forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
inode.c
1842 lines (1636 loc) · 49.6 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
#include <linux/ceph/ceph_debug.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/namei.h>
#include <linux/writeback.h>
#include <linux/vmalloc.h>
#include <linux/pagevec.h>
#include "super.h"
#include "mds_client.h"
#include <linux/ceph/decode.h>
/*
* Ceph inode operations
*
* Implement basic inode helpers (get, alloc) and inode ops (getattr,
* setattr, etc.), xattr helpers, and helpers for assimilating
* metadata returned by the MDS into our cache.
*
* Also define helpers for doing asynchronous writeback, invalidation,
* and truncation for the benefit of those who can't afford to block
* (typically because they are in the message handler path).
*/
static const struct inode_operations ceph_symlink_iops;
static void ceph_invalidate_work(struct work_struct *work);
static void ceph_writeback_work(struct work_struct *work);
static void ceph_vmtruncate_work(struct work_struct *work);
/*
* find or create an inode, given the ceph ino number
*/
static int ceph_set_ino_cb(struct inode *inode, void *data)
{
ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
return 0;
}
struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
{
struct inode *inode;
ino_t t = ceph_vino_to_ino(vino);
inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino);
if (inode == NULL)
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
dout("get_inode created new inode %p %llx.%llx ino %llx\n",
inode, ceph_vinop(inode), (u64)inode->i_ino);
unlock_new_inode(inode);
}
dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino,
vino.snap, inode);
return inode;
}
/*
* get/constuct snapdir inode for a given directory
*/
struct inode *ceph_get_snapdir(struct inode *parent)
{
struct ceph_vino vino = {
.ino = ceph_ino(parent),
.snap = CEPH_SNAPDIR,
};
struct inode *inode = ceph_get_inode(parent->i_sb, vino);
struct ceph_inode_info *ci = ceph_inode(inode);
BUG_ON(!S_ISDIR(parent->i_mode));
if (IS_ERR(inode))
return inode;
inode->i_mode = parent->i_mode;
inode->i_uid = parent->i_uid;
inode->i_gid = parent->i_gid;
inode->i_op = &ceph_dir_iops;
inode->i_fop = &ceph_dir_fops;
ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
ci->i_rbytes = 0;
return inode;
}
const struct inode_operations ceph_file_iops = {
.permission = ceph_permission,
.setattr = ceph_setattr,
.getattr = ceph_getattr,
.setxattr = ceph_setxattr,
.getxattr = ceph_getxattr,
.listxattr = ceph_listxattr,
.removexattr = ceph_removexattr,
};
/*
* We use a 'frag tree' to keep track of the MDS's directory fragments
* for a given inode (usually there is just a single fragment). We
* need to know when a child frag is delegated to a new MDS, or when
* it is flagged as replicated, so we can direct our requests
* accordingly.
*/
/*
* find/create a frag in the tree
*/
static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci,
u32 f)
{
struct rb_node **p;
struct rb_node *parent = NULL;
struct ceph_inode_frag *frag;
int c;
p = &ci->i_fragtree.rb_node;
while (*p) {
parent = *p;
frag = rb_entry(parent, struct ceph_inode_frag, node);
c = ceph_frag_compare(f, frag->frag);
if (c < 0)
p = &(*p)->rb_left;
else if (c > 0)
p = &(*p)->rb_right;
else
return frag;
}
frag = kmalloc(sizeof(*frag), GFP_NOFS);
if (!frag) {
pr_err("__get_or_create_frag ENOMEM on %p %llx.%llx "
"frag %x\n", &ci->vfs_inode,
ceph_vinop(&ci->vfs_inode), f);
return ERR_PTR(-ENOMEM);
}
frag->frag = f;
frag->split_by = 0;
frag->mds = -1;
frag->ndist = 0;
rb_link_node(&frag->node, parent, p);
rb_insert_color(&frag->node, &ci->i_fragtree);
dout("get_or_create_frag added %llx.%llx frag %x\n",
ceph_vinop(&ci->vfs_inode), f);
return frag;
}
/*
* find a specific frag @f
*/
struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f)
{
struct rb_node *n = ci->i_fragtree.rb_node;
while (n) {
struct ceph_inode_frag *frag =
rb_entry(n, struct ceph_inode_frag, node);
int c = ceph_frag_compare(f, frag->frag);
if (c < 0)
n = n->rb_left;
else if (c > 0)
n = n->rb_right;
else
return frag;
}
return NULL;
}
/*
* Choose frag containing the given value @v. If @pfrag is
* specified, copy the frag delegation info to the caller if
* it is present.
