forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathrbd.c
2355 lines (1939 loc) · 51.3 KB
/
rbd.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
/*
rbd.c -- Export ceph rados objects as a Linux block device
based on drivers/block/osdblk.c:
Copyright 2009 Red Hat, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
For usage instructions, please refer to:
Documentation/ABI/testing/sysfs-bus-rbd
*/
#include <linux/ceph/libceph.h>
#include <linux/ceph/osd_client.h>
#include <linux/ceph/mon_client.h>
#include <linux/ceph/decode.h>
#include <linux/parser.h>
#include <linux/kernel.h>
#include <linux/device.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include "rbd_types.h"
#define DRV_NAME "rbd"
#define DRV_NAME_LONG "rbd (rados block device)"
#define RBD_MINORS_PER_MAJOR 256 /* max minors per blkdev */
#define RBD_MAX_MD_NAME_LEN (96 + sizeof(RBD_SUFFIX))
#define RBD_MAX_POOL_NAME_LEN 64
#define RBD_MAX_SNAP_NAME_LEN 32
#define RBD_MAX_OPT_LEN 1024
#define RBD_SNAP_HEAD_NAME "-"
#define DEV_NAME_LEN 32
#define RBD_NOTIFY_TIMEOUT_DEFAULT 10
/*
* block device image metadata (in-memory version)
*/
struct rbd_image_header {
u64 image_size;
char block_name[32];
__u8 obj_order;
__u8 crypt_type;
__u8 comp_type;
struct rw_semaphore snap_rwsem;
struct ceph_snap_context *snapc;
size_t snap_names_len;
u64 snap_seq;
u32 total_snaps;
char *snap_names;
u64 *snap_sizes;
u64 obj_version;
};
struct rbd_options {
int notify_timeout;
};
/*
* an instance of the client. multiple devices may share a client.
*/
struct rbd_client {
struct ceph_client *client;
struct rbd_options *rbd_opts;
struct kref kref;
struct list_head node;
};
/*
* a single io request
*/
struct rbd_request {
struct request *rq; /* blk layer request */
struct bio *bio; /* cloned bio */
struct page **pages; /* list of used pages */
u64 len;
};
struct rbd_snap {
struct device dev;
const char *name;
size_t size;
struct list_head node;
u64 id;
};
/*
* a single device
*/
struct rbd_device {
int id; /* blkdev unique id */
int major; /* blkdev assigned major */
struct gendisk *disk; /* blkdev's gendisk and rq */
struct request_queue *q;
struct ceph_client *client;
struct rbd_client *rbd_client;
char name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */
spinlock_t lock; /* queue lock */
struct rbd_image_header header;
char obj[RBD_MAX_OBJ_NAME_LEN]; /* rbd image name */
int obj_len;
char obj_md_name[RBD_MAX_MD_NAME_LEN]; /* hdr nm. */
char pool_name[RBD_MAX_POOL_NAME_LEN];
int poolid;
struct ceph_osd_event *watch_event;
struct ceph_osd_request *watch_request;
char snap_name[RBD_MAX_SNAP_NAME_LEN];
u32 cur_snap; /* index+1 of current snapshot within snap context
0 - for the head */
int read_only;
struct list_head node;
/* list of snapshots */
struct list_head snaps;
/* sysfs related */
struct device dev;
};
static struct bus_type rbd_bus_type = {
.name = "rbd",
};
static spinlock_t node_lock; /* protects client get/put */
static DEFINE_MUTEX(ctl_mutex); /* Serialize open/close/setup/teardown */
static LIST_HEAD(rbd_dev_list); /* devices */
static LIST_HEAD(rbd_client_list); /* clients */
static int __rbd_init_snaps_header(struct rbd_device *rbd_dev);
static void rbd_dev_release(struct device *dev);
static ssize_t rbd_snap_rollback(struct device *dev,
struct device_attribute *attr,
const char *buf,
size_t size);
static ssize_t rbd_snap_add(struct device *dev,
struct device_attribute *attr,
const char *buf,
size_t count);
static void __rbd_remove_snap_dev(struct rbd_device *rbd_dev,
struct rbd_snap *snap);;
static struct rbd_device *dev_to_rbd(struct device *dev)
{
return container_of(dev, struct rbd_device, dev);
}
static struct device *rbd_get_dev(struct rbd_device *rbd_dev)
{
return get_device(&rbd_dev->dev);
}
static void rbd_put_dev(struct rbd_device *rbd_dev)
{
put_device(&rbd_dev->dev);
}
static int __rbd_update_snaps(struct rbd_device *rbd_dev);
static int rbd_open(struct block_device *bdev, fmode_t mode)
{
struct gendisk *disk = bdev->bd_disk;
struct rbd_device *rbd_dev = disk->private_data;
rbd_get_dev(rbd_dev);
set_device_ro(bdev, rbd_dev->read_only);
if ((mode & FMODE_WRITE) && rbd_dev->read_only)
return -EROFS;
return 0;
}
static int rbd_release(struct gendisk *disk, fmode_t mode)
{
struct rbd_device *rbd_dev = disk->private_data;
rbd_put_dev(rbd_dev);
return 0;
}
static const struct block_device_operations rbd_bd_ops = {
.owner = THIS_MODULE,
.open = rbd_open,
.release = rbd_release,
};
/*
* Initialize an rbd client instance.
