forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
vfs.c
2112 lines (1848 loc) · 50.1 KB
/
vfs.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
/*
* File operations used by nfsd. Some of these have been ripped from
* other parts of the kernel because they weren't exported, others
* are partial duplicates with added or changed functionality.
*
* Note that several functions dget() the dentry upon which they want
* to act, most notably those that create directory entries. Response
* dentry's are dput()'d if necessary in the release callback.
* So if you notice code paths that apparently fail to dput() the
* dentry, don't worry--they have been taken care of.
*
* Copyright (C) 1995-1999 Olaf Kirch <[email protected]>
* Zerocpy NFS support (C) 2002 Hirokazu Takahashi <[email protected]>
*/
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/splice.h>
#include <linux/fcntl.h>
#include <linux/namei.h>
#include <linux/delay.h>
#include <linux/fsnotify.h>
#include <linux/posix_acl_xattr.h>
#include <linux/xattr.h>
#include <linux/jhash.h>
#include <linux/ima.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/exportfs.h>
#include <linux/writeback.h>
#include <linux/security.h>
#ifdef CONFIG_NFSD_V3
#include "xdr3.h"
#endif /* CONFIG_NFSD_V3 */
#ifdef CONFIG_NFSD_V4
#include "acl.h"
#include "idmap.h"
#endif /* CONFIG_NFSD_V4 */
#include "nfsd.h"
#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_FILEOP
/*
* This is a cache of readahead params that help us choose the proper
* readahead strategy. Initially, we set all readahead parameters to 0
* and let the VFS handle things.
* If you increase the number of cached files very much, you'll need to
* add a hash table here.
*/
struct raparms {
struct raparms *p_next;
unsigned int p_count;
ino_t p_ino;
dev_t p_dev;
int p_set;
struct file_ra_state p_ra;
unsigned int p_hindex;
};
struct raparm_hbucket {
struct raparms *pb_head;
spinlock_t pb_lock;
} ____cacheline_aligned_in_smp;
#define RAPARM_HASH_BITS 4
#define RAPARM_HASH_SIZE (1<<RAPARM_HASH_BITS)
#define RAPARM_HASH_MASK (RAPARM_HASH_SIZE-1)
static struct raparm_hbucket raparm_hash[RAPARM_HASH_SIZE];
/*
* Called from nfsd_lookup and encode_dirent. Check if we have crossed
* a mount point.
* Returns -EAGAIN or -ETIMEDOUT leaving *dpp and *expp unchanged,
* or nfs_ok having possibly changed *dpp and *expp
*/
int
nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
struct svc_export **expp)
{
struct svc_export *exp = *expp, *exp2 = NULL;
struct dentry *dentry = *dpp;
struct path path = {.mnt = mntget(exp->ex_path.mnt),
.dentry = dget(dentry)};
int err = 0;
err = follow_down(&path);
if (err < 0)
goto out;
exp2 = rqst_exp_get_by_name(rqstp, &path);
if (IS_ERR(exp2)) {
err = PTR_ERR(exp2);
/*
* We normally allow NFS clients to continue
* "underneath" a mountpoint that is not exported.
* The exception is V4ROOT, where no traversal is ever
* allowed without an explicit export of the new
* directory.
*/
if (err == -ENOENT && !(exp->ex_flags & NFSEXP_V4ROOT))
err = 0;
path_put(&path);
goto out;
}
if (nfsd_v4client(rqstp) ||
(exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
/* successfully crossed mount point */
/*
* This is subtle: path.dentry is *not* on path.mnt
* at this point. The only reason we are safe is that
* original mnt is pinned down by exp, so we should
* put path *before* putting exp
*/
*dpp = path.dentry;
path.dentry = dentry;
*expp = exp2;
exp2 = exp;
}
path_put(&path);
exp_put(exp2);
out:
return err;
}
static void follow_to_parent(struct path *path)
{
struct dentry *dp;
while (path->dentry == path->mnt->mnt_root && follow_up(path))
;
dp = dget_parent(path->dentry);
dput(path->dentry);
path->dentry = dp;
}
static int nfsd_lookup_parent(struct svc_rqst *rqstp, struct dentry *dparent, struct svc_export **exp, struct dentry **dentryp)
{
struct svc_export *exp2;
struct path path = {.mnt = mntget((*exp)->ex_path.mnt),
.dentry = dget(dparent)};
follow_to_parent(&path);
exp2 = rqst_exp_parent(rqstp, &path);
if (PTR_ERR(exp2) == -ENOENT) {
*dentryp = dget(dparent);
} else if (IS_ERR(exp2)) {
path_put(&path);
return PTR_ERR(exp2);
} else {
*dentryp = dget(path.dentry);
exp_put(*exp);
*exp = exp2;
}
path_put(&path);
return 0;
}
/*
* For nfsd purposes, we treat V4ROOT exports as though there was an
* export at *every* directory.
