forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathraid5.c
7880 lines (7080 loc) · 221 KB
/
raid5.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
/*
* raid5.c : Multiple Devices driver for Linux
* Copyright (C) 1996, 1997 Ingo Molnar, Miguel de Icaza, Gadi Oxman
* Copyright (C) 1999, 2000 Ingo Molnar
* Copyright (C) 2002, 2003 H. Peter Anvin
*
* RAID-4/5/6 management functions.
* Thanks to Penguin Computing for making the RAID-6 development possible
* by donating a test server!
*
* 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.
*/
/*
* BITMAP UNPLUGGING:
*
* The sequencing for updating the bitmap reliably is a little
* subtle (and I got it wrong the first time) so it deserves some
* explanation.
*
* We group bitmap updates into batches. Each batch has a number.
* We may write out several batches at once, but that isn't very important.
* conf->seq_write is the number of the last batch successfully written.
* conf->seq_flush is the number of the last batch that was closed to
* new additions.
* When we discover that we will need to write to any block in a stripe
* (in add_stripe_bio) we update the in-memory bitmap and record in sh->bm_seq
* the number of the batch it will be in. This is seq_flush+1.
* When we are ready to do a write, if that batch hasn't been written yet,
* we plug the array and queue the stripe for later.
* When an unplug happens, we increment bm_flush, thus closing the current
* batch.
* When we notice that bm_flush > bm_write, we write out all pending updates
* to the bitmap, and advance bm_write to where bm_flush was.
* This may occasionally write a bit out twice, but is sure never to
* miss any bits.
*/
#include <linux/blkdev.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
#include <linux/module.h>
#include <linux/async.h>
#include <linux/seq_file.h>
#include <linux/cpu.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/nodemask.h>
#include <linux/flex_array.h>
#include <trace/events/block.h>
#include "md.h"
#include "raid5.h"
#include "raid0.h"
#include "bitmap.h"
#define cpu_to_group(cpu) cpu_to_node(cpu)
#define ANY_GROUP NUMA_NO_NODE
static bool devices_handle_discard_safely = false;
module_param(devices_handle_discard_safely, bool, 0644);
MODULE_PARM_DESC(devices_handle_discard_safely,
"Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
static struct workqueue_struct *raid5_wq;
/*
* Stripe cache
*/
#define NR_STRIPES 256
#define STRIPE_SIZE PAGE_SIZE
#define STRIPE_SHIFT (PAGE_SHIFT - 9)
#define STRIPE_SECTORS (STRIPE_SIZE>>9)
#define IO_THRESHOLD 1
#define BYPASS_THRESHOLD 1
#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
#define MAX_STRIPE_BATCH 8
static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
{
int hash = (sect >> STRIPE_SHIFT) & HASH_MASK;
return &conf->stripe_hashtbl[hash];
}
static inline int stripe_hash_locks_hash(sector_t sect)
{
return (sect >> STRIPE_SHIFT) & STRIPE_HASH_LOCKS_MASK;
}
static inline void lock_device_hash_lock(struct r5conf *conf, int hash)
{
spin_lock_irq(conf->hash_locks + hash);
spin_lock(&conf->device_lock);
}
static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
{
spin_unlock(&conf->device_lock);
spin_unlock_irq(conf->hash_locks + hash);
}
static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
{
int i;
local_irq_disable();
spin_lock(conf->hash_locks);
for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks);
spin_lock(&conf->device_lock);
}
static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
{
int i;
spin_unlock(&conf->device_lock);
for (i = NR_STRIPE_HASH_LOCKS; i; i--)
spin_unlock(conf->hash_locks + i - 1);
local_irq_enable();
}
/* bio's attached to a stripe+device for I/O are linked together in bi_sector
* order without overlap. There may be several bio's per stripe+device, and
* a bio could span several devices.
* When walking this list for a particular stripe+device, we must never proceed
* beyond a bio that extends past this device, as the next bio might no longer
* be valid.
