forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathraid1.c
3363 lines (2978 loc) · 91.5 KB
/
raid1.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
/*
* raid1.c : Multiple Devices driver for Linux
*
* Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat
*
* Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman
*
* RAID-1 management functions.
*
* Better read-balancing code written by Mika Kuoppala <[email protected]>, 2000
*
* Fixes to reconstruction by Jakob Østergaard" <[email protected]>
* Various fixes by Neil Brown <[email protected]>
*
* Changes by Peter T. Breuer <[email protected]> 31/1/2003 to support
* bitmapped intelligence in resync:
*
* - bitmap marked during normal i/o
* - bitmap used to skip nondirty blocks during sync
*
* Additions to bitmap code, (C) 2003-2004 Paul Clements, SteelEye Technology:
* - persistent bitmap code
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* You should have received a copy of the GNU General Public License
* (for example /usr/src/linux/COPYING); if not, write to the Free
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/ratelimit.h>
#include <trace/events/block.h>
#include "md.h"
#include "raid1.h"
#include "md-bitmap.h"
#define UNSUPPORTED_MDDEV_FLAGS \
((1L << MD_HAS_JOURNAL) | \
(1L << MD_JOURNAL_CLEAN) | \
(1L << MD_HAS_PPL) | \
(1L << MD_HAS_MULTIPLE_PPLS))
/*
* Number of guaranteed r1bios in case of extreme VM load:
*/
#define NR_RAID1_BIOS 256
/* when we get a read error on a read-only array, we redirect to another
* device without failing the first device, or trying to over-write to
* correct the read error. To keep track of bad blocks on a per-bio
* level, we store IO_BLOCKED in the appropriate 'bios' pointer
*/
#define IO_BLOCKED ((struct bio *)1)
/* When we successfully write to a known bad-block, we need to remove the
* bad-block marking which must be done from process context. So we record
* the success by setting devs[n].bio to IO_MADE_GOOD
*/
#define IO_MADE_GOOD ((struct bio *)2)
#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
/* When there are this many requests queue to be written by
* the raid1 thread, we become 'congested' to provide back-pressure
* for writeback.
*/
static int max_queued_requests = 1024;
static void allow_barrier(struct r1conf *conf, sector_t sector_nr);
static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
#define raid1_log(md, fmt, args...) \
do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
#include "raid1-10.c"
/*
* for resync bio, r1bio pointer can be retrieved from the per-bio
* 'struct resync_pages'.
*/
static inline struct r1bio *get_resync_r1bio(struct bio *bio)
{
return get_resync_pages(bio)->raid_bio;
}
static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
{
struct pool_info *pi = data;
int size = offsetof(struct r1bio, bios[pi->raid_disks]);
/* allocate a r1bio with room for raid_disks entries in the bios array */
return kzalloc(size, gfp_flags);
}
static void r1bio_pool_free(void *r1_bio, void *data)
{
kfree(r1_bio);
}
#define RESYNC_DEPTH 32
#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
#define RESYNC_WINDOW (RESYNC_BLOCK_SIZE * RESYNC_DEPTH)
#define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9)
#define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW)
#define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9)
static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
{
struct pool_info *pi = data;
struct r1bio *r1_bio;
struct bio *bio;
int need_pages;
int j;
struct resync_pages *rps;
r1_bio = r1bio_pool_alloc(gfp_flags, pi);
if (!r1_bio)
return NULL;
rps = kmalloc_array(pi->raid_disks, sizeof(struct resync_pages),
gfp_flags);
if (!rps)
goto out_free_r1bio;
/*
* Allocate bios : 1 for reading, n-1 for writing
*/
for (j = pi->raid_disks ; j-- ; ) {
bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
if (!bio)
goto out_free_bio;
r1_bio->bios[j] = bio;
}
/*
* Allocate RESYNC_PAGES data pages and attach them to
* the first bio.
* If this is a user-requested check/repair, allocate
* RESYNC_PAGES for each bio.
