forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
dir.c
2240 lines (1979 loc) · 58.6 KB
/
dir.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/spinlock.h>
#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/xattr.h>
#include "super.h"
#include "mds_client.h"
#include "crypto.h"
/*
* Directory operations: readdir, lookup, create, link, unlink,
* rename, etc.
*/
/*
* Ceph MDS operations are specified in terms of a base ino and
* relative path. Thus, the client can specify an operation on a
* specific inode (e.g., a getattr due to fstat(2)), or as a path
* relative to, say, the root directory.
*
* Normally, we limit ourselves to strict inode ops (no path component)
* or dentry operations (a single path component relative to an ino). The
* exception to this is open_root_dentry(), which will open the mount
* point by name.
*/
const struct dentry_operations ceph_dentry_ops;
static bool __dentry_lease_is_valid(struct ceph_dentry_info *di);
static int __dir_lease_try_check(const struct dentry *dentry);
/*
* Initialize ceph dentry state.
*/
static int ceph_d_init(struct dentry *dentry)
{
struct ceph_dentry_info *di;
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dentry->d_sb);
di = kmem_cache_zalloc(ceph_dentry_cachep, GFP_KERNEL);
if (!di)
return -ENOMEM; /* oh well */
di->dentry = dentry;
di->lease_session = NULL;
di->time = jiffies;
dentry->d_fsdata = di;
INIT_LIST_HEAD(&di->lease_list);
atomic64_inc(&mdsc->metric.total_dentries);
return 0;
}
/*
* for f_pos for readdir:
* - hash order:
* (0xff << 52) | ((24 bits hash) << 28) |
* (the nth entry has hash collision);
* - frag+name order;
* ((frag value) << 28) | (the nth entry in frag);
*/
#define OFFSET_BITS 28
#define OFFSET_MASK ((1 << OFFSET_BITS) - 1)
#define HASH_ORDER (0xffull << (OFFSET_BITS + 24))
loff_t ceph_make_fpos(unsigned high, unsigned off, bool hash_order)
{
loff_t fpos = ((loff_t)high << 28) | (loff_t)off;
if (hash_order)
fpos |= HASH_ORDER;
return fpos;
}
static bool is_hash_order(loff_t p)
{
return (p & HASH_ORDER) == HASH_ORDER;
}
static unsigned fpos_frag(loff_t p)
{
return p >> OFFSET_BITS;
}
static unsigned fpos_hash(loff_t p)
{
return ceph_frag_value(fpos_frag(p));
}
static unsigned fpos_off(loff_t p)
{
return p & OFFSET_MASK;
}
static int fpos_cmp(loff_t l, loff_t r)
{
int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r));
if (v)
return v;
return (int)(fpos_off(l) - fpos_off(r));
}
/*
* make note of the last dentry we read, so we can
* continue at the same lexicographical point,
* regardless of what dir changes take place on the
* server.
*/
static int note_last_dentry(struct ceph_fs_client *fsc,
struct ceph_dir_file_info *dfi,
const char *name,
int len, unsigned next_offset)
{
char *buf = kmalloc(len+1, GFP_KERNEL);
if (!buf)
return -ENOMEM;
kfree(dfi->last_name);
dfi->last_name = buf;
memcpy(dfi->last_name, name, len);
dfi->last_name[len] = 0;
dfi->next_offset = next_offset;
doutc(fsc->client, "'%s'\n", dfi->last_name);
return 0;
}
static struct dentry *
__dcache_find_get_entry(struct dentry *parent, u64 idx,
struct ceph_readdir_cache_control *cache_ctl)
{
struct inode *dir = d_inode(parent);
struct ceph_client *cl = ceph_inode_to_client(dir);
struct dentry *dentry;
unsigned idx_mask = (PAGE_SIZE / sizeof(struct dentry *)) - 1;
loff_t ptr_pos = idx * sizeof(struct dentry *);
pgoff_t ptr_pgoff = ptr_pos >> PAGE_SHIFT;
if (ptr_pos >= i_size_read(dir))
return NULL;
if (!cache_ctl->page || ptr_pgoff != page_index(cache_ctl->page)) {
ceph_readdir_cache_release(cache_ctl);
cache_ctl->page = find_lock_page(&dir->i_data, ptr_pgoff);
if (!cache_ctl->page) {
doutc(cl, " page %lu not found\n", ptr_pgoff);
return ERR_PTR(-EAGAIN);
}
/* reading/filling the cache are serialized by
i_rwsem, no need to use page lock */
unlock_page(cache_ctl->page);
cache_ctl->dentries = kmap(cache_ctl->page);
}
cache_ctl->index = idx & idx_mask;
rcu_read_lock();
spin_lock(&parent->d_lock);
/* check i_size again here, because empty directory can be
* marked as complete while not holding the i_rwsem. */
if (ceph_dir_is_complete_ordered(dir) && ptr_pos < i_size_read(dir))
dentry = cache_ctl->dentries[cache_ctl->index];
else
dentry = NULL;
spin_unlock(&parent->d_lock);
if (dentry && !lockref_get_not_dead(&dentry->d_lockref))
dentry = NULL;
rcu_read_unlock();
return dentry ? : ERR_PTR(-EAGAIN);
}
/*
* When possible, we try to satisfy a readdir by peeking at the
* dcache. We make this work by carefully ordering dentries on
* d_children when we initially get results back from the MDS, and
* falling back to a "normal" sync readdir if any dentries in the dir
* are dropped.
