forked from microsoft/WSL2-Linux-Kernel
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdir.c
1995 lines (1710 loc) · 48.8 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
/*
FUSE: Filesystem in Userspace
Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu>
This program can be distributed under the terms of the GNU GPL.
See the file COPYING.
*/
#include "fuse_i.h"
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/fs_context.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/xattr.h>
#include <linux/iversion.h>
#include <linux/posix_acl.h>
#include <linux/security.h>
#include <linux/types.h>
#include <linux/kernel.h>
static bool __read_mostly allow_sys_admin_access;
module_param(allow_sys_admin_access, bool, 0644);
MODULE_PARM_DESC(allow_sys_admin_access,
"Allow users with CAP_SYS_ADMIN in initial userns to bypass allow_other access check");
static void fuse_advise_use_readdirplus(struct inode *dir)
{
struct fuse_inode *fi = get_fuse_inode(dir);
set_bit(FUSE_I_ADVISE_RDPLUS, &fi->state);
}
#if BITS_PER_LONG >= 64
static inline void __fuse_dentry_settime(struct dentry *entry, u64 time)
{
entry->d_fsdata = (void *) time;
}
static inline u64 fuse_dentry_time(const struct dentry *entry)
{
return (u64)entry->d_fsdata;
}
#else
union fuse_dentry {
u64 time;
struct rcu_head rcu;
};
static inline void __fuse_dentry_settime(struct dentry *dentry, u64 time)
{
((union fuse_dentry *) dentry->d_fsdata)->time = time;
}
static inline u64 fuse_dentry_time(const struct dentry *entry)
{
return ((union fuse_dentry *) entry->d_fsdata)->time;
}
#endif
static void fuse_dentry_settime(struct dentry *dentry, u64 time)
{
struct fuse_conn *fc = get_fuse_conn_super(dentry->d_sb);
bool delete = !time && fc->delete_stale;
/*
* Mess with DCACHE_OP_DELETE because dput() will be faster without it.
* Don't care about races, either way it's just an optimization
*/
if ((!delete && (dentry->d_flags & DCACHE_OP_DELETE)) ||
(delete && !(dentry->d_flags & DCACHE_OP_DELETE))) {
spin_lock(&dentry->d_lock);
if (!delete)
dentry->d_flags &= ~DCACHE_OP_DELETE;
else
dentry->d_flags |= DCACHE_OP_DELETE;
spin_unlock(&dentry->d_lock);
}
__fuse_dentry_settime(dentry, time);
}
/*
* FUSE caches dentries and attributes with separate timeout. The
* time in jiffies until the dentry/attributes are valid is stored in
* dentry->d_fsdata and fuse_inode->i_time respectively.
*/
/*
* Calculate the time in jiffies until a dentry/attributes are valid
*/
static u64 time_to_jiffies(u64 sec, u32 nsec)
{
if (sec || nsec) {
struct timespec64 ts = {
sec,
min_t(u32, nsec, NSEC_PER_SEC - 1)
};
return get_jiffies_64() + timespec64_to_jiffies(&ts);
} else
return 0;
}
/*
* Set dentry and possibly attribute timeouts from the lookup/mk*
* replies
*/
void fuse_change_entry_timeout(struct dentry *entry, struct fuse_entry_out *o)
{
fuse_dentry_settime(entry,
time_to_jiffies(o->entry_valid, o->entry_valid_nsec));
}
static u64 attr_timeout(struct fuse_attr_out *o)
{
return time_to_jiffies(o->attr_valid, o->attr_valid_nsec);
}
u64 entry_attr_timeout(struct fuse_entry_out *o)
{
return time_to_jiffies(o->attr_valid, o->attr_valid_nsec);
}
void fuse_invalidate_attr_mask(struct inode *inode, u32 mask)
{
set_mask_bits(&get_fuse_inode(inode)->inval_mask, 0, mask);
}
/*
* Mark the attributes as stale, so that at the next call to
* ->getattr() they will be fetched from userspace
*/
void fuse_invalidate_attr(struct inode *inode)
{
fuse_invalidate_attr_mask(inode, STATX_BASIC_STATS);
}
static void fuse_dir_changed(struct inode *dir)
{
fuse_invalidate_attr(dir);
inode_maybe_inc_iversion(dir, false);
}
/**
* Mark the attributes as stale due to an atime change. Avoid the invalidate if
* atime is not used.
