forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdrbd_nl.c
5035 lines (4385 loc) · 148 KB
/
drbd_nl.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
/*
drbd_nl.c
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2001-2008, LINBIT Information Technologies GmbH.
Copyright (C) 1999-2008, Philipp Reisner <[email protected]>.
Copyright (C) 2002-2008, Lars Ellenberg <[email protected]>.
drbd 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; either version 2, or (at your option)
any later version.
drbd 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 drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/drbd.h>
#include <linux/in.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/blkpg.h>
#include <linux/cpumask.h>
#include "drbd_int.h"
#include "drbd_protocol.h"
#include "drbd_req.h"
#include "drbd_state_change.h"
#include <asm/unaligned.h>
#include <linux/drbd_limits.h>
#include <linux/kthread.h>
#include <net/genetlink.h>
/* .doit */
// int drbd_adm_create_resource(struct sk_buff *skb, struct genl_info *info);
// int drbd_adm_delete_resource(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_del_minor(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_down(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_pause_sync(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_suspend_io(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info);
int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info);
/* .dumpit */
int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb);
int drbd_adm_dump_resources(struct sk_buff *skb, struct netlink_callback *cb);
int drbd_adm_dump_devices(struct sk_buff *skb, struct netlink_callback *cb);
int drbd_adm_dump_devices_done(struct netlink_callback *cb);
int drbd_adm_dump_connections(struct sk_buff *skb, struct netlink_callback *cb);
int drbd_adm_dump_connections_done(struct netlink_callback *cb);
int drbd_adm_dump_peer_devices(struct sk_buff *skb, struct netlink_callback *cb);
int drbd_adm_dump_peer_devices_done(struct netlink_callback *cb);
int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb);
#include <linux/drbd_genl_api.h>
#include "drbd_nla.h"
#include <linux/genl_magic_func.h>
static atomic_t drbd_genl_seq = ATOMIC_INIT(2); /* two. */
static atomic_t notify_genl_seq = ATOMIC_INIT(2); /* two. */
DEFINE_MUTEX(notification_mutex);
/* used blkdev_get_by_path, to claim our meta data device(s) */
static char *drbd_m_holder = "Hands off! this is DRBD's meta data device.";
static void drbd_adm_send_reply(struct sk_buff *skb, struct genl_info *info)
{
genlmsg_end(skb, genlmsg_data(nlmsg_data(nlmsg_hdr(skb))));
if (genlmsg_reply(skb, info))
pr_err("error sending genl reply\n");
}
/* Used on a fresh "drbd_adm_prepare"d reply_skb, this cannot fail: The only
* reason it could fail was no space in skb, and there are 4k available. */
static int drbd_msg_put_info(struct sk_buff *skb, const char *info)
{
struct nlattr *nla;
int err = -EMSGSIZE;
if (!info || !info[0])
return 0;
nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_REPLY);
if (!nla)
return err;
err = nla_put_string(skb, T_info_text, info);
if (err) {
nla_nest_cancel(skb, nla);
return err;
} else
nla_nest_end(skb, nla);
return 0;
}
__printf(2, 3)
static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...)
{
va_list args;
struct nlattr *nla, *txt;
int err = -EMSGSIZE;
int len;
nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_REPLY);
if (!nla)
return err;
txt = nla_reserve(skb, T_info_text, 256);
if (!txt) {
nla_nest_cancel(skb, nla);
return err;
}
va_start(args, fmt);
len = vscnprintf(nla_data(txt), 256, fmt, args);
va_end(args);
/* maybe: retry with larger reserve, if truncated */
txt->nla_len = nla_attr_size(len+1);
nlmsg_trim(skb, (char*)txt + NLA_ALIGN(txt->nla_len));
nla_nest_end(skb, nla);
return 0;
}
/* This would be a good candidate for a "pre_doit" hook,
* and per-family private info->pointers.
* But we need to stay compatible with older kernels.
* If it returns successfully, adm_ctx members are valid.
*
* At this point, we still rely on the global genl_lock().
* If we want to avoid that, and allow "genl_family.parallel_ops", we may need
* to add additional synchronization against object destruction/modification.