* This function is used to determine the 'next' bio in the list, given the sector
* of the current stripe+device
*/
static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
{
int sectors = bio_sectors(bio);
if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS)
return bio->bi_next;
else
return NULL;
}
/*
* We maintain a biased count of active stripes in the bottom 16 bits of
* bi_phys_segments, and a count of processed stripes in the upper 16 bits
*/
static inline int raid5_bi_processed_stripes(struct bio *bio)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
return (atomic_read(segments) >> 16) & 0xffff;
}
static inline int raid5_dec_bi_active_stripes(struct bio *bio)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
return atomic_sub_return(1, segments) & 0xffff;
}
static inline void raid5_inc_bi_active_stripes(struct bio *bio)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
atomic_inc(segments);
}
static inline void raid5_set_bi_processed_stripes(struct bio *bio,
unsigned int cnt)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
int old, new;
do {
old = atomic_read(segments);
new = (old & 0xffff) | (cnt << 16);
} while (atomic_cmpxchg(segments, old, new) != old);
}
static inline void raid5_set_bi_stripes(struct bio *bio, unsigned int cnt)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
atomic_set(segments, cnt);
}
/* Find first data disk in a raid6 stripe */
static inline int raid6_d0(struct stripe_head *sh)
{
if (sh->ddf_layout)
/* ddf always start from first device */
return 0;
/* md starts just after Q block */
if (sh->qd_idx == sh->disks - 1)
return 0;
else
return sh->qd_idx + 1;
}
static inline int raid6_next_disk(int disk, int raid_disks)
{
disk++;
return (disk < raid_disks) ? disk : 0;
}
/* When walking through the disks in a raid5, starting at raid6_d0,
* We need to map each disk to a 'slot', where the data disks are slot
* 0 .. raid_disks-3, the parity disk is raid_disks-2 and the Q disk
* is raid_disks-1. This help does that mapping.
*/
static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
int *count, int syndrome_disks)
{
int slot = *count;
if (sh->ddf_layout)
(*count)++;
if (idx == sh->pd_idx)
return syndrome_disks;
if (idx == sh->qd_idx)
return syndrome_disks + 1;
if (!sh->ddf_layout)
(*count)++;
return slot;
}
static void return_io(struct bio *return_bi)
{
struct bio *bi = return_bi;
while (bi) {
return_bi = bi->bi_next;
bi->bi_next = NULL;
bi->bi_iter.bi_size = 0;
trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
bi, 0);
bio_endio(bi, 0);
bi = return_bi;
}
}
static void print_raid5_conf (struct r5conf *conf);
static int stripe_operations_active(struct stripe_head *sh)
{
return sh->check_state || sh->reconstruct_state ||
test_bit(STRIPE_BIOFILL_RUN, &sh->state) ||
test_bit(STRIPE_COMPUTE_RUN, &sh->state);
}
static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
{
struct r5conf *conf = sh->raid_conf;
struct r5worker_group *group;
int thread_cnt;
int i, cpu = sh->cpu;
if (!cpu_online(cpu)) {
cpu = cpumask_any(cpu_online_mask);
sh->cpu = cpu;
}
if (list_empty(&sh->lru)) {
struct r5worker_group *group;
group = conf->worker_groups + cpu_to_group(cpu);
list_add_tail(&sh->lru, &group->handle_list);
group->stripes_cnt++;
sh->group = group;
}
if (conf->worker_cnt_per_group == 0) {
md_wakeup_thread(conf->mddev->thread);
return;
}
group = conf->worker_groups + cpu_to_group(sh->cpu);
group->workers[0].working = true;
/* at least one worker should run to avoid race */
queue_work_on(sh->cpu, raid5_wq, &group->workers[0].work);