*/
void fuse_invalidate_atime(struct inode *inode)
{
if (!IS_RDONLY(inode))
fuse_invalidate_attr_mask(inode, STATX_ATIME);
}
/*
* Just mark the entry as stale, so that a next attempt to look it up
* will result in a new lookup call to userspace
*
* This is called when a dentry is about to become negative and the
* timeout is unknown (unlink, rmdir, rename and in some cases
* lookup)
*/
void fuse_invalidate_entry_cache(struct dentry *entry)
{
fuse_dentry_settime(entry, 0);
}
/*
* Same as fuse_invalidate_entry_cache(), but also try to remove the
* dentry from the hash
*/
static void fuse_invalidate_entry(struct dentry *entry)
{
d_invalidate(entry);
fuse_invalidate_entry_cache(entry);
}
static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args,
u64 nodeid, const struct qstr *name,
struct fuse_entry_out *outarg)
{
memset(outarg, 0, sizeof(struct fuse_entry_out));
args->opcode = FUSE_LOOKUP;
args->nodeid = nodeid;
args->in_numargs = 1;
args->in_args[0].size = name->len + 1;
args->in_args[0].value = name->name;
args->out_numargs = 1;
args->out_args[0].size = sizeof(struct fuse_entry_out);
args->out_args[0].value = outarg;
}
/*
* Check whether the dentry is still valid
*
* If the entry validity timeout has expired and the dentry is
* positive, try to redo the lookup. If the lookup results in a
* different inode, then let the VFS invalidate the dentry and redo
* the lookup once more. If the lookup results in the same inode,
* then refresh the attributes, timeouts and mark the dentry valid.
*/
static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
{
struct inode *inode;
struct dentry *parent;
struct fuse_mount *fm;
struct fuse_inode *fi;
int ret;
inode = d_inode_rcu(entry);
if (inode && fuse_is_bad(inode))
goto invalid;
else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) ||
(flags & (LOOKUP_EXCL | LOOKUP_REVAL))) {
struct fuse_entry_out outarg;
FUSE_ARGS(args);
struct fuse_forget_link *forget;
u64 attr_version;
/* For negative dentries, always do a fresh lookup */
if (!inode)
goto invalid;
ret = -ECHILD;
if (flags & LOOKUP_RCU)
goto out;
fm = get_fuse_mount(inode);
forget = fuse_alloc_forget();
ret = -ENOMEM;
if (!forget)
goto out;
attr_version = fuse_get_attr_version(fm->fc);
parent = dget_parent(entry);
fuse_lookup_init(fm->fc, &args, get_node_id(d_inode(parent)),
&entry->d_name, &outarg);
ret = fuse_simple_request(fm, &args);
dput(parent);
/* Zero nodeid is same as -ENOENT */
if (!ret && !outarg.nodeid)
ret = -ENOENT;
if (!ret) {
fi = get_fuse_inode(inode);
if (outarg.nodeid != get_node_id(inode) ||
(bool) IS_AUTOMOUNT(inode) != (bool) (outarg.attr.flags & FUSE_ATTR_SUBMOUNT)) {
fuse_queue_forget(fm->fc, forget,
outarg.nodeid, 1);
goto invalid;
}
spin_lock(&fi->lock);
fi->nlookup++;
spin_unlock(&fi->lock);
}
kfree(forget);
if (ret == -ENOMEM)
goto out;
if (ret || fuse_invalid_attr(&outarg.attr) ||
fuse_stale_inode(inode, outarg.generation, &outarg.attr))
goto invalid;
forget_all_cached_acls(inode);
fuse_change_attributes(inode, &outarg.attr,
entry_attr_timeout(&outarg),
attr_version);
fuse_change_entry_timeout(entry, &outarg);
} else if (inode) {
fi = get_fuse_inode(inode);
if (flags & LOOKUP_RCU) {
if (test_bit(FUSE_I_INIT_RDPLUS, &fi->state))
return -ECHILD;
} else if (test_and_clear_bit(FUSE_I_INIT_RDPLUS, &fi->state)) {
parent = dget_parent(entry);
fuse_advise_use_readdirplus(d_inode(parent));
dput(parent);
}
}
ret = 1;
out:
return ret;
invalid:
ret = 0;
goto out;
}
#if BITS_PER_LONG < 64
static int fuse_dentry_init(struct dentry *dentry)
{
dentry->d_fsdata = kzalloc(sizeof(union fuse_dentry),
GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE);
return dentry->d_fsdata ? 0 : -ENOMEM;
}
static void fuse_dentry_release(struct dentry *dentry)
{
union fuse_dentry *fd = dentry->d_fsdata;
kfree_rcu(fd, rcu);
}
#endif
static int fuse_dentry_delete(const struct dentry *dentry)
{
return time_before64(fuse_dentry_time(dentry), get_jiffies_64());
}
/*
* Create a fuse_mount object with a new superblock (with path->dentry
* as the root), and return that mount so it can be auto-mounted on
* @path.