*
* Complete dir indicates that we have all dentries in the dir. It is
* defined IFF we hold CEPH_CAP_FILE_SHARED (which will be revoked by
* the MDS if/when the directory is modified).
*/
static int __dcache_readdir(struct file *file, struct dir_context *ctx,
int shared_gen)
{
struct ceph_dir_file_info *dfi = file->private_data;
struct dentry *parent = file->f_path.dentry;
struct inode *dir = d_inode(parent);
struct ceph_fs_client *fsc = ceph_inode_to_fs_client(dir);
struct ceph_client *cl = ceph_inode_to_client(dir);
struct dentry *dentry, *last = NULL;
struct ceph_dentry_info *di;
struct ceph_readdir_cache_control cache_ctl = {};
u64 idx = 0;
int err = 0;
doutc(cl, "%p %llx.%llx v%u at %llx\n", dir, ceph_vinop(dir),
(unsigned)shared_gen, ctx->pos);
/* search start position */
if (ctx->pos > 2) {
u64 count = div_u64(i_size_read(dir), sizeof(struct dentry *));
while (count > 0) {
u64 step = count >> 1;
dentry = __dcache_find_get_entry(parent, idx + step,
&cache_ctl);
if (!dentry) {
/* use linar search */
idx = 0;
break;
}
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
goto out;
}
di = ceph_dentry(dentry);
spin_lock(&dentry->d_lock);
if (fpos_cmp(di->offset, ctx->pos) < 0) {
idx += step + 1;
count -= step + 1;
} else {
count = step;
}
spin_unlock(&dentry->d_lock);
dput(dentry);
}
doutc(cl, "%p %llx.%llx cache idx %llu\n", dir,
ceph_vinop(dir), idx);
}
for (;;) {
bool emit_dentry = false;
dentry = __dcache_find_get_entry(parent, idx++, &cache_ctl);
if (!dentry) {
dfi->file_info.flags |= CEPH_F_ATEND;
err = 0;
break;
}
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
goto out;
}
spin_lock(&dentry->d_lock);
di = ceph_dentry(dentry);
if (d_unhashed(dentry) ||
d_really_is_negative(dentry) ||
di->lease_shared_gen != shared_gen ||
((dentry->d_flags & DCACHE_NOKEY_NAME) &&
fscrypt_has_encryption_key(dir))) {
spin_unlock(&dentry->d_lock);
dput(dentry);
err = -EAGAIN;
goto out;
}
if (fpos_cmp(ctx->pos, di->offset) <= 0) {
__ceph_dentry_dir_lease_touch(di);
emit_dentry = true;
}
spin_unlock(&dentry->d_lock);
if (emit_dentry) {
doutc(cl, " %llx dentry %p %pd %p\n", di->offset,
dentry, dentry, d_inode(dentry));
ctx->pos = di->offset;
if (!dir_emit(ctx, dentry->d_name.name,
dentry->d_name.len, ceph_present_inode(d_inode(dentry)),
d_inode(dentry)->i_mode >> 12)) {
dput(dentry);
err = 0;
break;
}
ctx->pos++;
if (last)
dput(last);
last = dentry;
} else {
dput(dentry);
}
}
out:
ceph_readdir_cache_release(&cache_ctl);
if (last) {
