHITEOUT_DEV)
return -EPERM;
return ovl_create_object(dentry, mode, rdev, NULL);
}
static int ovl_symlink(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, const char *link)
{
return ovl_create_object(dentry, S_IFLNK, 0, link);
}
static int ovl_set_link_redirect(struct dentry *dentry)
{
const struct cred *old_cred;
int err;
old_cred = ovl_override_creds(dentry->d_sb);
err = ovl_set_redirect(dentry, false);
revert_creds(old_cred);
return err;
}
static int ovl_link(struct dentry *old, struct inode *newdir,
struct dentry *new)
{
int err;
struct inode *inode;
err = ovl_want_write(old);
if (err)
goto out;
err = ovl_copy_up(old);
if (err)
goto out_drop_write;
err = ovl_copy_up(new->d_parent);
if (err)
goto out_drop_write;
if (ovl_is_metacopy_dentry(old)) {
err = ovl_set_link_redirect(old);
if (err)
goto out_drop_write;
}
err = ovl_nlink_start(old);
if (err)
goto out_drop_write;
inode = d_inode(old);
ihold(inode);
err = ovl_create_or_link(new, inode,
&(struct ovl_cattr) {.hardlink = ovl_dentry_upper(old)},
ovl_type_origin(old));
if (err)
iput(inode);
ovl_nlink_end(old);
out_drop_write:
ovl_drop_write(old);
out:
return err;
}
static bool ovl_matches_upper(struct dentry *dentry, struct dentry *upper)
{
return d_inode(ovl_dentry_upper(dentry)) == d_inode(upper);
}
static int ovl_remove_and_whiteout(struct dentry *dentry,
struct list_head *list)
{
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
struct dentry *workdir = ovl_workdir(dentry);
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct dentry *upper;
struct dentry *opaquedir = NULL;
int err;
if (WARN_ON(!workdir))
return -EROFS;
if (!list_empty(list)) {
opaquedir = ovl_clear_empty(dentry, list);
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir))
goto out;
}
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out_dput;
upper = ovl_lookup_upper(ofs, dentry->d_name.name, upperdir,
dentry->d_name.len);
err = PTR_ERR(upper);
if (IS_ERR(upper))
goto out_unlock;
err = -ESTALE;
if ((opaquedir && upper != opaquedir) ||
(!opaquedir && ovl_dentry_upper(dentry) &&
!ovl_matches_upper(dentry, upper))) {
goto out_dput_upper;
}
err = ovl_cleanup_and_whiteout(ofs, d_inode(upperdir), upper);
if (err)
goto out_d_drop;
ovl_dir_modified(dentry->d_parent, true);
out_d_drop:
d_drop(dentry);
out_dput_upper:
dput(upper);
out_unlock:
unlock_rename(workdir, upperdir);
out_dput:
dput(opaquedir);
out:
return err;
}
static int ovl_remove_upper(struct dentry *dentry, bool is_dir,
struct list_head *list)
{
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *dir = upperdir->d_inode;
struct dentry *upper;
struct dentry *opaquedir = NULL;
int err;
if (!list_empty(list)) {
opaquedir = ovl_clear_empty(dentry, list);
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir))
goto out;
}
inode_lock_nested(dir, I_MUTEX_PARENT);
upper = ovl_lookup_upper(ofs, dentry->d_name.name, upperdir,
dentry->d_name.len);
err = PTR_ERR(upper);
if (IS_ERR(upper))
goto out_unlock;
err = -ESTALE;
if ((opaquedir && upper != opaquedir) ||
(!opaquedir && !ovl_matches_upper(dentry, upper)))
goto out_dput_upper;
if (is_dir)
err = ovl_do_rmdir(ofs, dir, upper);
else
err = ovl_do_unlink(ofs, dir, upper);
ovl_dir_modified(dentry->d_parent, ovl_type_origin(dentry));
/*
* Keeping this dentry hashed would mean having to release
* upperpath/lowerpath, which could only be done if we are the
* sole user of this dentry. Too tricky... Just unhash for
* now.
