forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdm-mpath.c
1516 lines (1232 loc) · 33.8 KB
/
dm-mpath.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
/*
* Copyright (C) 2003 Sistina Software Limited.
* Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
#include <linux/device-mapper.h>
#include "dm-path-selector.h"
#include "dm-bio-list.h"
#include "dm-bio-record.h"
#include "dm-uevent.h"
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/mempool.h>
#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/workqueue.h>
#include <scsi/scsi_dh.h>
#include <asm/atomic.h>
#define DM_MSG_PREFIX "multipath"
#define MESG_STR(x) x, sizeof(x)
/* Path properties */
struct pgpath {
struct list_head list;
struct priority_group *pg; /* Owning PG */
unsigned is_active; /* Path status */
unsigned fail_count; /* Cumulative failure count */
struct dm_path path;
struct work_struct deactivate_path;
};
#define path_to_pgpath(__pgp) container_of((__pgp), struct pgpath, path)
/*
* Paths are grouped into Priority Groups and numbered from 1 upwards.
* Each has a path selector which controls which path gets used.
*/
struct priority_group {
struct list_head list;
struct multipath *m; /* Owning multipath instance */
struct path_selector ps;
unsigned pg_num; /* Reference number */
unsigned bypassed; /* Temporarily bypass this PG? */
unsigned nr_pgpaths; /* Number of paths in PG */
struct list_head pgpaths;
};
/* Multipath context */
struct multipath {
struct list_head list;
struct dm_target *ti;
spinlock_t lock;
const char *hw_handler_name;
struct work_struct activate_path;
struct pgpath *pgpath_to_activate;
unsigned nr_priority_groups;
struct list_head priority_groups;
unsigned pg_init_required; /* pg_init needs calling? */
unsigned pg_init_in_progress; /* Only one pg_init allowed at once */
unsigned nr_valid_paths; /* Total number of usable paths */
struct pgpath *current_pgpath;
struct priority_group *current_pg;
struct priority_group *next_pg; /* Switch to this PG if set */
unsigned repeat_count; /* I/Os left before calling PS again */
unsigned queue_io; /* Must we queue all I/O? */
unsigned queue_if_no_path; /* Queue I/O if last path fails? */
unsigned saved_queue_if_no_path;/* Saved state during suspension */
unsigned pg_init_retries; /* Number of times to retry pg_init */
unsigned pg_init_count; /* Number of times pg_init called */
struct work_struct process_queued_ios;
struct bio_list queued_ios;
unsigned queue_size;
struct work_struct trigger_event;
/*
* We must use a mempool of dm_mpath_io structs so that we
* can resubmit bios on error.
*/
mempool_t *mpio_pool;
};
/*
* Context information attached to each bio we process.
*/
struct dm_mpath_io {
struct pgpath *pgpath;
struct dm_bio_details details;
};
typedef int (*action_fn) (struct pgpath *pgpath);
#define MIN_IOS 256 /* Mempool size */
static struct kmem_cache *_mpio_cache;
static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
static void process_queued_ios(struct work_struct *work);
static void trigger_event(struct work_struct *work);
static void activate_path(struct work_struct *work);
static void deactivate_path(struct work_struct *work);
/*-----------------------------------------------
* Allocation routines
*-----------------------------------------------*/
static struct pgpath *alloc_pgpath(void)
{
struct pgpath *pgpath = kzalloc(sizeof(*pgpath), GFP_KERNEL);
if (pgpath) {
pgpath->is_active = 1;
INIT_WORK(&pgpath->deactivate_path, deactivate_path);
}
return pgpath;
}
static void free_pgpath(struct pgpath *pgpath)
{
kfree(pgpath);
}
static void deactivate_path(struct work_struct *work)
{
struct pgpath *pgpath =
container_of(work, struct pgpath, deactivate_path);
