forked from analogdevicesinc/linux
-
Notifications
You must be signed in to change notification settings - Fork 3
/
inode.c
1281 lines (1124 loc) · 34.6 KB
/
inode.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
/*
* linux/fs/nfs/inode.c
*
* Copyright (C) 1992 Rick Sladkey
*
* nfs inode and superblock handling functions
*
* Modularised by Alan Cox <[email protected]>, while hacking some
* experimental NFS changes. Modularisation taken straight from SYS5 fs.
*
* Change to nfs_read_super() to permit NFS mounts to multi-homed hosts.
*
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/metrics.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/lockd/bind.h>
#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/nfs_idmap.h>
#include <linux/vfs.h>
#include <linux/inet.h>
#include <linux/nfs_xdr.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include "nfs4_fs.h"
#include "callback.h"
#include "delegation.h"
#include "iostat.h"
#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_VFS
#define NFS_PARANOIA 1
static void nfs_invalidate_inode(struct inode *);
static int nfs_update_inode(struct inode *, struct nfs_fattr *);
static void nfs_zap_acl_cache(struct inode *);
static struct kmem_cache * nfs_inode_cachep;
static inline unsigned long
nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
{
return nfs_fileid_to_ino_t(fattr->fileid);
}
int nfs_write_inode(struct inode *inode, int sync)
{
int ret;
if (sync) {
ret = filemap_fdatawait(inode->i_mapping);
if (ret == 0)
ret = nfs_commit_inode(inode, FLUSH_SYNC);
} else
ret = nfs_commit_inode(inode, 0);
if (ret >= 0)
return 0;
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
return ret;
}
void nfs_clear_inode(struct inode *inode)
{
/*
* The following should never happen...
*/
BUG_ON(nfs_have_writebacks(inode));
BUG_ON(!list_empty(&NFS_I(inode)->open_files));
BUG_ON(atomic_read(&NFS_I(inode)->data_updates) != 0);
nfs_zap_acl_cache(inode);
nfs_access_zap_cache(inode);
}
/**
* nfs_sync_mapping - helper to flush all mmapped dirty data to disk
*/
int nfs_sync_mapping(struct address_space *mapping)
{
int ret;
if (mapping->nrpages == 0)
return 0;
unmap_mapping_range(mapping, 0, 0, 0);
ret = filemap_write_and_wait(mapping);
if (ret != 0)
goto out;
ret = nfs_wb_all(mapping->host);
out:
return ret;
}
/*
* Invalidate the local caches
*/
static void nfs_zap_caches_locked(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
int mode = inode->i_mode;
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
NFS_ATTRTIMEO(inode) = NFS_MINATTRTIMEO(inode);
NFS_ATTRTIMEO_UPDATE(inode) = jiffies;
memset(NFS_COOKIEVERF(inode), 0, sizeof(NFS_COOKIEVERF(inode)));
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
else
nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
}
void nfs_zap_caches(struct inode *inode)
{
spin_lock(&inode->i_lock);
nfs_zap_caches_locked(inode);
spin_unlock(&inode->i_lock);
}
void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
{
if (mapping->nrpages != 0) {
spin_lock(&inode->i_lock);
NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
spin_unlock(&inode->i_lock);
}
}
static void nfs_zap_acl_cache(struct inode *inode)
{
void (*clear_acl_cache)(struct inode *);
clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache;
if (clear_acl_cache != NULL)
clear_acl_cache(inode);
spin_lock(&inode->i_lock);
NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL;
spin_unlock(&inode->i_lock);
}
/*
* Invalidate, but do not unhash, the inode.
* NB: must be called with inode->i_lock held!
*/
static void nfs_invalidate_inode(struct inode *inode)
{
set_bit(NFS_INO_STALE, &NFS_FLAGS(inode));
nfs_zap_caches_locked(inode);
}
struct nfs_find_desc {
struct nfs_fh *fh;
struct nfs_fattr *fattr;
};
/*
* In NFSv3 we can have 64bit inode numbers. In order to support
* this, and re-exported directories (also seen in NFSv2)
* we are forced to allow 2 different inodes to have the same
* i_ino.