*/
if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
need_pages = pi->raid_disks;
else
need_pages = 1;
for (j = 0; j < pi->raid_disks; j++) {
struct resync_pages *rp = &rps[j];
bio = r1_bio->bios[j];
if (j < need_pages) {
if (resync_alloc_pages(rp, gfp_flags))
goto out_free_pages;
} else {
memcpy(rp, &rps[0], sizeof(*rp));
resync_get_all_pages(rp);
}
rp->raid_bio = r1_bio;
bio->bi_private = rp;
}
r1_bio->master_bio = NULL;
return r1_bio;
out_free_pages:
while (--j >= 0)
resync_free_pages(&rps[j]);
out_free_bio:
while (++j < pi->raid_disks)
bio_put(r1_bio->bios[j]);
kfree(rps);
out_free_r1bio:
r1bio_pool_free(r1_bio, data);
return NULL;
}
static void r1buf_pool_free(void *__r1_bio, void *data)
{
struct pool_info *pi = data;
int i;
struct r1bio *r1bio = __r1_bio;
struct resync_pages *rp = NULL;
for (i = pi->raid_disks; i--; ) {
rp = get_resync_pages(r1bio->bios[i]);
resync_free_pages(rp);
bio_put(r1bio->bios[i]);
}
/* resync pages array stored in the 1st bio's .bi_private */
kfree(rp);
r1bio_pool_free(r1bio, data);
}
static void put_all_bios(struct r1conf *conf, struct r1bio *r1_bio)
{
int i;
for (i = 0; i < conf->raid_disks * 2; i++) {
struct bio **bio = r1_bio->bios + i;
if (!BIO_SPECIAL(*bio))
bio_put(*bio);
*bio = NULL;
}
}
static void free_r1bio(struct r1bio *r1_bio)
{
struct r1conf *conf = r1_bio->mddev->private;
put_all_bios(conf, r1_bio);
mempool_free(r1_bio, &conf->r1bio_pool);
}
static void put_buf(struct r1bio *r1_bio)
{
struct r1conf *conf = r1_bio->mddev->private;
sector_t sect = r1_bio->sector;
int i;
for (i = 0; i < conf->raid_disks * 2; i++) {
struct bio *bio = r1_bio->bios[i];
if (bio->bi_end_io)
rdev_dec_pending(conf->mirrors[i].rdev, r1_bio->mddev);
}
mempool_free(r1_bio, &conf->r1buf_pool);
lower_barrier(conf, sect);
}
static void reschedule_retry(struct r1bio *r1_bio)
{
unsigned long flags;
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
int idx;
idx = sector_to_idx(r1_bio->sector);
spin_lock_irqsave(&conf->device_lock, flags);
list_add(&r1_bio->retry_list, &conf->retry_list);
atomic_inc(&conf->nr_queued[idx]);
spin_unlock_irqrestore(&conf->device_lock, flags);
wake_up(&conf->wait_barrier);
md_wakeup_thread(mddev->thread);
}
/*
* raid_end_bio_io() is called when we have finished servicing a mirrored
* operation and are ready to return a success/failure code to the buffer
* cache layer.
*/
static void call_bio_endio(struct r1bio *r1_bio)
{
struct bio *bio = r1_bio->master_bio;
struct r1conf *conf = r1_bio->mddev->private;
if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
/*
* Wake up any possible resync thread that waits for the device
* to go idle.
*/
allow_barrier(conf, r1_bio->sector);
}
static void raid_end_bio_io(struct r1bio *r1_bio)
{
struct bio *bio = r1_bio->master_bio;
/* if nobody has done the final endio yet, do it now */
if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
pr_debug("raid1: sync end %s on sectors %llu-%llu\n",
(bio_data_dir(bio) == WRITE) ? "write" : "read",
(unsigned long long) bio->bi_iter.bi_sector,
(unsigned long long) bio_end_sector(bio) - 1);
call_bio_endio(r1_bio);
}
free_r1bio(r1_bio);
}
/*
* Update disk head position estimator based on IRQ completion info.