*/
u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
struct ceph_inode_frag *pfrag,
int *found)
{
u32 t = ceph_frag_make(0, 0);
struct ceph_inode_frag *frag;
unsigned nway, i;
u32 n;
if (found)
*found = 0;
mutex_lock(&ci->i_fragtree_mutex);
while (1) {
WARN_ON(!ceph_frag_contains_value(t, v));
frag = __ceph_find_frag(ci, t);
if (!frag)
break; /* t is a leaf */
if (frag->split_by == 0) {
if (pfrag)
memcpy(pfrag, frag, sizeof(*pfrag));
if (found)
*found = 1;
break;
}
/* choose child */
nway = 1 << frag->split_by;
dout("choose_frag(%x) %x splits by %d (%d ways)\n", v, t,
frag->split_by, nway);
for (i = 0; i < nway; i++) {
n = ceph_frag_make_child(t, frag->split_by, i);
if (ceph_frag_contains_value(n, v)) {
t = n;
break;
}
}
BUG_ON(i == nway);
}
dout("choose_frag(%x) = %x\n", v, t);
mutex_unlock(&ci->i_fragtree_mutex);
return t;
}
/*
* Process dirfrag (delegation) info from the mds. Include leaf
* fragment in tree ONLY if ndist > 0. Otherwise, only
* branches/splits are included in i_fragtree)
*/
static int ceph_fill_dirfrag(struct inode *inode,
struct ceph_mds_reply_dirfrag *dirinfo)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_inode_frag *frag;
u32 id = le32_to_cpu(dirinfo->frag);
int mds = le32_to_cpu(dirinfo->auth);
int ndist = le32_to_cpu(dirinfo->ndist);
int i;
int err = 0;
mutex_lock(&ci->i_fragtree_mutex);
if (ndist == 0) {
/* no delegation info needed. */
frag = __ceph_find_frag(ci, id);
if (!frag)
goto out;
if (frag->split_by == 0) {
/* tree leaf, remove */
dout("fill_dirfrag removed %llx.%llx frag %x"
" (no ref)\n", ceph_vinop(inode), id);
rb_erase(&frag->node, &ci->i_fragtree);
kfree(frag);
} else {
/* tree branch, keep and clear */
dout("fill_dirfrag cleared %llx.%llx frag %x"
" referral\n", ceph_vinop(inode), id);
frag->mds = -1;
frag->ndist = 0;
}
goto out;
}
/* find/add this frag to store mds delegation info */
frag = __get_or_create_frag(ci, id);
if (IS_ERR(frag)) {
/* this is not the end of the world; we can continue
with bad/inaccurate delegation info */
pr_err("fill_dirfrag ENOMEM on mds ref %llx.%llx fg %x\n",
ceph_vinop(inode), le32_to_cpu(dirinfo->frag));
err = -ENOMEM;
goto out;
}
frag->mds = mds;
frag->ndist = min_t(u32, ndist, CEPH_MAX_DIRFRAG_REP);
for (i = 0; i < frag->ndist; i++)
frag->dist[i] = le32_to_cpu(dirinfo->dist[i]);
dout("fill_dirfrag %llx.%llx frag %x ndist=%d\n",
ceph_vinop(inode), frag->frag, frag->ndist);
out:
mutex_unlock(&ci->i_fragtree_mutex);
return err;
}
/*
* initialize a newly allocated inode.