*/
#define DRBD_ADM_NEED_MINOR 1
#define DRBD_ADM_NEED_RESOURCE 2
#define DRBD_ADM_NEED_CONNECTION 4
static int drbd_adm_prepare(struct drbd_config_context *adm_ctx,
struct sk_buff *skb, struct genl_info *info, unsigned flags)
{
struct drbd_genlmsghdr *d_in = info->userhdr;
const u8 cmd = info->genlhdr->cmd;
int err;
memset(adm_ctx, 0, sizeof(*adm_ctx));
/* genl_rcv_msg only checks for CAP_NET_ADMIN on "GENL_ADMIN_PERM" :( */
if (cmd != DRBD_ADM_GET_STATUS && !capable(CAP_NET_ADMIN))
return -EPERM;
adm_ctx->reply_skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (!adm_ctx->reply_skb) {
err = -ENOMEM;
goto fail;
}
adm_ctx->reply_dh = genlmsg_put_reply(adm_ctx->reply_skb,
info, &drbd_genl_family, 0, cmd);
/* put of a few bytes into a fresh skb of >= 4k will always succeed.
* but anyways */
if (!adm_ctx->reply_dh) {
err = -ENOMEM;
goto fail;
}
adm_ctx->reply_dh->minor = d_in->minor;
adm_ctx->reply_dh->ret_code = NO_ERROR;
adm_ctx->volume = VOLUME_UNSPECIFIED;
if (info->attrs[DRBD_NLA_CFG_CONTEXT]) {
struct nlattr *nla;
/* parse and validate only */
err = drbd_cfg_context_from_attrs(NULL, info);
if (err)
goto fail;
/* It was present, and valid,
* copy it over to the reply skb. */
err = nla_put_nohdr(adm_ctx->reply_skb,
info->attrs[DRBD_NLA_CFG_CONTEXT]->nla_len,
info->attrs[DRBD_NLA_CFG_CONTEXT]);
if (err)
goto fail;
/* and assign stuff to the adm_ctx */
nla = nested_attr_tb[__nla_type(T_ctx_volume)];
if (nla)
adm_ctx->volume = nla_get_u32(nla);
nla = nested_attr_tb[__nla_type(T_ctx_resource_name)];
if (nla)
adm_ctx->resource_name = nla_data(nla);
adm_ctx->my_addr = nested_attr_tb[__nla_type(T_ctx_my_addr)];
adm_ctx->peer_addr = nested_attr_tb[__nla_type(T_ctx_peer_addr)];
if ((adm_ctx->my_addr &&
nla_len(adm_ctx->my_addr) > sizeof(adm_ctx->connection->my_addr)) ||
(adm_ctx->peer_addr &&
nla_len(adm_ctx->peer_addr) > sizeof(adm_ctx->connection->peer_addr))) {
err = -EINVAL;
goto fail;
}
}
adm_ctx->minor = d_in->minor;
adm_ctx->device = minor_to_device(d_in->minor);
/* We are protected by the global genl_lock().
* But we may explicitly drop it/retake it in drbd_adm_set_role(),
* so make sure this object stays around. */
if (adm_ctx->device)
kref_get(&adm_ctx->device->kref);
if (adm_ctx->resource_name) {
adm_ctx->resource = drbd_find_resource(adm_ctx->resource_name);
}
if (!adm_ctx->device && (flags & DRBD_ADM_NEED_MINOR)) {
drbd_msg_put_info(adm_ctx->reply_skb, "unknown minor");
return ERR_MINOR_INVALID;
}
if (!adm_ctx->resource && (flags & DRBD_ADM_NEED_RESOURCE)) {
drbd_msg_put_info(adm_ctx->reply_skb, "unknown resource");
if (adm_ctx->resource_name)
return ERR_RES_NOT_KNOWN;
return ERR_INVALID_REQUEST;
}
if (flags & DRBD_ADM_NEED_CONNECTION) {
if (adm_ctx->resource) {
drbd_msg_put_info(adm_ctx->reply_skb, "no resource name expected");
return ERR_INVALID_REQUEST;
}
if (adm_ctx->device) {
drbd_msg_put_info(adm_ctx->reply_skb, "no minor number expected");
return ERR_INVALID_REQUEST;
}
if (adm_ctx->my_addr && adm_ctx->peer_addr)
adm_ctx->connection = conn_get_by_addrs(nla_data(adm_ctx->my_addr),
nla_len(adm_ctx->my_addr),
nla_data(adm_ctx->peer_addr),
nla_len(adm_ctx->peer_addr));
if (!adm_ctx->connection) {
drbd_msg_put_info(adm_ctx->reply_skb, "unknown connection");