*/
int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp)
{
if (d_mountpoint(dentry))
return 1;
if (nfsd4_is_junction(dentry))
return 1;
if (!(exp->ex_flags & NFSEXP_V4ROOT))
return 0;
return dentry->d_inode != NULL;
}
__be32
nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
const char *name, unsigned int len,
struct svc_export **exp_ret, struct dentry **dentry_ret)
{
struct svc_export *exp;
struct dentry *dparent;
struct dentry *dentry;
int host_err;
dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
dparent = fhp->fh_dentry;
exp = exp_get(fhp->fh_export);
/* Lookup the name, but don't follow links */
if (isdotent(name, len)) {
if (len==1)
dentry = dget(dparent);
else if (dparent != exp->ex_path.dentry)
dentry = dget_parent(dparent);
else if (!EX_NOHIDE(exp) && !nfsd_v4client(rqstp))
dentry = dget(dparent); /* .. == . just like at / */
else {
/* checking mountpoint crossing is very different when stepping up */
host_err = nfsd_lookup_parent(rqstp, dparent, &exp, &dentry);
if (host_err)
goto out_nfserr;
}
} else {
/*
* In the nfsd4_open() case, this may be held across
* subsequent open and delegation acquisition which may
* need to take the child's i_mutex:
*/
fh_lock_nested(fhp, I_MUTEX_PARENT);
dentry = lookup_one_len(name, dparent, len);
host_err = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_nfserr;
/*
* check if we have crossed a mount point ...
*/
if (nfsd_mountpoint(dentry, exp)) {
if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
dput(dentry);
goto out_nfserr;
}
}
}
*dentry_ret = dentry;
*exp_ret = exp;
return 0;
out_nfserr:
exp_put(exp);
return nfserrno(host_err);
}
/*
* Look up one component of a pathname.
* N.B. After this call _both_ fhp and resfh need an fh_put
*
* If the lookup would cross a mountpoint, and the mounted filesystem
* is exported to the client with NFSEXP_NOHIDE, then the lookup is
* accepted as it stands and the mounted directory is
* returned. Otherwise the covered directory is returned.
* NOTE: this mountpoint crossing is not supported properly by all
* clients and is explicitly disallowed for NFSv3
* NeilBrown <[email protected]>
*/
__be32
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
unsigned int len, struct svc_fh *resfh)
{
struct svc_export *exp;
struct dentry *dentry;
__be32 err;
err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
if (err)
return err;
err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry);
if (err)
return err;
err = check_nfsd_access(exp, rqstp);
if (err)
goto out;
/*
* Note: we compose the file handle now, but as the
* dentry may be negative, it may need to be updated.
*/
err = fh_compose(resfh, exp, dentry, fhp);
if (!err && !dentry->d_inode)
err = nfserr_noent;
out:
dput(dentry);
exp_put(exp);
return err;
}
/*
* Commit metadata changes to stable storage.
*/
static int
commit_metadata(struct svc_fh *fhp)
{
struct inode *inode = fhp->fh_dentry->d_inode;
const struct export_operations *export_ops = inode->i_sb->s_export_op;
if (!EX_ISSYNC(fhp->fh_export))
return 0;
if (export_ops->commit_metadata)
return export_ops->commit_metadata(inode);
return sync_inode_metadata(inode, 1);
}
/*
* Go over the attributes and take care of the small differences between
* NFS semantics and what Linux expects.
*/
static void
nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
{
/*
* NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
* requires ownership.
* So if it looks like it might be "set both to the same time which
* is close to now", and if inode_change_ok fails, then we
* convert to "set to now" instead of "set to explicit time"
*
* We only call inode_change_ok as the last test as technically
* it is not an interface that we should be using.
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET &&
iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) {
/*
* Looks probable.
*
* Now just make sure time is in the right ballpark.
* Solaris, at least, doesn't seem to care what the time
* request is. We require it be within 30 minutes of now.
