forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdm-raid.c
1210 lines (1022 loc) · 31.4 KB
/
dm-raid.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) 2010-2011 Neil Brown
* Copyright (C) 2010-2011 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
#include <linux/slab.h>
#include "md.h"
#include "raid1.h"
#include "raid5.h"
#include "bitmap.h"
#include <linux/device-mapper.h>
#define DM_MSG_PREFIX "raid"
/*
* The following flags are used by dm-raid.c to set up the array state.
* They must be cleared before md_run is called.
*/
#define FirstUse 10 /* rdev flag */
struct raid_dev {
/*
* Two DM devices, one to hold metadata and one to hold the
* actual data/parity. The reason for this is to not confuse
* ti->len and give more flexibility in altering size and
* characteristics.
*
* While it is possible for this device to be associated
* with a different physical device than the data_dev, it
* is intended for it to be the same.
* |--------- Physical Device ---------|
* |- meta_dev -|------ data_dev ------|
*/
struct dm_dev *meta_dev;
struct dm_dev *data_dev;
struct mdk_rdev_s rdev;
};
/*
* Flags for rs->print_flags field.
*/
#define DMPF_SYNC 0x1
#define DMPF_NOSYNC 0x2
#define DMPF_REBUILD 0x4
#define DMPF_DAEMON_SLEEP 0x8
#define DMPF_MIN_RECOVERY_RATE 0x10
#define DMPF_MAX_RECOVERY_RATE 0x20
#define DMPF_MAX_WRITE_BEHIND 0x40
#define DMPF_STRIPE_CACHE 0x80
#define DMPF_REGION_SIZE 0X100
struct raid_set {
struct dm_target *ti;
uint64_t print_flags;
struct mddev_s md;
struct raid_type *raid_type;
struct dm_target_callbacks callbacks;
struct raid_dev dev[0];
};
/* Supported raid types and properties. */
static struct raid_type {
const char *name; /* RAID algorithm. */
const char *descr; /* Descriptor text for logging. */
const unsigned parity_devs; /* # of parity devices. */
const unsigned minimal_devs; /* minimal # of devices in set. */
const unsigned level; /* RAID level. */
const unsigned algorithm; /* RAID algorithm. */
} raid_types[] = {
{"raid1", "RAID1 (mirroring)", 0, 2, 1, 0 /* NONE */},
{"raid4", "RAID4 (dedicated parity disk)", 1, 2, 5, ALGORITHM_PARITY_0},
{"raid5_la", "RAID5 (left asymmetric)", 1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC},
{"raid5_ra", "RAID5 (right asymmetric)", 1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC},
{"raid5_ls", "RAID5 (left symmetric)", 1, 2, 5, ALGORITHM_LEFT_SYMMETRIC},
{"raid5_rs", "RAID5 (right symmetric)", 1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC},
{"raid6_zr", "RAID6 (zero restart)", 2, 4, 6, ALGORITHM_ROTATING_ZERO_RESTART},
{"raid6_nr", "RAID6 (N restart)", 2, 4, 6, ALGORITHM_ROTATING_N_RESTART},
{"raid6_nc", "RAID6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE}
};
static struct raid_type *get_raid_type(char *name)
{
int i;
for (i = 0; i < ARRAY_SIZE(raid_types); i++)
if (!strcmp(raid_types[i].name, name))
return &raid_types[i];
return NULL;
}
static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *raid_type, unsigned raid_devs)
{
unsigned i;
struct raid_set *rs;
sector_t sectors_per_dev;
if (raid_devs <= raid_type->parity_devs) {
ti->error = "Insufficient number of devices";
return ERR_PTR(-EINVAL);
}
sectors_per_dev = ti->len;
if ((raid_type->level > 1) &&
sector_div(sectors_per_dev, (raid_devs - raid_type->parity_devs))) {
ti->error = "Target length not divisible by number of data devices";
return ERR_PTR(-EINVAL);
}
rs = kzalloc(sizeof(*rs) + raid_devs * sizeof(rs->dev[0]), GFP_KERNEL);
if (!rs) {
ti->error = "Cannot allocate raid context";
return ERR_PTR(-ENOMEM);