*/
static struct vfsmount *fuse_dentry_automount(struct path *path)
{
struct fs_context *fsc;
struct vfsmount *mnt;
struct fuse_inode *mp_fi = get_fuse_inode(d_inode(path->dentry));
fsc = fs_context_for_submount(path->mnt->mnt_sb->s_type, path->dentry);
if (IS_ERR(fsc))
return ERR_CAST(fsc);
/* Pass the FUSE inode of the mount for fuse_get_tree_submount() */
fsc->fs_private = mp_fi;
/* Create the submount */
mnt = fc_mount(fsc);
if (!IS_ERR(mnt))
mntget(mnt);
put_fs_context(fsc);
return mnt;
}
const struct dentry_operations fuse_dentry_operations = {
.d_revalidate = fuse_dentry_revalidate,
.d_delete = fuse_dentry_delete,
#if BITS_PER_LONG < 64
.d_init = fuse_dentry_init,
.d_release = fuse_dentry_release,
#endif
.d_automount = fuse_dentry_automount,
};
const struct dentry_operations fuse_root_dentry_operations = {
#if BITS_PER_LONG < 64
.d_init = fuse_dentry_init,
.d_release = fuse_dentry_release,
#endif
};
int fuse_valid_type(int m)
{
return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) ||
S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m);
}
bool fuse_invalid_attr(struct fuse_attr *attr)
{
return !fuse_valid_type(attr->mode) ||
attr->size > LLONG_MAX;
}
int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name,
struct fuse_entry_out *outarg, struct inode **inode)
{
struct fuse_mount *fm = get_fuse_mount_super(sb);
FUSE_ARGS(args);
struct fuse_forget_link *forget;
u64 attr_version;
int err;
*inode = NULL;
err = -ENAMETOOLONG;
if (name->len > FUSE_NAME_MAX)
goto out;
forget = fuse_alloc_forget();
err = -ENOMEM;
if (!forget)
goto out;
attr_version = fuse_get_attr_version(fm->fc);
fuse_lookup_init(fm->fc, &args, nodeid, name, outarg);
err = fuse_simple_request(fm, &args);
/* Zero nodeid is same as -ENOENT, but with valid timeout */
if (err || !outarg->nodeid)
goto out_put_forget;
err = -EIO;
if (!outarg->nodeid)
goto out_put_forget;
if (fuse_invalid_attr(&outarg->attr))
goto out_put_forget;
*inode = fuse_iget(sb, outarg->nodeid, outarg->generation,
&outarg->attr, entry_attr_timeout(outarg),
attr_version);
err = -ENOMEM;
if (!*inode) {
fuse_queue_forget(fm->fc, forget, outarg->nodeid, 1);
goto out;
}
err = 0;
out_put_forget:
kfree(forget);
out:
return err;
}
static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
unsigned int flags)
{
int err;
struct fuse_entry_out outarg;
struct inode *inode;
struct dentry *newent;
bool outarg_valid = true;
bool locked;
if (fuse_is_bad(dir))
return ERR_PTR(-EIO);
locked = fuse_lock_inode(dir);
err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name,
&outarg, &inode);
fuse_unlock_inode(dir, locked);
if (err == -ENOENT) {
outarg_valid = false;
err = 0;
}
if (err)
goto out_err;
err = -EIO;
if (inode && get_node_id(inode) == FUSE_ROOT_ID)
goto out_iput;
newent = d_splice_alias(inode, entry);
err = PTR_ERR(newent);
if (IS_ERR(newent))
goto out_err;
entry = newent ? newent : entry;
if (outarg_valid)
fuse_change_entry_timeout(entry, &outarg);
else
fuse_invalidate_entry_cache(entry);
if (inode)
fuse_advise_use_readdirplus(dir);
return newent;
out_iput:
iput(inode);
out_err:
return ERR_PTR(err);
}