blk_abort_queue(pgpath->path.dev->bdev->bd_disk->queue);
}
static struct priority_group *alloc_priority_group(void)
{
struct priority_group *pg;
pg = kzalloc(sizeof(*pg), GFP_KERNEL);
if (pg)
INIT_LIST_HEAD(&pg->pgpaths);
return pg;
}
static void free_pgpaths(struct list_head *pgpaths, struct dm_target *ti)
{
unsigned long flags;
struct pgpath *pgpath, *tmp;
struct multipath *m = ti->private;
list_for_each_entry_safe(pgpath, tmp, pgpaths, list) {
list_del(&pgpath->list);
if (m->hw_handler_name)
scsi_dh_detach(bdev_get_queue(pgpath->path.dev->bdev));
dm_put_device(ti, pgpath->path.dev);
spin_lock_irqsave(&m->lock, flags);
if (m->pgpath_to_activate == pgpath)
m->pgpath_to_activate = NULL;
spin_unlock_irqrestore(&m->lock, flags);
free_pgpath(pgpath);
}
}
static void free_priority_group(struct priority_group *pg,
struct dm_target *ti)
{
struct path_selector *ps = &pg->ps;
if (ps->type) {
ps->type->destroy(ps);
dm_put_path_selector(ps->type);
}
free_pgpaths(&pg->pgpaths, ti);
kfree(pg);
}
static struct multipath *alloc_multipath(struct dm_target *ti)
{
struct multipath *m;
m = kzalloc(sizeof(*m), GFP_KERNEL);
if (m) {
INIT_LIST_HEAD(&m->priority_groups);
spin_lock_init(&m->lock);
m->queue_io = 1;
INIT_WORK(&m->process_queued_ios, process_queued_ios);
INIT_WORK(&m->trigger_event, trigger_event);
INIT_WORK(&m->activate_path, activate_path);
m->mpio_pool = mempool_create_slab_pool(MIN_IOS, _mpio_cache);
if (!m->mpio_pool) {
kfree(m);
return NULL;
}
m->ti = ti;
ti->private = m;
}
return m;
}
static void free_multipath(struct multipath *m)
{
struct priority_group *pg, *tmp;
list_for_each_entry_safe(pg, tmp, &m->priority_groups, list) {
list_del(&pg->list);
free_priority_group(pg, m->ti);
}
kfree(m->hw_handler_name);
mempool_destroy(m->mpio_pool);
kfree(m);
}
/*-----------------------------------------------
* Path selection
*-----------------------------------------------*/
static void __switch_pg(struct multipath *m, struct pgpath *pgpath)
{
m->current_pg = pgpath->pg;
/* Must we initialise the PG first, and queue I/O till it's ready? */
if (m->hw_handler_name) {
m->pg_init_required = 1;
m->queue_io = 1;
} else {
m->pg_init_required = 0;
m->queue_io = 0;
}
m->pg_init_count = 0;
}
static int __choose_path_in_pg(struct multipath *m, struct priority_group *pg)
{
struct dm_path *path;
path = pg->ps.type->select_path(&pg->ps, &m->repeat_count);
if (!path)
return -ENXIO;
m->current_pgpath = path_to_pgpath(path);
if (m->current_pg != pg)
__switch_pg(m, m->current_pgpath);
return 0;
}
static void __choose_pgpath(struct multipath *m)
{
struct priority_group *pg;
unsigned bypassed = 1;
if (!m->nr_valid_paths)
goto failed;
/* Were we instructed to switch PG? */
if (m->next_pg) {
pg = m->next_pg;
m->next_pg = NULL;
if (!__choose_path_in_pg(m, pg))
return;
}
/* Don't change PG until it has no remaining paths */
if (m->current_pg && !__choose_path_in_pg(m, m->current_pg))
return;
/*
* Loop through priority groups until we find a valid path.
* First time we skip PGs marked 'bypassed'.
* Second time we only try the ones we skipped.
*/
do {
list_for_each_entry(pg, &m->priority_groups, list) {
if (pg->bypassed == bypassed)
continue;
if (!__choose_path_in_pg(m, pg))
return;
}
} while (bypassed--);
failed:
m->current_pgpath = NULL;
m->current_pg = NULL;
}
/*
* Check whether bios must be queued in the device-mapper core rather
* than here in the target.
*
* m->lock must be held on entry.
*
* If m->queue_if_no_path and m->saved_queue_if_no_path hold the
* same value then we are not between multipath_presuspend()
* and multipath_resume() calls and we have no need to check
* for the DMF_NOFLUSH_SUSPENDING flag.