}
mddev_init(&rs->md);
rs->ti = ti;
rs->raid_type = raid_type;
rs->md.raid_disks = raid_devs;
rs->md.level = raid_type->level;
rs->md.new_level = rs->md.level;
rs->md.dev_sectors = sectors_per_dev;
rs->md.layout = raid_type->algorithm;
rs->md.new_layout = rs->md.layout;
rs->md.delta_disks = 0;
rs->md.recovery_cp = 0;
for (i = 0; i < raid_devs; i++)
md_rdev_init(&rs->dev[i].rdev);
/*
* Remaining items to be initialized by further RAID params:
* rs->md.persistent
* rs->md.external
* rs->md.chunk_sectors
* rs->md.new_chunk_sectors
*/
return rs;
}
static void context_free(struct raid_set *rs)
{
int i;
for (i = 0; i < rs->md.raid_disks; i++) {
if (rs->dev[i].meta_dev)
dm_put_device(rs->ti, rs->dev[i].meta_dev);
if (rs->dev[i].rdev.sb_page)
put_page(rs->dev[i].rdev.sb_page);
rs->dev[i].rdev.sb_page = NULL;
rs->dev[i].rdev.sb_loaded = 0;
if (rs->dev[i].data_dev)
dm_put_device(rs->ti, rs->dev[i].data_dev);
}
kfree(rs);
}
/*
* For every device we have two words
* <meta_dev>: meta device name or '-' if missing
* <data_dev>: data device name or '-' if missing
*
* The following are permitted:
* - -
* - <data_dev>
* <meta_dev> <data_dev>
*
* The following is not allowed:
* <meta_dev> -
*
* This code parses those words. If there is a failure,
* the caller must use context_free to unwind the operations.
*/
static int dev_parms(struct raid_set *rs, char **argv)
{
int i;
int rebuild = 0;
int metadata_available = 0;
int ret = 0;
for (i = 0; i < rs->md.raid_disks; i++, argv += 2) {
rs->dev[i].rdev.raid_disk = i;
rs->dev[i].meta_dev = NULL;
rs->dev[i].data_dev = NULL;
/*
* There are no offsets, since there is a separate device
* for data and metadata.
*/
rs->dev[i].rdev.data_offset = 0;
rs->dev[i].rdev.mddev = &rs->md;
if (strcmp(argv[0], "-")) {
ret = dm_get_device(rs->ti, argv[0],
dm_table_get_mode(rs->ti->table),
&rs->dev[i].meta_dev);
rs->ti->error = "RAID metadata device lookup failure";
if (ret)
return ret;
rs->dev[i].rdev.sb_page = alloc_page(GFP_KERNEL);
if (!rs->dev[i].rdev.sb_page)
return -ENOMEM;
}
if (!strcmp(argv[1], "-")) {
if (!test_bit(In_sync, &rs->dev[i].rdev.flags) &&
(!rs->dev[i].rdev.recovery_offset)) {
rs->ti->error = "Drive designated for rebuild not specified";
return -EINVAL;
}
rs->ti->error = "No data device supplied with metadata device";
if (rs->dev[i].meta_dev)
return -EINVAL;
continue;
}
ret = dm_get_device(rs->ti, argv[1],
dm_table_get_mode(rs->ti->table),
&rs->dev[i].data_dev);
if (ret) {
rs->ti->error = "RAID device lookup failure";
return ret;
}
if (rs->dev[i].meta_dev) {
metadata_available = 1;
rs->dev[i].rdev.meta_bdev = rs->dev[i].meta_dev->bdev;
}
rs->dev[i].rdev.bdev = rs->dev[i].data_dev->bdev;
list_add(&rs->dev[i].rdev.same_set, &rs->md.disks);
if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
rebuild++;
}
if (metadata_available) {
rs->md.external = 0;
rs->md.persistent = 1;
rs->md.major_version = 2;
} else if (rebuild && !rs->md.recovery_cp) {
/*
* Without metadata, we will not be able to tell if the array
* is in-sync or not - we must assume it is not. Therefore,
* it is impossible to rebuild a drive.
*
* Even if there is metadata, the on-disk information may
* indicate that the array is not in-sync and it will then
* fail at that time.
*
* User could specify 'nosync' option if desperate.
*/
DMERR("Unable to rebuild drive while array is not in-sync");
rs->ti->error = "RAID device lookup failure";
return -EINVAL;
}
return 0;
}
/*
* validate_region_size
* @rs
* @region_size: region size in sectors. If 0, pick a size (4MiB default).