*/
static inline void update_head_pos(int disk, struct r1bio *r1_bio)
{
struct r1conf *conf = r1_bio->mddev->private;
conf->mirrors[disk].head_position =
r1_bio->sector + (r1_bio->sectors);
}
/*
* Find the disk number which triggered given bio
*/
static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio)
{
int mirror;
struct r1conf *conf = r1_bio->mddev->private;
int raid_disks = conf->raid_disks;
for (mirror = 0; mirror < raid_disks * 2; mirror++)
if (r1_bio->bios[mirror] == bio)
break;
BUG_ON(mirror == raid_disks * 2);
update_head_pos(mirror, r1_bio);
return mirror;
}
static void raid1_end_read_request(struct bio *bio)
{
int uptodate = !bio->bi_status;
struct r1bio *r1_bio = bio->bi_private;
struct r1conf *conf = r1_bio->mddev->private;
struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
update_head_pos(r1_bio->read_disk, r1_bio);
if (uptodate)
set_bit(R1BIO_Uptodate, &r1_bio->state);
else if (test_bit(FailFast, &rdev->flags) &&
test_bit(R1BIO_FailFast, &r1_bio->state))
/* This was a fail-fast read so we definitely
* want to retry */
;
else {
/* If all other devices have failed, we want to return
* the error upwards rather than fail the last device.
* Here we redefine "uptodate" to mean "Don't want to retry"
*/
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
if (r1_bio->mddev->degraded == conf->raid_disks ||
(r1_bio->mddev->degraded == conf->raid_disks-1 &&
test_bit(In_sync, &rdev->flags)))
uptodate = 1;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
if (uptodate) {
raid_end_bio_io(r1_bio);
rdev_dec_pending(rdev, conf->mddev);
} else {
/*
* oops, read error:
*/
char b[BDEVNAME_SIZE];
pr_err_ratelimited("md/raid1:%s: %s: rescheduling sector %llu\n",
mdname(conf->mddev),
bdevname(rdev->bdev, b),
(unsigned long long)r1_bio->sector);
set_bit(R1BIO_ReadError, &r1_bio->state);
reschedule_retry(r1_bio);
/* don't drop the reference on read_disk yet */
}
}
static void close_write(struct r1bio *r1_bio)
{
/* it really is the end of this request */
if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
bio_free_pages(r1_bio->behind_master_bio);
bio_put(r1_bio->behind_master_bio);
r1_bio->behind_master_bio = NULL;
}
/* clear the bitmap if all writes complete successfully */
md_bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
r1_bio->sectors,
!test_bit(R1BIO_Degraded, &r1_bio->state),
test_bit(R1BIO_BehindIO, &r1_bio->state));
md_write_end(r1_bio->mddev);
}
static void r1_bio_write_done(struct r1bio *r1_bio)
{
if (!atomic_dec_and_test(&r1_bio->remaining))
return;
if (test_bit(R1BIO_WriteError, &r1_bio->state))
reschedule_retry(r1_bio);
else {
close_write(r1_bio);
if (test_bit(R1BIO_MadeGood, &r1_bio->state))
reschedule_retry(r1_bio);
else
raid_end_bio_io(r1_bio);
}
}
static void raid1_end_write_request(struct bio *bio)
{
struct r1bio *r1_bio = bio->bi_private;
int behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
struct r1conf *conf = r1_bio->mddev->private;
struct bio *to_put = NULL;
int mirror = find_bio_disk(r1_bio, bio);
struct md_rdev *rdev = conf->mirrors[mirror].rdev;
bool discard_error;
discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
/*
* 'one mirror IO has finished' event handler:
*/
if (bio->bi_status && !discard_error) {
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED, &
conf->mddev->recovery);
if (test_bit(FailFast, &rdev->flags) &&
(bio->bi_opf & MD_FAILFAST) &&
/* We never try FailFast to WriteMostly devices */
!test_bit(WriteMostly, &rdev->flags)) {
md_error(r1_bio->mddev, rdev);
if (!test_bit(Faulty, &rdev->flags))
/* This is the only remaining device,
* We need to retry the write without
* FailFast
*/
set_bit(R1BIO_WriteError, &r1_bio->state);
else {
/* Finished with this branch */
r1_bio->bios[mirror] = NULL;
to_put = bio;
}
} else
set_bit(R1BIO_WriteError, &r1_bio->state);
} else {
/*
* Set R1BIO_Uptodate in our master bio, so that we
* will return a good error code for to the higher
* levels even if IO on some other mirrored buffer
* fails.
*
* The 'master' represents the composite IO operation
* to user-side. So if something waits for IO, then it
* will wait for the 'master' bio.