return ERR_INVALID_REQUEST;
}
}
/* some more paranoia, if the request was over-determined */
if (adm_ctx->device && adm_ctx->resource &&
adm_ctx->device->resource != adm_ctx->resource) {
pr_warning("request: minor=%u, resource=%s; but that minor belongs to resource %s\n",
adm_ctx->minor, adm_ctx->resource->name,
adm_ctx->device->resource->name);
drbd_msg_put_info(adm_ctx->reply_skb, "minor exists in different resource");
return ERR_INVALID_REQUEST;
}
if (adm_ctx->device &&
adm_ctx->volume != VOLUME_UNSPECIFIED &&
adm_ctx->volume != adm_ctx->device->vnr) {
pr_warning("request: minor=%u, volume=%u; but that minor is volume %u in %s\n",
adm_ctx->minor, adm_ctx->volume,
adm_ctx->device->vnr,
adm_ctx->device->resource->name);
drbd_msg_put_info(adm_ctx->reply_skb, "minor exists as different volume");
return ERR_INVALID_REQUEST;
}
/* still, provide adm_ctx->resource always, if possible. */
if (!adm_ctx->resource) {
adm_ctx->resource = adm_ctx->device ? adm_ctx->device->resource
: adm_ctx->connection ? adm_ctx->connection->resource : NULL;
if (adm_ctx->resource)
kref_get(&adm_ctx->resource->kref);
}
return NO_ERROR;
fail:
nlmsg_free(adm_ctx->reply_skb);
adm_ctx->reply_skb = NULL;
return err;
}
static int drbd_adm_finish(struct drbd_config_context *adm_ctx,
struct genl_info *info, int retcode)
{
if (adm_ctx->device) {
kref_put(&adm_ctx->device->kref, drbd_destroy_device);
adm_ctx->device = NULL;
}
if (adm_ctx->connection) {
kref_put(&adm_ctx->connection->kref, &drbd_destroy_connection);
adm_ctx->connection = NULL;
}
if (adm_ctx->resource) {
kref_put(&adm_ctx->resource->kref, drbd_destroy_resource);
adm_ctx->resource = NULL;
}
if (!adm_ctx->reply_skb)
return -ENOMEM;
adm_ctx->reply_dh->ret_code = retcode;
drbd_adm_send_reply(adm_ctx->reply_skb, info);
return 0;
}
static void setup_khelper_env(struct drbd_connection *connection, char **envp)
{
char *afs;
/* FIXME: A future version will not allow this case. */
if (connection->my_addr_len == 0 || connection->peer_addr_len == 0)
return;
switch (((struct sockaddr *)&connection->peer_addr)->sa_family) {
case AF_INET6:
afs = "ipv6";
snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI6",
&((struct sockaddr_in6 *)&connection->peer_addr)->sin6_addr);
break;
case AF_INET:
afs = "ipv4";
snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI4",
&((struct sockaddr_in *)&connection->peer_addr)->sin_addr);
break;
default:
afs = "ssocks";
snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI4",
&((struct sockaddr_in *)&connection->peer_addr)->sin_addr);
}
snprintf(envp[3], 20, "DRBD_PEER_AF=%s", afs);
}
int drbd_khelper(struct drbd_device *device, char *cmd)
{
char *envp[] = { "HOME=/",
"TERM=linux",
"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
(char[20]) { }, /* address family */
(char[60]) { }, /* address */
NULL };
char mb[14];
char *argv[] = {drbd_usermode_helper, cmd, mb, NULL };
struct drbd_connection *connection = first_peer_device(device)->connection;
struct sib_info sib;
int ret;
if (current == connection->worker.task)
set_bit(CALLBACK_PENDING, &connection->flags);
snprintf(mb, 14, "minor-%d", device_to_minor(device));
setup_khelper_env(connection, envp);
/* The helper may take some time.