* We own *opt.
*/
static struct rbd_client *rbd_client_create(struct ceph_options *opt,
struct rbd_options *rbd_opts)
{
struct rbd_client *rbdc;
int ret = -ENOMEM;
dout("rbd_client_create\n");
rbdc = kmalloc(sizeof(struct rbd_client), GFP_KERNEL);
if (!rbdc)
goto out_opt;
kref_init(&rbdc->kref);
INIT_LIST_HEAD(&rbdc->node);
rbdc->client = ceph_create_client(opt, rbdc);
if (IS_ERR(rbdc->client))
goto out_rbdc;
opt = NULL; /* Now rbdc->client is responsible for opt */
ret = ceph_open_session(rbdc->client);
if (ret < 0)
goto out_err;
rbdc->rbd_opts = rbd_opts;
spin_lock(&node_lock);
list_add_tail(&rbdc->node, &rbd_client_list);
spin_unlock(&node_lock);
dout("rbd_client_create created %p\n", rbdc);
return rbdc;
out_err:
ceph_destroy_client(rbdc->client);
out_rbdc:
kfree(rbdc);
out_opt:
if (opt)
ceph_destroy_options(opt);
return ERR_PTR(ret);
}
/*
* Find a ceph client with specific addr and configuration.
*/
static struct rbd_client *__rbd_client_find(struct ceph_options *opt)
{
struct rbd_client *client_node;
if (opt->flags & CEPH_OPT_NOSHARE)
return NULL;
list_for_each_entry(client_node, &rbd_client_list, node)
if (ceph_compare_options(opt, client_node->client) == 0)
return client_node;
return NULL;
}
/*
* mount options
*/
enum {
Opt_notify_timeout,
Opt_last_int,
/* int args above */
Opt_last_string,
/* string args above */
};
static match_table_t rbdopt_tokens = {
{Opt_notify_timeout, "notify_timeout=%d"},
/* int args above */
/* string args above */
{-1, NULL}
};
static int parse_rbd_opts_token(char *c, void *private)
{
struct rbd_options *rbdopt = private;
substring_t argstr[MAX_OPT_ARGS];
int token, intval, ret;
token = match_token((char *)c, rbdopt_tokens, argstr);
if (token < 0)
return -EINVAL;
if (token < Opt_last_int) {
ret = match_int(&argstr[0], &intval);
if (ret < 0) {
pr_err("bad mount option arg (not int) "
"at '%s'\n", c);
return ret;
}
dout("got int token %d val %d\n", token, intval);
} else if (token > Opt_last_int && token < Opt_last_string) {
dout("got string token %d val %s\n", token,
argstr[0].from);
} else {
dout("got token %d\n", token);
}
switch (token) {
case Opt_notify_timeout:
rbdopt->notify_timeout = intval;
break;
default:
BUG_ON(token);
}
return 0;
}
/*
* Get a ceph client with specific addr and configuration, if one does
* not exist create it.