static int get_security_context(struct dentry *entry, umode_t mode,
void **security_ctx, u32 *security_ctxlen)
{
struct fuse_secctx *fctx;
struct fuse_secctx_header *header;
void *ctx = NULL, *ptr;
u32 ctxlen, total_len = sizeof(*header);
int err, nr_ctx = 0;
const char *name;
size_t namelen;
err = security_dentry_init_security(entry, mode, &entry->d_name,
&name, &ctx, &ctxlen);
if (err) {
if (err != -EOPNOTSUPP)
goto out_err;
/* No LSM is supporting this security hook. Ignore error */
ctxlen = 0;
ctx = NULL;
}
if (ctxlen) {
nr_ctx = 1;
namelen = strlen(name) + 1;
err = -EIO;
if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || ctxlen > S32_MAX))
goto out_err;
total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + ctxlen);
}
err = -ENOMEM;
header = ptr = kzalloc(total_len, GFP_KERNEL);
if (!ptr)
goto out_err;
header->nr_secctx = nr_ctx;
header->size = total_len;
ptr += sizeof(*header);
if (nr_ctx) {
fctx = ptr;
fctx->size = ctxlen;
ptr += sizeof(*fctx);
strcpy(ptr, name);
ptr += namelen;
memcpy(ptr, ctx, ctxlen);
}
*security_ctxlen = total_len;
*security_ctx = header;
err = 0;
out_err:
kfree(ctx);
return err;
}
/*
* Atomic create+open operation
*
* If the filesystem doesn't support this, then fall back to separate
* 'mknod' + 'open' requests.
*/
static int fuse_create_open(struct inode *dir, struct dentry *entry,
struct file *file, unsigned int flags,
umode_t mode)
{
int err;
struct inode *inode;
struct fuse_mount *fm = get_fuse_mount(dir);
FUSE_ARGS(args);
struct fuse_forget_link *forget;
struct fuse_create_in inarg;
struct fuse_open_out outopen;
struct fuse_entry_out outentry;
struct fuse_inode *fi;
struct fuse_file *ff;
void *security_ctx = NULL;
u32 security_ctxlen;
bool trunc = flags & O_TRUNC;
/* Userspace expects S_IFREG in create mode */
BUG_ON((mode & S_IFMT) != S_IFREG);
forget = fuse_alloc_forget();
err = -ENOMEM;
if (!forget)
goto out_err;
err = -ENOMEM;
ff = fuse_file_alloc(fm);
if (!ff)
goto out_put_forget_req;
if (!fm->fc->dont_mask)
mode &= ~current_umask();
flags &= ~O_NOCTTY;
memset(&inarg, 0, sizeof(inarg));
memset(&outentry, 0, sizeof(outentry));
inarg.flags = flags;
inarg.mode = mode;
inarg.umask = current_umask();
if (fm->fc->handle_killpriv_v2 && trunc &&
!(flags & O_EXCL) && !capable(CAP_FSETID)) {
inarg.open_flags |= FUSE_OPEN_KILL_SUIDGID;
}
args.opcode = FUSE_CREATE;
args.nodeid = get_node_id(dir);
args.in_numargs = 2;
args.in_args[0].size = sizeof(inarg);
args.in_args[0].value = &inarg;
args.in_args[1].size = entry->d_name.len + 1;
args.in_args[1].value = entry->d_name.name;
args.out_numargs = 2;
args.out_args[0].size = sizeof(outentry);
args.out_args[0].value = &outentry;
args.out_args[1].size = sizeof(outopen);
args.out_args[1].value = &outopen;
if (fm->fc->init_security) {
err = get_security_context(entry, mode, &security_ctx,
&security_ctxlen);
if (err)
goto out_put_forget_req;
args.in_numargs = 3;
args.in_args[2].size = security_ctxlen;
args.in_args[2].value = security_ctx;
}
err = fuse_simple_request(fm, &args);
kfree(security_ctx);
if (err)
goto out_free_ff;
err = -EIO;
if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid) ||