* write out any unsynced meta data changes now */
drbd_md_sync(device);
drbd_info(device, "helper command: %s %s %s\n", drbd_usermode_helper, cmd, mb);
sib.sib_reason = SIB_HELPER_PRE;
sib.helper_name = cmd;
drbd_bcast_event(device, &sib);
notify_helper(NOTIFY_CALL, device, connection, cmd, 0);
ret = call_usermodehelper(drbd_usermode_helper, argv, envp, UMH_WAIT_PROC);
if (ret)
drbd_warn(device, "helper command: %s %s %s exit code %u (0x%x)\n",
drbd_usermode_helper, cmd, mb,
(ret >> 8) & 0xff, ret);
else
drbd_info(device, "helper command: %s %s %s exit code %u (0x%x)\n",
drbd_usermode_helper, cmd, mb,
(ret >> 8) & 0xff, ret);
sib.sib_reason = SIB_HELPER_POST;
sib.helper_exit_code = ret;
drbd_bcast_event(device, &sib);
notify_helper(NOTIFY_RESPONSE, device, connection, cmd, ret);
if (current == connection->worker.task)
clear_bit(CALLBACK_PENDING, &connection->flags);
if (ret < 0) /* Ignore any ERRNOs we got. */
ret = 0;
return ret;
}
enum drbd_peer_state conn_khelper(struct drbd_connection *connection, char *cmd)
{
char *envp[] = { "HOME=/",
"TERM=linux",
"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
(char[20]) { }, /* address family */
(char[60]) { }, /* address */
NULL };
char *resource_name = connection->resource->name;
char *argv[] = {drbd_usermode_helper, cmd, resource_name, NULL };
int ret;
setup_khelper_env(connection, envp);
conn_md_sync(connection);
drbd_info(connection, "helper command: %s %s %s\n", drbd_usermode_helper, cmd, resource_name);
/* TODO: conn_bcast_event() ?? */
notify_helper(NOTIFY_CALL, NULL, connection, cmd, 0);
ret = call_usermodehelper(drbd_usermode_helper, argv, envp, UMH_WAIT_PROC);
if (ret)
drbd_warn(connection, "helper command: %s %s %s exit code %u (0x%x)\n",
drbd_usermode_helper, cmd, resource_name,
(ret >> 8) & 0xff, ret);
else
drbd_info(connection, "helper command: %s %s %s exit code %u (0x%x)\n",
drbd_usermode_helper, cmd, resource_name,
(ret >> 8) & 0xff, ret);
/* TODO: conn_bcast_event() ?? */
notify_helper(NOTIFY_RESPONSE, NULL, connection, cmd, ret);
if (ret < 0) /* Ignore any ERRNOs we got. */
ret = 0;
return ret;
}
static enum drbd_fencing_p highest_fencing_policy(struct drbd_connection *connection)
{
enum drbd_fencing_p fp = FP_NOT_AVAIL;
struct drbd_peer_device *peer_device;
int vnr;
rcu_read_lock();
idr_for_each_entry(&connection->peer_devices, peer_device, vnr) {
struct drbd_device *device = peer_device->device;
if (get_ldev_if_state(device, D_CONSISTENT)) {
struct disk_conf *disk_conf =
rcu_dereference(peer_device->device->ldev->disk_conf);
fp = max_t(enum drbd_fencing_p, fp, disk_conf->fencing);
put_ldev(device);
}
}
rcu_read_unlock();
return fp;
}
static bool resource_is_supended(struct drbd_resource *resource)
{
return resource->susp || resource->susp_fen || resource->susp_nod;
}
bool conn_try_outdate_peer(struct drbd_connection *connection)
{
struct drbd_resource * const resource = connection->resource;
unsigned int connect_cnt;
union drbd_state mask = { };
union drbd_state val = { };
enum drbd_fencing_p fp;
char *ex_to_string;
int r;
spin_lock_irq(&resource->req_lock);
if (connection->cstate >= C_WF_REPORT_PARAMS) {
drbd_err(connection, "Expected cstate < C_WF_REPORT_PARAMS\n");
spin_unlock_irq(&resource->req_lock);
return false;
}
connect_cnt = connection->connect_cnt;
spin_unlock_irq(&resource->req_lock);
fp = highest_fencing_policy(connection);
switch (fp) {
case FP_NOT_AVAIL:
drbd_warn(connection, "Not fencing peer, I'm not even Consistent myself.\n");
spin_lock_irq(&resource->req_lock);
if (connection->cstate < C_WF_REPORT_PARAMS) {
_conn_request_state(connection,
(union drbd_state) { { .susp_fen = 1 } },
(union drbd_state) { { .susp_fen = 0 } },
CS_VERBOSE | CS_HARD | CS_DC_SUSP);
/* We are no longer suspended due to the fencing policy.