*/
time_t delta = iap->ia_atime.tv_sec - get_seconds();
if (delta < 0)
delta = -delta;
if (delta < MAX_TOUCH_TIME_ERROR &&
inode_change_ok(inode, iap) != 0) {
/*
* Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
* This will cause notify_change to set these times
* to "now"
*/
iap->ia_valid &= ~BOTH_TIME_SET;
}
}
/* sanitize the mode change */
if (iap->ia_valid & ATTR_MODE) {
iap->ia_mode &= S_IALLUGO;
iap->ia_mode |= (inode->i_mode & ~S_IALLUGO);
}
/* Revoke setuid/setgid on chown */
if (!S_ISDIR(inode->i_mode) &&
((iap->ia_valid & ATTR_UID) || (iap->ia_valid & ATTR_GID))) {
iap->ia_valid |= ATTR_KILL_PRIV;
if (iap->ia_valid & ATTR_MODE) {
/* we're setting mode too, just clear the s*id bits */
iap->ia_mode &= ~S_ISUID;
if (iap->ia_mode & S_IXGRP)
iap->ia_mode &= ~S_ISGID;
} else {
/* set ATTR_KILL_* bits and let VFS handle it */
iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID);
}
}
}
static __be32
nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct iattr *iap)
{
struct inode *inode = fhp->fh_dentry->d_inode;
int host_err;
if (iap->ia_size < inode->i_size) {
__be32 err;
err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE);
if (err)
return err;
}
host_err = get_write_access(inode);
if (host_err)
goto out_nfserrno;
host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
if (host_err)
goto out_put_write_access;
return 0;
out_put_write_access:
put_write_access(inode);
out_nfserrno:
return nfserrno(host_err);
}
/*
* Set various file attributes. After this call fhp needs an fh_put.
*/
__be32
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
int check_guard, time_t guardtime)
{
struct dentry *dentry;
struct inode *inode;
int accmode = NFSD_MAY_SATTR;
umode_t ftype = 0;
__be32 err;
int host_err;
bool get_write_count;
int size_change = 0;
if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
if (iap->ia_valid & ATTR_SIZE)
ftype = S_IFREG;
/* Callers that do fh_verify should do the fh_want_write: */
get_write_count = !fhp->fh_dentry;
/* Get inode */
err = fh_verify(rqstp, fhp, ftype, accmode);
if (err)
goto out;
if (get_write_count) {
host_err = fh_want_write(fhp);
if (host_err)
return nfserrno(host_err);
}
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
/* Ignore any mode updates on symlinks */
if (S_ISLNK(inode->i_mode))
iap->ia_valid &= ~ATTR_MODE;
if (!iap->ia_valid)
goto out;
nfsd_sanitize_attrs(inode, iap);
/*
* The size case is special, it changes the file in addition to the
* attributes.
*/
if (iap->ia_valid & ATTR_SIZE) {
err = nfsd_get_write_access(rqstp, fhp, iap);
if (err)
goto out;
size_change = 1;
}
iap->ia_valid |= ATTR_CTIME;
if (check_guard && guardtime != inode->i_ctime.tv_sec) {
err = nfserr_notsync;
goto out_put_write_access;
}
fh_lock(fhp);
host_err = notify_change(dentry, iap, NULL);
fh_unlock(fhp);
err = nfserrno(host_err);
out_put_write_access:
if (size_change)
put_write_access(inode);
if (!err)
err = nfserrno(commit_metadata(fhp));
out:
return err;
}
#if defined(CONFIG_NFSD_V4)
/*
* NFS junction information is stored in an extended attribute.
*/
#define NFSD_JUNCTION_XATTR_NAME XATTR_TRUSTED_PREFIX "junction.nfs"
/**
* nfsd4_is_junction - Test if an object could be an NFS junction
*
* @dentry: object to test
*
* Returns 1 if "dentry" appears to contain NFS junction information.
* Otherwise 0 is returned.
