forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmon_client.c
1490 lines (1244 loc) · 35.6 KB
/
mon_client.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/module.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/ceph/ceph_features.h>
#include <linux/ceph/mon_client.h>
#include <linux/ceph/libceph.h>
#include <linux/ceph/debugfs.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/auth.h>
/*
* Interact with Ceph monitor cluster. Handle requests for new map
* versions, and periodically resend as needed. Also implement
* statfs() and umount().
*
* A small cluster of Ceph "monitors" are responsible for managing critical
* cluster configuration and state information. An odd number (e.g., 3, 5)
* of cmon daemons use a modified version of the Paxos part-time parliament
* algorithm to manage the MDS map (mds cluster membership), OSD map, and
* list of clients who have mounted the file system.
*
* We maintain an open, active session with a monitor at all times in order to
* receive timely MDSMap updates. We periodically send a keepalive byte on the
* TCP socket to ensure we detect a failure. If the connection does break, we
* randomly hunt for a new monitor. Once the connection is reestablished, we
* resend any outstanding requests.
*/
static const struct ceph_connection_operations mon_con_ops;
static int __validate_auth(struct ceph_mon_client *monc);
static int decode_mon_info(void **p, void *end, bool msgr2,
struct ceph_entity_addr *addr)
{
void *mon_info_end;
u32 struct_len;
u8 struct_v;
int ret;
ret = ceph_start_decoding(p, end, 1, "mon_info_t", &struct_v,
&struct_len);
if (ret)
return ret;
mon_info_end = *p + struct_len;
ceph_decode_skip_string(p, end, e_inval); /* skip mon name */
ret = ceph_decode_entity_addrvec(p, end, msgr2, addr);
if (ret)
return ret;
*p = mon_info_end;
return 0;
e_inval:
return -EINVAL;
}
/*
* Decode a monmap blob (e.g., during mount).
*
* Assume MonMap v3 (i.e. encoding with MONNAMES and MONENC).
*/
static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
{
struct ceph_monmap *monmap = NULL;
struct ceph_fsid fsid;
u32 struct_len;
int blob_len;
int num_mon;
u8 struct_v;
u32 epoch;
int ret;
int i;
ceph_decode_32_safe(p, end, blob_len, e_inval);
ceph_decode_need(p, end, blob_len, e_inval);
ret = ceph_start_decoding(p, end, 6, "monmap", &struct_v, &struct_len);
if (ret)
goto fail;
dout("%s struct_v %d\n", __func__, struct_v);
ceph_decode_copy_safe(p, end, &fsid, sizeof(fsid), e_inval);
ceph_decode_32_safe(p, end, epoch, e_inval);
if (struct_v >= 6) {
u32 feat_struct_len;
u8 feat_struct_v;
*p += sizeof(struct ceph_timespec); /* skip last_changed */
*p += sizeof(struct ceph_timespec); /* skip created */
ret = ceph_start_decoding(p, end, 1, "mon_feature_t",
&feat_struct_v, &feat_struct_len);
if (ret)
goto fail;
*p += feat_struct_len; /* skip persistent_features */
ret = ceph_start_decoding(p, end, 1, "mon_feature_t",
&feat_struct_v, &feat_struct_len);
if (ret)
goto fail;
*p += feat_struct_len; /* skip optional_features */
}
ceph_decode_32_safe(p, end, num_mon, e_inval);
dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch,
num_mon);
if (num_mon > CEPH_MAX_MON)
goto e_inval;
monmap = kmalloc(struct_size(monmap, mon_inst, num_mon), GFP_NOIO);
if (!monmap) {
ret = -ENOMEM;
goto fail;
}
monmap->fsid = fsid;
monmap->epoch = epoch;
monmap->num_mon = num_mon;
/* legacy_mon_addr map or mon_info map */
for (i = 0; i < num_mon; i++) {
struct ceph_entity_inst *inst = &monmap->mon_inst[i];
ceph_decode_skip_string(p, end, e_inval); /* skip mon name */
inst->name.type = CEPH_ENTITY_TYPE_MON;
inst->name.num = cpu_to_le64(i);
if (struct_v >= 6)
ret = decode_mon_info(p, end, msgr2, &inst->addr);
else
ret = ceph_decode_entity_addr(p, end, &inst->addr);
if (ret)
goto fail;
dout("%s mon%d addr %s\n", __func__, i,
ceph_pr_addr(&inst->addr));
}
return monmap;
e_inval:
ret = -EINVAL;
fail:
kfree(monmap);
return ERR_PTR(ret);
}
/*
* return true if *addr is included in the monmap.