*
* Set rs->md.bitmap_info.chunksize (which really refers to 'region size').
* Ensure that (ti->len/region_size < 2^21) - required by MD bitmap.
*
* Returns: 0 on success, -EINVAL on failure.
*/
static int validate_region_size(struct raid_set *rs, unsigned long region_size)
{
unsigned long min_region_size = rs->ti->len / (1 << 21);
if (!region_size) {
/*
* Choose a reasonable default. All figures in sectors.
*/
if (min_region_size > (1 << 13)) {
DMINFO("Choosing default region size of %lu sectors",
region_size);
region_size = min_region_size;
} else {
DMINFO("Choosing default region size of 4MiB");
region_size = 1 << 13; /* sectors */
}
} else {
/*
* Validate user-supplied value.
*/
if (region_size > rs->ti->len) {
rs->ti->error = "Supplied region size is too large";
return -EINVAL;
}
if (region_size < min_region_size) {
DMERR("Supplied region_size (%lu sectors) below minimum (%lu)",
region_size, min_region_size);
rs->ti->error = "Supplied region size is too small";
return -EINVAL;
}
if (!is_power_of_2(region_size)) {
rs->ti->error = "Region size is not a power of 2";
return -EINVAL;
}
if (region_size < rs->md.chunk_sectors) {
rs->ti->error = "Region size is smaller than the chunk size";
return -EINVAL;
}
}
/*
* Convert sectors to bytes.
*/
rs->md.bitmap_info.chunksize = (region_size << 9);
return 0;
}
/*
* Possible arguments are...
* <chunk_size> [optional_args]
*
* Argument definitions
* <chunk_size> The number of sectors per disk that
* will form the "stripe"
* [[no]sync] Force or prevent recovery of the
* entire array
* [rebuild <idx>] Rebuild the drive indicated by the index
* [daemon_sleep <ms>] Time between bitmap daemon work to
* clear bits
* [min_recovery_rate <kB/sec/disk>] Throttle RAID initialization
* [max_recovery_rate <kB/sec/disk>] Throttle RAID initialization
* [write_mostly <idx>] Indicate a write mostly drive via index
* [max_write_behind <sectors>] See '-write-behind=' (man mdadm)
* [stripe_cache <sectors>] Stripe cache size for higher RAIDs
* [region_size <sectors>] Defines granularity of bitmap
*/
static int parse_raid_params(struct raid_set *rs, char **argv,
unsigned num_raid_params)
{
unsigned i, rebuild_cnt = 0;
unsigned long value, region_size = 0;
char *key;
/*
* First, parse the in-order required arguments
* "chunk_size" is the only argument of this type.
*/
if ((strict_strtoul(argv[0], 10, &value) < 0)) {
rs->ti->error = "Bad chunk size";
return -EINVAL;
} else if (rs->raid_type->level == 1) {
if (value)
DMERR("Ignoring chunk size parameter for RAID 1");
value = 0;
} else if (!is_power_of_2(value)) {
rs->ti->error = "Chunk size must be a power of 2";
return -EINVAL;
} else if (value < 8) {
rs->ti->error = "Chunk size value is too small";
return -EINVAL;
}
rs->md.new_chunk_sectors = rs->md.chunk_sectors = value;
argv++;
num_raid_params--;
/*
* We set each individual device as In_sync with a completed
* 'recovery_offset'. If there has been a device failure or
* replacement then one of the following cases applies:
*
* 1) User specifies 'rebuild'.
* - Device is reset when param is read.
* 2) A new device is supplied.
* - No matching superblock found, resets device.
* 3) Device failure was transient and returns on reload.
* - Failure noticed, resets device for bitmap replay.
* 4) Device hadn't completed recovery after previous failure.
* - Superblock is read and overrides recovery_offset.
*
* What is found in the superblocks of the devices is always
* authoritative, unless 'rebuild' or '[no]sync' was specified.