*/
static int
nfs_find_actor(struct inode *inode, void *opaque)
{
struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque;
struct nfs_fh *fh = desc->fh;
struct nfs_fattr *fattr = desc->fattr;
if (NFS_FILEID(inode) != fattr->fileid)
return 0;
if (nfs_compare_fh(NFS_FH(inode), fh))
return 0;
if (is_bad_inode(inode) || NFS_STALE(inode))
return 0;
return 1;
}
static int
nfs_init_locked(struct inode *inode, void *opaque)
{
struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque;
struct nfs_fattr *fattr = desc->fattr;
NFS_FILEID(inode) = fattr->fileid;
nfs_copy_fh(NFS_FH(inode), desc->fh);
return 0;
}
/* Don't use READDIRPLUS on directories that we believe are too large */
#define NFS_LIMIT_READDIRPLUS (8*PAGE_SIZE)
/*
* This is our front-end to iget that looks up inodes by file handle
* instead of inode number.
*/
struct inode *
nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
{
struct nfs_find_desc desc = {
.fh = fh,
.fattr = fattr
};
struct inode *inode = ERR_PTR(-ENOENT);
unsigned long hash;
if ((fattr->valid & NFS_ATTR_FATTR) == 0)
goto out_no_inode;
if (!fattr->nlink) {
printk("NFS: Buggy server - nlink == 0!\n");
goto out_no_inode;
}
hash = nfs_fattr_to_ino_t(fattr);
inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc);
if (inode == NULL) {
inode = ERR_PTR(-ENOMEM);
goto out_no_inode;
}
if (inode->i_state & I_NEW) {
struct nfs_inode *nfsi = NFS_I(inode);
unsigned long now = jiffies;
/* We set i_ino for the few things that still rely on it,
* such as stat(2) */
inode->i_ino = hash;
/* We can't support update_atime(), since the server will reset it */
inode->i_flags |= S_NOATIME|S_NOCMTIME;
inode->i_mode = fattr->mode;
/* Why so? Because we want revalidate for devices/FIFOs, and
* that's precisely what we have in nfs_file_inode_operations.
*/
inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
if (S_ISREG(inode->i_mode)) {
inode->i_fop = &nfs_file_operations;
inode->i_data.a_ops = &nfs_file_aops;
inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
inode->i_fop = &nfs_dir_operations;
if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)
&& fattr->size <= NFS_LIMIT_READDIRPLUS)
set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_FLAGS(inode));
/* Deal with crossing mountpoints */
if (!nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) {
if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
inode->i_op = &nfs_referral_inode_operations;
else
inode->i_op = &nfs_mountpoint_inode_operations;
inode->i_fop = NULL;
}
} else if (S_ISLNK(inode->i_mode))
inode->i_op = &nfs_symlink_inode_operations;
else
init_special_inode(inode, inode->i_mode, fattr->rdev);
nfsi->read_cache_jiffies = fattr->time_start;
nfsi->last_updated = now;
nfsi->cache_change_attribute = now;
inode->i_atime = fattr->atime;
inode->i_mtime = fattr->mtime;
inode->i_ctime = fattr->ctime;
if (fattr->valid & NFS_ATTR_FATTR_V4)
nfsi->change_attr = fattr->change_attr;
inode->i_size = nfs_size_to_loff_t(fattr->size);
inode->i_nlink = fattr->nlink;
inode->i_uid = fattr->uid;
inode->i_gid = fattr->gid;
if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) {
/*
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
} else {
inode->i_blocks = fattr->du.nfs2.blocks;
}
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = now;
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
nfsi->access_cache = RB_ROOT;
unlock_new_inode(inode);
} else
nfs_refresh_inode(inode, fattr);
dprintk("NFS: nfs_fhget(%s/%Ld ct=%d)\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode),
atomic_read(&inode->i_count));
out:
return inode;
out_no_inode:
dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode));
goto out;
}
#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET)
int
nfs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
struct nfs_fattr fattr;
int error;
nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
if (attr->ia_valid & ATTR_SIZE) {
if (!S_ISREG(inode->i_mode) || attr->ia_size == i_size_read(inode))
attr->ia_valid &= ~ATTR_SIZE;
}
/* Optimization: if the end result is no change, don't RPC */
attr->ia_valid &= NFS_VALID_ATTRS;
if (attr->ia_valid == 0)
return 0;
lock_kernel();
nfs_begin_data_update(inode);
/* Write all dirty data */
if (S_ISREG(inode->i_mode)) {
filemap_write_and_wait(inode->i_mapping);
nfs_wb_all(inode);
}
/*
* Return any delegations if we're going to change ACLs
*/
if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0)
nfs_inode_return_delegation(inode);
error = NFS_PROTO(inode)->setattr(dentry, &fattr, attr);
if (error == 0)
nfs_refresh_inode(inode, &fattr);
nfs_end_data_update(inode);
unlock_kernel();
return error;
}
/**
* nfs_setattr_update_inode - Update inode metadata after a setattr call.