* We may still be suspended due to the on-no-data-accessible policy.
* If that was OND_IO_ERROR, fail pending requests. */
if (!resource_is_supended(resource))
_tl_restart(connection, CONNECTION_LOST_WHILE_PENDING);
}
/* Else: in case we raced with a connection handshake,
* let the handshake figure out if we maybe can RESEND,
* and do not resume/fail pending requests here.
* Worst case is we stay suspended for now, which may be
* resolved by either re-establishing the replication link, or
* the next link failure, or eventually the administrator. */
spin_unlock_irq(&resource->req_lock);
return false;
case FP_DONT_CARE:
return true;
default: ;
}
r = conn_khelper(connection, "fence-peer");
switch ((r>>8) & 0xff) {
case P_INCONSISTENT: /* peer is inconsistent */
ex_to_string = "peer is inconsistent or worse";
mask.pdsk = D_MASK;
val.pdsk = D_INCONSISTENT;
break;
case P_OUTDATED: /* peer got outdated, or was already outdated */
ex_to_string = "peer was fenced";
mask.pdsk = D_MASK;
val.pdsk = D_OUTDATED;
break;
case P_DOWN: /* peer was down */
if (conn_highest_disk(connection) == D_UP_TO_DATE) {
/* we will(have) create(d) a new UUID anyways... */
ex_to_string = "peer is unreachable, assumed to be dead";
mask.pdsk = D_MASK;
val.pdsk = D_OUTDATED;
} else {
ex_to_string = "peer unreachable, doing nothing since disk != UpToDate";
}
break;
case P_PRIMARY: /* Peer is primary, voluntarily outdate myself.
* This is useful when an unconnected R_SECONDARY is asked to
* become R_PRIMARY, but finds the other peer being active. */
ex_to_string = "peer is active";
drbd_warn(connection, "Peer is primary, outdating myself.\n");
mask.disk = D_MASK;
val.disk = D_OUTDATED;
break;
case P_FENCING:
/* THINK: do we need to handle this
* like case 4, or more like case 5? */
if (fp != FP_STONITH)
drbd_err(connection, "fence-peer() = 7 && fencing != Stonith !!!\n");
ex_to_string = "peer was stonithed";
mask.pdsk = D_MASK;
val.pdsk = D_OUTDATED;
break;
default:
/* The script is broken ... */
drbd_err(connection, "fence-peer helper broken, returned %d\n", (r>>8)&0xff);
return false; /* Eventually leave IO frozen */
}
drbd_info(connection, "fence-peer helper returned %d (%s)\n",
(r>>8) & 0xff, ex_to_string);
/* Not using
conn_request_state(connection, mask, val, CS_VERBOSE);
here, because we might were able to re-establish the connection in the
meantime. */
spin_lock_irq(&resource->req_lock);
if (connection->cstate < C_WF_REPORT_PARAMS && !test_bit(STATE_SENT, &connection->flags)) {
if (connection->connect_cnt != connect_cnt)
/* In case the connection was established and droped
while the fence-peer handler was running, ignore it */
drbd_info(connection, "Ignoring fence-peer exit code\n");
else
_conn_request_state(connection, mask, val, CS_VERBOSE);
}
spin_unlock_irq(&resource->req_lock);
return conn_highest_pdsk(connection) <= D_OUTDATED;
}
static int _try_outdate_peer_async(void *data)
{
struct drbd_connection *connection = (struct drbd_connection *)data;
conn_try_outdate_peer(connection);
kref_put(&connection->kref, drbd_destroy_connection);
return 0;
}
void conn_try_outdate_peer_async(struct drbd_connection *connection)
{
struct task_struct *opa;
kref_get(&connection->kref);
/* We may just have force_sig()'ed this thread
* to get it out of some blocking network function.