*/
int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr)
{
int i;
for (i = 0; i < m->num_mon; i++) {
if (ceph_addr_equal_no_type(addr, &m->mon_inst[i].addr))
return 1;
}
return 0;
}
/*
* Send an auth request.
*/
static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len)
{
monc->pending_auth = 1;
monc->m_auth->front.iov_len = len;
monc->m_auth->hdr.front_len = cpu_to_le32(len);
ceph_msg_revoke(monc->m_auth);
ceph_msg_get(monc->m_auth); /* keep our ref */
ceph_con_send(&monc->con, monc->m_auth);
}
/*
* Close monitor session, if any.
*/
static void __close_session(struct ceph_mon_client *monc)
{
dout("__close_session closing mon%d\n", monc->cur_mon);
ceph_msg_revoke(monc->m_auth);
ceph_msg_revoke_incoming(monc->m_auth_reply);
ceph_msg_revoke(monc->m_subscribe);
ceph_msg_revoke_incoming(monc->m_subscribe_ack);
ceph_con_close(&monc->con);
monc->pending_auth = 0;
ceph_auth_reset(monc->auth);
}
/*
* Pick a new monitor at random and set cur_mon. If we are repicking
* (i.e. cur_mon is already set), be sure to pick a different one.
*/
static void pick_new_mon(struct ceph_mon_client *monc)
{
int old_mon = monc->cur_mon;
BUG_ON(monc->monmap->num_mon < 1);
if (monc->monmap->num_mon == 1) {
monc->cur_mon = 0;
} else {
int max = monc->monmap->num_mon;
int o = -1;
int n;
if (monc->cur_mon >= 0) {
if (monc->cur_mon < monc->monmap->num_mon)
o = monc->cur_mon;
if (o >= 0)
max--;
}
n = prandom_u32() % max;
if (o >= 0 && n >= o)
n++;
monc->cur_mon = n;
}
dout("%s mon%d -> mon%d out of %d mons\n", __func__, old_mon,
monc->cur_mon, monc->monmap->num_mon);
}
/*
* Open a session with a new monitor.
*/
static void __open_session(struct ceph_mon_client *monc)
{
int ret;
pick_new_mon(monc);
monc->hunting = true;
if (monc->had_a_connection) {
monc->hunt_mult *= CEPH_MONC_HUNT_BACKOFF;
if (monc->hunt_mult > CEPH_MONC_HUNT_MAX_MULT)
monc->hunt_mult = CEPH_MONC_HUNT_MAX_MULT;
}
monc->sub_renew_after = jiffies; /* i.e., expired */
monc->sub_renew_sent = 0;
dout("%s opening mon%d\n", __func__, monc->cur_mon);
ceph_con_open(&monc->con, CEPH_ENTITY_TYPE_MON, monc->cur_mon,
&monc->monmap->mon_inst[monc->cur_mon].addr);
/*
* send an initial keepalive to ensure our timestamp is valid
* by the time we are in an OPENED state
*/
ceph_con_keepalive(&monc->con);
/* initiate authentication handshake */
ret = ceph_auth_build_hello(monc->auth,
monc->m_auth->front.iov_base,
monc->m_auth->front_alloc_len);
BUG_ON(ret <= 0);
__send_prepared_auth_request(monc, ret);
}
static void reopen_session(struct ceph_mon_client *monc)
{
if (!monc->hunting)
pr_info("mon%d %s session lost, hunting for new mon\n",
monc->cur_mon, ceph_pr_addr(&monc->con.peer_addr));
__close_session(monc);
__open_session(monc);
}
void ceph_monc_reopen_session(struct ceph_mon_client *monc)
{
mutex_lock(&monc->mutex);
reopen_session(monc);
mutex_unlock(&monc->mutex);
}
static void un_backoff(struct ceph_mon_client *monc)
{
monc->hunt_mult /= 2; /* reduce by 50% */
if (monc->hunt_mult < 1)
monc->hunt_mult = 1;
dout("%s hunt_mult now %d\n", __func__, monc->hunt_mult);
}
/*
* Reschedule delayed work timer.