* @inode: pointer to struct inode
* @attr: pointer to struct iattr
*
* Note: we do this in the *proc.c in order to ensure that
* it works for things like exclusive creates too.
*/
void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
{
if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
if ((attr->ia_valid & ATTR_MODE) != 0) {
int mode = attr->ia_mode & S_IALLUGO;
mode |= inode->i_mode & ~S_IALLUGO;
inode->i_mode = mode;
}
if ((attr->ia_valid & ATTR_UID) != 0)
inode->i_uid = attr->ia_uid;
if ((attr->ia_valid & ATTR_GID) != 0)
inode->i_gid = attr->ia_gid;
spin_lock(&inode->i_lock);
NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
spin_unlock(&inode->i_lock);
}
if ((attr->ia_valid & ATTR_SIZE) != 0) {
nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
inode->i_size = attr->ia_size;
vmtruncate(inode, attr->ia_size);
}
}
static int nfs_wait_schedule(void *word)
{
if (signal_pending(current))
return -ERESTARTSYS;
schedule();
return 0;
}
/*
* Wait for the inode to get unlocked.
*/
static int nfs_wait_on_inode(struct inode *inode)
{
struct rpc_clnt *clnt = NFS_CLIENT(inode);
struct nfs_inode *nfsi = NFS_I(inode);
sigset_t oldmask;
int error;
rpc_clnt_sigmask(clnt, &oldmask);
error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING,
nfs_wait_schedule, TASK_INTERRUPTIBLE);
rpc_clnt_sigunmask(clnt, &oldmask);
return error;
}
static void nfs_wake_up_inode(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
clear_bit(NFS_INO_REVALIDATING, &nfsi->flags);
smp_mb__after_clear_bit();
wake_up_bit(&nfsi->flags, NFS_INO_REVALIDATING);
}
int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
int err;
/* Flush out writes to the server in order to update c/mtime */
if (S_ISREG(inode->i_mode))
nfs_sync_mapping_range(inode->i_mapping, 0, 0, FLUSH_NOCOMMIT);
/*
* We may force a getattr if the user cares about atime.
*
* Note that we only have to check the vfsmount flags here:
* - NFS always sets S_NOATIME by so checking it would give a
* bogus result
* - NFS never sets MS_NOATIME or MS_NODIRATIME so there is
* no point in checking those.
*/
if ((mnt->mnt_flags & MNT_NOATIME) ||
((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
need_atime = 0;
if (need_atime)
err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
else
err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
if (!err)
generic_fillattr(inode, stat);
return err;
}
static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, struct dentry *dentry, struct rpc_cred *cred)
{
struct nfs_open_context *ctx;
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (ctx != NULL) {
atomic_set(&ctx->count, 1);
ctx->dentry = dget(dentry);
ctx->vfsmnt = mntget(mnt);
ctx->cred = get_rpccred(cred);
ctx->state = NULL;
ctx->lockowner = current->files;
ctx->error = 0;
ctx->dir_cookie = 0;
}
return ctx;
}
struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
{
if (ctx != NULL)
atomic_inc(&ctx->count);
return ctx;
}
void put_nfs_open_context(struct nfs_open_context *ctx)
{
if (atomic_dec_and_test(&ctx->count)) {
if (!list_empty(&ctx->list)) {
struct inode *inode = ctx->dentry->d_inode;
spin_lock(&inode->i_lock);
list_del(&ctx->list);
spin_unlock(&inode->i_lock);
}
if (ctx->state != NULL)
nfs4_close_state(ctx->state, ctx->mode);
if (ctx->cred != NULL)
put_rpccred(ctx->cred);
dput(ctx->dentry);
mntput(ctx->vfsmnt);
kfree(ctx);
}
}
/*
* Ensure that mmap has a recent RPC credential for use when writing out
* shared pages
*/
static void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
{
struct inode *inode = filp->f_path.dentry->d_inode;
struct nfs_inode *nfsi = NFS_I(inode);
filp->private_data = get_nfs_open_context(ctx);
spin_lock(&inode->i_lock);