* Clear signals; otherwise kthread_run(), which internally uses
* wait_on_completion_killable(), will mistake our pending signal
* for a new fatal signal and fail. */
flush_signals(current);
opa = kthread_run(_try_outdate_peer_async, connection, "drbd_async_h");
if (IS_ERR(opa)) {
drbd_err(connection, "out of mem, failed to invoke fence-peer helper\n");
kref_put(&connection->kref, drbd_destroy_connection);
}
}
enum drbd_state_rv
drbd_set_role(struct drbd_device *const device, enum drbd_role new_role, int force)
{
struct drbd_peer_device *const peer_device = first_peer_device(device);
struct drbd_connection *const connection = peer_device ? peer_device->connection : NULL;
const int max_tries = 4;
enum drbd_state_rv rv = SS_UNKNOWN_ERROR;
struct net_conf *nc;
int try = 0;
int forced = 0;
union drbd_state mask, val;
if (new_role == R_PRIMARY) {
struct drbd_connection *connection;
/* Detect dead peers as soon as possible. */
rcu_read_lock();
for_each_connection(connection, device->resource)
request_ping(connection);
rcu_read_unlock();
}
mutex_lock(device->state_mutex);
mask.i = 0; mask.role = R_MASK;
val.i = 0; val.role = new_role;
while (try++ < max_tries) {
rv = _drbd_request_state_holding_state_mutex(device, mask, val, CS_WAIT_COMPLETE);
/* in case we first succeeded to outdate,
* but now suddenly could establish a connection */
if (rv == SS_CW_FAILED_BY_PEER && mask.pdsk != 0) {
val.pdsk = 0;
mask.pdsk = 0;
continue;
}
if (rv == SS_NO_UP_TO_DATE_DISK && force &&
(device->state.disk < D_UP_TO_DATE &&
device->state.disk >= D_INCONSISTENT)) {
mask.disk = D_MASK;
val.disk = D_UP_TO_DATE;
forced = 1;
continue;
}
if (rv == SS_NO_UP_TO_DATE_DISK &&
device->state.disk == D_CONSISTENT && mask.pdsk == 0) {
D_ASSERT(device, device->state.pdsk == D_UNKNOWN);
if (conn_try_outdate_peer(connection)) {
val.disk = D_UP_TO_DATE;
mask.disk = D_MASK;
}
continue;
}
if (rv == SS_NOTHING_TO_DO)
goto out;
if (rv == SS_PRIMARY_NOP && mask.pdsk == 0) {
if (!conn_try_outdate_peer(connection) && force) {
drbd_warn(device, "Forced into split brain situation!\n");
mask.pdsk = D_MASK;
val.pdsk = D_OUTDATED;
}
continue;
}
if (rv == SS_TWO_PRIMARIES) {
/* Maybe the peer is detected as dead very soon...
retry at most once more in this case. */
if (try < max_tries) {
int timeo;
try = max_tries - 1;
rcu_read_lock();
nc = rcu_dereference(connection->net_conf);
timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1;
rcu_read_unlock();
schedule_timeout_interruptible(timeo);
}
continue;
}
if (rv < SS_SUCCESS) {
rv = _drbd_request_state(device, mask, val,
CS_VERBOSE + CS_WAIT_COMPLETE);
if (rv < SS_SUCCESS)
goto out;
}
break;
}
if (rv < SS_SUCCESS)
goto out;
if (forced)
drbd_warn(device, "Forced to consider local data as UpToDate!\n");
/* Wait until nothing is on the fly :) */
wait_event(device->misc_wait, atomic_read(&device->ap_pending_cnt) == 0);
/* FIXME also wait for all pending P_BARRIER_ACK? */
if (new_role == R_SECONDARY) {
if (get_ldev(device)) {
device->ldev->md.uuid[UI_CURRENT] &= ~(u64)1;
put_ldev(device);
}
} else {
mutex_lock(&device->resource->conf_update);
nc = connection->net_conf;
if (nc)
nc->discard_my_data = 0; /* without copy; single bit op is atomic */
mutex_unlock(&device->resource->conf_update);
if (get_ldev(device)) {
if (((device->state.conn < C_CONNECTED ||
device->state.pdsk <= D_FAILED)
&& device->ldev->md.uuid[UI_BITMAP] == 0) || forced)
drbd_uuid_new_current(device);
device->ldev->md.uuid[UI_CURRENT] |= (u64)1;
put_ldev(device);
}
}
/* writeout of activity log covered areas of the bitmap
* to stable storage done in after state change already */
if (device->state.conn >= C_WF_REPORT_PARAMS) {
/* if this was forced, we should consider sync */
if (forced)
drbd_send_uuids(peer_device);
drbd_send_current_state(peer_device);
}
drbd_md_sync(device);
set_disk_ro(device->vdisk, new_role == R_SECONDARY);
