forked from Xilinx/linux-xlnx
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathfile.c
2487 lines (2164 loc) · 64.7 KB
/
file.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/ceph/striper.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/writeback.h>
#include <linux/falloc.h>
#include <linux/iversion.h>
#include <linux/ktime.h>
#include "super.h"
#include "mds_client.h"
#include "cache.h"
#include "io.h"
#include "metric.h"
static __le32 ceph_flags_sys2wire(u32 flags)
{
u32 wire_flags = 0;
switch (flags & O_ACCMODE) {
case O_RDONLY:
wire_flags |= CEPH_O_RDONLY;
break;
case O_WRONLY:
wire_flags |= CEPH_O_WRONLY;
break;
case O_RDWR:
wire_flags |= CEPH_O_RDWR;
break;
}
flags &= ~O_ACCMODE;
#define ceph_sys2wire(a) if (flags & a) { wire_flags |= CEPH_##a; flags &= ~a; }
ceph_sys2wire(O_CREAT);
ceph_sys2wire(O_EXCL);
ceph_sys2wire(O_TRUNC);
ceph_sys2wire(O_DIRECTORY);
ceph_sys2wire(O_NOFOLLOW);
#undef ceph_sys2wire
if (flags)
dout("unused open flags: %x\n", flags);
return cpu_to_le32(wire_flags);
}
/*
* Ceph file operations
*
* Implement basic open/close functionality, and implement
* read/write.
*
* We implement three modes of file I/O:
* - buffered uses the generic_file_aio_{read,write} helpers
*
* - synchronous is used when there is multi-client read/write
* sharing, avoids the page cache, and synchronously waits for an
* ack from the OSD.
*
* - direct io takes the variant of the sync path that references
* user pages directly.
*
* fsync() flushes and waits on dirty pages, but just queues metadata
* for writeback: since the MDS can recover size and mtime there is no
* need to wait for MDS acknowledgement.
*/
/*
* How many pages to get in one call to iov_iter_get_pages(). This
* determines the size of the on-stack array used as a buffer.
*/
#define ITER_GET_BVECS_PAGES 64
static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize,
struct bio_vec *bvecs)
{
size_t size = 0;
int bvec_idx = 0;
if (maxsize > iov_iter_count(iter))
maxsize = iov_iter_count(iter);
while (size < maxsize) {
struct page *pages[ITER_GET_BVECS_PAGES];
ssize_t bytes;
size_t start;
int idx = 0;
bytes = iov_iter_get_pages(iter, pages, maxsize - size,
ITER_GET_BVECS_PAGES, &start);
if (bytes < 0)
return size ?: bytes;
iov_iter_advance(iter, bytes);
size += bytes;
for ( ; bytes; idx++, bvec_idx++) {
struct bio_vec bv = {
.bv_page = pages[idx],
.bv_len = min_t(int, bytes, PAGE_SIZE - start),
.bv_offset = start,
};
bvecs[bvec_idx] = bv;
bytes -= bv.bv_len;
start = 0;
}
}
return size;
}
/*
* iov_iter_get_pages() only considers one iov_iter segment, no matter
* what maxsize or maxpages are given. For ITER_BVEC that is a single
* page.
*
* Attempt to get up to @maxsize bytes worth of pages from @iter.
* Return the number of bytes in the created bio_vec array, or an error.
*/
static ssize_t iter_get_bvecs_alloc(struct iov_iter *iter, size_t maxsize,
struct bio_vec **bvecs, int *num_bvecs)
{
struct bio_vec *bv;
size_t orig_count = iov_iter_count(iter);
ssize_t bytes;
int npages;
iov_iter_truncate(iter, maxsize);
npages = iov_iter_npages(iter, INT_MAX);
iov_iter_reexpand(iter, orig_count);
/*
* __iter_get_bvecs() may populate only part of the array -- zero it
* out.
*/
bv = kvmalloc_array(npages, sizeof(*bv), GFP_KERNEL | __GFP_ZERO);
if (!bv)
return -ENOMEM;
bytes = __iter_get_bvecs(iter, maxsize, bv);
if (bytes < 0) {
/*
* No pages were pinned -- just free the array.