list_add(&ctx->list, &nfsi->open_files);
spin_unlock(&inode->i_lock);
}
/*
* Given an inode, search for an open context with the desired characteristics
*/
struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, int mode)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_open_context *pos, *ctx = NULL;
spin_lock(&inode->i_lock);
list_for_each_entry(pos, &nfsi->open_files, list) {
if (cred != NULL && pos->cred != cred)
continue;
if ((pos->mode & mode) == mode) {
ctx = get_nfs_open_context(pos);
break;
}
}
spin_unlock(&inode->i_lock);
return ctx;
}
static void nfs_file_clear_open_context(struct file *filp)
{
struct inode *inode = filp->f_path.dentry->d_inode;
struct nfs_open_context *ctx = (struct nfs_open_context *)filp->private_data;
if (ctx) {
filp->private_data = NULL;
spin_lock(&inode->i_lock);
list_move_tail(&ctx->list, &NFS_I(inode)->open_files);
spin_unlock(&inode->i_lock);
put_nfs_open_context(ctx);
}
}
/*
* These allocate and release file read/write context information.
*/
int nfs_open(struct inode *inode, struct file *filp)
{
struct nfs_open_context *ctx;
struct rpc_cred *cred;
cred = rpcauth_lookupcred(NFS_CLIENT(inode)->cl_auth, 0);
if (IS_ERR(cred))
return PTR_ERR(cred);
ctx = alloc_nfs_open_context(filp->f_path.mnt, filp->f_path.dentry, cred);
put_rpccred(cred);
if (ctx == NULL)
return -ENOMEM;
ctx->mode = filp->f_mode;
nfs_file_set_open_context(filp, ctx);
put_nfs_open_context(ctx);
return 0;
}
int nfs_release(struct inode *inode, struct file *filp)
{
nfs_file_clear_open_context(filp);
return 0;
}
/*
* This function is called whenever some part of NFS notices that
* the cached attributes have to be refreshed.
*/
int
__nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
int status = -ESTALE;
struct nfs_fattr fattr;
struct nfs_inode *nfsi = NFS_I(inode);
dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
inode->i_sb->s_id, (long long)NFS_FILEID(inode));
nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
lock_kernel();
if (is_bad_inode(inode))
goto out_nowait;
if (NFS_STALE(inode))
goto out_nowait;
status = nfs_wait_on_inode(inode);
if (status < 0)
goto out;
if (NFS_STALE(inode)) {
status = -ESTALE;
/* Do we trust the cached ESTALE? */
if (NFS_ATTRTIMEO(inode) != 0) {
if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ATIME)) {
/* no */
} else
goto out;
}
}
status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), &fattr);
if (status != 0) {
dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) getattr failed, error=%d\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode), status);
if (status == -ESTALE) {
nfs_zap_caches(inode);
if (!S_ISDIR(inode->i_mode))
set_bit(NFS_INO_STALE, &NFS_FLAGS(inode));
}
goto out;
}
spin_lock(&inode->i_lock);
status = nfs_update_inode(inode, &fattr);
if (status) {
spin_unlock(&inode->i_lock);
dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) refresh failed, error=%d\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode), status);
goto out;
}
spin_unlock(&inode->i_lock);
if (nfsi->cache_validity & NFS_INO_INVALID_ACL)
nfs_zap_acl_cache(inode);
dfprintk(PAGECACHE, "NFS: (%s/%Ld) revalidation complete\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode));
out:
nfs_wake_up_inode(inode);
out_nowait:
unlock_kernel();
return status;
}
int nfs_attribute_timeout(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
if (nfs_have_delegation(inode, FMODE_READ))
return 0;
return time_after(jiffies, nfsi->read_cache_jiffies+nfsi->attrtimeo);
}
/**
* nfs_revalidate_inode - Revalidate the inode attributes
* @server - pointer to nfs_server struct
* @inode - pointer to inode struct
*
* Updates inode attribute information by retrieving the data from the server.