*/
sector_t first_bad;
int bad_sectors;
r1_bio->bios[mirror] = NULL;
to_put = bio;
/*
* Do not set R1BIO_Uptodate if the current device is
* rebuilding or Faulty. This is because we cannot use
* such device for properly reading the data back (we could
* potentially use it, if the current write would have felt
* before rdev->recovery_offset, but for simplicity we don't
* check this here.
*/
if (test_bit(In_sync, &rdev->flags) &&
!test_bit(Faulty, &rdev->flags))
set_bit(R1BIO_Uptodate, &r1_bio->state);
/* Maybe we can clear some bad blocks. */
if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
&first_bad, &bad_sectors) && !discard_error) {
r1_bio->bios[mirror] = IO_MADE_GOOD;
set_bit(R1BIO_MadeGood, &r1_bio->state);
}
}
if (behind) {
if (test_bit(WriteMostly, &rdev->flags))
atomic_dec(&r1_bio->behind_remaining);
/*
* In behind mode, we ACK the master bio once the I/O
* has safely reached all non-writemostly
* disks. Setting the Returned bit ensures that this
* gets done only once -- we don't ever want to return
* -EIO here, instead we'll wait
*/
if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
test_bit(R1BIO_Uptodate, &r1_bio->state)) {
/* Maybe we can return now */
if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
struct bio *mbio = r1_bio->master_bio;
pr_debug("raid1: behind end write sectors"
" %llu-%llu\n",
(unsigned long long) mbio->bi_iter.bi_sector,
(unsigned long long) bio_end_sector(mbio) - 1);
call_bio_endio(r1_bio);
}
}
}
if (r1_bio->bios[mirror] == NULL)
rdev_dec_pending(rdev, conf->mddev);
/*
* Let's see if all mirrored write operations have finished
* already.
*/
r1_bio_write_done(r1_bio);
if (to_put)
bio_put(to_put);
}
static sector_t align_to_barrier_unit_end(sector_t start_sector,
sector_t sectors)
{
sector_t len;
WARN_ON(sectors == 0);
/*
* len is the number of sectors from start_sector to end of the
* barrier unit which start_sector belongs to.
*/
len = round_up(start_sector + 1, BARRIER_UNIT_SECTOR_SIZE) -
start_sector;
if (len > sectors)
len = sectors;
return len;
}
/*
* This routine returns the disk from which the requested read should
* be done. There is a per-array 'next expected sequential IO' sector
* number - if this matches on the next IO then we use the last disk.
* There is also a per-disk 'last know head position' sector that is
* maintained from IRQ contexts, both the normal and the resync IO
* completion handlers update this position correctly. If there is no
* perfect sequential match then we pick the disk whose head is closest.
*
* If there are 2 mirrors in the same 2 devices, performance degrades
* because position is mirror, not device based.
*
* The rdev for the device selected will have nr_pending incremented.
*/
static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors)
{
const sector_t this_sector = r1_bio->sector;
int sectors;
int best_good_sectors;
int best_disk, best_dist_disk, best_pending_disk;
int has_nonrot_disk;
int disk;
sector_t best_dist;
unsigned int min_pending;
struct md_rdev *rdev;
int choose_first;
int choose_next_idle;
rcu_read_lock();
/*
* Check if we can balance. We can balance on the whole
* device if no resync is going on, or below the resync window.
* We take the first readable disk when above the resync window.