*/
kvfree(bv);
return bytes;
}
*bvecs = bv;
*num_bvecs = npages;
return bytes;
}
static void put_bvecs(struct bio_vec *bvecs, int num_bvecs, bool should_dirty)
{
int i;
for (i = 0; i < num_bvecs; i++) {
if (bvecs[i].bv_page) {
if (should_dirty)
set_page_dirty_lock(bvecs[i].bv_page);
put_page(bvecs[i].bv_page);
}
}
kvfree(bvecs);
}
/*
* Prepare an open request. Preallocate ceph_cap to avoid an
* inopportune ENOMEM later.
*/
static struct ceph_mds_request *
prepare_open_request(struct super_block *sb, int flags, int create_mode)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(sb);
struct ceph_mds_request *req;
int want_auth = USE_ANY_MDS;
int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;
if (flags & (O_WRONLY|O_RDWR|O_CREAT|O_TRUNC))
want_auth = USE_AUTH_MDS;
req = ceph_mdsc_create_request(mdsc, op, want_auth);
if (IS_ERR(req))
goto out;
req->r_fmode = ceph_flags_to_mode(flags);
req->r_args.open.flags = ceph_flags_sys2wire(flags);
req->r_args.open.mode = cpu_to_le32(create_mode);
out:
return req;
}
static int ceph_init_file_info(struct inode *inode, struct file *file,
int fmode, bool isdir)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi;
dout("%s %p %p 0%o (%s)\n", __func__, inode, file,
inode->i_mode, isdir ? "dir" : "regular");
BUG_ON(inode->i_fop->release != ceph_release);
if (isdir) {
struct ceph_dir_file_info *dfi =
kmem_cache_zalloc(ceph_dir_file_cachep, GFP_KERNEL);
if (!dfi)
return -ENOMEM;
file->private_data = dfi;
fi = &dfi->file_info;
dfi->next_offset = 2;
dfi->readdir_cache_idx = -1;
} else {
fi = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL);
if (!fi)
return -ENOMEM;
file->private_data = fi;
}
ceph_get_fmode(ci, fmode, 1);
fi->fmode = fmode;
spin_lock_init(&fi->rw_contexts_lock);
INIT_LIST_HEAD(&fi->rw_contexts);
fi->meta_err = errseq_sample(&ci->i_meta_err);
fi->filp_gen = READ_ONCE(ceph_inode_to_client(inode)->filp_gen);
return 0;
}
/*
* initialize private struct file data.
* if we fail, clean up by dropping fmode reference on the ceph_inode
*/
static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
{
int ret = 0;
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
ceph_fscache_register_inode_cookie(inode);
ceph_fscache_file_set_cookie(inode, file);
fallthrough;
case S_IFDIR:
ret = ceph_init_file_info(inode, file, fmode,
S_ISDIR(inode->i_mode));
break;
case S_IFLNK:
dout("init_file %p %p 0%o (symlink)\n", inode, file,
inode->i_mode);
break;
default:
dout("init_file %p %p 0%o (special)\n", inode, file,
inode->i_mode);
/*
* we need to drop the open ref now, since we don't
* have .release set to ceph_release.
*/
BUG_ON(inode->i_fop->release == ceph_release);
/* call the proper open fop */
ret = inode->i_fop->open(inode, file);
}
return ret;
}
/*
* try renew caps after session gets killed.