*/
static int __must_push_back(struct multipath *m)
{
return (m->queue_if_no_path != m->saved_queue_if_no_path &&
dm_noflush_suspending(m->ti));
}
static int map_io(struct multipath *m, struct bio *bio,
struct dm_mpath_io *mpio, unsigned was_queued)
{
int r = DM_MAPIO_REMAPPED;
unsigned long flags;
struct pgpath *pgpath;
spin_lock_irqsave(&m->lock, flags);
/* Do we need to select a new pgpath? */
if (!m->current_pgpath ||
(!m->queue_io && (m->repeat_count && --m->repeat_count == 0)))
__choose_pgpath(m);
pgpath = m->current_pgpath;
if (was_queued)
m->queue_size--;
if ((pgpath && m->queue_io) ||
(!pgpath && m->queue_if_no_path)) {
/* Queue for the daemon to resubmit */
bio_list_add(&m->queued_ios, bio);
m->queue_size++;
if ((m->pg_init_required && !m->pg_init_in_progress) ||
!m->queue_io)
queue_work(kmultipathd, &m->process_queued_ios);
pgpath = NULL;
r = DM_MAPIO_SUBMITTED;
} else if (pgpath)
bio->bi_bdev = pgpath->path.dev->bdev;
else if (__must_push_back(m))
r = DM_MAPIO_REQUEUE;
else
r = -EIO; /* Failed */
mpio->pgpath = pgpath;
spin_unlock_irqrestore(&m->lock, flags);
return r;
}
/*
* If we run out of usable paths, should we queue I/O or error it?
*/
static int queue_if_no_path(struct multipath *m, unsigned queue_if_no_path,
unsigned save_old_value)
{
unsigned long flags;
spin_lock_irqsave(&m->lock, flags);
if (save_old_value)
m->saved_queue_if_no_path = m->queue_if_no_path;
else
m->saved_queue_if_no_path = queue_if_no_path;
m->queue_if_no_path = queue_if_no_path;
if (!m->queue_if_no_path && m->queue_size)
queue_work(kmultipathd, &m->process_queued_ios);
spin_unlock_irqrestore(&m->lock, flags);
return 0;
}
/*-----------------------------------------------------------------
* The multipath daemon is responsible for resubmitting queued ios.
*---------------------------------------------------------------*/
static void dispatch_queued_ios(struct multipath *m)
{
int r;
unsigned long flags;
struct bio *bio = NULL, *next;
struct dm_mpath_io *mpio;
union map_info *info;
spin_lock_irqsave(&m->lock, flags);
bio = bio_list_get(&m->queued_ios);
spin_unlock_irqrestore(&m->lock, flags);
while (bio) {
next = bio->bi_next;
bio->bi_next = NULL;
info = dm_get_mapinfo(bio);
mpio = info->ptr;
r = map_io(m, bio, mpio, 1);
if (r < 0)
bio_endio(bio, r);
else if (r == DM_MAPIO_REMAPPED)
generic_make_request(bio);
else if (r == DM_MAPIO_REQUEUE)
bio_endio(bio, -EIO);
bio = next;
}
}
static void process_queued_ios(struct work_struct *work)
{
struct multipath *m =
container_of(work, struct multipath, process_queued_ios);
struct pgpath *pgpath = NULL;
unsigned init_required = 0, must_queue = 1;
unsigned long flags;
spin_lock_irqsave(&m->lock, flags);
if (!m->queue_size)
goto out;
if (!m->current_pgpath)
__choose_pgpath(m);
pgpath = m->current_pgpath;
m->pgpath_to_activate = m->current_pgpath;
if ((pgpath && !m->queue_io) ||
(!pgpath && !m->queue_if_no_path))
must_queue = 0;
if (m->pg_init_required && !m->pg_init_in_progress) {
m->pg_init_count++;
m->pg_init_required = 0;
m->pg_init_in_progress = 1;
init_required = 1;
}
out:
spin_unlock_irqrestore(&m->lock, flags);
if (init_required)
queue_work(kmpath_handlerd, &m->activate_path);
if (!must_queue)
dispatch_queued_ios(m);
}
/*
* An event is triggered whenever a path is taken out of use.
* Includes path failure and PG bypass.