kobject_uevent(&disk_to_dev(device->vdisk)->kobj, KOBJ_CHANGE);
out:
mutex_unlock(device->state_mutex);
return rv;
}
static const char *from_attrs_err_to_txt(int err)
{
return err == -ENOMSG ? "required attribute missing" :
err == -EOPNOTSUPP ? "unknown mandatory attribute" :
err == -EEXIST ? "can not change invariant setting" :
"invalid attribute value";
}
int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info)
{
struct drbd_config_context adm_ctx;
struct set_role_parms parms;
int err;
enum drbd_ret_code retcode;
retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
if (!adm_ctx.reply_skb)
return retcode;
if (retcode != NO_ERROR)
goto out;
memset(&parms, 0, sizeof(parms));
if (info->attrs[DRBD_NLA_SET_ROLE_PARMS]) {
err = set_role_parms_from_attrs(&parms, info);
if (err) {
retcode = ERR_MANDATORY_TAG;
drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
goto out;
}
}
genl_unlock();
mutex_lock(&adm_ctx.resource->adm_mutex);
if (info->genlhdr->cmd == DRBD_ADM_PRIMARY)
retcode = drbd_set_role(adm_ctx.device, R_PRIMARY, parms.assume_uptodate);
else
retcode = drbd_set_role(adm_ctx.device, R_SECONDARY, 0);
mutex_unlock(&adm_ctx.resource->adm_mutex);
genl_lock();
out:
drbd_adm_finish(&adm_ctx, info, retcode);
return 0;
}
/* Initializes the md.*_offset members, so we are able to find
* the on disk meta data.
*
* We currently have two possible layouts:
* external:
* |----------- md_size_sect ------------------|
* [ 4k superblock ][ activity log ][ Bitmap ]
* | al_offset == 8 |
* | bm_offset = al_offset + X |
* ==> bitmap sectors = md_size_sect - bm_offset
*
* internal:
* |----------- md_size_sect ------------------|
* [data.....][ Bitmap ][ activity log ][ 4k superblock ]
* | al_offset < 0 |
* | bm_offset = al_offset - Y |
* ==> bitmap sectors = Y = al_offset - bm_offset
*
* Activity log size used to be fixed 32kB,
* but is about to become configurable.
*/
static void drbd_md_set_sector_offsets(struct drbd_device *device,
struct drbd_backing_dev *bdev)
{
sector_t md_size_sect = 0;
unsigned int al_size_sect = bdev->md.al_size_4k * 8;
bdev->md.md_offset = drbd_md_ss(bdev);
switch (bdev->md.meta_dev_idx) {
default:
/* v07 style fixed size indexed meta data */
bdev->md.md_size_sect = MD_128MB_SECT;
bdev->md.al_offset = MD_4kB_SECT;
bdev->md.bm_offset = MD_4kB_SECT + al_size_sect;
break;
case DRBD_MD_INDEX_FLEX_EXT:
/* just occupy the full device; unit: sectors */
bdev->md.md_size_sect = drbd_get_capacity(bdev->md_bdev);
bdev->md.al_offset = MD_4kB_SECT;
bdev->md.bm_offset = MD_4kB_SECT + al_size_sect;
break;
case DRBD_MD_INDEX_INTERNAL:
case DRBD_MD_INDEX_FLEX_INT:
/* al size is still fixed */
bdev->md.al_offset = -al_size_sect;
/* we need (slightly less than) ~ this much bitmap sectors: */
md_size_sect = drbd_get_capacity(bdev->backing_bdev);
md_size_sect = ALIGN(md_size_sect, BM_SECT_PER_EXT);
md_size_sect = BM_SECT_TO_EXT(md_size_sect);
md_size_sect = ALIGN(md_size_sect, 8);
/* plus the "drbd meta data super block",
* and the activity log; */
md_size_sect += MD_4kB_SECT + al_size_sect;
bdev->md.md_size_sect = md_size_sect;
/* bitmap offset is adjusted by 'super' block size */
bdev->md.bm_offset = -md_size_sect + MD_4kB_SECT;
break;
}
}
/* input size is expected to be in KB */
char *ppsize(char *buf, unsigned long long size)
{
/* Needs 9 bytes at max including trailing NUL:
* -1ULL ==> "16384 EB" */
static char units[] = { 'K', 'M', 'G', 'T', 'P', 'E' };
int base = 0;
while (size >= 10000 && base < sizeof(units)-1) {
/* shift + round */
size = (size >> 10) + !!(size & (1<<9));
base++;
}
sprintf(buf, "%u %cB", (unsigned)size, units[base]);
return buf;
}
/* there is still a theoretical deadlock when called from receiver
* on an D_INCONSISTENT R_PRIMARY:
* remote READ does inc_ap_bio, receiver would need to receive answer
* packet from remote to dec_ap_bio again.