*/
int ceph_renew_caps(struct inode *inode, int fmode)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_request *req;
int err, flags, wanted;
spin_lock(&ci->i_ceph_lock);
__ceph_touch_fmode(ci, mdsc, fmode);
wanted = __ceph_caps_file_wanted(ci);
if (__ceph_is_any_real_caps(ci) &&
(!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
int issued = __ceph_caps_issued(ci, NULL);
spin_unlock(&ci->i_ceph_lock);
dout("renew caps %p want %s issued %s updating mds_wanted\n",
inode, ceph_cap_string(wanted), ceph_cap_string(issued));
ceph_check_caps(ci, 0, NULL);
return 0;
}
spin_unlock(&ci->i_ceph_lock);
flags = 0;
if ((wanted & CEPH_CAP_FILE_RD) && (wanted & CEPH_CAP_FILE_WR))
flags = O_RDWR;
else if (wanted & CEPH_CAP_FILE_RD)
flags = O_RDONLY;
else if (wanted & CEPH_CAP_FILE_WR)
flags = O_WRONLY;
#ifdef O_LAZY
if (wanted & CEPH_CAP_FILE_LAZYIO)
flags |= O_LAZY;
#endif
req = prepare_open_request(inode->i_sb, flags, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
ceph_mdsc_put_request(req);
out:
dout("renew caps %p open result=%d\n", inode, err);
return err < 0 ? err : 0;
}
/*
* If we already have the requisite capabilities, we can satisfy
* the open request locally (no need to request new caps from the
* MDS). We do, however, need to inform the MDS (asynchronously)
* if our wanted caps set expands.
*/
int ceph_open(struct inode *inode, struct file *file)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct ceph_file_info *fi = file->private_data;
int err;
int flags, fmode, wanted;
if (fi) {
dout("open file %p is already opened\n", file);
return 0;
}
/* filter out O_CREAT|O_EXCL; vfs did that already. yuck. */
flags = file->f_flags & ~(O_CREAT|O_EXCL);
if (S_ISDIR(inode->i_mode))
flags = O_DIRECTORY; /* mds likes to know */
dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
ceph_vinop(inode), file, flags, file->f_flags);
fmode = ceph_flags_to_mode(flags);
wanted = ceph_caps_for_mode(fmode);
/* snapped files are read-only */
if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE))
return -EROFS;
/* trivially open snapdir */
if (ceph_snap(inode) == CEPH_SNAPDIR) {
return ceph_init_file(inode, file, fmode);
}
/*
* No need to block if we have caps on the auth MDS (for
* write) or any MDS (for read). Update wanted set
* asynchronously.
*/
spin_lock(&ci->i_ceph_lock);
if (__ceph_is_any_real_caps(ci) &&
(((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
int mds_wanted = __ceph_caps_mds_wanted(ci, true);
int issued = __ceph_caps_issued(ci, NULL);
dout("open %p fmode %d want %s issued %s using existing\n",
inode, fmode, ceph_cap_string(wanted),
ceph_cap_string(issued));
__ceph_touch_fmode(ci, mdsc, fmode);
spin_unlock(&ci->i_ceph_lock);
/* adjust wanted? */
if ((issued & wanted) != wanted &&
(mds_wanted & wanted) != wanted &&
ceph_snap(inode) != CEPH_SNAPDIR)
ceph_check_caps(ci, 0, NULL);
return ceph_init_file(inode, file, fmode);
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
__ceph_touch_fmode(ci, mdsc, fmode);
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
spin_unlock(&ci->i_ceph_lock);
dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
req = prepare_open_request(inode->i_sb, flags, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (!err)
err = ceph_init_file(inode, file, req->r_fmode);
ceph_mdsc_put_request(req);
dout("open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
out:
return err;
}
/* Clone the layout from a synchronous create, if the dir now has Dc caps */
static void
cache_file_layout(struct inode *dst, struct inode *src)
{
struct ceph_inode_info *cdst = ceph_inode(dst);
struct ceph_inode_info *csrc = ceph_inode(src);
spin_lock(&cdst->i_ceph_lock);
if ((__ceph_caps_issued(cdst, NULL) & CEPH_CAP_DIR_CREATE) &&
!ceph_file_layout_is_valid(&cdst->i_cached_layout)) {
memcpy(&cdst->i_cached_layout, &csrc->i_layout,
sizeof(cdst->i_cached_layout));
rcu_assign_pointer(cdst->i_cached_layout.pool_ns,
ceph_try_get_string(csrc->i_layout.pool_ns));
}
spin_unlock(&cdst->i_ceph_lock);
}
/*
* Try to set up an async create. We need caps, a file layout, and inode number,
* and either a lease on the dentry or complete dir info. If any of those
* criteria are not satisfied, then return false and the caller can go
* synchronous.