*/
int nfsd4_is_junction(struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
if (inode == NULL)
return 0;
if (inode->i_mode & S_IXUGO)
return 0;
if (!(inode->i_mode & S_ISVTX))
return 0;
if (vfs_getxattr(dentry, NFSD_JUNCTION_XATTR_NAME, NULL, 0) <= 0)
return 0;
return 1;
}
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct xdr_netobj *label)
{
__be32 error;
int host_error;
struct dentry *dentry;
error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR);
if (error)
return error;
dentry = fhp->fh_dentry;
mutex_lock(&dentry->d_inode->i_mutex);
host_error = security_inode_setsecctx(dentry, label->data, label->len);
mutex_unlock(&dentry->d_inode->i_mutex);
return nfserrno(host_error);
}
#else
__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct xdr_netobj *label)
{
return nfserr_notsupp;
}
#endif
#endif /* defined(CONFIG_NFSD_V4) */
#ifdef CONFIG_NFSD_V3
/*
* Check server access rights to a file system object
*/
struct accessmap {
u32 access;
int how;
};
static struct accessmap nfs3_regaccess[] = {
{ NFS3_ACCESS_READ, NFSD_MAY_READ },
{ NFS3_ACCESS_EXECUTE, NFSD_MAY_EXEC },
{ NFS3_ACCESS_MODIFY, NFSD_MAY_WRITE|NFSD_MAY_TRUNC },
{ NFS3_ACCESS_EXTEND, NFSD_MAY_WRITE },
{ 0, 0 }
};
static struct accessmap nfs3_diraccess[] = {
{ NFS3_ACCESS_READ, NFSD_MAY_READ },
{ NFS3_ACCESS_LOOKUP, NFSD_MAY_EXEC },
{ NFS3_ACCESS_MODIFY, NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC},
{ NFS3_ACCESS_EXTEND, NFSD_MAY_EXEC|NFSD_MAY_WRITE },
{ NFS3_ACCESS_DELETE, NFSD_MAY_REMOVE },
{ 0, 0 }
};
static struct accessmap nfs3_anyaccess[] = {
/* Some clients - Solaris 2.6 at least, make an access call
* to the server to check for access for things like /dev/null
* (which really, the server doesn't care about). So
* We provide simple access checking for them, looking
* mainly at mode bits, and we make sure to ignore read-only
* filesystem checks
*/
{ NFS3_ACCESS_READ, NFSD_MAY_READ },
{ NFS3_ACCESS_EXECUTE, NFSD_MAY_EXEC },
{ NFS3_ACCESS_MODIFY, NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS },
{ NFS3_ACCESS_EXTEND, NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS },
{ 0, 0 }
};
__be32
nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *supported)
{
struct accessmap *map;
struct svc_export *export;
struct dentry *dentry;
u32 query, result = 0, sresult = 0;
__be32 error;
error = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP);
if (error)
goto out;
export = fhp->fh_export;
dentry = fhp->fh_dentry;
if (S_ISREG(dentry->d_inode->i_mode))
map = nfs3_regaccess;
else if (S_ISDIR(dentry->d_inode->i_mode))
map = nfs3_diraccess;
else
map = nfs3_anyaccess;
query = *access;
for (; map->access; map++) {
if (map->access & query) {
__be32 err2;
sresult |= map->access;
err2 = nfsd_permission(rqstp, export, dentry, map->how);
switch (err2) {
case nfs_ok:
result |= map->access;
break;
/* the following error codes just mean the access was not allowed,
* rather than an error occurred */
case nfserr_rofs:
case nfserr_acces:
case nfserr_perm:
/* simply don't "or" in the access bit. */
break;
default:
error = err2;
goto out;
}
}
}
*access = result;
if (supported)
*supported = sresult;
out:
return error;
}
#endif /* CONFIG_NFSD_V3 */
static int nfsd_open_break_lease(struct inode *inode, int access)
{
unsigned int mode;
if (access & NFSD_MAY_NOT_BREAK_LEASE)
return 0;
mode = (access & NFSD_MAY_WRITE) ? O_WRONLY : O_RDONLY;
return break_lease(inode, mode | O_NONBLOCK);
}
/*
* Open an existing file or directory.
* The may_flags argument indicates the type of open (read/write/lock)
* and additional flags.
* N.B. After this call fhp needs an fh_put
*/
__be32
nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
int may_flags, struct file **filp)
{
struct path path;
struct inode *inode;
int flags = O_RDONLY|O_LARGEFILE;
__be32 err;
int host_err = 0;
validate_process_creds();
/*
* If we get here, then the client has already done an "open",
* and (hopefully) checked permission - so allow OWNER_OVERRIDE
* in case a chmod has now revoked permission.
*
* Arguably we should also allow the owner override for
* directories, but we never have and it doesn't seem to have
* caused anyone a problem. If we were to change this, note
* also that our filldir callbacks would need a variant of
* lookup_one_len that doesn't check permissions.