fuse_invalid_attr(&outentry.attr))
goto out_free_ff;
ff->fh = outopen.fh;
ff->nodeid = outentry.nodeid;
ff->open_flags = outopen.open_flags;
inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation,
&outentry.attr, entry_attr_timeout(&outentry), 0);
if (!inode) {
flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
fuse_sync_release(NULL, ff, flags);
fuse_queue_forget(fm->fc, forget, outentry.nodeid, 1);
err = -ENOMEM;
goto out_err;
}
kfree(forget);
d_instantiate(entry, inode);
fuse_change_entry_timeout(entry, &outentry);
fuse_dir_changed(dir);
err = finish_open(file, entry, generic_file_open);
if (err) {
fi = get_fuse_inode(inode);
fuse_sync_release(fi, ff, flags);
} else {
file->private_data = ff;
fuse_finish_open(inode, file);
if (fm->fc->atomic_o_trunc && trunc)
truncate_pagecache(inode, 0);
else if (!(ff->open_flags & FOPEN_KEEP_CACHE))
invalidate_inode_pages2(inode->i_mapping);
}
return err;
out_free_ff:
fuse_file_free(ff);
out_put_forget_req:
kfree(forget);
out_err:
return err;
}
static int fuse_mknod(struct user_namespace *, struct inode *, struct dentry *,
umode_t, dev_t);
static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
struct file *file, unsigned flags,
umode_t mode)
{
int err;
struct fuse_conn *fc = get_fuse_conn(dir);
struct dentry *res = NULL;
if (fuse_is_bad(dir))
return -EIO;
if (d_in_lookup(entry)) {
res = fuse_lookup(dir, entry, 0);
if (IS_ERR(res))
return PTR_ERR(res);
if (res)
entry = res;
}
if (!(flags & O_CREAT) || d_really_is_positive(entry))
goto no_open;
/* Only creates */
file->f_mode |= FMODE_CREATED;
if (fc->no_create)
goto mknod;
err = fuse_create_open(dir, entry, file, flags, mode);
if (err == -ENOSYS) {
fc->no_create = 1;
goto mknod;
}
out_dput:
dput(res);
return err;
mknod:
err = fuse_mknod(&init_user_ns, dir, entry, mode, 0);
if (err)
goto out_dput;
no_open:
return finish_no_open(file, res);
}
/*
* Code shared between mknod, mkdir, symlink and link
*/
static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args,
struct inode *dir, struct dentry *entry,
umode_t mode)
{
struct fuse_entry_out outarg;
struct inode *inode;
struct dentry *d;
int err;
struct fuse_forget_link *forget;
void *security_ctx = NULL;
u32 security_ctxlen;
if (fuse_is_bad(dir))
return -EIO;
forget = fuse_alloc_forget();
if (!forget)
return -ENOMEM;
memset(&outarg, 0, sizeof(outarg));
args->nodeid = get_node_id(dir);
args->out_numargs = 1;
args->out_args[0].size = sizeof(outarg);
args->out_args[0].value = &outarg;
if (fm->fc->init_security && args->opcode != FUSE_LINK) {
err = get_security_context(entry, mode, &security_ctx,
&security_ctxlen);
if (err)
goto out_put_forget_req;
BUG_ON(args->in_numargs != 2);
args->in_numargs = 3;
args->in_args[2].size = security_ctxlen;
args->in_args[2].value = security_ctx;
}
err = fuse_simple_request(fm, args);
kfree(security_ctx);
if (err)
goto out_put_forget_req;
err = -EIO;
if (invalid_nodeid(outarg.nodeid) || fuse_invalid_attr(&outarg.attr))
goto out_put_forget_req;
if ((outarg.attr.mode ^ mode) & S_IFMT)
goto out_put_forget_req;
inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation,