*/
int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
if (!(NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATTR)
&& !nfs_attribute_timeout(inode))
return NFS_STALE(inode) ? -ESTALE : 0;
return __nfs_revalidate_inode(server, inode);
}
static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
if (mapping->nrpages != 0) {
int ret = invalidate_inode_pages2(mapping);
if (ret < 0)
return ret;
}
spin_lock(&inode->i_lock);
nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
if (S_ISDIR(inode->i_mode)) {
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
/* This ensures we revalidate child dentries */
nfsi->cache_change_attribute = jiffies;
}
spin_unlock(&inode->i_lock);
nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
inode->i_sb->s_id, (long long)NFS_FILEID(inode));
return 0;
}
static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
{
int ret = 0;
mutex_lock(&inode->i_mutex);
if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_DATA) {
ret = nfs_sync_mapping(mapping);
if (ret == 0)
ret = nfs_invalidate_mapping_nolock(inode, mapping);
}
mutex_unlock(&inode->i_mutex);
return ret;
}
/**
* nfs_revalidate_mapping_nolock - Revalidate the pagecache
* @inode - pointer to host inode
* @mapping - pointer to mapping
*/
int nfs_revalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
int ret = 0;
if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
|| nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
if (ret < 0)
goto out;
}
if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
ret = nfs_invalidate_mapping_nolock(inode, mapping);
out:
return ret;
}
/**
* nfs_revalidate_mapping - Revalidate the pagecache
* @inode - pointer to host inode
* @mapping - pointer to mapping
*
* This version of the function will take the inode->i_mutex and attempt to
* flush out all dirty data if it needs to invalidate the page cache.
*/
int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
int ret = 0;
if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
|| nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
if (ret < 0)
goto out;
}
if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
ret = nfs_invalidate_mapping(inode, mapping);
out:
return ret;
}
/**
* nfs_begin_data_update
* @inode - pointer to inode
* Declare that a set of operations will update file data on the server
*/
void nfs_begin_data_update(struct inode *inode)
{
atomic_inc(&NFS_I(inode)->data_updates);
}
/**
* nfs_end_data_update
* @inode - pointer to inode
* Declare end of the operations that will update file data
* This will mark the inode as immediately needing revalidation
* of its attribute cache.
*/
void nfs_end_data_update(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
/* Directories: invalidate page cache */
if (S_ISDIR(inode->i_mode)) {
spin_lock(&inode->i_lock);
nfsi->cache_validity |= NFS_INO_INVALID_DATA;
spin_unlock(&inode->i_lock);
}
nfsi->cache_change_attribute = jiffies;
atomic_dec(&nfsi->data_updates);
}
static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
unsigned long now = jiffies;
/* If we have atomic WCC data, we may update some attributes */
if ((fattr->valid & NFS_ATTR_WCC) != 0) {
if (timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) {
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
nfsi->cache_change_attribute = now;
}
if (timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
nfsi->cache_change_attribute = now;
}
if (inode->i_size == fattr->pre_size && nfsi->npages == 0) {
inode->i_size = fattr->size;
nfsi->cache_change_attribute = now;
}
}
}
/**
* nfs_check_inode_attributes - verify consistency of the inode attribute cache
* @inode - pointer to inode
* @fattr - updated attributes
*
* Verifies the attribute cache. If we have just changed the attributes,
* so that fattr carries weak cache consistency data, then it may
* also update the ctime/mtime/change_attribute.
*/
static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
loff_t cur_size, new_isize;
int data_unstable;
/* Has the inode gone and changed behind our back? */
if (nfsi->fileid != fattr->fileid
|| (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) {
return -EIO;
}
/* Are we in the process of updating data on the server? */
data_unstable = nfs_caches_unstable(inode);
/* Do atomic weak cache consistency updates */
nfs_wcc_update_inode(inode, fattr);
if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
nfsi->change_attr != fattr->change_attr)
nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
/* Verify a few of the more important attributes */
if (!timespec_equal(&inode->i_mtime, &fattr->mtime))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
cur_size = i_size_read(inode);
new_isize = nfs_size_to_loff_t(fattr->size);
if (cur_size != new_isize && nfsi->npages == 0)
nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
/* Have any file permissions changed? */
if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)
|| inode->i_uid != fattr->uid
|| inode->i_gid != fattr->gid)
nfsi->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
/* Has the link count changed? */
if (inode->i_nlink != fattr->nlink)
nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
if (!timespec_equal(&inode->i_atime, &fattr->atime))
nfsi->cache_validity |= NFS_INO_INVALID_ATIME;
nfsi->read_cache_jiffies = fattr->time_start;
return 0;
}
/**
* nfs_refresh_inode - try to update the inode attribute cache
* @inode - pointer to inode
* @fattr - updated attributes
*
* Check that an RPC call that returned attributes has not overlapped with
* other recent updates of the inode metadata, then decide whether it is
* safe to do a full update of the inode attributes, or whether just to
* call nfs_check_inode_attributes.