*/
struct inode *ceph_alloc_inode(struct super_block *sb)
{
struct ceph_inode_info *ci;
int i;
ci = kmem_cache_alloc(ceph_inode_cachep, GFP_NOFS);
if (!ci)
return NULL;
dout("alloc_inode %p\n", &ci->vfs_inode);
ci->i_version = 0;
ci->i_time_warp_seq = 0;
ci->i_ceph_flags = 0;
ci->i_release_count = 0;
ci->i_symlink = NULL;
memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
ci->i_fragtree = RB_ROOT;
mutex_init(&ci->i_fragtree_mutex);
ci->i_xattrs.blob = NULL;
ci->i_xattrs.prealloc_blob = NULL;
ci->i_xattrs.dirty = false;
ci->i_xattrs.index = RB_ROOT;
ci->i_xattrs.count = 0;
ci->i_xattrs.names_size = 0;
ci->i_xattrs.vals_size = 0;
ci->i_xattrs.version = 0;
ci->i_xattrs.index_version = 0;
ci->i_caps = RB_ROOT;
ci->i_auth_cap = NULL;
ci->i_dirty_caps = 0;
ci->i_flushing_caps = 0;
INIT_LIST_HEAD(&ci->i_dirty_item);
INIT_LIST_HEAD(&ci->i_flushing_item);
ci->i_cap_flush_seq = 0;
ci->i_cap_flush_last_tid = 0;
memset(&ci->i_cap_flush_tid, 0, sizeof(ci->i_cap_flush_tid));
init_waitqueue_head(&ci->i_cap_wq);
ci->i_hold_caps_min = 0;
ci->i_hold_caps_max = 0;
INIT_LIST_HEAD(&ci->i_cap_delay_list);
ci->i_cap_exporting_mds = 0;
ci->i_cap_exporting_mseq = 0;
ci->i_cap_exporting_issued = 0;
INIT_LIST_HEAD(&ci->i_cap_snaps);
ci->i_head_snapc = NULL;
ci->i_snap_caps = 0;
for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
ci->i_nr_by_mode[i] = 0;
ci->i_truncate_seq = 0;
ci->i_truncate_size = 0;
ci->i_truncate_pending = 0;
ci->i_max_size = 0;
ci->i_reported_size = 0;
ci->i_wanted_max_size = 0;
ci->i_requested_max_size = 0;
ci->i_pin_ref = 0;
ci->i_rd_ref = 0;
ci->i_rdcache_ref = 0;
ci->i_wr_ref = 0;
ci->i_wb_ref = 0;
ci->i_wrbuffer_ref = 0;
ci->i_wrbuffer_ref_head = 0;
ci->i_shared_gen = 0;
ci->i_rdcache_gen = 0;
ci->i_rdcache_revoking = 0;
INIT_LIST_HEAD(&ci->i_unsafe_writes);
INIT_LIST_HEAD(&ci->i_unsafe_dirops);
spin_lock_init(&ci->i_unsafe_lock);
ci->i_snap_realm = NULL;
INIT_LIST_HEAD(&ci->i_snap_realm_item);
INIT_LIST_HEAD(&ci->i_snap_flush_item);
INIT_WORK(&ci->i_wb_work, ceph_writeback_work);
INIT_WORK(&ci->i_pg_inv_work, ceph_invalidate_work);
INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work);
return &ci->vfs_inode;
}
static void ceph_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
struct ceph_inode_info *ci = ceph_inode(inode);
INIT_LIST_HEAD(&inode->i_dentry);
kmem_cache_free(ceph_inode_cachep, ci);
}
void ceph_destroy_inode(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_inode_frag *frag;
struct rb_node *n;
dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
ceph_queue_caps_release(inode);
/*
* we may still have a snap_realm reference if there are stray
* caps in i_cap_exporting_issued or i_snap_caps.