*/
if (!err)
d_drop(dentry);
out_dput_upper:
dput(upper);
out_unlock:
inode_unlock(dir);
dput(opaquedir);
out:
return err;
}
static bool ovl_pure_upper(struct dentry *dentry)
{
return !ovl_dentry_lower(dentry) &&
!ovl_test_flag(OVL_WHITEOUTS, d_inode(dentry));
}
static void ovl_drop_nlink(struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
struct dentry *alias;
/* Try to find another, hashed alias */
spin_lock(&inode->i_lock);
hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
if (alias != dentry && !d_unhashed(alias))
break;
}
spin_unlock(&inode->i_lock);
/*
* Changes to underlying layers may cause i_nlink to lose sync with
* reality. In this case prevent the link count from going to zero
* prematurely.
*/
if (inode->i_nlink > !!alias)
drop_nlink(inode);
}
static int ovl_do_remove(struct dentry *dentry, bool is_dir)
{
int err;
const struct cred *old_cred;
bool lower_positive = ovl_lower_positive(dentry);
LIST_HEAD(list);
/* No need to clean pure upper removed by vfs_rmdir() */
if (is_dir && (lower_positive || !ovl_pure_upper(dentry))) {
err = ovl_check_empty_dir(dentry, &list);
if (err)
goto out;
}
err = ovl_want_write(dentry);
if (err)
goto out;
err = ovl_copy_up(dentry->d_parent);
if (err)
goto out_drop_write;
err = ovl_nlink_start(dentry);
if (err)
goto out_drop_write;
old_cred = ovl_override_creds(dentry->d_sb);
if (!lower_positive)
err = ovl_remove_upper(dentry, is_dir, &list);
else
err = ovl_remove_and_whiteout(dentry, &list);
revert_creds(old_cred);
if (!err) {
if (is_dir)
clear_nlink(dentry->d_inode);
else
ovl_drop_nlink(dentry);
}
ovl_nlink_end(dentry);
/*
* Copy ctime
*
* Note: we fail to update ctime if there was no copy-up, only a
* whiteout
*/
if (ovl_dentry_upper(dentry))
ovl_copyattr(d_inode(dentry));
out_drop_write:
ovl_drop_write(dentry);
out:
ovl_cache_free(&list);
return err;
}
static int ovl_unlink(struct inode *dir, struct dentry *dentry)
{
return ovl_do_remove(dentry, false);
}
static int ovl_rmdir(struct inode *dir, struct dentry *dentry)
{
return ovl_do_remove(dentry, true);
}
static bool ovl_type_merge_or_lower(struct dentry *dentry)
{
enum ovl_path_type type = ovl_path_type(dentry);
return OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type);
}
static bool ovl_can_move(struct dentry *dentry)
{
return ovl_redirect_dir(dentry->d_sb) ||
!d_is_dir(dentry) || !ovl_type_merge_or_lower(dentry);
}
static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect)
{
char *buf, *ret;
struct dentry *d, *tmp;
int buflen = ovl_redirect_max + 1;
if (!abs_redirect) {
ret = kstrndup(dentry->d_name.name, dentry->d_name.len,
GFP_KERNEL);
goto out;
}
buf = ret = kmalloc(buflen, GFP_KERNEL);
if (!buf)
goto out;
buflen--;
buf[buflen] = '\0';
for (d = dget(dentry); !IS_ROOT(d);) {
const char *name;
int thislen;
spin_lock(&d->d_lock);
name = ovl_dentry_get_redirect(d);
if (name) {
thislen = strlen(name);
} else {
name = d->d_name.name;
thislen = d->d_name.len;
}
/* If path is too long, fall back to userspace move */
if (thislen + (name[0] != '/') > buflen) {
ret = ERR_PTR(-EXDEV);
spin_unlock(&d->d_lock);
goto out_put;
}
buflen -= thislen;
memcpy(&buf[buflen], name, thislen);
spin_unlock(&d->d_lock);