*/
int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
int status;
if ((fattr->valid & NFS_ATTR_FATTR) == 0)
return 0;
spin_lock(&inode->i_lock);
if (time_after(fattr->time_start, nfsi->last_updated))
status = nfs_update_inode(inode, fattr);
else
status = nfs_check_inode_attributes(inode, fattr);
spin_unlock(&inode->i_lock);
return status;
}
/**
* nfs_post_op_update_inode - try to update the inode attribute cache
* @inode - pointer to inode
* @fattr - updated attributes
*
* After an operation that has changed the inode metadata, mark the
* attribute cache as being invalid, then try to update it.
*
* NB: if the server didn't return any post op attributes, this
* function will force the retrieval of attributes before the next
* NFS request. Thus it should be used only for operations that
* are expected to change one or more attributes, to avoid
* unnecessary NFS requests and trips through nfs_update_inode().
*/
int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
int status = 0;
spin_lock(&inode->i_lock);
if (unlikely((fattr->valid & NFS_ATTR_FATTR) == 0)) {
nfsi->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
goto out;
}
status = nfs_update_inode(inode, fattr);
out:
spin_unlock(&inode->i_lock);
return status;
}
/*
* Many nfs protocol calls return the new file attributes after
* an operation. Here we update the inode to reflect the state
* of the server's inode.
*
* This is a bit tricky because we have to make sure all dirty pages
* have been sent off to the server before calling invalidate_inode_pages.
* To make sure no other process adds more write requests while we try
* our best to flush them, we make them sleep during the attribute refresh.
*
* A very similar scenario holds for the dir cache.
*/
static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_server *server;
struct nfs_inode *nfsi = NFS_I(inode);
loff_t cur_isize, new_isize;
unsigned int invalid = 0;
unsigned long now = jiffies;
int data_stable;
dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
__FUNCTION__, inode->i_sb->s_id, inode->i_ino,
atomic_read(&inode->i_count), fattr->valid);
if (nfsi->fileid != fattr->fileid)
goto out_fileid;
/*
* Make sure the inode's type hasn't changed.
*/
if ((inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
goto out_changed;
server = NFS_SERVER(inode);
/* Update the fsid if and only if this is the root directory */
if (inode == inode->i_sb->s_root->d_inode
&& !nfs_fsid_equal(&server->fsid, &fattr->fsid))
server->fsid = fattr->fsid;
/*
* Update the read time so we don't revalidate too often.
*/
nfsi->read_cache_jiffies = fattr->time_start;
nfsi->last_updated = now;
/* Fix a wraparound issue with nfsi->cache_change_attribute */
if (time_before(now, nfsi->cache_change_attribute))
nfsi->cache_change_attribute = now - 600*HZ;
/* Are we racing with known updates of the metadata on the server? */
data_stable = nfs_verify_change_attribute(inode, fattr->time_start);
if (data_stable)
nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_ATIME);
/* Do atomic weak cache consistency updates */
nfs_wcc_update_inode(inode, fattr);
/* Check if our cached file size is stale */
new_isize = nfs_size_to_loff_t(fattr->size);
cur_isize = i_size_read(inode);
if (new_isize != cur_isize) {
/* Do we perhaps have any outstanding writes? */
if (nfsi->npages == 0) {
/* No, but did we race with nfs_end_data_update()? */
if (data_stable) {
inode->i_size = new_isize;
invalid |= NFS_INO_INVALID_DATA;
}
invalid |= NFS_INO_INVALID_ATTR;
} else if (new_isize > cur_isize) {