*/
static void trigger_event(struct work_struct *work)
{
struct multipath *m =
container_of(work, struct multipath, trigger_event);
dm_table_event(m->ti->table);
}
/*-----------------------------------------------------------------
* Constructor/argument parsing:
* <#multipath feature args> [<arg>]*
* <#hw_handler args> [hw_handler [<arg>]*]
* <#priority groups>
* <initial priority group>
* [<selector> <#selector args> [<arg>]*
* <#paths> <#per-path selector args>
* [<path> [<arg>]* ]+ ]+
*---------------------------------------------------------------*/
struct param {
unsigned min;
unsigned max;
char *error;
};
static int read_param(struct param *param, char *str, unsigned *v, char **error)
{
if (!str ||
(sscanf(str, "%u", v) != 1) ||
(*v < param->min) ||
(*v > param->max)) {
*error = param->error;
return -EINVAL;
}
return 0;
}
struct arg_set {
unsigned argc;
char **argv;
};
static char *shift(struct arg_set *as)
{
char *r;
if (as->argc) {
as->argc--;
r = *as->argv;
as->argv++;
return r;
}
return NULL;
}
static void consume(struct arg_set *as, unsigned n)
{
BUG_ON (as->argc < n);
as->argc -= n;
as->argv += n;
}
static int parse_path_selector(struct arg_set *as, struct priority_group *pg,
struct dm_target *ti)
{
int r;
struct path_selector_type *pst;
unsigned ps_argc;
static struct param _params[] = {
{0, 1024, "invalid number of path selector args"},
};
pst = dm_get_path_selector(shift(as));
if (!pst) {
ti->error = "unknown path selector type";
return -EINVAL;
}
r = read_param(_params, shift(as), &ps_argc, &ti->error);
if (r) {
dm_put_path_selector(pst);
return -EINVAL;
}
r = pst->create(&pg->ps, ps_argc, as->argv);
if (r) {
dm_put_path_selector(pst);
ti->error = "path selector constructor failed";
return r;
}
pg->ps.type = pst;
consume(as, ps_argc);
return 0;
}
static struct pgpath *parse_path(struct arg_set *as, struct path_selector *ps,
struct dm_target *ti)
{
int r;
struct pgpath *p;
struct multipath *m = ti->private;
/* we need at least a path arg */
if (as->argc < 1) {
ti->error = "no device given";
return ERR_PTR(-EINVAL);
}
p = alloc_pgpath();
if (!p)
return ERR_PTR(-ENOMEM);
r = dm_get_device(ti, shift(as), ti->begin, ti->len,
dm_table_get_mode(ti->table), &p->path.dev);
if (r) {
ti->error = "error getting device";
goto bad;
}
if (m->hw_handler_name) {
r = scsi_dh_attach(bdev_get_queue(p->path.dev->bdev),
m->hw_handler_name);
if (r < 0) {
dm_put_device(ti, p->path.dev);
goto bad;
}
}
r = ps->type->add_path(ps, &p->path, as->argc, as->argv, &ti->error);
if (r) {
dm_put_device(ti, p->path.dev);
goto bad;
}
return p;
bad:
free_pgpath(p);
return ERR_PTR(r);
}
static struct priority_group *parse_priority_group(struct arg_set *as,
struct multipath *m)
{
static struct param _params[] = {
{1, 1024, "invalid number of paths"},
{0, 1024, "invalid number of selector args"}
};
int r;
unsigned i, nr_selector_args, nr_params;
struct priority_group *pg;
struct dm_target *ti = m->ti;
if (as->argc < 2) {
as->argc = 0;
ti->error = "not enough priority group arguments";
return ERR_PTR(-EINVAL);
}
pg = alloc_priority_group();
if (!pg) {
ti->error = "couldn't allocate priority group";
return ERR_PTR(-ENOMEM);
}
pg->m = m;
r = parse_path_selector(as, pg, ti);
if (r)
goto bad;
/*
* read the paths
*/
r = read_param(_params, shift(as), &pg->nr_pgpaths, &ti->error);
if (r)
goto bad;
r = read_param(_params + 1, shift(as), &nr_selector_args, &ti->error);
if (r)
goto bad;
nr_params = 1 + nr_selector_args;
for (i = 0; i < pg->nr_pgpaths; i++) {
struct pgpath *pgpath;
struct arg_set path_args;
if (as->argc < nr_params) {
ti->error = "not enough path parameters";
goto bad;
}
path_args.argc = nr_params;