int ret;
di = ceph_dentry(last);
ret = note_last_dentry(fsc, dfi, last->d_name.name,
last->d_name.len,
fpos_off(di->offset) + 1);
if (ret < 0)
err = ret;
dput(last);
/* last_name no longer match cache index */
if (dfi->readdir_cache_idx >= 0) {
dfi->readdir_cache_idx = -1;
dfi->dir_release_count = 0;
}
}
return err;
}
static bool need_send_readdir(struct ceph_dir_file_info *dfi, loff_t pos)
{
if (!dfi->last_readdir)
return true;
if (is_hash_order(pos))
return !ceph_frag_contains_value(dfi->frag, fpos_hash(pos));
else
return dfi->frag != fpos_frag(pos);
}
static int ceph_readdir(struct file *file, struct dir_context *ctx)
{
struct ceph_dir_file_info *dfi = file->private_data;
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_client *cl = fsc->client;
int i;
int err;
unsigned frag = -1;
struct ceph_mds_reply_info_parsed *rinfo;
doutc(cl, "%p %llx.%llx file %p pos %llx\n", inode,
ceph_vinop(inode), file, ctx->pos);
if (dfi->file_info.flags & CEPH_F_ATEND)
return 0;
/* always start with . and .. */
if (ctx->pos == 0) {
doutc(cl, "%p %llx.%llx off 0 -> '.'\n", inode,
ceph_vinop(inode));
if (!dir_emit(ctx, ".", 1, ceph_present_inode(inode),
inode->i_mode >> 12))
return 0;
ctx->pos = 1;
}
if (ctx->pos == 1) {
u64 ino;
struct dentry *dentry = file->f_path.dentry;
spin_lock(&dentry->d_lock);
ino = ceph_present_inode(dentry->d_parent->d_inode);
spin_unlock(&dentry->d_lock);
doutc(cl, "%p %llx.%llx off 1 -> '..'\n", inode,
ceph_vinop(inode));
if (!dir_emit(ctx, "..", 2, ino, inode->i_mode >> 12))
return 0;
ctx->pos = 2;
}
err = ceph_fscrypt_prepare_readdir(inode);
if (err < 0)
return err;
spin_lock(&ci->i_ceph_lock);
/* request Fx cap. if have Fx, we don't need to release Fs cap
* for later create/unlink. */
__ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_WR);
/* can we use the dcache? */
if (ceph_test_mount_opt(fsc, DCACHE) &&
!ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
ceph_snap(inode) != CEPH_SNAPDIR &&
__ceph_dir_is_complete_ordered(ci) &&
__ceph_caps_issued_mask_metric(ci, CEPH_CAP_FILE_SHARED, 1)) {
int shared_gen = atomic_read(&ci->i_shared_gen);
spin_unlock(&ci->i_ceph_lock);
err = __dcache_readdir(file, ctx, shared_gen);
if (err != -EAGAIN)
return err;
} else {
spin_unlock(&ci->i_ceph_lock);
}
/* proceed with a normal readdir */
more:
/* do we have the correct frag content buffered? */
if (need_send_readdir(dfi, ctx->pos)) {
struct ceph_mds_request *req;
int op = ceph_snap(inode) == CEPH_SNAPDIR ?
CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR;
/* discard old result, if any */
if (dfi->last_readdir) {
ceph_mdsc_put_request(dfi->last_readdir);
dfi->last_readdir = NULL;
}
if (is_hash_order(ctx->pos)) {
/* fragtree isn't always accurate. choose frag
* based on previous reply when possible. */
if (frag == (unsigned)-1)
frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
NULL, NULL);
} else {
frag = fpos_frag(ctx->pos);
}
doutc(cl, "fetching %p %llx.%llx frag %x offset '%s'\n",
inode, ceph_vinop(inode), frag, dfi->last_name);
req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
err = ceph_alloc_readdir_reply_buffer(req, inode);
if (err) {
ceph_mdsc_put_request(req);
return err;
}
/* hints to request -> mds selection code */
req->r_direct_mode = USE_AUTH_MDS;
if (op == CEPH_MDS_OP_READDIR) {
req->r_direct_hash = ceph_frag_value(frag);
__set_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags);
req->r_inode_drop = CEPH_CAP_FILE_EXCL;
}
if (dfi->last_name) {
struct qstr d_name = { .name = dfi->last_name,
.len = strlen(dfi->last_name) };
req->r_path2 = kzalloc(NAME_MAX + 1, GFP_KERNEL);
if (!req->r_path2) {
ceph_mdsc_put_request(req);
return -ENOMEM;
}
err = ceph_encode_encrypted_dname(inode, &d_name,
req->r_path2);
if (err < 0) {
ceph_mdsc_put_request(req);
return err;
}
} else if (is_hash_order(ctx->pos)) {
req->r_args.readdir.offset_hash =
cpu_to_le32(fpos_hash(ctx->pos));
}
req->r_dir_release_cnt = dfi->dir_release_count;
req->r_dir_ordered_cnt = dfi->dir_ordered_count;
req->r_readdir_cache_idx = dfi->readdir_cache_idx;
req->r_readdir_offset = dfi->next_offset;
req->r_args.readdir.frag = cpu_to_le32(frag);
req->r_args.readdir.flags =
cpu_to_le16(CEPH_READDIR_REPLY_BITFLAGS);
req->r_inode = inode;
ihold(inode);
req->r_dentry = dget(file->f_path.dentry);
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (err < 0) {
ceph_mdsc_put_request(req);
return err;
}
doutc(cl, "%p %llx.%llx got and parsed readdir result=%d"
"on frag %x, end=%d, complete=%d, hash_order=%d\n",
inode, ceph_vinop(inode), err, frag,
(int)req->r_reply_info.dir_end,
(int)req->r_reply_info.dir_complete,
(int)req->r_reply_info.hash_order);
rinfo = &req->r_reply_info;
if (le32_to_cpu(rinfo->dir_dir->frag) != frag) {
frag = le32_to_cpu(rinfo->dir_dir->frag);
if (!rinfo->hash_order) {
dfi->next_offset = req->r_readdir_offset;
/* adjust ctx->pos to beginning of frag */
ctx->pos = ceph_make_fpos(frag,
dfi->next_offset,
false);
}
}
dfi->frag = frag;
dfi->last_readdir = req;
if (test_bit(CEPH_MDS_R_DID_PREPOPULATE, &req->r_req_flags)) {
dfi->readdir_cache_idx = req->r_readdir_cache_idx;
if (dfi->readdir_cache_idx < 0) {
/* preclude from marking dir ordered */
dfi->dir_ordered_count = 0;
} else if (ceph_frag_is_leftmost(frag) &&
dfi->next_offset == 2) {
/* note dir version at start of readdir so
* we can tell if any dentries get dropped */
dfi->dir_release_count = req->r_dir_release_cnt;
dfi->dir_ordered_count = req->r_dir_ordered_cnt;
}
} else {
doutc(cl, "%p %llx.%llx !did_prepopulate\n", inode,
ceph_vinop(inode));
/* disable readdir cache */
dfi->readdir_cache_idx = -1;
/* preclude from marking dir complete */
dfi->dir_release_count = 0;
}
/* note next offset and last dentry name */
if (rinfo->dir_nr > 0) {
struct ceph_mds_reply_dir_entry *rde =
rinfo->dir_entries + (rinfo->dir_nr-1);
unsigned next_offset = req->r_reply_info.dir_end ?
2 : (fpos_off(rde->offset) + 1);
err = note_last_dentry(fsc, dfi, rde->name,
rde->name_len, next_offset);
if (err) {
ceph_mdsc_put_request(dfi->last_readdir);
dfi->last_readdir = NULL;
return err;
}
} else if (req->r_reply_info.dir_end) {
dfi->next_offset = 2;
/* keep last name */
}
}
rinfo = &dfi->last_readdir->r_reply_info;
doutc(cl, "%p %llx.%llx frag %x num %d pos %llx chunk first %llx\n",
inode, ceph_vinop(inode), dfi->frag, rinfo->dir_nr, ctx->pos,
rinfo->dir_nr ? rinfo->dir_entries[0].offset : 0LL);
i = 0;
/* search start position */
if (rinfo->dir_nr > 0) {
int step, nr = rinfo->dir_nr;
while (nr > 0) {
step = nr >> 1;
if (rinfo->dir_entries[i + step].offset < ctx->pos) {
i += step + 1;
nr -= step + 1;
} else {
nr = step;
}
}
}
for (; i < rinfo->dir_nr; i++) {
struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
if (rde->offset < ctx->pos) {
pr_warn_client(cl,
"%p %llx.%llx rde->offset 0x%llx ctx->pos 0x%llx\n",
inode, ceph_vinop(inode), rde->offset, ctx->pos);
return -EIO;
}
if (WARN_ON_ONCE(!rde->inode.in))
return -EIO;
ctx->pos = rde->offset;
doutc(cl, "%p %llx.%llx (%d/%d) -> %llx '%.*s' %p\n", inode,
ceph_vinop(inode), i, rinfo->dir_nr, ctx->pos,
rde->name_len, rde->name, &rde->inode.in);
if (!dir_emit(ctx, rde->name, rde->name_len,
ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
le32_to_cpu(rde->inode.in->mode) >> 12)) {
/*
* NOTE: Here no need to put the 'dfi->last_readdir',
* because when dir_emit stops us it's most likely
* doesn't have enough memory, etc. So for next readdir
* it will continue.