*/
static void __schedule_delayed(struct ceph_mon_client *monc)
{
unsigned long delay;
if (monc->hunting)
delay = CEPH_MONC_HUNT_INTERVAL * monc->hunt_mult;
else
delay = CEPH_MONC_PING_INTERVAL;
dout("__schedule_delayed after %lu\n", delay);
mod_delayed_work(system_wq, &monc->delayed_work,
round_jiffies_relative(delay));
}
const char *ceph_sub_str[] = {
[CEPH_SUB_MONMAP] = "monmap",
[CEPH_SUB_OSDMAP] = "osdmap",
[CEPH_SUB_FSMAP] = "fsmap.user",
[CEPH_SUB_MDSMAP] = "mdsmap",
};
/*
* Send subscribe request for one or more maps, according to
* monc->subs.
*/
static void __send_subscribe(struct ceph_mon_client *monc)
{
struct ceph_msg *msg = monc->m_subscribe;
void *p = msg->front.iov_base;
void *const end = p + msg->front_alloc_len;
int num = 0;
int i;
dout("%s sent %lu\n", __func__, monc->sub_renew_sent);
BUG_ON(monc->cur_mon < 0);
if (!monc->sub_renew_sent)
monc->sub_renew_sent = jiffies | 1; /* never 0 */
msg->hdr.version = cpu_to_le16(2);
for (i = 0; i < ARRAY_SIZE(monc->subs); i++) {
if (monc->subs[i].want)
num++;
}
BUG_ON(num < 1); /* monmap sub is always there */
ceph_encode_32(&p, num);
for (i = 0; i < ARRAY_SIZE(monc->subs); i++) {
char buf[32];
int len;
if (!monc->subs[i].want)
continue;
len = sprintf(buf, "%s", ceph_sub_str[i]);
if (i == CEPH_SUB_MDSMAP &&
monc->fs_cluster_id != CEPH_FS_CLUSTER_ID_NONE)
len += sprintf(buf + len, ".%d", monc->fs_cluster_id);
dout("%s %s start %llu flags 0x%x\n", __func__, buf,
le64_to_cpu(monc->subs[i].item.start),
monc->subs[i].item.flags);
ceph_encode_string(&p, end, buf, len);
memcpy(p, &monc->subs[i].item, sizeof(monc->subs[i].item));
p += sizeof(monc->subs[i].item);
}
BUG_ON(p > end);
msg->front.iov_len = p - msg->front.iov_base;
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
ceph_msg_revoke(msg);
ceph_con_send(&monc->con, ceph_msg_get(msg));
}
static void handle_subscribe_ack(struct ceph_mon_client *monc,
struct ceph_msg *msg)
{
unsigned int seconds;
struct ceph_mon_subscribe_ack *h = msg->front.iov_base;
if (msg->front.iov_len < sizeof(*h))
goto bad;
seconds = le32_to_cpu(h->duration);
mutex_lock(&monc->mutex);
if (monc->sub_renew_sent) {
/*
* This is only needed for legacy (infernalis or older)
* MONs -- see delayed_work().