*/
for (i = 0; i < rs->md.raid_disks; i++) {
set_bit(In_sync, &rs->dev[i].rdev.flags);
rs->dev[i].rdev.recovery_offset = MaxSector;
}
/*
* Second, parse the unordered optional arguments
*/
for (i = 0; i < num_raid_params; i++) {
if (!strcasecmp(argv[i], "nosync")) {
rs->md.recovery_cp = MaxSector;
rs->print_flags |= DMPF_NOSYNC;
continue;
}
if (!strcasecmp(argv[i], "sync")) {
rs->md.recovery_cp = 0;
rs->print_flags |= DMPF_SYNC;
continue;
}
/* The rest of the optional arguments come in key/value pairs */
if ((i + 1) >= num_raid_params) {
rs->ti->error = "Wrong number of raid parameters given";
return -EINVAL;
}
key = argv[i++];
if (strict_strtoul(argv[i], 10, &value) < 0) {
rs->ti->error = "Bad numerical argument given in raid params";
return -EINVAL;
}
if (!strcasecmp(key, "rebuild")) {
rebuild_cnt++;
if (((rs->raid_type->level != 1) &&
(rebuild_cnt > rs->raid_type->parity_devs)) ||
((rs->raid_type->level == 1) &&
(rebuild_cnt > (rs->md.raid_disks - 1)))) {
rs->ti->error = "Too many rebuild devices specified for given RAID type";
return -EINVAL;
}
if (value > rs->md.raid_disks) {
rs->ti->error = "Invalid rebuild index given";
return -EINVAL;
}
clear_bit(In_sync, &rs->dev[value].rdev.flags);
rs->dev[value].rdev.recovery_offset = 0;
rs->print_flags |= DMPF_REBUILD;
} else if (!strcasecmp(key, "write_mostly")) {
if (rs->raid_type->level != 1) {
rs->ti->error = "write_mostly option is only valid for RAID1";
return -EINVAL;
}
if (value > rs->md.raid_disks) {
rs->ti->error = "Invalid write_mostly drive index given";
return -EINVAL;
}
set_bit(WriteMostly, &rs->dev[value].rdev.flags);
} else if (!strcasecmp(key, "max_write_behind")) {
if (rs->raid_type->level != 1) {
rs->ti->error = "max_write_behind option is only valid for RAID1";
return -EINVAL;
}
rs->print_flags |= DMPF_MAX_WRITE_BEHIND;
/*
* In device-mapper, we specify things in sectors, but
* MD records this value in kB
*/
value /= 2;
if (value > COUNTER_MAX) {
rs->ti->error = "Max write-behind limit out of range";
return -EINVAL;
}
rs->md.bitmap_info.max_write_behind = value;
} else if (!strcasecmp(key, "daemon_sleep")) {
rs->print_flags |= DMPF_DAEMON_SLEEP;
if (!value || (value > MAX_SCHEDULE_TIMEOUT)) {
rs->ti->error = "daemon sleep period out of range";
return -EINVAL;
}
rs->md.bitmap_info.daemon_sleep = value;
} else if (!strcasecmp(key, "stripe_cache")) {
rs->print_flags |= DMPF_STRIPE_CACHE;
/*
* In device-mapper, we specify things in sectors, but
* MD records this value in kB
*/
value /= 2;
if (rs->raid_type->level < 5) {
rs->ti->error = "Inappropriate argument: stripe_cache";
return -EINVAL;
}
if (raid5_set_cache_size(&rs->md, (int)value)) {
rs->ti->error = "Bad stripe_cache size";
return -EINVAL;
}
} else if (!strcasecmp(key, "min_recovery_rate")) {
rs->print_flags |= DMPF_MIN_RECOVERY_RATE;
if (value > INT_MAX) {
rs->ti->error = "min_recovery_rate out of range";
return -EINVAL;
}
rs->md.sync_speed_min = (int)value;
} else if (!strcasecmp(key, "max_recovery_rate")) {
rs->print_flags |= DMPF_MAX_RECOVERY_RATE;
if (value > INT_MAX) {
rs->ti->error = "max_recovery_rate out of range";
return -EINVAL;
}
rs->md.sync_speed_max = (int)value;
} else if (!strcasecmp(key, "region_size")) {
rs->print_flags |= DMPF_REGION_SIZE;
region_size = value;
} else {
DMERR("Unable to parse RAID parameter: %s", key);
rs->ti->error = "Unable to parse RAID parameters";
return -EINVAL;
}
}
if (validate_region_size(rs, region_size))
return -EINVAL;
if (rs->md.chunk_sectors)
rs->ti->split_io = rs->md.chunk_sectors;
else
rs->ti->split_io = region_size;
if (rs->md.chunk_sectors)
rs->ti->split_io = rs->md.chunk_sectors;
else
rs->ti->split_io = region_size;
/* Assume there are no metadata devices until the drives are parsed */
rs->md.persistent = 0;
rs->md.external = 1;
return 0;
}
static void do_table_event(struct work_struct *ws)
{
struct raid_set *rs = container_of(ws, struct raid_set, md.event_work);
dm_table_event(rs->ti->table);
}
static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
{
struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
if (rs->raid_type->level == 1)
return md_raid1_congested(&rs->md, bits);
return md_raid5_congested(&rs->md, bits);
}
/*
* This structure is never routinely used by userspace, unlike md superblocks.