*/
retry:
sectors = r1_bio->sectors;
best_disk = -1;
best_dist_disk = -1;
best_dist = MaxSector;
best_pending_disk = -1;
min_pending = UINT_MAX;
best_good_sectors = 0;
has_nonrot_disk = 0;
choose_next_idle = 0;
clear_bit(R1BIO_FailFast, &r1_bio->state);
if ((conf->mddev->recovery_cp < this_sector + sectors) ||
(mddev_is_clustered(conf->mddev) &&
md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
this_sector + sectors)))
choose_first = 1;
else
choose_first = 0;
for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
sector_t dist;
sector_t first_bad;
int bad_sectors;
unsigned int pending;
bool nonrot;
rdev = rcu_dereference(conf->mirrors[disk].rdev);
if (r1_bio->bios[disk] == IO_BLOCKED
|| rdev == NULL
|| test_bit(Faulty, &rdev->flags))
continue;
if (!test_bit(In_sync, &rdev->flags) &&
rdev->recovery_offset < this_sector + sectors)
continue;
if (test_bit(WriteMostly, &rdev->flags)) {
/* Don't balance among write-mostly, just
* use the first as a last resort */
if (best_dist_disk < 0) {
if (is_badblock(rdev, this_sector, sectors,
&first_bad, &bad_sectors)) {
if (first_bad <= this_sector)
/* Cannot use this */
continue;
best_good_sectors = first_bad - this_sector;
} else
best_good_sectors = sectors;
best_dist_disk = disk;
best_pending_disk = disk;
}
continue;
}
/* This is a reasonable device to use. It might
* even be best.
*/
if (is_badblock(rdev, this_sector, sectors,
&first_bad, &bad_sectors)) {
if (best_dist < MaxSector)
/* already have a better device */
continue;
if (first_bad <= this_sector) {
/* cannot read here. If this is the 'primary'
* device, then we must not read beyond
* bad_sectors from another device..
*/
bad_sectors -= (this_sector - first_bad);
if (choose_first && sectors > bad_sectors)
sectors = bad_sectors;
if (best_good_sectors > sectors)
best_good_sectors = sectors;
} else {
sector_t good_sectors = first_bad - this_sector;
if (good_sectors > best_good_sectors) {
best_good_sectors = good_sectors;
best_disk = disk;
}
if (choose_first)
break;
}
continue;
} else {
if ((sectors > best_good_sectors) && (best_disk >= 0))
best_disk = -1;
best_good_sectors = sectors;
}
if (best_disk >= 0)
/* At least two disks to choose from so failfast is OK */
set_bit(R1BIO_FailFast, &r1_bio->state);
nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
has_nonrot_disk |= nonrot;
pending = atomic_read(&rdev->nr_pending);
dist = abs(this_sector - conf->mirrors[disk].head_position);
if (choose_first) {
best_disk = disk;
break;
}
/* Don't change to another disk for sequential reads */
if (conf->mirrors[disk].next_seq_sect == this_sector
|| dist == 0) {
int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
struct raid1_info *mirror = &conf->mirrors[disk];
best_disk = disk;
/*
* If buffered sequential IO size exceeds optimal
* iosize, check if there is idle disk. If yes, choose
* the idle disk. read_balance could already choose an
* idle disk before noticing it's a sequential IO in
* this disk. This doesn't matter because this disk
* will idle, next time it will be utilized after the
* first disk has IO size exceeds optimal iosize. In
* this way, iosize of the first disk will be optimal
* iosize at least. iosize of the second disk might be
* small, but not a big deal since when the second disk
* starts IO, the first disk is likely still busy.
*/
if (nonrot && opt_iosize > 0 &&
mirror->seq_start != MaxSector &&
mirror->next_seq_sect > opt_iosize &&
mirror->next_seq_sect - opt_iosize >=
mirror->seq_start) {
choose_next_idle = 1;
continue;
}
break;
}
if (choose_next_idle)
continue;
if (min_pending > pending) {
min_pending = pending;
best_pending_disk = disk;
}
if (dist < best_dist) {
best_dist = dist;
best_dist_disk = disk;
}
}
/*
* If all disks are rotational, choose the closest disk. If any disk is
* non-rotational, choose the disk with less pending request even the
* disk is rotational, which might/might not be optimal for raids with
* mixed ratation/non-rotational disks depending on workload.