*/
if (type == S_IFREG)
may_flags |= NFSD_MAY_OWNER_OVERRIDE;
err = fh_verify(rqstp, fhp, type, may_flags);
if (err)
goto out;
path.mnt = fhp->fh_export->ex_path.mnt;
path.dentry = fhp->fh_dentry;
inode = path.dentry->d_inode;
/* Disallow write access to files with the append-only bit set
* or any access when mandatory locking enabled
*/
err = nfserr_perm;
if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE))
goto out;
/*
* We must ignore files (but only files) which might have mandatory
* locks on them because there is no way to know if the accesser has
* the lock.
*/
if (S_ISREG((inode)->i_mode) && mandatory_lock(inode))
goto out;
if (!inode->i_fop)
goto out;
host_err = nfsd_open_break_lease(inode, may_flags);
if (host_err) /* NOMEM or WOULDBLOCK */
goto out_nfserr;
if (may_flags & NFSD_MAY_WRITE) {
if (may_flags & NFSD_MAY_READ)
flags = O_RDWR|O_LARGEFILE;
else
flags = O_WRONLY|O_LARGEFILE;
}
*filp = dentry_open(&path, flags, current_cred());
if (IS_ERR(*filp)) {
host_err = PTR_ERR(*filp);
*filp = NULL;
} else {
host_err = ima_file_check(*filp, may_flags);
if (may_flags & NFSD_MAY_64BIT_COOKIE)
(*filp)->f_mode |= FMODE_64BITHASH;
else
(*filp)->f_mode |= FMODE_32BITHASH;
}
out_nfserr:
err = nfserrno(host_err);
out:
validate_process_creds();
return err;
}
/*
* Close a file.
*/
void
nfsd_close(struct file *filp)
{
fput(filp);
}
/*
* Obtain the readahead parameters for the file
* specified by (dev, ino).
*/
static inline struct raparms *
nfsd_get_raparms(dev_t dev, ino_t ino)
{
struct raparms *ra, **rap, **frap = NULL;
int depth = 0;
unsigned int hash;
struct raparm_hbucket *rab;
hash = jhash_2words(dev, ino, 0xfeedbeef) & RAPARM_HASH_MASK;
rab = &raparm_hash[hash];
spin_lock(&rab->pb_lock);
for (rap = &rab->pb_head; (ra = *rap); rap = &ra->p_next) {
if (ra->p_ino == ino && ra->p_dev == dev)
goto found;
depth++;
if (ra->p_count == 0)
frap = rap;
}
depth = nfsdstats.ra_size;
if (!frap) {
spin_unlock(&rab->pb_lock);
return NULL;
}
rap = frap;
ra = *frap;
ra->p_dev = dev;
ra->p_ino = ino;
ra->p_set = 0;
ra->p_hindex = hash;
found:
if (rap != &rab->pb_head) {
*rap = ra->p_next;
ra->p_next = rab->pb_head;
rab->pb_head = ra;
}
ra->p_count++;
nfsdstats.ra_depth[depth*10/nfsdstats.ra_size]++;
spin_unlock(&rab->pb_lock);
return ra;
}
/*
* Grab and keep cached pages associated with a file in the svc_rqst
* so that they can be passed to the network sendmsg/sendpage routines
* directly. They will be released after the sending has completed.