&outarg.attr, entry_attr_timeout(&outarg), 0);
if (!inode) {
fuse_queue_forget(fm->fc, forget, outarg.nodeid, 1);
return -ENOMEM;
}
kfree(forget);
d_drop(entry);
d = d_splice_alias(inode, entry);
if (IS_ERR(d))
return PTR_ERR(d);
if (d) {
fuse_change_entry_timeout(d, &outarg);
dput(d);
} else {
fuse_change_entry_timeout(entry, &outarg);
}
fuse_dir_changed(dir);
return 0;
out_put_forget_req:
kfree(forget);
return err;
}
static int fuse_mknod(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *entry, umode_t mode, dev_t rdev)
{
struct fuse_mknod_in inarg;
struct fuse_mount *fm = get_fuse_mount(dir);
FUSE_ARGS(args);
if (!fm->fc->dont_mask)
mode &= ~current_umask();
memset(&inarg, 0, sizeof(inarg));
inarg.mode = mode;
inarg.rdev = new_encode_dev(rdev);
inarg.umask = current_umask();
args.opcode = FUSE_MKNOD;
args.in_numargs = 2;
args.in_args[0].size = sizeof(inarg);
args.in_args[0].value = &inarg;
args.in_args[1].size = entry->d_name.len + 1;
args.in_args[1].value = entry->d_name.name;
return create_new_entry(fm, &args, dir, entry, mode);
}
static int fuse_create(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *entry, umode_t mode, bool excl)
{
return fuse_mknod(&init_user_ns, dir, entry, mode, 0);
}
static int fuse_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *entry, umode_t mode)
{
struct fuse_mkdir_in inarg;
struct fuse_mount *fm = get_fuse_mount(dir);
FUSE_ARGS(args);
if (!fm->fc->dont_mask)
mode &= ~current_umask();
memset(&inarg, 0, sizeof(inarg));
inarg.mode = mode;
inarg.umask = current_umask();
args.opcode = FUSE_MKDIR;
args.in_numargs = 2;
args.in_args[0].size = sizeof(inarg);
args.in_args[0].value = &inarg;
args.in_args[1].size = entry->d_name.len + 1;
args.in_args[1].value = entry->d_name.name;
return create_new_entry(fm, &args, dir, entry, S_IFDIR);
}
static int fuse_symlink(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *entry, const char *link)
{
struct fuse_mount *fm = get_fuse_mount(dir);
unsigned len = strlen(link) + 1;
FUSE_ARGS(args);
args.opcode = FUSE_SYMLINK;
args.in_numargs = 2;
args.in_args[0].size = entry->d_name.len + 1;
args.in_args[0].value = entry->d_name.name;
args.in_args[1].size = len;
args.in_args[1].value = link;
return create_new_entry(fm, &args, dir, entry, S_IFLNK);
}
void fuse_flush_time_update(struct inode *inode)
{
int err = sync_inode_metadata(inode, 1);
mapping_set_error(inode->i_mapping, err);
}
static void fuse_update_ctime_in_cache(struct inode *inode)
{
if (!IS_NOCMTIME(inode)) {
inode->i_ctime = current_time(inode);
mark_inode_dirty_sync(inode);
fuse_flush_time_update(inode);
}
}
void fuse_update_ctime(struct inode *inode)
{
fuse_invalidate_attr_mask(inode, STATX_CTIME);
fuse_update_ctime_in_cache(inode);
}
static void fuse_entry_unlinked(struct dentry *entry)
{
struct inode *inode = d_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
spin_lock(&fi->lock);
fi->attr_version = atomic64_inc_return(&fc->attr_version);
/*
* If i_nlink == 0 then unlink doesn't make sense, yet this can
* happen if userspace filesystem is careless. It would be