*/
if (ci->i_snap_realm) {
struct ceph_mds_client *mdsc =
ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
struct ceph_snap_realm *realm = ci->i_snap_realm;
dout(" dropping residual ref to snap realm %p\n", realm);
spin_lock(&realm->inodes_with_caps_lock);
list_del_init(&ci->i_snap_realm_item);
spin_unlock(&realm->inodes_with_caps_lock);
ceph_put_snap_realm(mdsc, realm);
}
kfree(ci->i_symlink);
while ((n = rb_first(&ci->i_fragtree)) != NULL) {
frag = rb_entry(n, struct ceph_inode_frag, node);
rb_erase(n, &ci->i_fragtree);
kfree(frag);
}
__ceph_destroy_xattrs(ci);
if (ci->i_xattrs.blob)
ceph_buffer_put(ci->i_xattrs.blob);
if (ci->i_xattrs.prealloc_blob)
ceph_buffer_put(ci->i_xattrs.prealloc_blob);
call_rcu(&inode->i_rcu, ceph_i_callback);
}
/*
* Helpers to fill in size, ctime, mtime, and atime. We have to be
* careful because either the client or MDS may have more up to date
* info, depending on which capabilities are held, and whether
* time_warp_seq or truncate_seq have increased. (Ordinarily, mtime
* and size are monotonically increasing, except when utimes() or
* truncate() increments the corresponding _seq values.)
*/
int ceph_fill_file_size(struct inode *inode, int issued,
u32 truncate_seq, u64 truncate_size, u64 size)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int queue_trunc = 0;
if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 ||
(truncate_seq == ci->i_truncate_seq && size > inode->i_size)) {
dout("size %lld -> %llu\n", inode->i_size, size);
inode->i_size = size;
inode->i_blocks = (size + (1<<9) - 1) >> 9;
ci->i_reported_size = size;
if (truncate_seq != ci->i_truncate_seq) {
dout("truncate_seq %u -> %u\n",
ci->i_truncate_seq, truncate_seq);
ci->i_truncate_seq = truncate_seq;
/*
* If we hold relevant caps, or in the case where we're
* not the only client referencing this file and we
* don't hold those caps, then we need to check whether
* the file is either opened or mmaped
*/
if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_RD|
CEPH_CAP_FILE_WR|CEPH_CAP_FILE_BUFFER|
CEPH_CAP_FILE_EXCL|
CEPH_CAP_FILE_LAZYIO)) ||
mapping_mapped(inode->i_mapping) ||
__ceph_caps_file_wanted(ci)) {
ci->i_truncate_pending++;
queue_trunc = 1;
}
}
}
if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) >= 0 &&
ci->i_truncate_size != truncate_size) {
dout("truncate_size %lld -> %llu\n", ci->i_truncate_size,
truncate_size);
ci->i_truncate_size = truncate_size;
}
return queue_trunc;
}
void ceph_fill_file_time(struct inode *inode, int issued,
u64 time_warp_seq, struct timespec *ctime,
struct timespec *mtime, struct timespec *atime)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int warn = 0;
if (issued & (CEPH_CAP_FILE_EXCL|
CEPH_CAP_FILE_WR|
CEPH_CAP_FILE_BUFFER|
CEPH_CAP_AUTH_EXCL|
CEPH_CAP_XATTR_EXCL)) {
if (timespec_compare(ctime, &inode->i_ctime) > 0) {
dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",
inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
ctime->tv_sec, ctime->tv_nsec);
inode->i_ctime = *ctime;
}
if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
/* the MDS did a utimes() */
dout("mtime %ld.%09ld -> %ld.%09ld "
"tw %d -> %d\n",
inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
mtime->tv_sec, mtime->tv_nsec,
ci->i_time_warp_seq, (int)time_warp_seq);
inode->i_mtime = *mtime;
inode->i_atime = *atime;
ci->i_time_warp_seq = time_warp_seq;
} else if (time_warp_seq == ci->i_time_warp_seq) {
/* nobody did utimes(); take the max */
if (timespec_compare(mtime, &inode->i_mtime) > 0) {
dout("mtime %ld.%09ld -> %ld.%09ld inc\n",
inode->i_mtime.tv_sec,
inode->i_mtime.tv_nsec,
mtime->tv_sec, mtime->tv_nsec);
inode->i_mtime = *mtime;
}
if (timespec_compare(atime, &inode->i_atime) > 0) {
dout("atime %ld.%09ld -> %ld.%09ld inc\n",
inode->i_atime.tv_sec,
inode->i_atime.tv_nsec,
atime->tv_sec, atime->tv_nsec);
inode->i_atime = *atime;
}
} else if (issued & CEPH_CAP_FILE_EXCL) {
/* we did a utimes(); ignore mds values */
} else {
warn = 1;
}
} else {
/* we have no write|excl caps; whatever the MDS says is true */
if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) {
inode->i_ctime = *ctime;
inode->i_mtime = *mtime;
inode->i_atime = *atime;
ci->i_time_warp_seq = time_warp_seq;
} else {
warn = 1;
}
}
if (warn) /* time_warp_seq shouldn't go backwards */
dout("%p mds time_warp_seq %llu < %u\n",
inode, time_warp_seq, ci->i_time_warp_seq);
}
/*
* Populate an inode based on info from mds. May be called on new or
* existing inodes.