*/
static int try_prep_async_create(struct inode *dir, struct dentry *dentry,
struct ceph_file_layout *lo, u64 *pino)
{
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_dentry_info *di = ceph_dentry(dentry);
int got = 0, want = CEPH_CAP_FILE_EXCL | CEPH_CAP_DIR_CREATE;
u64 ino;
spin_lock(&ci->i_ceph_lock);
/* No auth cap means no chance for Dc caps */
if (!ci->i_auth_cap)
goto no_async;
/* Any delegated inos? */
if (xa_empty(&ci->i_auth_cap->session->s_delegated_inos))
goto no_async;
if (!ceph_file_layout_is_valid(&ci->i_cached_layout))
goto no_async;
if ((__ceph_caps_issued(ci, NULL) & want) != want)
goto no_async;
if (d_in_lookup(dentry)) {
if (!__ceph_dir_is_complete(ci))
goto no_async;
spin_lock(&dentry->d_lock);
di->lease_shared_gen = atomic_read(&ci->i_shared_gen);
spin_unlock(&dentry->d_lock);
} else if (atomic_read(&ci->i_shared_gen) !=
READ_ONCE(di->lease_shared_gen)) {
goto no_async;
}
ino = ceph_get_deleg_ino(ci->i_auth_cap->session);
if (!ino)
goto no_async;
*pino = ino;
ceph_take_cap_refs(ci, want, false);
memcpy(lo, &ci->i_cached_layout, sizeof(*lo));
rcu_assign_pointer(lo->pool_ns,
ceph_try_get_string(ci->i_cached_layout.pool_ns));
got = want;
no_async:
spin_unlock(&ci->i_ceph_lock);
return got;
}
static void restore_deleg_ino(struct inode *dir, u64 ino)
{
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_mds_session *s = NULL;
spin_lock(&ci->i_ceph_lock);
if (ci->i_auth_cap)
s = ceph_get_mds_session(ci->i_auth_cap->session);
spin_unlock(&ci->i_ceph_lock);
if (s) {
int err = ceph_restore_deleg_ino(s, ino);
if (err)
pr_warn("ceph: unable to restore delegated ino 0x%llx to session: %d\n",
ino, err);
ceph_put_mds_session(s);
}
}
static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
struct ceph_mds_request *req)
{
int result = req->r_err ? req->r_err :
le32_to_cpu(req->r_reply_info.head->result);
if (result == -EJUKEBOX)
goto out;
mapping_set_error(req->r_parent->i_mapping, result);
if (result) {
struct dentry *dentry = req->r_dentry;
int pathlen = 0;
u64 base = 0;
char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
&base, 0);
ceph_dir_clear_complete(req->r_parent);
if (!d_unhashed(dentry))
d_drop(dentry);
/* FIXME: start returning I/O errors on all accesses? */
pr_warn("ceph: async create failure path=(%llx)%s result=%d!\n",
base, IS_ERR(path) ? "<<bad>>" : path, result);
ceph_mdsc_free_path(path, pathlen);
}
if (req->r_target_inode) {
struct ceph_inode_info *ci = ceph_inode(req->r_target_inode);
u64 ino = ceph_vino(req->r_target_inode).ino;
if (req->r_deleg_ino != ino)
pr_warn("%s: inode number mismatch! err=%d deleg_ino=0x%llx target=0x%llx\n",
__func__, req->r_err, req->r_deleg_ino, ino);
mapping_set_error(req->r_target_inode->i_mapping, result);
spin_lock(&ci->i_ceph_lock);
if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) {
ci->i_ceph_flags &= ~CEPH_I_ASYNC_CREATE;
wake_up_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT);
}
ceph_kick_flushing_inode_caps(req->r_session, ci);
spin_unlock(&ci->i_ceph_lock);
} else {
pr_warn("%s: no req->r_target_inode for 0x%llx\n", __func__,
req->r_deleg_ino);
}
out:
ceph_mdsc_release_dir_caps(req);
}
static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
struct file *file, umode_t mode,
struct ceph_mds_request *req,
struct ceph_acl_sec_ctx *as_ctx,
struct ceph_file_layout *lo)
{
int ret;
char xattr_buf[4];
struct ceph_mds_reply_inode in = { };
struct ceph_mds_reply_info_in iinfo = { .in = &in };
struct ceph_inode_info *ci = ceph_inode(dir);
struct inode *inode;
struct timespec64 now;
struct ceph_vino vino = { .ino = req->r_deleg_ino,
.snap = CEPH_NOSNAP };
ktime_get_real_ts64(&now);
inode = ceph_get_inode(dentry->d_sb, vino);
if (IS_ERR(inode))
return PTR_ERR(inode);
iinfo.inline_version = CEPH_INLINE_NONE;
iinfo.change_attr = 1;
ceph_encode_timespec64(&iinfo.btime, &now);
iinfo.xattr_len = ARRAY_SIZE(xattr_buf);
iinfo.xattr_data = xattr_buf;
memset(iinfo.xattr_data, 0, iinfo.xattr_len);
in.ino = cpu_to_le64(vino.ino);
in.snapid = cpu_to_le64(CEPH_NOSNAP);
in.version = cpu_to_le64(1); // ???