* difficult to enforce correct nlink usage so just ignore this
* condition here
*/
if (S_ISDIR(inode->i_mode))
clear_nlink(inode);
else if (inode->i_nlink > 0)
drop_nlink(inode);
spin_unlock(&fi->lock);
fuse_invalidate_entry_cache(entry);
fuse_update_ctime(inode);
}
static int fuse_unlink(struct inode *dir, struct dentry *entry)
{
int err;
struct fuse_mount *fm = get_fuse_mount(dir);
FUSE_ARGS(args);
if (fuse_is_bad(dir))
return -EIO;
args.opcode = FUSE_UNLINK;
args.nodeid = get_node_id(dir);
args.in_numargs = 1;
args.in_args[0].size = entry->d_name.len + 1;
args.in_args[0].value = entry->d_name.name;
err = fuse_simple_request(fm, &args);
if (!err) {
fuse_dir_changed(dir);
fuse_entry_unlinked(entry);
} else if (err == -EINTR)
fuse_invalidate_entry(entry);
return err;
}
static int fuse_rmdir(struct inode *dir, struct dentry *entry)
{
int err;
struct fuse_mount *fm = get_fuse_mount(dir);
FUSE_ARGS(args);
if (fuse_is_bad(dir))
return -EIO;
args.opcode = FUSE_RMDIR;
args.nodeid = get_node_id(dir);
args.in_numargs = 1;
args.in_args[0].size = entry->d_name.len + 1;
args.in_args[0].value = entry->d_name.name;
err = fuse_simple_request(fm, &args);
if (!err) {
fuse_dir_changed(dir);
fuse_entry_unlinked(entry);
} else if (err == -EINTR)
fuse_invalidate_entry(entry);
return err;
}
static int fuse_rename_common(struct inode *olddir, struct dentry *oldent,
struct inode *newdir, struct dentry *newent,
unsigned int flags, int opcode, size_t argsize)
{
int err;
struct fuse_rename2_in inarg;
struct fuse_mount *fm = get_fuse_mount(olddir);
FUSE_ARGS(args);
memset(&inarg, 0, argsize);
inarg.newdir = get_node_id(newdir);
inarg.flags = flags;
args.opcode = opcode;
args.nodeid = get_node_id(olddir);
args.in_numargs = 3;
args.in_args[0].size = argsize;
args.in_args[0].value = &inarg;
args.in_args[1].size = oldent->d_name.len + 1;
args.in_args[1].value = oldent->d_name.name;
args.in_args[2].size = newent->d_name.len + 1;
args.in_args[2].value = newent->d_name.name;
err = fuse_simple_request(fm, &args);
if (!err) {
/* ctime changes */
fuse_update_ctime(d_inode(oldent));
if (flags & RENAME_EXCHANGE)
fuse_update_ctime(d_inode(newent));
fuse_dir_changed(olddir);
if (olddir != newdir)
fuse_dir_changed(newdir);
/* newent will end up negative */
if (!(flags & RENAME_EXCHANGE) && d_really_is_positive(newent))
fuse_entry_unlinked(newent);
} else if (err == -EINTR) {
/* If request was interrupted, DEITY only knows if the
rename actually took place. If the invalidation
fails (e.g. some process has CWD under the renamed
directory), then there can be inconsistency between
the dcache and the real filesystem. Tough luck. */
fuse_invalidate_entry(oldent);
if (d_really_is_positive(newent))
fuse_invalidate_entry(newent);
}
return err;
}
static int fuse_rename2(struct user_namespace *mnt_userns, struct inode *olddir,
struct dentry *oldent, struct inode *newdir,
struct dentry *newent, unsigned int flags)
{
struct fuse_conn *fc = get_fuse_conn(olddir);
int err;
if (fuse_is_bad(olddir))
return -EIO;
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
if (flags) {
if (fc->no_rename2 || fc->minor < 23)
return -EINVAL;