*/
static int fill_inode(struct inode *inode,
struct ceph_mds_reply_info_in *iinfo,
struct ceph_mds_reply_dirfrag *dirinfo,
struct ceph_mds_session *session,
unsigned long ttl_from, int cap_fmode,
struct ceph_cap_reservation *caps_reservation)
{
struct ceph_mds_reply_inode *info = iinfo->in;
struct ceph_inode_info *ci = ceph_inode(inode);
int i;
int issued, implemented;
struct timespec mtime, atime, ctime;
u32 nsplits;
struct ceph_buffer *xattr_blob = NULL;
int err = 0;
int queue_trunc = 0;
dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
inode, ceph_vinop(inode), le64_to_cpu(info->version),
ci->i_version);
/*
* prealloc xattr data, if it looks like we'll need it. only
* if len > 4 (meaning there are actually xattrs; the first 4
* bytes are the xattr count).
*/
if (iinfo->xattr_len > 4) {
xattr_blob = ceph_buffer_new(iinfo->xattr_len, GFP_NOFS);
if (!xattr_blob)
pr_err("fill_inode ENOMEM xattr blob %d bytes\n",
iinfo->xattr_len);
}
spin_lock(&inode->i_lock);
/*
* provided version will be odd if inode value is projected,
* even if stable. skip the update if we have newer stable
* info (ours>=theirs, e.g. due to racing mds replies), unless
* we are getting projected (unstable) info (in which case the
* version is odd, and we want ours>theirs).
* us them
* 2 2 skip
* 3 2 skip
* 3 3 update
*/
if (le64_to_cpu(info->version) > 0 &&
(ci->i_version & ~1) >= le64_to_cpu(info->version))
goto no_change;
issued = __ceph_caps_issued(ci, &implemented);
issued |= implemented | __ceph_caps_dirty(ci);
/* update inode */
ci->i_version = le64_to_cpu(info->version);
inode->i_version++;
inode->i_rdev = le32_to_cpu(info->rdev);
if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(info->mode);
inode->i_uid = le32_to_cpu(info->uid);
inode->i_gid = le32_to_cpu(info->gid);
dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
inode->i_uid, inode->i_gid);
}
if ((issued & CEPH_CAP_LINK_EXCL) == 0)
inode->i_nlink = le32_to_cpu(info->nlink);
/* be careful with mtime, atime, size */
ceph_decode_timespec(&atime, &info->atime);
ceph_decode_timespec(&mtime, &info->mtime);
ceph_decode_timespec(&ctime, &info->ctime);
queue_trunc = ceph_fill_file_size(inode, issued,
le32_to_cpu(info->truncate_seq),
le64_to_cpu(info->truncate_size),
le64_to_cpu(info->size));
ceph_fill_file_time(inode, issued,
le32_to_cpu(info->time_warp_seq),
&ctime, &mtime, &atime);
/* only update max_size on auth cap */
if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
ci->i_max_size != le64_to_cpu(info->max_size)) {
dout("max_size %lld -> %llu\n", ci->i_max_size,
le64_to_cpu(info->max_size));
ci->i_max_size = le64_to_cpu(info->max_size);
}
ci->i_layout = info->layout;
inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
/* xattrs */
/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
if ((issued & CEPH_CAP_XATTR_EXCL) == 0 &&