*/
static int rbd_get_client(struct rbd_device *rbd_dev, const char *mon_addr,
char *options)
{
struct rbd_client *rbdc;
struct ceph_options *opt;
int ret;
struct rbd_options *rbd_opts;
rbd_opts = kzalloc(sizeof(*rbd_opts), GFP_KERNEL);
if (!rbd_opts)
return -ENOMEM;
rbd_opts->notify_timeout = RBD_NOTIFY_TIMEOUT_DEFAULT;
ret = ceph_parse_options(&opt, options, mon_addr,
mon_addr + strlen(mon_addr), parse_rbd_opts_token, rbd_opts);
if (ret < 0)
goto done_err;
spin_lock(&node_lock);
rbdc = __rbd_client_find(opt);
if (rbdc) {
ceph_destroy_options(opt);
/* using an existing client */
kref_get(&rbdc->kref);
rbd_dev->rbd_client = rbdc;
rbd_dev->client = rbdc->client;
spin_unlock(&node_lock);
return 0;
}
spin_unlock(&node_lock);
rbdc = rbd_client_create(opt, rbd_opts);
if (IS_ERR(rbdc)) {
ret = PTR_ERR(rbdc);
goto done_err;
}
rbd_dev->rbd_client = rbdc;
rbd_dev->client = rbdc->client;
return 0;
done_err:
kfree(rbd_opts);
return ret;
}
/*
* Destroy ceph client
*/
static void rbd_client_release(struct kref *kref)
{
struct rbd_client *rbdc = container_of(kref, struct rbd_client, kref);
dout("rbd_release_client %p\n", rbdc);
spin_lock(&node_lock);
list_del(&rbdc->node);
spin_unlock(&node_lock);
ceph_destroy_client(rbdc->client);
kfree(rbdc->rbd_opts);
kfree(rbdc);
}
/*
* Drop reference to ceph client node. If it's not referenced anymore, release
* it.
*/
static void rbd_put_client(struct rbd_device *rbd_dev)
{
kref_put(&rbd_dev->rbd_client->kref, rbd_client_release);
rbd_dev->rbd_client = NULL;
rbd_dev->client = NULL;
}
/*
* Create a new header structure, translate header format from the on-disk
* header.
*/
static int rbd_header_from_disk(struct rbd_image_header *header,
struct rbd_image_header_ondisk *ondisk,
int allocated_snaps,
gfp_t gfp_flags)
{
int i;
u32 snap_count = le32_to_cpu(ondisk->snap_count);
int ret = -ENOMEM;
init_rwsem(&header->snap_rwsem);
header->snap_names_len = le64_to_cpu(ondisk->snap_names_len);
header->snapc = kmalloc(sizeof(struct ceph_snap_context) +
snap_count *
sizeof(struct rbd_image_snap_ondisk),
gfp_flags);
if (!header->snapc)
return -ENOMEM;
if (snap_count) {
header->snap_names = kmalloc(header->snap_names_len,
GFP_KERNEL);
if (!header->snap_names)
goto err_snapc;
header->snap_sizes = kmalloc(snap_count * sizeof(u64),
GFP_KERNEL);
if (!header->snap_sizes)
goto err_names;
} else {
header->snap_names = NULL;
header->snap_sizes = NULL;
}
memcpy(header->block_name, ondisk->block_name,
sizeof(ondisk->block_name));
header->image_size = le64_to_cpu(ondisk->image_size);
header->obj_order = ondisk->options.order;
header->crypt_type = ondisk->options.crypt_type;
header->comp_type = ondisk->options.comp_type;
atomic_set(&header->snapc->nref, 1);
header->snap_seq = le64_to_cpu(ondisk->snap_seq);
header->snapc->num_snaps = snap_count;
header->total_snaps = snap_count;
if (snap_count &&
allocated_snaps == snap_count) {
for (i = 0; i < snap_count; i++) {
header->snapc->snaps[i] =
le64_to_cpu(ondisk->snaps[i].id);
header->snap_sizes[i] =
le64_to_cpu(ondisk->snaps[i].image_size);
}
/* copy snapshot names */
memcpy(header->snap_names, &ondisk->snaps[i],
header->snap_names_len);
}
return 0;
err_names:
kfree(header->snap_names);
err_snapc:
kfree(header->snapc);
return ret;
}
static int snap_index(struct rbd_image_header *header, int snap_num)
{
return header->total_snaps - snap_num;
}
static u64 cur_snap_id(struct rbd_device *rbd_dev)
{
struct rbd_image_header *header = &rbd_dev->header;
if (!rbd_dev->cur_snap)
return 0;
return header->snapc->snaps[snap_index(header, rbd_dev->cur_snap)];
}
static int snap_by_name(struct rbd_image_header *header, const char *snap_name,
u64 *seq, u64 *size)
{
int i;
char *p = header->snap_names;