* Devices with this superblock should only ever be accessed via device-mapper.
*/
#define DM_RAID_MAGIC 0x64526D44
struct dm_raid_superblock {
__le32 magic; /* "DmRd" */
__le32 features; /* Used to indicate possible future changes */
__le32 num_devices; /* Number of devices in this array. (Max 64) */
__le32 array_position; /* The position of this drive in the array */
__le64 events; /* Incremented by md when superblock updated */
__le64 failed_devices; /* Bit field of devices to indicate failures */
/*
* This offset tracks the progress of the repair or replacement of
* an individual drive.
*/
__le64 disk_recovery_offset;
/*
* This offset tracks the progress of the initial array
* synchronisation/parity calculation.
*/
__le64 array_resync_offset;
/*
* RAID characteristics
*/
__le32 level;
__le32 layout;
__le32 stripe_sectors;
__u8 pad[452]; /* Round struct to 512 bytes. */
/* Always set to 0 when writing. */
} __packed;
static int read_disk_sb(mdk_rdev_t *rdev, int size)
{
BUG_ON(!rdev->sb_page);
if (rdev->sb_loaded)
return 0;
if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, 1)) {
DMERR("Failed to read device superblock");
return -EINVAL;
}
rdev->sb_loaded = 1;
return 0;
}
static void super_sync(mddev_t *mddev, mdk_rdev_t *rdev)
{
mdk_rdev_t *r, *t;
uint64_t failed_devices;
struct dm_raid_superblock *sb;
sb = page_address(rdev->sb_page);
failed_devices = le64_to_cpu(sb->failed_devices);
rdev_for_each(r, t, mddev)
if ((r->raid_disk >= 0) && test_bit(Faulty, &r->flags))
failed_devices |= (1ULL << r->raid_disk);
memset(sb, 0, sizeof(*sb));
sb->magic = cpu_to_le32(DM_RAID_MAGIC);
sb->features = cpu_to_le32(0); /* No features yet */
sb->num_devices = cpu_to_le32(mddev->raid_disks);
sb->array_position = cpu_to_le32(rdev->raid_disk);
sb->events = cpu_to_le64(mddev->events);
sb->failed_devices = cpu_to_le64(failed_devices);
sb->disk_recovery_offset = cpu_to_le64(rdev->recovery_offset);
sb->array_resync_offset = cpu_to_le64(mddev->recovery_cp);
sb->level = cpu_to_le32(mddev->level);
sb->layout = cpu_to_le32(mddev->layout);
sb->stripe_sectors = cpu_to_le32(mddev->chunk_sectors);
}
/*
* super_load
*
* This function creates a superblock if one is not found on the device
* and will decide which superblock to use if there's a choice.
*
* Return: 1 if use rdev, 0 if use refdev, -Exxx otherwise
*/
static int super_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev)
{
int ret;
struct dm_raid_superblock *sb;
struct dm_raid_superblock *refsb;
uint64_t events_sb, events_refsb;
rdev->sb_start = 0;
rdev->sb_size = sizeof(*sb);
ret = read_disk_sb(rdev, rdev->sb_size);
if (ret)
return ret;
sb = page_address(rdev->sb_page);
if (sb->magic != cpu_to_le32(DM_RAID_MAGIC)) {
super_sync(rdev->mddev, rdev);
set_bit(FirstUse, &rdev->flags);
/* Force writing of superblocks to disk */
set_bit(MD_CHANGE_DEVS, &rdev->mddev->flags);
/* Any superblock is better than none, choose that if given */
return refdev ? 0 : 1;
}
if (!refdev)
return 1;
events_sb = le64_to_cpu(sb->events);
refsb = page_address(refdev->sb_page);
events_refsb = le64_to_cpu(refsb->events);
return (events_sb > events_refsb) ? 1 : 0;
}
static int super_init_validation(mddev_t *mddev, mdk_rdev_t *rdev)
{
int role;
struct raid_set *rs = container_of(mddev, struct raid_set, md);
uint64_t events_sb;
uint64_t failed_devices;
struct dm_raid_superblock *sb;
uint32_t new_devs = 0;
uint32_t rebuilds = 0;
mdk_rdev_t *r, *t;
struct dm_raid_superblock *sb2;
sb = page_address(rdev->sb_page);
events_sb = le64_to_cpu(sb->events);
failed_devices = le64_to_cpu(sb->failed_devices);
/*
* Initialise to 1 if this is a new superblock.