le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
if (ci->i_xattrs.blob)
ceph_buffer_put(ci->i_xattrs.blob);
ci->i_xattrs.blob = xattr_blob;
if (xattr_blob)
memcpy(ci->i_xattrs.blob->vec.iov_base,
iinfo->xattr_data, iinfo->xattr_len);
ci->i_xattrs.version = le64_to_cpu(info->xattr_version);
xattr_blob = NULL;
}
inode->i_mapping->a_ops = &ceph_aops;
inode->i_mapping->backing_dev_info =
&ceph_sb_to_client(inode->i_sb)->backing_dev_info;
switch (inode->i_mode & S_IFMT) {
case S_IFIFO:
case S_IFBLK:
case S_IFCHR:
case S_IFSOCK:
init_special_inode(inode, inode->i_mode, inode->i_rdev);
inode->i_op = &ceph_file_iops;
break;
case S_IFREG:
inode->i_op = &ceph_file_iops;
inode->i_fop = &ceph_file_fops;
break;
case S_IFLNK:
inode->i_op = &ceph_symlink_iops;
if (!ci->i_symlink) {
int symlen = iinfo->symlink_len;
char *sym;
BUG_ON(symlen != inode->i_size);
spin_unlock(&inode->i_lock);
err = -ENOMEM;
sym = kmalloc(symlen+1, GFP_NOFS);
if (!sym)
goto out;
memcpy(sym, iinfo->symlink, symlen);
sym[symlen] = 0;
spin_lock(&inode->i_lock);
if (!ci->i_symlink)
ci->i_symlink = sym;
else
kfree(sym); /* lost a race */
}
break;
case S_IFDIR:
inode->i_op = &ceph_dir_iops;
inode->i_fop = &ceph_dir_fops;
ci->i_dir_layout = iinfo->dir_layout;
ci->i_files = le64_to_cpu(info->files);
ci->i_subdirs = le64_to_cpu(info->subdirs);
ci->i_rbytes = le64_to_cpu(info->rbytes);
ci->i_rfiles = le64_to_cpu(info->rfiles);
ci->i_rsubdirs = le64_to_cpu(info->rsubdirs);
ceph_decode_timespec(&ci->i_rctime, &info->rctime);
/* set dir completion flag? */
if (ci->i_files == 0 && ci->i_subdirs == 0 &&
ceph_snap(inode) == CEPH_NOSNAP &&
(le32_to_cpu(info->cap.caps) & CEPH_CAP_FILE_SHARED) &&
(issued & CEPH_CAP_FILE_EXCL) == 0 &&
(ci->i_ceph_flags & CEPH_I_COMPLETE) == 0) {
dout(" marking %p complete (empty)\n", inode);
/* ci->i_ceph_flags |= CEPH_I_COMPLETE; */
ci->i_max_offset = 2;
}
break;
default:
pr_err("fill_inode %llx.%llx BAD mode 0%o\n",
ceph_vinop(inode), inode->i_mode);
}
no_change:
spin_unlock(&inode->i_lock);
/* queue truncate if we saw i_size decrease */
if (queue_trunc)
ceph_queue_vmtruncate(inode);
/* populate frag tree */
/* FIXME: move me up, if/when version reflects fragtree changes */
nsplits = le32_to_cpu(info->fragtree.nsplits);
mutex_lock(&ci->i_fragtree_mutex);
for (i = 0; i < nsplits; i++) {
u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
struct ceph_inode_frag *frag = __get_or_create_frag(ci, id);
if (IS_ERR(frag))
continue;
frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
dout(" frag %x split by %d\n", frag->frag, frag->split_by);
}
mutex_unlock(&ci->i_fragtree_mutex);
/* were we issued a capability? */
if (info->cap.caps) {
if (ceph_snap(inode) == CEPH_NOSNAP) {
ceph_add_cap(inode, session,
le64_to_cpu(info->cap.cap_id),
cap_fmode,
le32_to_cpu(info->cap.caps),
le32_to_cpu(info->cap.wanted),
le32_to_cpu(info->cap.seq),