*/
doutc(cl, "filldir stopping us...\n");
return 0;
}
/* Reset the lengths to their original allocated vals */
ctx->pos++;
}
ceph_mdsc_put_request(dfi->last_readdir);
dfi->last_readdir = NULL;
if (dfi->next_offset > 2) {
frag = dfi->frag;
goto more;
}
/* more frags? */
if (!ceph_frag_is_rightmost(dfi->frag)) {
frag = ceph_frag_next(dfi->frag);
if (is_hash_order(ctx->pos)) {
loff_t new_pos = ceph_make_fpos(ceph_frag_value(frag),
dfi->next_offset, true);
if (new_pos > ctx->pos)
ctx->pos = new_pos;
/* keep last_name */
} else {
ctx->pos = ceph_make_fpos(frag, dfi->next_offset,
false);
kfree(dfi->last_name);
dfi->last_name = NULL;
}
doutc(cl, "%p %llx.%llx next frag is %x\n", inode,
ceph_vinop(inode), frag);
goto more;
}
dfi->file_info.flags |= CEPH_F_ATEND;
/*
* if dir_release_count still matches the dir, no dentries
* were released during the whole readdir, and we should have
* the complete dir contents in our cache.
*/
if (atomic64_read(&ci->i_release_count) ==
dfi->dir_release_count) {
spin_lock(&ci->i_ceph_lock);
if (dfi->dir_ordered_count ==
atomic64_read(&ci->i_ordered_count)) {
doutc(cl, " marking %p %llx.%llx complete and ordered\n",
inode, ceph_vinop(inode));
/* use i_size to track number of entries in
* readdir cache */
BUG_ON(dfi->readdir_cache_idx < 0);
i_size_write(inode, dfi->readdir_cache_idx *
sizeof(struct dentry*));
} else {
doutc(cl, " marking %llx.%llx complete\n",
ceph_vinop(inode));
}
__ceph_dir_set_complete(ci, dfi->dir_release_count,
dfi->dir_ordered_count);
spin_unlock(&ci->i_ceph_lock);
}
doutc(cl, "%p %llx.%llx file %p done.\n", inode, ceph_vinop(inode),
file);
return 0;
}
static void reset_readdir(struct ceph_dir_file_info *dfi)
{
if (dfi->last_readdir) {
ceph_mdsc_put_request(dfi->last_readdir);
dfi->last_readdir = NULL;
}
kfree(dfi->last_name);
dfi->last_name = NULL;
dfi->dir_release_count = 0;
dfi->readdir_cache_idx = -1;
dfi->next_offset = 2; /* compensate for . and .. */
dfi->file_info.flags &= ~CEPH_F_ATEND;
}
/*
* discard buffered readdir content on seekdir(0), or seek to new frag,
* or seek prior to current chunk
*/
static bool need_reset_readdir(struct ceph_dir_file_info *dfi, loff_t new_pos)
{
struct ceph_mds_reply_info_parsed *rinfo;
loff_t chunk_offset;
if (new_pos == 0)
return true;
if (is_hash_order(new_pos)) {
/* no need to reset last_name for a forward seek when
* dentries are sotred in hash order */
} else if (dfi->frag != fpos_frag(new_pos)) {
return true;
}
rinfo = dfi->last_readdir ? &dfi->last_readdir->r_reply_info : NULL;
if (!rinfo || !rinfo->dir_nr)
return true;
chunk_offset = rinfo->dir_entries[0].offset;
return new_pos < chunk_offset ||
is_hash_order(new_pos) != is_hash_order(chunk_offset);
}
static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
{
struct ceph_dir_file_info *dfi = file->private_data;
struct inode *inode = file->f_mapping->host;
struct ceph_client *cl = ceph_inode_to_client(inode);
loff_t retval;
inode_lock(inode);
retval = -EINVAL;
switch (whence) {
case SEEK_CUR:
offset += file->f_pos;
break;
case SEEK_SET:
break;
case SEEK_END:
retval = -EOPNOTSUPP;
goto out;
default:
goto out;
}
if (offset >= 0) {
if (need_reset_readdir(dfi, offset)) {
doutc(cl, "%p %llx.%llx dropping %p content\n",
inode, ceph_vinop(inode), file);
reset_readdir(dfi);
} else if (is_hash_order(offset) && offset > file->f_pos) {
/* for hash offset, we don't know if a forward seek
* is within same frag */
dfi->dir_release_count = 0;
dfi->readdir_cache_idx = -1;
}
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
dfi->file_info.flags &= ~CEPH_F_ATEND;
}
retval = offset;
}
out:
inode_unlock(inode);
return retval;
}
/*
* Handle lookups for the hidden .snap directory.