*/
mddev->events = events_sb ? : 1;
/*
* Reshaping is not currently allowed
*/
if ((le32_to_cpu(sb->level) != mddev->level) ||
(le32_to_cpu(sb->layout) != mddev->layout) ||
(le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors)) {
DMERR("Reshaping arrays not yet supported.");
return -EINVAL;
}
/* We can only change the number of devices in RAID1 right now */
if ((rs->raid_type->level != 1) &&
(le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
DMERR("Reshaping arrays not yet supported.");
return -EINVAL;
}
if (!(rs->print_flags & (DMPF_SYNC | DMPF_NOSYNC)))
mddev->recovery_cp = le64_to_cpu(sb->array_resync_offset);
/*
* During load, we set FirstUse if a new superblock was written.
* There are two reasons we might not have a superblock:
* 1) The array is brand new - in which case, all of the
* devices must have their In_sync bit set. Also,
* recovery_cp must be 0, unless forced.
* 2) This is a new device being added to an old array
* and the new device needs to be rebuilt - in which
* case the In_sync bit will /not/ be set and
* recovery_cp must be MaxSector.
*/
rdev_for_each(r, t, mddev) {
if (!test_bit(In_sync, &r->flags)) {
if (!test_bit(FirstUse, &r->flags))
DMERR("Superblock area of "
"rebuild device %d should have been "
"cleared.", r->raid_disk);
set_bit(FirstUse, &r->flags);
rebuilds++;
} else if (test_bit(FirstUse, &r->flags))
new_devs++;
}
if (!rebuilds) {
if (new_devs == mddev->raid_disks) {
DMINFO("Superblocks created for new array");
set_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
} else if (new_devs) {
DMERR("New device injected "
"into existing array without 'rebuild' "
"parameter specified");
return -EINVAL;
}
} else if (new_devs) {
DMERR("'rebuild' devices cannot be "
"injected into an array with other first-time devices");
return -EINVAL;
} else if (mddev->recovery_cp != MaxSector) {
DMERR("'rebuild' specified while array is not in-sync");
return -EINVAL;
}
/*
* Now we set the Faulty bit for those devices that are
* recorded in the superblock as failed.
*/
rdev_for_each(r, t, mddev) {
if (!r->sb_page)
continue;
sb2 = page_address(r->sb_page);
sb2->failed_devices = 0;
/*
* Check for any device re-ordering.
*/
if (!test_bit(FirstUse, &r->flags) && (r->raid_disk >= 0)) {
role = le32_to_cpu(sb2->array_position);
if (role != r->raid_disk) {
if (rs->raid_type->level != 1) {
rs->ti->error = "Cannot change device "
"positions in RAID array";
return -EINVAL;
}
DMINFO("RAID1 device #%d now at position #%d",
role, r->raid_disk);
}
/*
* Partial recovery is performed on
* returning failed devices.
*/
if (failed_devices & (1 << role))
set_bit(Faulty, &r->flags);
}
}
return 0;
}
static int super_validate(mddev_t *mddev, mdk_rdev_t *rdev)
{
struct dm_raid_superblock *sb = page_address(rdev->sb_page);
/*
* If mddev->events is not set, we know we have not yet initialized
* the array.
*/
if (!mddev->events && super_init_validation(mddev, rdev))
return -EINVAL;
mddev->bitmap_info.offset = 4096 >> 9; /* Enable bitmap creation */
rdev->mddev->bitmap_info.default_offset = 4096 >> 9;
if (!test_bit(FirstUse, &rdev->flags)) {
rdev->recovery_offset = le64_to_cpu(sb->disk_recovery_offset);
if (rdev->recovery_offset != MaxSector)
clear_bit(In_sync, &rdev->flags);
}
/*
* If a device comes back, set it as not In_sync and no longer faulty.