*/
if (best_disk == -1) {
if (has_nonrot_disk || min_pending == 0)
best_disk = best_pending_disk;
else
best_disk = best_dist_disk;
}
if (best_disk >= 0) {
rdev = rcu_dereference(conf->mirrors[best_disk].rdev);
if (!rdev)
goto retry;
atomic_inc(&rdev->nr_pending);
sectors = best_good_sectors;
if (conf->mirrors[best_disk].next_seq_sect != this_sector)
conf->mirrors[best_disk].seq_start = this_sector;
conf->mirrors[best_disk].next_seq_sect = this_sector + sectors;
}
rcu_read_unlock();
*max_sectors = sectors;
return best_disk;
}
static int raid1_congested(struct mddev *mddev, int bits)
{
struct r1conf *conf = mddev->private;
int i, ret = 0;
if ((bits & (1 << WB_async_congested)) &&
conf->pending_count >= max_queued_requests)
return 1;
rcu_read_lock();
for (i = 0; i < conf->raid_disks * 2; i++) {
struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct request_queue *q = bdev_get_queue(rdev->bdev);
BUG_ON(!q);
/* Note the '|| 1' - when read_balance prefers
* non-congested targets, it can be removed
*/
if ((bits & (1 << WB_async_congested)) || 1)
ret |= bdi_congested(q->backing_dev_info, bits);
else
ret &= bdi_congested(q->backing_dev_info, bits);
}
}
rcu_read_unlock();
return ret;
}
static void flush_bio_list(struct r1conf *conf, struct bio *bio)
{
/* flush any pending bitmap writes to disk before proceeding w/ I/O */
md_bitmap_unplug(conf->mddev->bitmap);
wake_up(&conf->wait_barrier);
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
struct md_rdev *rdev = (void *)bio->bi_disk;
bio->bi_next = NULL;
bio_set_dev(bio, rdev->bdev);
if (test_bit(Faulty, &rdev->flags)) {
bio_io_error(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bio->bi_disk->queue)))
/* Just ignore it */
bio_endio(bio);
else
generic_make_request(bio);
bio = next;
}
}
static void flush_pending_writes(struct r1conf *conf)
{
/* Any writes that have been queued but are awaiting
* bitmap updates get flushed here.
*/
spin_lock_irq(&conf->device_lock);
if (conf->pending_bio_list.head) {
struct blk_plug plug;
struct bio *bio;
bio = bio_list_get(&conf->pending_bio_list);
conf->pending_count = 0;
spin_unlock_irq(&conf->device_lock);
/*
* As this is called in a wait_event() loop (see freeze_array),
* current->state might be TASK_UNINTERRUPTIBLE which will
* cause a warning when we prepare to wait again. As it is
* rare that this path is taken, it is perfectly safe to force
* us to go around the wait_event() loop again, so the warning
* is a false-positive. Silence the warning by resetting
* thread state
*/
__set_current_state(TASK_RUNNING);
blk_start_plug(&plug);
flush_bio_list(conf, bio);
blk_finish_plug(&plug);
} else
spin_unlock_irq(&conf->device_lock);
}
/* Barriers....
* Sometimes we need to suspend IO while we do something else,
* either some resync/recovery, or reconfigure the array.
* To do this we raise a 'barrier'.
* The 'barrier' is a counter that can be raised multiple times
* to count how many activities are happening which preclude
* normal IO.
* We can only raise the barrier if there is no pending IO.
* i.e. if nr_pending == 0.
* We choose only to raise the barrier if no-one is waiting for the
* barrier to go down. This means that as soon as an IO request
* is ready, no other operations which require a barrier will start
* until the IO request has had a chance.
*
* So: regular IO calls 'wait_barrier'. When that returns there
* is no backgroup IO happening, It must arrange to call
* allow_barrier when it has finished its IO.
* backgroup IO calls must call raise_barrier. Once that returns
* there is no normal IO happeing. It must arrange to call
* lower_barrier when the particular background IO completes.
*/
static sector_t raise_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
spin_lock_irq(&conf->resync_lock);
/* Wait until no block IO is waiting */
wait_event_lock_irq(conf->wait_barrier,
!atomic_read(&conf->nr_waiting[idx]),
conf->resync_lock);
/* block any new IO from starting */
atomic_inc(&conf->barrier[idx]);
/*
* In raise_barrier() we firstly increase conf->barrier[idx] then
* check conf->nr_pending[idx]. In _wait_barrier() we firstly
* increase conf->nr_pending[idx] then check conf->barrier[idx].
* A memory barrier here to make sure conf->nr_pending[idx] won't
* be fetched before conf->barrier[idx] is increased. Otherwise
* there will be a race between raise_barrier() and _wait_barrier().