*/
monc->sub_renew_after = monc->sub_renew_sent +
(seconds >> 1) * HZ - 1;
dout("%s sent %lu duration %d renew after %lu\n", __func__,
monc->sub_renew_sent, seconds, monc->sub_renew_after);
monc->sub_renew_sent = 0;
} else {
dout("%s sent %lu renew after %lu, ignoring\n", __func__,
monc->sub_renew_sent, monc->sub_renew_after);
}
mutex_unlock(&monc->mutex);
return;
bad:
pr_err("got corrupt subscribe-ack msg\n");
ceph_msg_dump(msg);
}
/*
* Register interest in a map
*
* @sub: one of CEPH_SUB_*
* @epoch: X for "every map since X", or 0 for "just the latest"
*/
static bool __ceph_monc_want_map(struct ceph_mon_client *monc, int sub,
u32 epoch, bool continuous)
{
__le64 start = cpu_to_le64(epoch);
u8 flags = !continuous ? CEPH_SUBSCRIBE_ONETIME : 0;
dout("%s %s epoch %u continuous %d\n", __func__, ceph_sub_str[sub],
epoch, continuous);
if (monc->subs[sub].want &&
monc->subs[sub].item.start == start &&
monc->subs[sub].item.flags == flags)
return false;
monc->subs[sub].item.start = start;
monc->subs[sub].item.flags = flags;
monc->subs[sub].want = true;
return true;
}
bool ceph_monc_want_map(struct ceph_mon_client *monc, int sub, u32 epoch,
bool continuous)
{
bool need_request;
mutex_lock(&monc->mutex);
need_request = __ceph_monc_want_map(monc, sub, epoch, continuous);
mutex_unlock(&monc->mutex);
return need_request;
}
EXPORT_SYMBOL(ceph_monc_want_map);
/*
* Keep track of which maps we have
*
* @sub: one of CEPH_SUB_*
*/
static void __ceph_monc_got_map(struct ceph_mon_client *monc, int sub,
u32 epoch)
{
dout("%s %s epoch %u\n", __func__, ceph_sub_str[sub], epoch);
if (monc->subs[sub].want) {
if (monc->subs[sub].item.flags & CEPH_SUBSCRIBE_ONETIME)
monc->subs[sub].want = false;
else
monc->subs[sub].item.start = cpu_to_le64(epoch + 1);
}
monc->subs[sub].have = epoch;
}
void ceph_monc_got_map(struct ceph_mon_client *monc, int sub, u32 epoch)
{
mutex_lock(&monc->mutex);
__ceph_monc_got_map(monc, sub, epoch);
mutex_unlock(&monc->mutex);
}
EXPORT_SYMBOL(ceph_monc_got_map);
void ceph_monc_renew_subs(struct ceph_mon_client *monc)
{
mutex_lock(&monc->mutex);
__send_subscribe(monc);
mutex_unlock(&monc->mutex);
}
EXPORT_SYMBOL(ceph_monc_renew_subs);
/*
* Wait for an osdmap with a given epoch.
*
* @epoch: epoch to wait for
* @timeout: in jiffies, 0 means "wait forever"
*/
int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
unsigned long timeout)
{
unsigned long started = jiffies;
long ret;
mutex_lock(&monc->mutex);
while (monc->subs[CEPH_SUB_OSDMAP].have < epoch) {
mutex_unlock(&monc->mutex);
if (timeout && time_after_eq(jiffies, started + timeout))
return -ETIMEDOUT;
ret = wait_event_interruptible_timeout(monc->client->auth_wq,
monc->subs[CEPH_SUB_OSDMAP].have >= epoch,
ceph_timeout_jiffies(timeout));
if (ret < 0)
return ret;
mutex_lock(&monc->mutex);
}
mutex_unlock(&monc->mutex);
return 0;
}
EXPORT_SYMBOL(ceph_monc_wait_osdmap);
/*
* Open a session with a random monitor. Request monmap and osdmap,
* which are waited upon in __ceph_open_session().