path_args.argv = as->argv;
pgpath = parse_path(&path_args, &pg->ps, ti);
if (IS_ERR(pgpath)) {
r = PTR_ERR(pgpath);
goto bad;
}
pgpath->pg = pg;
list_add_tail(&pgpath->list, &pg->pgpaths);
consume(as, nr_params);
}
return pg;
bad:
free_priority_group(pg, ti);
return ERR_PTR(r);
}
static int parse_hw_handler(struct arg_set *as, struct multipath *m)
{
unsigned hw_argc;
struct dm_target *ti = m->ti;
static struct param _params[] = {
{0, 1024, "invalid number of hardware handler args"},
};
if (read_param(_params, shift(as), &hw_argc, &ti->error))
return -EINVAL;
if (!hw_argc)
return 0;
m->hw_handler_name = kstrdup(shift(as), GFP_KERNEL);
request_module("scsi_dh_%s", m->hw_handler_name);
if (scsi_dh_handler_exist(m->hw_handler_name) == 0) {
ti->error = "unknown hardware handler type";
kfree(m->hw_handler_name);
m->hw_handler_name = NULL;
return -EINVAL;
}
consume(as, hw_argc - 1);
return 0;
}
static int parse_features(struct arg_set *as, struct multipath *m)
{
int r;
unsigned argc;
struct dm_target *ti = m->ti;
const char *param_name;
static struct param _params[] = {
{0, 3, "invalid number of feature args"},
{1, 50, "pg_init_retries must be between 1 and 50"},
};
r = read_param(_params, shift(as), &argc, &ti->error);
if (r)
return -EINVAL;
if (!argc)
return 0;
do {
param_name = shift(as);
argc--;
if (!strnicmp(param_name, MESG_STR("queue_if_no_path"))) {
r = queue_if_no_path(m, 1, 0);
continue;
}
if (!strnicmp(param_name, MESG_STR("pg_init_retries")) &&
(argc >= 1)) {
r = read_param(_params + 1, shift(as),
&m->pg_init_retries, &ti->error);
argc--;
continue;
}
ti->error = "Unrecognised multipath feature request";
r = -EINVAL;
} while (argc && !r);
return r;
}
static int multipath_ctr(struct dm_target *ti, unsigned int argc,
char **argv)
{
/* target parameters */
static struct param _params[] = {
{1, 1024, "invalid number of priority groups"},
{1, 1024, "invalid initial priority group number"},
};
int r;
struct multipath *m;
struct arg_set as;
unsigned pg_count = 0;
unsigned next_pg_num;
as.argc = argc;
as.argv = argv;
m = alloc_multipath(ti);
if (!m) {
ti->error = "can't allocate multipath";
return -EINVAL;
}
r = parse_features(&as, m);
if (r)
goto bad;
r = parse_hw_handler(&as, m);
if (r)
goto bad;
r = read_param(_params, shift(&as), &m->nr_priority_groups, &ti->error);
if (r)
goto bad;
r = read_param(_params + 1, shift(&as), &next_pg_num, &ti->error);
if (r)
goto bad;
/* parse the priority groups */
while (as.argc) {
struct priority_group *pg;
pg = parse_priority_group(&as, m);
if (IS_ERR(pg)) {
r = PTR_ERR(pg);
goto bad;
}
m->nr_valid_paths += pg->nr_pgpaths;
list_add_tail(&pg->list, &m->priority_groups);
pg_count++;
pg->pg_num = pg_count;
if (!--next_pg_num)
m->next_pg = pg;
}
if (pg_count != m->nr_priority_groups) {
ti->error = "priority group count mismatch";
r = -EINVAL;
goto bad;
}
return 0;
bad:
free_multipath(m);
return r;
}
static void multipath_dtr(struct dm_target *ti)
{
struct multipath *m = (struct multipath *) ti->private;
flush_workqueue(kmpath_handlerd);
flush_workqueue(kmultipathd);
free_multipath(m);
}
/*
* Map bios, recording original fields for later in case we have to resubmit
*/
static int multipath_map(struct dm_target *ti, struct bio *bio,
union map_info *map_context)
{
int r;
struct dm_mpath_io *mpio;
struct multipath *m = (struct multipath *) ti->private;
mpio = mempool_alloc(m->mpio_pool, GFP_NOIO);
dm_bio_record(&mpio->details, bio);
map_context->ptr = mpio;
bio->bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
r = map_io(m, bio, mpio, 0);
if (r < 0 || r == DM_MAPIO_REQUEUE)
mempool_free(mpio, m->mpio_pool);
return r;
}
/*
* Take a path out of use.