le32_to_cpu(info->cap.mseq),
le64_to_cpu(info->cap.realm),
info->cap.flags,
caps_reservation);
} else {
spin_lock(&inode->i_lock);
dout(" %p got snap_caps %s\n", inode,
ceph_cap_string(le32_to_cpu(info->cap.caps)));
ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
if (cap_fmode >= 0)
__ceph_get_fmode(ci, cap_fmode);
spin_unlock(&inode->i_lock);
}
} else if (cap_fmode >= 0) {
pr_warning("mds issued no caps on %llx.%llx\n",
ceph_vinop(inode));
__ceph_get_fmode(ci, cap_fmode);
}
/* update delegation info? */
if (dirinfo)
ceph_fill_dirfrag(inode, dirinfo);
err = 0;
out:
if (xattr_blob)
ceph_buffer_put(xattr_blob);
return err;
}
/*
* caller should hold session s_mutex.
*/
static void update_dentry_lease(struct dentry *dentry,
struct ceph_mds_reply_lease *lease,
struct ceph_mds_session *session,
unsigned long from_time)
{
struct ceph_dentry_info *di = ceph_dentry(dentry);
long unsigned duration = le32_to_cpu(lease->duration_ms);
long unsigned ttl = from_time + (duration * HZ) / 1000;
long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000;
struct inode *dir;
/* only track leases on regular dentries */
if (dentry->d_op != &ceph_dentry_ops)
return;
spin_lock(&dentry->d_lock);
dout("update_dentry_lease %p mask %d duration %lu ms ttl %lu\n",
dentry, le16_to_cpu(lease->mask), duration, ttl);
/* make lease_rdcache_gen match directory */
dir = dentry->d_parent->d_inode;
di->lease_shared_gen = ceph_inode(dir)->i_shared_gen;
if (lease->mask == 0)
goto out_unlock;
if (di->lease_gen == session->s_cap_gen &&
time_before(ttl, dentry->d_time))
goto out_unlock; /* we already have a newer lease. */
if (di->lease_session && di->lease_session != session)
goto out_unlock;
ceph_dentry_lru_touch(dentry);
if (!di->lease_session)
di->lease_session = ceph_get_mds_session(session);
di->lease_gen = session->s_cap_gen;
di->lease_seq = le32_to_cpu(lease->seq);
di->lease_renew_after = half_ttl;
di->lease_renew_from = 0;
dentry->d_time = ttl;
out_unlock:
spin_unlock(&dentry->d_lock);
return;
}
/*
* Set dentry's directory position based on the current dir's max, and
* order it in d_subdirs, so that dcache_readdir behaves.
*/
static void ceph_set_dentry_offset(struct dentry *dn)
{
struct dentry *dir = dn->d_parent;
struct inode *inode = dn->d_parent->d_inode;
struct ceph_dentry_info *di;
BUG_ON(!inode);
di = ceph_dentry(dn);
spin_lock(&inode->i_lock);
if ((ceph_inode(inode)->i_ceph_flags & CEPH_I_COMPLETE) == 0) {
spin_unlock(&inode->i_lock);
return;
}
di->offset = ceph_inode(inode)->i_max_offset++;
spin_unlock(&inode->i_lock);
spin_lock(&dir->d_lock);
spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
list_move(&dn->d_u.d_child, &dir->d_subdirs);
dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset,
dn->d_u.d_child.prev, dn->d_u.d_child.next);
spin_unlock(&dn->d_lock);
spin_unlock(&dir->d_lock);
}
/*
* splice a dentry to an inode.