*/
int ceph_monc_open_session(struct ceph_mon_client *monc)
{
mutex_lock(&monc->mutex);
__ceph_monc_want_map(monc, CEPH_SUB_MONMAP, 0, true);
__ceph_monc_want_map(monc, CEPH_SUB_OSDMAP, 0, false);
__open_session(monc);
__schedule_delayed(monc);
mutex_unlock(&monc->mutex);
return 0;
}
EXPORT_SYMBOL(ceph_monc_open_session);
static void ceph_monc_handle_map(struct ceph_mon_client *monc,
struct ceph_msg *msg)
{
struct ceph_client *client = monc->client;
struct ceph_monmap *monmap;
void *p, *end;
mutex_lock(&monc->mutex);
dout("handle_monmap\n");
p = msg->front.iov_base;
end = p + msg->front.iov_len;
monmap = ceph_monmap_decode(&p, end, false);
if (IS_ERR(monmap)) {
pr_err("problem decoding monmap, %d\n",
(int)PTR_ERR(monmap));
ceph_msg_dump(msg);
goto out;
}
if (ceph_check_fsid(client, &monmap->fsid) < 0) {
kfree(monmap);
goto out;
}
kfree(monc->monmap);
monc->monmap = monmap;
__ceph_monc_got_map(monc, CEPH_SUB_MONMAP, monc->monmap->epoch);
client->have_fsid = true;
out:
mutex_unlock(&monc->mutex);
wake_up_all(&client->auth_wq);
}
/*
* generic requests (currently statfs, mon_get_version)
*/
DEFINE_RB_FUNCS(generic_request, struct ceph_mon_generic_request, tid, node)
static void release_generic_request(struct kref *kref)
{
struct ceph_mon_generic_request *req =
container_of(kref, struct ceph_mon_generic_request, kref);
dout("%s greq %p request %p reply %p\n", __func__, req, req->request,
req->reply);
WARN_ON(!RB_EMPTY_NODE(&req->node));
if (req->reply)
ceph_msg_put(req->reply);
if (req->request)
ceph_msg_put(req->request);
kfree(req);
}
static void put_generic_request(struct ceph_mon_generic_request *req)
{
if (req)
kref_put(&req->kref, release_generic_request);
}
static void get_generic_request(struct ceph_mon_generic_request *req)
{
kref_get(&req->kref);
}
static struct ceph_mon_generic_request *
alloc_generic_request(struct ceph_mon_client *monc, gfp_t gfp)
{
struct ceph_mon_generic_request *req;
req = kzalloc(sizeof(*req), gfp);
if (!req)
return NULL;
req->monc = monc;
kref_init(&req->kref);
RB_CLEAR_NODE(&req->node);
init_completion(&req->completion);
dout("%s greq %p\n", __func__, req);
return req;
}
static void register_generic_request(struct ceph_mon_generic_request *req)
{
struct ceph_mon_client *monc = req->monc;
WARN_ON(req->tid);
get_generic_request(req);
req->tid = ++monc->last_tid;
insert_generic_request(&monc->generic_request_tree, req);
}
static void send_generic_request(struct ceph_mon_client *monc,
struct ceph_mon_generic_request *req)
{
WARN_ON(!req->tid);
dout("%s greq %p tid %llu\n", __func__, req, req->tid);
req->request->hdr.tid = cpu_to_le64(req->tid);
ceph_con_send(&monc->con, ceph_msg_get(req->request));
}
static void __finish_generic_request(struct ceph_mon_generic_request *req)
{
struct ceph_mon_client *monc = req->monc;
dout("%s greq %p tid %llu\n", __func__, req, req->tid);
erase_generic_request(&monc->generic_request_tree, req);
ceph_msg_revoke(req->request);
ceph_msg_revoke_incoming(req->reply);
}
static void finish_generic_request(struct ceph_mon_generic_request *req)
{
__finish_generic_request(req);
put_generic_request(req);
}
static void complete_generic_request(struct ceph_mon_generic_request *req)
{
if (req->complete_cb)
req->complete_cb(req);
else
complete_all(&req->completion);
put_generic_request(req);
}
static void cancel_generic_request(struct ceph_mon_generic_request *req)
{
struct ceph_mon_client *monc = req->monc;
struct ceph_mon_generic_request *lookup_req;
dout("%s greq %p tid %llu\n", __func__, req, req->tid);
mutex_lock(&monc->mutex);
lookup_req = lookup_generic_request(&monc->generic_request_tree,
req->tid);
if (lookup_req) {
WARN_ON(lookup_req != req);
finish_generic_request(req);
}
mutex_unlock(&monc->mutex);
}
static int wait_generic_request(struct ceph_mon_generic_request *req)
{
int ret;
dout("%s greq %p tid %llu\n", __func__, req, req->tid);
ret = wait_for_completion_interruptible(&req->completion);
if (ret)
cancel_generic_request(req);
else
ret = req->result; /* completed */
return ret;
}
static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
struct ceph_msg_header *hdr,
int *skip)
{
struct ceph_mon_client *monc = con->private;
struct ceph_mon_generic_request *req;
u64 tid = le64_to_cpu(hdr->tid);
struct ceph_msg *m;
mutex_lock(&monc->mutex);
req = lookup_generic_request(&monc->generic_request_tree, tid);
if (!req) {
dout("get_generic_reply %lld dne\n", tid);
*skip = 1;
m = NULL;
} else {
dout("get_generic_reply %lld got %p\n", tid, req->reply);
*skip = 0;
m = ceph_msg_get(req->reply);
/*
* we don't need to track the connection reading into
* this reply because we only have one open connection
* at a time, ever.