*/
if (test_bit(Faulty, &rdev->flags)) {
clear_bit(Faulty, &rdev->flags);
clear_bit(In_sync, &rdev->flags);
rdev->saved_raid_disk = rdev->raid_disk;
rdev->recovery_offset = 0;
}
clear_bit(FirstUse, &rdev->flags);
return 0;
}
/*
* Analyse superblocks and select the freshest.
*/
static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
{
int ret;
mdk_rdev_t *rdev, *freshest, *tmp;
mddev_t *mddev = &rs->md;
freshest = NULL;
rdev_for_each(rdev, tmp, mddev) {
if (!rdev->meta_bdev)
continue;
ret = super_load(rdev, freshest);
switch (ret) {
case 1:
freshest = rdev;
break;
case 0:
break;
default:
ti->error = "Failed to load superblock";
return ret;
}
}
if (!freshest)
return 0;
/*
* Validation of the freshest device provides the source of
* validation for the remaining devices.
*/
ti->error = "Unable to assemble array: Invalid superblocks";
if (super_validate(mddev, freshest))
return -EINVAL;
rdev_for_each(rdev, tmp, mddev)
if ((rdev != freshest) && super_validate(mddev, rdev))
return -EINVAL;
return 0;
}
/*
* Construct a RAID4/5/6 mapping:
* Args:
* <raid_type> <#raid_params> <raid_params> \
* <#raid_devs> { <meta_dev1> <dev1> .. <meta_devN> <devN> }
*
* <raid_params> varies by <raid_type>. See 'parse_raid_params' for
* details on possible <raid_params>.
*/
static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
{
int ret;
struct raid_type *rt;
unsigned long num_raid_params, num_raid_devs;
struct raid_set *rs = NULL;
/* Must have at least <raid_type> <#raid_params> */
if (argc < 2) {
ti->error = "Too few arguments";
return -EINVAL;
}
/* raid type */
rt = get_raid_type(argv[0]);
if (!rt) {
ti->error = "Unrecognised raid_type";
return -EINVAL;
}
argc--;
argv++;
/* number of RAID parameters */
if (strict_strtoul(argv[0], 10, &num_raid_params) < 0) {
ti->error = "Cannot understand number of RAID parameters";
return -EINVAL;
}
argc--;
argv++;
/* Skip over RAID params for now and find out # of devices */
if (num_raid_params + 1 > argc) {
ti->error = "Arguments do not agree with counts given";
return -EINVAL;
}
if ((strict_strtoul(argv[num_raid_params], 10, &num_raid_devs) < 0) ||
(num_raid_devs >= INT_MAX)) {
ti->error = "Cannot understand number of raid devices";
return -EINVAL;
}
rs = context_alloc(ti, rt, (unsigned)num_raid_devs);
if (IS_ERR(rs))
return PTR_ERR(rs);
ret = parse_raid_params(rs, argv, (unsigned)num_raid_params);
if (ret)
goto bad;
ret = -EINVAL;
argc -= num_raid_params + 1; /* +1: we already have num_raid_devs */
argv += num_raid_params + 1;
if (argc != (num_raid_devs * 2)) {
ti->error = "Supplied RAID devices does not match the count given";
goto bad;
}
ret = dev_parms(rs, argv);
if (ret)
goto bad;
rs->md.sync_super = super_sync;
ret = analyse_superblocks(ti, rs);
if (ret)
goto bad;
INIT_WORK(&rs->md.event_work, do_table_event);
ti->private = rs;
mutex_lock(&rs->md.reconfig_mutex);
ret = md_run(&rs->md);
rs->md.in_sync = 0; /* Assume already marked dirty */
mutex_unlock(&rs->md.reconfig_mutex);
if (ret) {
ti->error = "Fail to run raid array";
goto bad;
}
rs->callbacks.congested_fn = raid_is_congested;
dm_table_add_target_callbacks(ti->table, &rs->callbacks);
mddev_suspend(&rs->md);
return 0;
bad:
context_free(rs);
return ret;
}
static void raid_dtr(struct dm_target *ti)
{
struct raid_set *rs = ti->private;
list_del_init(&rs->callbacks.list);
md_stop(&rs->md);