* receiver receive_sizes(), comes here,
* waits for ap_bio_cnt == 0. -> deadlock.
* but this cannot happen, actually, because:
* R_PRIMARY D_INCONSISTENT, and peer's disk is unreachable
* (not connected, or bad/no disk on peer):
* see drbd_fail_request_early, ap_bio_cnt is zero.
* R_PRIMARY D_INCONSISTENT, and C_SYNC_TARGET:
* peer may not initiate a resize.
*/
/* Note these are not to be confused with
* drbd_adm_suspend_io/drbd_adm_resume_io,
* which are (sub) state changes triggered by admin (drbdsetup),
* and can be long lived.
* This changes an device->flag, is triggered by drbd internals,
* and should be short-lived. */
/* It needs to be a counter, since multiple threads might
independently suspend and resume IO. */
void drbd_suspend_io(struct drbd_device *device)
{
atomic_inc(&device->suspend_cnt);
if (drbd_suspended(device))
return;
wait_event(device->misc_wait, !atomic_read(&device->ap_bio_cnt));
}
void drbd_resume_io(struct drbd_device *device)
{
if (atomic_dec_and_test(&device->suspend_cnt))
wake_up(&device->misc_wait);
}
/**
* drbd_determine_dev_size() - Sets the right device size obeying all constraints
* @device: DRBD device.
*
* Returns 0 on success, negative return values indicate errors.
* You should call drbd_md_sync() after calling this function.
*/
enum determine_dev_size
drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct resize_parms *rs) __must_hold(local)
{
struct md_offsets_and_sizes {
u64 last_agreed_sect;
u64 md_offset;
s32 al_offset;
s32 bm_offset;
u32 md_size_sect;
u32 al_stripes;
u32 al_stripe_size_4k;
} prev;
sector_t u_size, size;
struct drbd_md *md = &device->ldev->md;
void *buffer;
int md_moved, la_size_changed;
enum determine_dev_size rv = DS_UNCHANGED;
/* We may change the on-disk offsets of our meta data below. Lock out
* anything that may cause meta data IO, to avoid acting on incomplete
* layout changes or scribbling over meta data that is in the process
* of being moved.
*
* Move is not exactly correct, btw, currently we have all our meta
* data in core memory, to "move" it we just write it all out, there
* are no reads. */
drbd_suspend_io(device);
buffer = drbd_md_get_buffer(device, __func__); /* Lock meta-data IO */
if (!buffer) {
drbd_resume_io(device);
return DS_ERROR;
}
/* remember current offset and sizes */
prev.last_agreed_sect = md->la_size_sect;
prev.md_offset = md->md_offset;
prev.al_offset = md->al_offset;
prev.bm_offset = md->bm_offset;
prev.md_size_sect = md->md_size_sect;
prev.al_stripes = md->al_stripes;
prev.al_stripe_size_4k = md->al_stripe_size_4k;
if (rs) {
/* rs is non NULL if we should change the AL layout only */
md->al_stripes = rs->al_stripes;
md->al_stripe_size_4k = rs->al_stripe_size / 4;
md->al_size_4k = (u64)rs->al_stripes * rs->al_stripe_size / 4;
}
drbd_md_set_sector_offsets(device, device->ldev);
rcu_read_lock();
u_size = rcu_dereference(device->ldev->disk_conf)->disk_size;
rcu_read_unlock();
size = drbd_new_dev_size(device, device->ldev, u_size, flags & DDSF_FORCED);
if (size < prev.last_agreed_sect) {
if (rs && u_size == 0) {
/* Remove "rs &&" later. This check should always be active, but
right now the receiver expects the permissive behavior */