*/
}
mutex_unlock(&monc->mutex);
return m;
}
/*
* statfs
*/
static void handle_statfs_reply(struct ceph_mon_client *monc,
struct ceph_msg *msg)
{
struct ceph_mon_generic_request *req;
struct ceph_mon_statfs_reply *reply = msg->front.iov_base;
u64 tid = le64_to_cpu(msg->hdr.tid);
dout("%s msg %p tid %llu\n", __func__, msg, tid);
if (msg->front.iov_len != sizeof(*reply))
goto bad;
mutex_lock(&monc->mutex);
req = lookup_generic_request(&monc->generic_request_tree, tid);
if (!req) {
mutex_unlock(&monc->mutex);
return;
}
req->result = 0;
*req->u.st = reply->st; /* struct */
__finish_generic_request(req);
mutex_unlock(&monc->mutex);
complete_generic_request(req);
return;
bad:
pr_err("corrupt statfs reply, tid %llu\n", tid);
ceph_msg_dump(msg);
}
/*
* Do a synchronous statfs().
*/
int ceph_monc_do_statfs(struct ceph_mon_client *monc, u64 data_pool,
struct ceph_statfs *buf)
{
struct ceph_mon_generic_request *req;
struct ceph_mon_statfs *h;
int ret = -ENOMEM;
req = alloc_generic_request(monc, GFP_NOFS);
if (!req)
goto out;
req->request = ceph_msg_new(CEPH_MSG_STATFS, sizeof(*h), GFP_NOFS,
true);
if (!req->request)
goto out;
req->reply = ceph_msg_new(CEPH_MSG_STATFS_REPLY, 64, GFP_NOFS, true);
if (!req->reply)
goto out;
req->u.st = buf;
req->request->hdr.version = cpu_to_le16(2);
mutex_lock(&monc->mutex);
register_generic_request(req);
/* fill out request */
h = req->request->front.iov_base;
h->monhdr.have_version = 0;
h->monhdr.session_mon = cpu_to_le16(-1);
h->monhdr.session_mon_tid = 0;
h->fsid = monc->monmap->fsid;
h->contains_data_pool = (data_pool != CEPH_NOPOOL);
h->data_pool = cpu_to_le64(data_pool);
send_generic_request(monc, req);
mutex_unlock(&monc->mutex);
ret = wait_generic_request(req);
out:
put_generic_request(req);
return ret;
}
EXPORT_SYMBOL(ceph_monc_do_statfs);
static void handle_get_version_reply(struct ceph_mon_client *monc,
struct ceph_msg *msg)
{
struct ceph_mon_generic_request *req;
u64 tid = le64_to_cpu(msg->hdr.tid);
void *p = msg->front.iov_base;
void *end = p + msg->front_alloc_len;
u64 handle;
dout("%s msg %p tid %llu\n", __func__, msg, tid);
ceph_decode_need(&p, end, 2*sizeof(u64), bad);
handle = ceph_decode_64(&p);
if (tid != 0 && tid != handle)
goto bad;
mutex_lock(&monc->mutex);
req = lookup_generic_request(&monc->generic_request_tree, handle);
if (!req) {
mutex_unlock(&monc->mutex);
return;
}
req->result = 0;
req->u.newest = ceph_decode_64(&p);
__finish_generic_request(req);
mutex_unlock(&monc->mutex);
complete_generic_request(req);
return;
bad:
pr_err("corrupt mon_get_version reply, tid %llu\n", tid);
ceph_msg_dump(msg);
}
static struct ceph_mon_generic_request *
__ceph_monc_get_version(struct ceph_mon_client *monc, const char *what,
ceph_monc_callback_t cb, u64 private_data)
{
struct ceph_mon_generic_request *req;
req = alloc_generic_request(monc, GFP_NOIO);
if (!req)
goto err_put_req;
req->request = ceph_msg_new(CEPH_MSG_MON_GET_VERSION,
sizeof(u64) + sizeof(u32) + strlen(what),
GFP_NOIO, true);
if (!req->request)
goto err_put_req;
req->reply = ceph_msg_new(CEPH_MSG_MON_GET_VERSION_REPLY, 32, GFP_NOIO,
true);
if (!req->reply)
goto err_put_req;
req->complete_cb = cb;
req->private_data = private_data;
mutex_lock(&monc->mutex);
register_generic_request(req);
{
void *p = req->request->front.iov_base;
void *const end = p + req->request->front_alloc_len;
ceph_encode_64(&p, req->tid); /* handle */
ceph_encode_string(&p, end, what, strlen(what));
WARN_ON(p != end);
}
send_generic_request(monc, req);
mutex_unlock(&monc->mutex);
return req;
err_put_req:
put_generic_request(req);
return ERR_PTR(-ENOMEM);
}
/*
* Send MMonGetVersion and wait for the reply.