*/
smp_mb__after_atomic();
/* For these conditions we must wait:
* A: while the array is in frozen state
* B: while conf->nr_pending[idx] is not 0, meaning regular I/O
* existing in corresponding I/O barrier bucket.
* C: while conf->barrier[idx] >= RESYNC_DEPTH, meaning reaches
* max resync count which allowed on current I/O barrier bucket.
*/
wait_event_lock_irq(conf->wait_barrier,
(!conf->array_frozen &&
!atomic_read(&conf->nr_pending[idx]) &&
atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH) ||
test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery),
conf->resync_lock);
if (test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
atomic_dec(&conf->barrier[idx]);
spin_unlock_irq(&conf->resync_lock);
wake_up(&conf->wait_barrier);
return -EINTR;
}
atomic_inc(&conf->nr_sync_pending);
spin_unlock_irq(&conf->resync_lock);
return 0;
}
static void lower_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
BUG_ON(atomic_read(&conf->barrier[idx]) <= 0);
atomic_dec(&conf->barrier[idx]);
atomic_dec(&conf->nr_sync_pending);
wake_up(&conf->wait_barrier);
}
static void _wait_barrier(struct r1conf *conf, int idx)
{
/*
* We need to increase conf->nr_pending[idx] very early here,
* then raise_barrier() can be blocked when it waits for
* conf->nr_pending[idx] to be 0. Then we can avoid holding
* conf->resync_lock when there is no barrier raised in same
* barrier unit bucket. Also if the array is frozen, I/O
* should be blocked until array is unfrozen.
*/
atomic_inc(&conf->nr_pending[idx]);
/*
* In _wait_barrier() we firstly increase conf->nr_pending[idx], then
* check conf->barrier[idx]. In raise_barrier() we firstly increase
* conf->barrier[idx], then check conf->nr_pending[idx]. A memory
* barrier is necessary here to make sure conf->barrier[idx] won't be
* fetched before conf->nr_pending[idx] is increased. Otherwise there
* will be a race between _wait_barrier() and raise_barrier().
*/
smp_mb__after_atomic();
/*
* Don't worry about checking two atomic_t variables at same time
* here. If during we check conf->barrier[idx], the array is
* frozen (conf->array_frozen is 1), and chonf->barrier[idx] is
* 0, it is safe to return and make the I/O continue. Because the
* array is frozen, all I/O returned here will eventually complete
* or be queued, no race will happen. See code comment in
* frozen_array().
*/
if (!READ_ONCE(conf->array_frozen) &&
!atomic_read(&conf->barrier[idx]))
return;
/*
* After holding conf->resync_lock, conf->nr_pending[idx]
* should be decreased before waiting for barrier to drop.
* Otherwise, we may encounter a race condition because
* raise_barrer() might be waiting for conf->nr_pending[idx]
* to be 0 at same time.
*/
spin_lock_irq(&conf->resync_lock);
atomic_inc(&conf->nr_waiting[idx]);
atomic_dec(&conf->nr_pending[idx]);
/*
* In case freeze_array() is waiting for
* get_unqueued_pending() == extra
*/
wake_up(&conf->wait_barrier);
/* Wait for the barrier in same barrier unit bucket to drop. */
wait_event_lock_irq(conf->wait_barrier,
!conf->array_frozen &&
!atomic_read(&conf->barrier[idx]),
conf->resync_lock);
atomic_inc(&conf->nr_pending[idx]);
atomic_dec(&conf->nr_waiting[idx]);
spin_unlock_irq(&conf->resync_lock);
}
static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
/*
* Very similar to _wait_barrier(). The difference is, for read
* I/O we don't need wait for sync I/O, but if the whole array
* is frozen, the read I/O still has to wait until the array is
* unfrozen. Since there is no ordering requirement with
* conf->barrier[idx] here, memory barrier is unnecessary as well.
*/
atomic_inc(&conf->nr_pending[idx]);
if (!READ_ONCE(conf->array_frozen))
return;
spin_lock_irq(&conf->resync_lock);
atomic_inc(&conf->nr_waiting[idx]);
atomic_dec(&conf->nr_pending[idx]);
/*
* In case freeze_array() is waiting for
* get_unqueued_pending() == extra
*/
wake_up(&conf->wait_barrier);