*/
struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
struct dentry *dentry)
{
struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dentry->d_sb);
struct inode *parent = d_inode(dentry->d_parent); /* we hold i_rwsem */
struct ceph_client *cl = ceph_inode_to_client(parent);
/* .snap dir? */
if (ceph_snap(parent) == CEPH_NOSNAP &&
strcmp(dentry->d_name.name, fsc->mount_options->snapdir_name) == 0) {
struct dentry *res;
struct inode *inode = ceph_get_snapdir(parent);
res = d_splice_alias(inode, dentry);
doutc(cl, "ENOENT on snapdir %p '%pd', linking to "
"snapdir %p %llx.%llx. Spliced dentry %p\n",
dentry, dentry, inode, ceph_vinop(inode), res);
if (res)
dentry = res;
}
return dentry;
}
/*
* Figure out final result of a lookup/open request.
*
* Mainly, make sure we return the final req->r_dentry (if it already
* existed) in place of the original VFS-provided dentry when they
* differ.
*
* Gracefully handle the case where the MDS replies with -ENOENT and
* no trace (which it may do, at its discretion, e.g., if it doesn't
* care to issue a lease on the negative dentry).
*/
struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
struct dentry *dentry, int err)
{
struct ceph_client *cl = req->r_mdsc->fsc->client;
if (err == -ENOENT) {
/* no trace? */
err = 0;
if (!req->r_reply_info.head->is_dentry) {
doutc(cl,
"ENOENT and no trace, dentry %p inode %llx.%llx\n",
dentry, ceph_vinop(d_inode(dentry)));
if (d_really_is_positive(dentry)) {
d_drop(dentry);
err = -ENOENT;
} else {
d_add(dentry, NULL);
}
}
}
if (err)
dentry = ERR_PTR(err);
else if (dentry != req->r_dentry)
dentry = dget(req->r_dentry); /* we got spliced */
else
dentry = NULL;
return dentry;
}
static bool is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
{
return ceph_ino(inode) == CEPH_INO_ROOT &&
strncmp(dentry->d_name.name, ".ceph", 5) == 0;
}
/*
* Look up a single dir entry. If there is a lookup intent, inform
* the MDS so that it gets our 'caps wanted' value in a single op.
*/
static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dir->i_sb);
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_client *cl = fsc->client;
struct ceph_mds_request *req;
int op;
int mask;
int err;
doutc(cl, "%p %llx.%llx/'%pd' dentry %p\n", dir, ceph_vinop(dir),
dentry, dentry);
if (dentry->d_name.len > NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
if (IS_ENCRYPTED(dir)) {
bool had_key = fscrypt_has_encryption_key(dir);
err = fscrypt_prepare_lookup_partial(dir, dentry);
if (err < 0)
return ERR_PTR(err);
/* mark directory as incomplete if it has been unlocked */
if (!had_key && fscrypt_has_encryption_key(dir))
ceph_dir_clear_complete(dir);
}
/* can we conclude ENOENT locally? */
if (d_really_is_negative(dentry)) {
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_dentry_info *di = ceph_dentry(dentry);
spin_lock(&ci->i_ceph_lock);
doutc(cl, " dir %llx.%llx flags are 0x%lx\n",
ceph_vinop(dir), ci->i_ceph_flags);
if (strncmp(dentry->d_name.name,
fsc->mount_options->snapdir_name,
dentry->d_name.len) &&
!is_root_ceph_dentry(dir, dentry) &&
ceph_test_mount_opt(fsc, DCACHE) &&
__ceph_dir_is_complete(ci) &&
__ceph_caps_issued_mask_metric(ci, CEPH_CAP_FILE_SHARED, 1)) {
__ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_RD);
spin_unlock(&ci->i_ceph_lock);
doutc(cl, " dir %llx.%llx complete, -ENOENT\n",
ceph_vinop(dir));
d_add(dentry, NULL);
di->lease_shared_gen = atomic_read(&ci->i_shared_gen);
return NULL;
}
spin_unlock(&ci->i_ceph_lock);
}
op = ceph_snap(dir) == CEPH_SNAPDIR ?
CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;
req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
if (IS_ERR(req))
return ERR_CAST(req);
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
if (ceph_security_xattr_wanted(dir))
mask |= CEPH_CAP_XATTR_SHARED;
req->r_args.getattr.mask = cpu_to_le32(mask);
ihold(dir);
req->r_parent = dir;
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (err == -ENOENT) {
struct dentry *res;
res = ceph_handle_snapdir(req, dentry);
if (IS_ERR(res)) {
err = PTR_ERR(res);
} else {
dentry = res;
err = 0;
}
}
dentry = ceph_finish_lookup(req, dentry, err);
ceph_mdsc_put_request(req); /* will dput(dentry) */
doutc(cl, "result=%p\n", dentry);
return dentry;
}
/*
* If we do a create but get no trace back from the MDS, follow up with
* a lookup (the VFS expects us to link up the provided dentry).
*/
int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
{
struct dentry *result = ceph_lookup(dir, dentry, 0);
if (result && !IS_ERR(result)) {
/*
* We created the item, then did a lookup, and found
* it was already linked to another inode we already
* had in our cache (and thus got spliced). To not
* confuse VFS (especially when inode is a directory),
* we don't link our dentry to that inode, return an
* error instead.
*
* This event should be rare and it happens only when
* we talk to old MDS. Recent MDS does not send traceless
* reply for request that creates new inode.
*/
d_drop(result);
return -ESTALE;
}
return PTR_ERR(result);
}
static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_client *cl = mdsc->fsc->client;
struct ceph_mds_request *req;
struct ceph_acl_sec_ctx as_ctx = {};
int err;
if (ceph_snap(dir) != CEPH_NOSNAP)
return -EROFS;
err = ceph_wait_on_conflict_unlink(dentry);
if (err)
return err;
if (ceph_quota_is_max_files_exceeded(dir)) {
err = -EDQUOT;
goto out;
}
doutc(cl, "%p %llx.%llx/'%pd' dentry %p mode 0%ho rdev %d\n",
dir, ceph_vinop(dir), dentry, dentry, mode, rdev);
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_MKNOD, USE_AUTH_MDS);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
if (IS_ERR(req->r_new_inode)) {
err = PTR_ERR(req->r_new_inode);
req->r_new_inode = NULL;
goto out_req;
}
if (S_ISREG(mode) && IS_ENCRYPTED(dir))
set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
req->r_parent = dir;
ihold(dir);
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
req->r_mnt_idmap = mnt_idmap_get(idmap);
req->r_args.mknod.mode = cpu_to_le32(mode);
req->r_args.mknod.rdev = cpu_to_le32(rdev);
req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL |
CEPH_CAP_XATTR_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
ceph_as_ctx_to_req(req, &as_ctx);
err = ceph_mdsc_do_request(mdsc, dir, req);
if (!err && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
out_req:
ceph_mdsc_put_request(req);
out:
if (!err)
ceph_init_inode_acls(d_inode(dentry), &as_ctx);
else
d_drop(dentry);
ceph_release_acl_sec_ctx(&as_ctx);
return err;
}
static int ceph_create(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, bool excl)
{
return ceph_mknod(idmap, dir, dentry, mode, 0);
}
#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
static int prep_encrypted_symlink_target(struct ceph_mds_request *req,
const char *dest)
{
int err;
int len = strlen(dest);
struct fscrypt_str osd_link = FSTR_INIT(NULL, 0);
err = fscrypt_prepare_symlink(req->r_parent, dest, len, PATH_MAX,
&osd_link);
if (err)
goto out;
err = fscrypt_encrypt_symlink(req->r_new_inode, dest, len, &osd_link);
if (err)
goto out;