*
* @what: one of "mdsmap", "osdmap" or "monmap"
*/
int ceph_monc_get_version(struct ceph_mon_client *monc, const char *what,
u64 *newest)
{
struct ceph_mon_generic_request *req;
int ret;
req = __ceph_monc_get_version(monc, what, NULL, 0);
if (IS_ERR(req))
return PTR_ERR(req);
ret = wait_generic_request(req);
if (!ret)
*newest = req->u.newest;
put_generic_request(req);
return ret;
}
EXPORT_SYMBOL(ceph_monc_get_version);
/*
* Send MMonGetVersion,
*
* @what: one of "mdsmap", "osdmap" or "monmap"
*/
int ceph_monc_get_version_async(struct ceph_mon_client *monc, const char *what,
ceph_monc_callback_t cb, u64 private_data)
{
struct ceph_mon_generic_request *req;
req = __ceph_monc_get_version(monc, what, cb, private_data);
if (IS_ERR(req))
return PTR_ERR(req);
put_generic_request(req);
return 0;
}
EXPORT_SYMBOL(ceph_monc_get_version_async);
static void handle_command_ack(struct ceph_mon_client *monc,
struct ceph_msg *msg)
{
struct ceph_mon_generic_request *req;
void *p = msg->front.iov_base;
void *const end = p + msg->front_alloc_len;
u64 tid = le64_to_cpu(msg->hdr.tid);
dout("%s msg %p tid %llu\n", __func__, msg, tid);
ceph_decode_need(&p, end, sizeof(struct ceph_mon_request_header) +
sizeof(u32), bad);
p += sizeof(struct ceph_mon_request_header);
mutex_lock(&monc->mutex);
req = lookup_generic_request(&monc->generic_request_tree, tid);
if (!req) {
mutex_unlock(&monc->mutex);
return;
}
req->result = ceph_decode_32(&p);
__finish_generic_request(req);
mutex_unlock(&monc->mutex);
complete_generic_request(req);
return;
bad:
pr_err("corrupt mon_command ack, tid %llu\n", tid);
ceph_msg_dump(msg);
}
static __printf(2, 0)
int do_mon_command_vargs(struct ceph_mon_client *monc, const char *fmt,
va_list ap)
{
struct ceph_mon_generic_request *req;
struct ceph_mon_command *h;
int ret = -ENOMEM;
int len;
req = alloc_generic_request(monc, GFP_NOIO);
if (!req)
goto out;
req->request = ceph_msg_new(CEPH_MSG_MON_COMMAND, 256, GFP_NOIO, true);
if (!req->request)
goto out;
req->reply = ceph_msg_new(CEPH_MSG_MON_COMMAND_ACK, 512, GFP_NOIO,
true);
if (!req->reply)
goto out;
mutex_lock(&monc->mutex);
register_generic_request(req);
h = req->request->front.iov_base;
h->monhdr.have_version = 0;
h->monhdr.session_mon = cpu_to_le16(-1);
h->monhdr.session_mon_tid = 0;
h->fsid = monc->monmap->fsid;
h->num_strs = cpu_to_le32(1);
len = vsprintf(h->str, fmt, ap);
h->str_len = cpu_to_le32(len);
send_generic_request(monc, req);
mutex_unlock(&monc->mutex);