* caller must hold directory i_mutex for this to be safe.
*
* we will only rehash the resulting dentry if @prehash is
* true; @prehash will be set to false (for the benefit of
* the caller) if we fail.
*/
static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
bool *prehash, bool set_offset)
{
struct dentry *realdn;
BUG_ON(dn->d_inode);
/* dn must be unhashed */
if (!d_unhashed(dn))
d_drop(dn);
realdn = d_materialise_unique(dn, in);
if (IS_ERR(realdn)) {
pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
PTR_ERR(realdn), dn, in, ceph_vinop(in));
if (prehash)
*prehash = false; /* don't rehash on error */
dn = realdn; /* note realdn contains the error */
goto out;
} else if (realdn) {
dout("dn %p (%d) spliced with %p (%d) "
"inode %p ino %llx.%llx\n",
dn, dn->d_count,
realdn, realdn->d_count,
realdn->d_inode, ceph_vinop(realdn->d_inode));
dput(dn);
dn = realdn;
} else {
BUG_ON(!ceph_dentry(dn));
dout("dn %p attached to %p ino %llx.%llx\n",
dn, dn->d_inode, ceph_vinop(dn->d_inode));
}
if ((!prehash || *prehash) && d_unhashed(dn))
d_rehash(dn);
if (set_offset)
ceph_set_dentry_offset(dn);
out:
return dn;
}
/*
* Incorporate results into the local cache. This is either just
* one inode, or a directory, dentry, and possibly linked-to inode (e.g.,
* after a lookup).
*
* A reply may contain
* a directory inode along with a dentry.
* and/or a target inode
*
* Called with snap_rwsem (read).
*/
int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
struct ceph_mds_session *session)
{
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
struct inode *in = NULL;
struct ceph_mds_reply_inode *ininfo;
struct ceph_vino vino;
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
int i = 0;
int err = 0;
dout("fill_trace %p is_dentry %d is_target %d\n", req,
rinfo->head->is_dentry, rinfo->head->is_target);
#if 0
/*
* Debugging hook:
*
* If we resend completed ops to a recovering mds, we get no
* trace. Since that is very rare, pretend this is the case
* to ensure the 'no trace' handlers in the callers behave.
*
* Fill in inodes unconditionally to avoid breaking cap
* invariants.
*/
if (rinfo->head->op & CEPH_MDS_OP_WRITE) {
pr_info("fill_trace faking empty trace on %lld %s\n",
req->r_tid, ceph_mds_op_name(rinfo->head->op));
if (rinfo->head->is_dentry) {
rinfo->head->is_dentry = 0;
err = fill_inode(req->r_locked_dir,
&rinfo->diri, rinfo->dirfrag,
session, req->r_request_started, -1);
}
if (rinfo->head->is_target) {
rinfo->head->is_target = 0;
ininfo = rinfo->targeti.in;
vino.ino = le64_to_cpu(ininfo->ino);
vino.snap = le64_to_cpu(ininfo->snapid);
in = ceph_get_inode(sb, vino);
err = fill_inode(in, &rinfo->targeti, NULL,
session, req->r_request_started,
req->r_fmode);
iput(in);
}
}
#endif
if (!rinfo->head->is_target && !rinfo->head->is_dentry) {
dout("fill_trace reply is empty!\n");
if (rinfo->head->result == 0 && req->r_locked_dir)
ceph_invalidate_dir_request(req);
return 0;
}
if (rinfo->head->is_dentry) {
struct inode *dir = req->r_locked_dir;
err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
session, req->r_request_started, -1,
&req->r_caps_reservation);
if (err < 0)
return err;
}
/*
* ignore null lease/binding on snapdir ENOENT, or else we
* will have trouble splicing in the virtual snapdir later
*/
if (rinfo->head->is_dentry && !req->r_aborted &&
(rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
fsc->mount_options->snapdir_name,
req->r_dentry->d_name.len))) {