in.cap.caps = in.cap.wanted = cpu_to_le32(CEPH_CAP_ALL_FILE);
in.cap.cap_id = cpu_to_le64(1);
in.cap.realm = cpu_to_le64(ci->i_snap_realm->ino);
in.cap.flags = CEPH_CAP_FLAG_AUTH;
in.ctime = in.mtime = in.atime = iinfo.btime;
in.mode = cpu_to_le32((u32)mode);
in.truncate_seq = cpu_to_le32(1);
in.truncate_size = cpu_to_le64(-1ULL);
in.xattr_version = cpu_to_le64(1);
in.uid = cpu_to_le32(from_kuid(&init_user_ns, current_fsuid()));
in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_mode & S_ISGID ?
dir->i_gid : current_fsgid()));
in.nlink = cpu_to_le32(1);
in.max_size = cpu_to_le64(lo->stripe_unit);
ceph_file_layout_to_legacy(lo, &in.layout);
ret = ceph_fill_inode(inode, NULL, &iinfo, NULL, req->r_session,
req->r_fmode, NULL);
if (ret) {
dout("%s failed to fill inode: %d\n", __func__, ret);
ceph_dir_clear_complete(dir);
if (!d_unhashed(dentry))
d_drop(dentry);
if (inode->i_state & I_NEW)
discard_new_inode(inode);
} else {
struct dentry *dn;
dout("%s d_adding new inode 0x%llx to 0x%llx/%s\n", __func__,
vino.ino, ceph_ino(dir), dentry->d_name.name);
ceph_dir_clear_ordered(dir);
ceph_init_inode_acls(inode, as_ctx);
if (inode->i_state & I_NEW) {
/*
* If it's not I_NEW, then someone created this before
* we got here. Assume the server is aware of it at
* that point and don't worry about setting
* CEPH_I_ASYNC_CREATE.
*/
ceph_inode(inode)->i_ceph_flags = CEPH_I_ASYNC_CREATE;
unlock_new_inode(inode);
}
if (d_in_lookup(dentry) || d_really_is_negative(dentry)) {
if (!d_unhashed(dentry))
d_drop(dentry);
dn = d_splice_alias(inode, dentry);
WARN_ON_ONCE(dn && dn != dentry);
}
file->f_mode |= FMODE_CREATED;
ret = finish_open(file, dentry, ceph_open);
}
return ret;
}
/*
* Do a lookup + open with a single request. If we get a non-existent
* file or symlink, return 1 so the VFS can retry.