for (i = 0; i < header->total_snaps; i++, p += strlen(p) + 1) {
if (strcmp(snap_name, p) == 0)
break;
}
if (i == header->total_snaps)
return -ENOENT;
if (seq)
*seq = header->snapc->snaps[i];
if (size)
*size = header->snap_sizes[i];
return i;
}
static int rbd_header_set_snap(struct rbd_device *dev,
const char *snap_name,
u64 *size)
{
struct rbd_image_header *header = &dev->header;
struct ceph_snap_context *snapc = header->snapc;
int ret = -ENOENT;
down_write(&header->snap_rwsem);
if (!snap_name ||
!*snap_name ||
strcmp(snap_name, "-") == 0 ||
strcmp(snap_name, RBD_SNAP_HEAD_NAME) == 0) {
if (header->total_snaps)
snapc->seq = header->snap_seq;
else
snapc->seq = 0;
dev->cur_snap = 0;
dev->read_only = 0;
if (size)
*size = header->image_size;
} else {
ret = snap_by_name(header, snap_name, &snapc->seq, size);
if (ret < 0)
goto done;
dev->cur_snap = header->total_snaps - ret;
dev->read_only = 1;
}
ret = 0;
done:
up_write(&header->snap_rwsem);
return ret;
}
static void rbd_header_free(struct rbd_image_header *header)
{
kfree(header->snapc);
kfree(header->snap_names);
kfree(header->snap_sizes);
}
/*
* get the actual striped segment name, offset and length
*/
static u64 rbd_get_segment(struct rbd_image_header *header,
const char *block_name,
u64 ofs, u64 len,
char *seg_name, u64 *segofs)
{
u64 seg = ofs >> header->obj_order;
if (seg_name)
snprintf(seg_name, RBD_MAX_SEG_NAME_LEN,
"%s.%012llx", block_name, seg);
ofs = ofs & ((1 << header->obj_order) - 1);
len = min_t(u64, len, (1 << header->obj_order) - ofs);
if (segofs)
*segofs = ofs;
return len;
}
/*
* bio helpers
*/
static void bio_chain_put(struct bio *chain)
{
struct bio *tmp;
while (chain) {
tmp = chain;
chain = chain->bi_next;
bio_put(tmp);
}
}
/*
* zeros a bio chain, starting at specific offset
*/
static void zero_bio_chain(struct bio *chain, int start_ofs)
{
struct bio_vec *bv;
unsigned long flags;
void *buf;
int i;
int pos = 0;
while (chain) {
bio_for_each_segment(bv, chain, i) {
if (pos + bv->bv_len > start_ofs) {
int remainder = max(start_ofs - pos, 0);
buf = bvec_kmap_irq(bv, &flags);
memset(buf + remainder, 0,
bv->bv_len - remainder);
bvec_kunmap_irq(buf, &flags);
}
pos += bv->bv_len;
}
chain = chain->bi_next;
}
}
/*
* bio_chain_clone - clone a chain of bios up to a certain length.
* might return a bio_pair that will need to be released.
*/
static struct bio *bio_chain_clone(struct bio **old, struct bio **next,
struct bio_pair **bp,
int len, gfp_t gfpmask)
{
struct bio *tmp, *old_chain = *old, *new_chain = NULL, *tail = NULL;
int total = 0;
if (*bp) {
bio_pair_release(*bp);
*bp = NULL;
}
while (old_chain && (total < len)) {
tmp = bio_kmalloc(gfpmask, old_chain->bi_max_vecs);
if (!tmp)
goto err_out;
if (total + old_chain->bi_size > len) {
struct bio_pair *bp;
/*
* this split can only happen with a single paged bio,
* split_bio will BUG_ON if this is not the case
*/
dout("bio_chain_clone split! total=%d remaining=%d"
"bi_size=%d\n",
(int)total, (int)len-total,
(int)old_chain->bi_size);
/* split the bio. We'll release it either in the next
call, or it will have to be released outside */
bp = bio_split(old_chain, (len - total) / 512ULL);
if (!bp)
goto err_out;
__bio_clone(tmp, &bp->bio1);
*next = &bp->bio2;
} else {
__bio_clone(tmp, old_chain);
*next = old_chain->bi_next;
}
tmp->bi_bdev = NULL;
gfpmask &= ~__GFP_WAIT;
tmp->bi_next = NULL;
if (!new_chain) {
new_chain = tail = tmp;
} else {
tail->bi_next = tmp;
tail = tmp;
}
old_chain = old_chain->bi_next;
total += tmp->bi_size;
}
BUG_ON(total < len);
if (tail)
tail->bi_next = NULL;
*old = old_chain;
return new_chain;
err_out:
dout("bio_chain_clone with err\n");
bio_chain_put(new_chain);
return NULL;
}
/*
* helpers for osd request op vectors.