*/
static int
nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct svc_rqst *rqstp = sd->u.data;
struct page **pp = rqstp->rq_next_page;
struct page *page = buf->page;
size_t size;
size = sd->len;
if (rqstp->rq_res.page_len == 0) {
get_page(page);
put_page(*rqstp->rq_next_page);
*(rqstp->rq_next_page++) = page;
rqstp->rq_res.page_base = buf->offset;
rqstp->rq_res.page_len = size;
} else if (page != pp[-1]) {
get_page(page);
if (*rqstp->rq_next_page)
put_page(*rqstp->rq_next_page);
*(rqstp->rq_next_page++) = page;
rqstp->rq_res.page_len += size;
} else
rqstp->rq_res.page_len += size;
return size;
}
static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
struct splice_desc *sd)
{
return __splice_from_pipe(pipe, sd, nfsd_splice_actor);
}
static __be32
nfsd_finish_read(struct file *file, unsigned long *count, int host_err)
{
if (host_err >= 0) {
nfsdstats.io_read += host_err;
*count = host_err;
fsnotify_access(file);
return 0;
} else
return nfserrno(host_err);
}
__be32 nfsd_splice_read(struct svc_rqst *rqstp,
struct file *file, loff_t offset, unsigned long *count)
{
struct splice_desc sd = {
.len = 0,
.total_len = *count,
.pos = offset,
.u.data = rqstp,
};
int host_err;
rqstp->rq_next_page = rqstp->rq_respages + 1;
host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
return nfsd_finish_read(file, count, host_err);
}
__be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
unsigned long *count)
{
mm_segment_t oldfs;
int host_err;
oldfs = get_fs();
set_fs(KERNEL_DS);
host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
set_fs(oldfs);
return nfsd_finish_read(file, count, host_err);
}
static __be32
nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file,
loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
{
if (file->f_op->splice_read && rqstp->rq_splice_ok)
return nfsd_splice_read(rqstp, file, offset, count);
else
return nfsd_readv(file, offset, vec, vlen, count);
}
/*
* Gathered writes: If another process is currently writing to the file,
* there's a high chance this is another nfsd (triggered by a bulk write
* from a client's biod). Rather than syncing the file with each write
* request, we sleep for 10 msec.
*
* I don't know if this roughly approximates C. Juszak's idea of
* gathered writes, but it's a nice and simple solution (IMHO), and it
* seems to work:-)
*
* Note: we do this only in the NFSv2 case, since v3 and higher have a
* better tool (separate unstable writes and commits) for solving this
* problem.
*/
static int wait_for_concurrent_writes(struct file *file)
{
struct inode *inode = file_inode(file);
static ino_t last_ino;
static dev_t last_dev;
int err = 0;
if (atomic_read(&inode->i_writecount) > 1
|| (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) {
dprintk("nfsd: write defer %d\n", task_pid_nr(current));
msleep(10);
dprintk("nfsd: write resume %d\n", task_pid_nr(current));
}
if (inode->i_state & I_DIRTY) {
dprintk("nfsd: write sync %d\n", task_pid_nr(current));
err = vfs_fsync(file, 0);
}
last_ino = inode->i_ino;
last_dev = inode->i_sb->s_dev;
return err;
}
static __be32
nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
loff_t offset, struct kvec *vec, int vlen,
unsigned long *cnt, int *stablep)
{
struct svc_export *exp;
struct dentry *dentry;
struct inode *inode;
mm_segment_t oldfs;
__be32 err = 0;
int host_err;
int stable = *stablep;
int use_wgather;
loff_t pos = offset;
unsigned int pflags = current->flags;
if (rqstp->rq_local)
/*
* We want less throttling in balance_dirty_pages()
* and shrink_inactive_list() so that nfs to
* localhost doesn't cause nfsd to lock up due to all
* the client's dirty pages or its congested queue.
*/
current->flags |= PF_LESS_THROTTLE;
dentry = file->f_path.dentry;
inode = dentry->d_inode;
exp = fhp->fh_export;
use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
if (!EX_ISSYNC(exp))
stable = 0;
/* Write the data. */
oldfs = get_fs(); set_fs(KERNEL_DS);
host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos);
set_fs(oldfs);
if (host_err < 0)
goto out_nfserr;
*cnt = host_err;
nfsdstats.io_write += host_err;
fsnotify_modify(file);
if (stable) {
if (use_wgather)
host_err = wait_for_concurrent_writes(file);
else
host_err = vfs_fsync_range(file, offset, offset+*cnt, 0);
}
out_nfserr:
dprintk("nfsd: write complete host_err=%d\n", host_err);
if (host_err >= 0)
err = 0;
else
err = nfserrno(host_err);
if (rqstp->rq_local)
tsk_restore_flags(current, pflags, PF_LESS_THROTTLE);
return err;
}
__be32 nfsd_get_tmp_read_open(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct file **file, struct raparms **ra)
{
struct inode *inode;
__be32 err;
err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, file);
if (err)
return err;
inode = file_inode(*file);
/* Get readahead parameters */
*ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
if (*ra && (*ra)->p_set)
(*file)->f_ra = (*ra)->p_ra;
return nfs_ok;
}
void nfsd_put_tmp_read_open(struct file *file, struct raparms *ra)
{
/* Write back readahead params */
if (ra) {
struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
spin_lock(&rab->pb_lock);
ra->p_ra = file->f_ra;
ra->p_set = 1;
ra->p_count--;