*/
static int fail_path(struct pgpath *pgpath)
{
unsigned long flags;
struct multipath *m = pgpath->pg->m;
spin_lock_irqsave(&m->lock, flags);
if (!pgpath->is_active)
goto out;
DMWARN("Failing path %s.", pgpath->path.dev->name);
pgpath->pg->ps.type->fail_path(&pgpath->pg->ps, &pgpath->path);
pgpath->is_active = 0;
pgpath->fail_count++;
m->nr_valid_paths--;
if (pgpath == m->current_pgpath)
m->current_pgpath = NULL;
dm_path_uevent(DM_UEVENT_PATH_FAILED, m->ti,
pgpath->path.dev->name, m->nr_valid_paths);
queue_work(kmultipathd, &m->trigger_event);
queue_work(kmultipathd, &pgpath->deactivate_path);
out:
spin_unlock_irqrestore(&m->lock, flags);
return 0;
}
/*
* Reinstate a previously-failed path
*/
static int reinstate_path(struct pgpath *pgpath)
{
int r = 0;
unsigned long flags;
struct multipath *m = pgpath->pg->m;
spin_lock_irqsave(&m->lock, flags);
if (pgpath->is_active)
goto out;
if (!pgpath->pg->ps.type->reinstate_path) {
DMWARN("Reinstate path not supported by path selector %s",
pgpath->pg->ps.type->name);
r = -EINVAL;
goto out;
}
r = pgpath->pg->ps.type->reinstate_path(&pgpath->pg->ps, &pgpath->path);
if (r)
goto out;
pgpath->is_active = 1;
m->current_pgpath = NULL;
if (!m->nr_valid_paths++ && m->queue_size)
queue_work(kmultipathd, &m->process_queued_ios);
dm_path_uevent(DM_UEVENT_PATH_REINSTATED, m->ti,
pgpath->path.dev->name, m->nr_valid_paths);
queue_work(kmultipathd, &m->trigger_event);
out:
spin_unlock_irqrestore(&m->lock, flags);
return r;
}
/*
* Fail or reinstate all paths that match the provided struct dm_dev.
*/
static int action_dev(struct multipath *m, struct dm_dev *dev,
action_fn action)
{
int r = 0;
struct pgpath *pgpath;
struct priority_group *pg;
list_for_each_entry(pg, &m->priority_groups, list) {
list_for_each_entry(pgpath, &pg->pgpaths, list) {
if (pgpath->path.dev == dev)
r = action(pgpath);
}
}
return r;
}
/*
* Temporarily try to avoid having to use the specified PG
*/
static void bypass_pg(struct multipath *m, struct priority_group *pg,
int bypassed)
{
unsigned long flags;
spin_lock_irqsave(&m->lock, flags);
pg->bypassed = bypassed;
m->current_pgpath = NULL;
m->current_pg = NULL;
spin_unlock_irqrestore(&m->lock, flags);
queue_work(kmultipathd, &m->trigger_event);
}
/*
* Switch to using the specified PG from the next I/O that gets mapped
*/
static int switch_pg_num(struct multipath *m, const char *pgstr)
{
struct priority_group *pg;
unsigned pgnum;
unsigned long flags;
if (!pgstr || (sscanf(pgstr, "%u", &pgnum) != 1) || !pgnum ||
(pgnum > m->nr_priority_groups)) {
DMWARN("invalid PG number supplied to switch_pg_num");
return -EINVAL;
}
spin_lock_irqsave(&m->lock, flags);
list_for_each_entry(pg, &m->priority_groups, list) {
pg->bypassed = 0;
if (--pgnum)
continue;
m->current_pgpath = NULL;
m->current_pg = NULL;