*/
static int rbd_create_rw_ops(struct ceph_osd_req_op **ops,
int num_ops,
int opcode,
u32 payload_len)
{
*ops = kzalloc(sizeof(struct ceph_osd_req_op) * (num_ops + 1),
GFP_NOIO);
if (!*ops)
return -ENOMEM;
(*ops)[0].op = opcode;
/*
* op extent offset and length will be set later on
* in calc_raw_layout()
*/
(*ops)[0].payload_len = payload_len;
return 0;
}
static void rbd_destroy_ops(struct ceph_osd_req_op *ops)
{
kfree(ops);
}
/*
* Send ceph osd request
*/
static int rbd_do_request(struct request *rq,
struct rbd_device *dev,
struct ceph_snap_context *snapc,
u64 snapid,
const char *obj, u64 ofs, u64 len,
struct bio *bio,
struct page **pages,
int num_pages,
int flags,
struct ceph_osd_req_op *ops,
int num_reply,
void (*rbd_cb)(struct ceph_osd_request *req,
struct ceph_msg *msg),
struct ceph_osd_request **linger_req,
u64 *ver)
{
struct ceph_osd_request *req;
struct ceph_file_layout *layout;
int ret;
u64 bno;
struct timespec mtime = CURRENT_TIME;
struct rbd_request *req_data;
struct ceph_osd_request_head *reqhead;
struct rbd_image_header *header = &dev->header;
ret = -ENOMEM;
req_data = kzalloc(sizeof(*req_data), GFP_NOIO);
if (!req_data)
goto done;
dout("rbd_do_request len=%lld ofs=%lld\n", len, ofs);
down_read(&header->snap_rwsem);
req = ceph_osdc_alloc_request(&dev->client->osdc, flags,
snapc,
ops,
false,
GFP_NOIO, pages, bio);
if (IS_ERR(req)) {
up_read(&header->snap_rwsem);
ret = PTR_ERR(req);
goto done_pages;
}
req->r_callback = rbd_cb;
req_data->rq = rq;
req_data->bio = bio;
req_data->pages = pages;
req_data->len = len;
req->r_priv = req_data;
reqhead = req->r_request->front.iov_base;
reqhead->snapid = cpu_to_le64(CEPH_NOSNAP);
strncpy(req->r_oid, obj, sizeof(req->r_oid));
req->r_oid_len = strlen(req->r_oid);
layout = &req->r_file_layout;
memset(layout, 0, sizeof(*layout));
layout->fl_stripe_unit = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
layout->fl_stripe_count = cpu_to_le32(1);
layout->fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
layout->fl_pg_preferred = cpu_to_le32(-1);
layout->fl_pg_pool = cpu_to_le32(dev->poolid);
ceph_calc_raw_layout(&dev->client->osdc, layout, snapid,
ofs, &len, &bno, req, ops);
ceph_osdc_build_request(req, ofs, &len,
ops,
snapc,
&mtime,
req->r_oid, req->r_oid_len);
up_read(&header->snap_rwsem);
if (linger_req) {
ceph_osdc_set_request_linger(&dev->client->osdc, req);
*linger_req = req;
}
ret = ceph_osdc_start_request(&dev->client->osdc, req, false);
if (ret < 0)
goto done_err;
if (!rbd_cb) {
ret = ceph_osdc_wait_request(&dev->client->osdc, req);
if (ver)
*ver = le64_to_cpu(req->r_reassert_version.version);
dout("reassert_ver=%lld\n", le64_to_cpu(req->r_reassert_version.version));
ceph_osdc_put_request(req);
}
return ret;
done_err:
bio_chain_put(req_data->bio);
ceph_osdc_put_request(req);
done_pages:
kfree(req_data);
done:
if (rq)
blk_end_request(rq, ret, len);
return ret;
}
/*
* Ceph osd op callback
*/
static void rbd_req_cb(struct ceph_osd_request *req, struct ceph_msg *msg)
{
struct rbd_request *req_data = req->r_priv;