*/
int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct dentry *dn;
struct ceph_acl_sec_ctx as_ctx = {};
bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS);
int mask;
int err;
dout("atomic_open %p dentry %p '%pd' %s flags %d mode 0%o\n",
dir, dentry, dentry,
d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);
if (dentry->d_name.len > NAME_MAX)
return -ENAMETOOLONG;
if (flags & O_CREAT) {
if (ceph_quota_is_max_files_exceeded(dir))
return -EDQUOT;
err = ceph_pre_init_acls(dir, &mode, &as_ctx);
if (err < 0)
return err;
err = ceph_security_init_secctx(dentry, mode, &as_ctx);
if (err < 0)
goto out_ctx;
} else if (!d_in_lookup(dentry)) {
/* If it's not being looked up, it's negative */
return -ENOENT;
}
retry:
/* do the open */
req = prepare_open_request(dir->i_sb, flags, mode);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out_ctx;
}
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.open.mask = cpu_to_le32(mask);
req->r_parent = dir;
if (flags & O_CREAT) {
struct ceph_file_layout lo;
req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
if (as_ctx.pagelist) {
req->r_pagelist = as_ctx.pagelist;
as_ctx.pagelist = NULL;
}
if (try_async &&
(req->r_dir_caps =
try_prep_async_create(dir, dentry, &lo,
&req->r_deleg_ino))) {
set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);
req->r_args.open.flags |= cpu_to_le32(CEPH_O_EXCL);
req->r_callback = ceph_async_create_cb;
err = ceph_mdsc_submit_request(mdsc, dir, req);
if (!err) {
err = ceph_finish_async_create(dir, dentry,
file, mode, req,
&as_ctx, &lo);
} else if (err == -EJUKEBOX) {
restore_deleg_ino(dir, req->r_deleg_ino);
ceph_mdsc_put_request(req);
try_async = false;
goto retry;
}
goto out_req;
}
}
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
err = ceph_mdsc_do_request(mdsc,
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
req);
dentry = ceph_handle_snapdir(req, dentry, err);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
goto out_req;
}
err = 0;
if ((flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
if (d_in_lookup(dentry)) {
dn = ceph_finish_lookup(req, dentry, err);
if (IS_ERR(dn))
err = PTR_ERR(dn);
} else {
/* we were given a hashed negative dentry */
dn = NULL;
}
if (err)
goto out_req;
if (dn || d_really_is_negative(dentry) || d_is_symlink(dentry)) {
/* make vfs retry on splice, ENOENT, or symlink */
dout("atomic_open finish_no_open on dn %p\n", dn);
err = finish_no_open(file, dn);
} else {
dout("atomic_open finish_open on dn %p\n", dn);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
struct inode *newino = d_inode(dentry);
cache_file_layout(dir, newino);
ceph_init_inode_acls(newino, &as_ctx);
file->f_mode |= FMODE_CREATED;
}
err = finish_open(file, dentry, ceph_open);
}
out_req:
ceph_mdsc_put_request(req);
out_ctx:
ceph_release_acl_sec_ctx(&as_ctx);
dout("atomic_open result=%d\n", err);
return err;
}
int ceph_release(struct inode *inode, struct file *file)
{
struct ceph_inode_info *ci = ceph_inode(inode);
if (S_ISDIR(inode->i_mode)) {
struct ceph_dir_file_info *dfi = file->private_data;
dout("release inode %p dir file %p\n", inode, file);
WARN_ON(!list_empty(&dfi->file_info.rw_contexts));
ceph_put_fmode(ci, dfi->file_info.fmode, 1);
if (dfi->last_readdir)
ceph_mdsc_put_request(dfi->last_readdir);
kfree(dfi->last_name);
kfree(dfi->dir_info);
kmem_cache_free(ceph_dir_file_cachep, dfi);
} else {
struct ceph_file_info *fi = file->private_data;
dout("release inode %p regular file %p\n", inode, file);
WARN_ON(!list_empty(&fi->rw_contexts));
ceph_put_fmode(ci, fi->fmode, 1);
kmem_cache_free(ceph_file_cachep, fi);
}
/* wake up anyone waiting for caps on this inode */
wake_up_all(&ci->i_cap_wq);
return 0;
}
enum {
HAVE_RETRIED = 1,
CHECK_EOF = 2,
READ_INLINE = 3,
};
/*
* Completely synchronous read and write methods. Direct from __user
* buffer to osd, or directly to user pages (if O_DIRECT).
*
* If the read spans object boundary, just do multiple reads. (That's not
* atomic, but good enough for now.)
*
* If we get a short result from the OSD, check against i_size; we need to
* only return a short read to the caller if we hit EOF.