struct ceph_osd_reply_head *replyhead;
struct ceph_osd_op *op;
__s32 rc;
u64 bytes;
int read_op;
/* parse reply */
replyhead = msg->front.iov_base;
WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
op = (void *)(replyhead + 1);
rc = le32_to_cpu(replyhead->result);
bytes = le64_to_cpu(op->extent.length);
read_op = (le32_to_cpu(op->op) == CEPH_OSD_OP_READ);
dout("rbd_req_cb bytes=%lld readop=%d rc=%d\n", bytes, read_op, rc);
if (rc == -ENOENT && read_op) {
zero_bio_chain(req_data->bio, 0);
rc = 0;
} else if (rc == 0 && read_op && bytes < req_data->len) {
zero_bio_chain(req_data->bio, bytes);
bytes = req_data->len;
}
blk_end_request(req_data->rq, rc, bytes);
if (req_data->bio)
bio_chain_put(req_data->bio);
ceph_osdc_put_request(req);
kfree(req_data);
}
static void rbd_simple_req_cb(struct ceph_osd_request *req, struct ceph_msg *msg)
{
ceph_osdc_put_request(req);
}
/*
* Do a synchronous ceph osd operation
*/
static int rbd_req_sync_op(struct rbd_device *dev,
struct ceph_snap_context *snapc,
u64 snapid,
int opcode,
int flags,
struct ceph_osd_req_op *orig_ops,
int num_reply,
const char *obj,
u64 ofs, u64 len,
char *buf,
struct ceph_osd_request **linger_req,
u64 *ver)
{
int ret;
struct page **pages;
int num_pages;
struct ceph_osd_req_op *ops = orig_ops;
u32 payload_len;
num_pages = calc_pages_for(ofs , len);
pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
if (IS_ERR(pages))
return PTR_ERR(pages);
if (!orig_ops) {
payload_len = (flags & CEPH_OSD_FLAG_WRITE ? len : 0);
ret = rbd_create_rw_ops(&ops, 1, opcode, payload_len);
if (ret < 0)
goto done;
if ((flags & CEPH_OSD_FLAG_WRITE) && buf) {
ret = ceph_copy_to_page_vector(pages, buf, ofs, len);
if (ret < 0)
goto done_ops;
}
}
ret = rbd_do_request(NULL, dev, snapc, snapid,
obj, ofs, len, NULL,
pages, num_pages,
flags,
ops,
2,
NULL,
linger_req, ver);
if (ret < 0)
goto done_ops;
if ((flags & CEPH_OSD_FLAG_READ) && buf)
ret = ceph_copy_from_page_vector(pages, buf, ofs, ret);
done_ops:
if (!orig_ops)
rbd_destroy_ops(ops);
done:
ceph_release_page_vector(pages, num_pages);
return ret;
}
/*
* Do an asynchronous ceph osd operation
*/
static int rbd_do_op(struct request *rq,
struct rbd_device *rbd_dev ,
struct ceph_snap_context *snapc,
u64 snapid,
int opcode, int flags, int num_reply,
u64 ofs, u64 len,
struct bio *bio)
{
char *seg_name;
u64 seg_ofs;
u64 seg_len;
int ret;
struct ceph_osd_req_op *ops;
u32 payload_len;
seg_name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO);
if (!seg_name)
return -ENOMEM;
seg_len = rbd_get_segment(&rbd_dev->header,
rbd_dev->header.block_name,
ofs, len,
seg_name, &seg_ofs);
payload_len = (flags & CEPH_OSD_FLAG_WRITE ? seg_len : 0);
ret = rbd_create_rw_ops(&ops, 1, opcode, payload_len);
if (ret < 0)
goto done;
/* we've taken care of segment sizes earlier when we
cloned the bios. We should never have a segment
truncated at this point */
BUG_ON(seg_len < len);
ret = rbd_do_request(rq, rbd_dev, snapc, snapid,
seg_name, seg_ofs, seg_len,
bio,
NULL, 0,
flags,
ops,
num_reply,
rbd_req_cb, 0, NULL);
done:
kfree(seg_name);