*/
static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
int *retry_op)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_osd_client *osdc = &fsc->client->osdc;
ssize_t ret;
u64 off = iocb->ki_pos;
u64 len = iov_iter_count(to);
dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len,
(file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
if (!len)
return 0;
/*
* flush any page cache pages in this range. this
* will make concurrent normal and sync io slow,
* but it will at least behave sensibly when they are
* in sequence.
*/
ret = filemap_write_and_wait_range(inode->i_mapping,
off, off + len - 1);
if (ret < 0)
return ret;
ret = 0;
while ((len = iov_iter_count(to)) > 0) {
struct ceph_osd_request *req;
struct page **pages;
int num_pages;
size_t page_off;
u64 i_size;
bool more;
int idx;
size_t left;
req = ceph_osdc_new_request(osdc, &ci->i_layout,
ci->i_vino, off, &len, 0, 1,
CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
NULL, ci->i_truncate_seq,
ci->i_truncate_size, false);
if (IS_ERR(req)) {
ret = PTR_ERR(req);
break;
}
more = len < iov_iter_count(to);
num_pages = calc_pages_for(off, len);
page_off = off & ~PAGE_MASK;
pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
if (IS_ERR(pages)) {
ceph_osdc_put_request(req);
ret = PTR_ERR(pages);
break;
}
osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
false, false);
ret = ceph_osdc_start_request(osdc, req, false);
if (!ret)
ret = ceph_osdc_wait_request(osdc, req);
ceph_update_read_metrics(&fsc->mdsc->metric,
req->r_start_latency,
req->r_end_latency,
ret);
ceph_osdc_put_request(req);
i_size = i_size_read(inode);
dout("sync_read %llu~%llu got %zd i_size %llu%s\n",
off, len, ret, i_size, (more ? " MORE" : ""));
if (ret == -ENOENT)
ret = 0;
if (ret >= 0 && ret < len && (off + ret < i_size)) {
int zlen = min(len - ret, i_size - off - ret);
int zoff = page_off + ret;
dout("sync_read zero gap %llu~%llu\n",
off + ret, off + ret + zlen);
ceph_zero_page_vector_range(zoff, zlen, pages);
ret += zlen;
}
idx = 0;
left = ret > 0 ? ret : 0;
while (left > 0) {
size_t len, copied;
page_off = off & ~PAGE_MASK;
len = min_t(size_t, left, PAGE_SIZE - page_off);
SetPageUptodate(pages[idx]);
copied = copy_page_to_iter(pages[idx++],
page_off, len, to);
off += copied;
left -= copied;
if (copied < len) {
ret = -EFAULT;
break;
}
}
ceph_release_page_vector(pages, num_pages);
if (ret < 0) {
if (ret == -EBLOCKLISTED)
fsc->blocklisted = true;
break;
}
if (off >= i_size || !more)
break;
}
if (off > iocb->ki_pos) {
if (ret >= 0 &&
iov_iter_count(to) > 0 && off >= i_size_read(inode))
*retry_op = CHECK_EOF;
ret = off - iocb->ki_pos;
iocb->ki_pos = off;
}
dout("sync_read result %zd retry_op %d\n", ret, *retry_op);
return ret;
}
struct ceph_aio_request {
struct kiocb *iocb;
size_t total_len;
bool write;
bool should_dirty;
int error;
struct list_head osd_reqs;
unsigned num_reqs;
atomic_t pending_reqs;
struct timespec64 mtime;
struct ceph_cap_flush *prealloc_cf;
};
struct ceph_aio_work {
struct work_struct work;
struct ceph_osd_request *req;
};
static void ceph_aio_retry_work(struct work_struct *work);
static void ceph_aio_complete(struct inode *inode,
struct ceph_aio_request *aio_req)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int ret;
if (!atomic_dec_and_test(&aio_req->pending_reqs))
return;
if (aio_req->iocb->ki_flags & IOCB_DIRECT)
inode_dio_end(inode);
ret = aio_req->error;
if (!ret)
ret = aio_req->total_len;
dout("ceph_aio_complete %p rc %d\n", inode, ret);
if (ret >= 0 && aio_req->write) {
int dirty;