thread_cnt = group->stripes_cnt / MAX_STRIPE_BATCH - 1;
/* wakeup more workers */
for (i = 1; i < conf->worker_cnt_per_group && thread_cnt > 0; i++) {
if (group->workers[i].working == false) {
group->workers[i].working = true;
queue_work_on(sh->cpu, raid5_wq,
&group->workers[i].work);
thread_cnt--;
}
}
}
static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
struct list_head *temp_inactive_list)
{
BUG_ON(!list_empty(&sh->lru));
BUG_ON(atomic_read(&conf->active_stripes)==0);
if (test_bit(STRIPE_HANDLE, &sh->state)) {
if (test_bit(STRIPE_DELAYED, &sh->state) &&
!test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
list_add_tail(&sh->lru, &conf->delayed_list);
else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
sh->bm_seq - conf->seq_write > 0)
list_add_tail(&sh->lru, &conf->bitmap_list);
else {
clear_bit(STRIPE_DELAYED, &sh->state);
clear_bit(STRIPE_BIT_DELAY, &sh->state);
if (conf->worker_cnt_per_group == 0) {
list_add_tail(&sh->lru, &conf->handle_list);
} else {
raid5_wakeup_stripe_thread(sh);
return;
}
}
md_wakeup_thread(conf->mddev->thread);
} else {
BUG_ON(stripe_operations_active(sh));
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
if (atomic_dec_return(&conf->preread_active_stripes)
< IO_THRESHOLD)
md_wakeup_thread(conf->mddev->thread);
atomic_dec(&conf->active_stripes);
if (!test_bit(STRIPE_EXPANDING, &sh->state))
list_add_tail(&sh->lru, temp_inactive_list);
}
}
static void __release_stripe(struct r5conf *conf, struct stripe_head *sh,
struct list_head *temp_inactive_list)
{
if (atomic_dec_and_test(&sh->count))
do_release_stripe(conf, sh, temp_inactive_list);
}
/*
* @hash could be NR_STRIPE_HASH_LOCKS, then we have a list of inactive_list
*
* Be careful: Only one task can add/delete stripes from temp_inactive_list at
* given time. Adding stripes only takes device lock, while deleting stripes
* only takes hash lock.
*/
static void release_inactive_stripe_list(struct r5conf *conf,
struct list_head *temp_inactive_list,
int hash)
{
int size;
unsigned long do_wakeup = 0;
int i = 0;
unsigned long flags;
if (hash == NR_STRIPE_HASH_LOCKS) {
size = NR_STRIPE_HASH_LOCKS;
hash = NR_STRIPE_HASH_LOCKS - 1;
} else
size = 1;
while (size) {
struct list_head *list = &temp_inactive_list[size - 1];
/*
* We don't hold any lock here yet, get_active_stripe() might
* remove stripes from the list
*/
if (!list_empty_careful(list)) {
spin_lock_irqsave(conf->hash_locks + hash, flags);
if (list_empty(conf->inactive_list + hash) &&
!list_empty(list))
atomic_dec(&conf->empty_inactive_list_nr);
list_splice_tail_init(list, conf->inactive_list + hash);
do_wakeup |= 1 << hash;
spin_unlock_irqrestore(conf->hash_locks + hash, flags);
}
size--;
hash--;
}
for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
if (do_wakeup & (1 << i))
wake_up(&conf->wait_for_stripe[i]);
}
if (do_wakeup) {
if (atomic_read(&conf->active_stripes) == 0)
wake_up(&conf->wait_for_quiescent);
if (conf->retry_read_aligned)
md_wakeup_thread(conf->mddev->thread);
}
}
/* should hold conf->device_lock already */
static int release_stripe_list(struct r5conf *conf,
struct list_head *temp_inactive_list)
{
struct stripe_head *sh;
int count = 0;
struct llist_node *head;
head = llist_del_all(&conf->released_stripes);
head = llist_reverse_order(head);
while (head) {
int hash;
sh = llist_entry(head, struct stripe_head, release_list);
head = llist_next(head);
/* sh could be readded after STRIPE_ON_RELEASE_LIST is cleard */
smp_mb();
clear_bit(STRIPE_ON_RELEASE_LIST, &sh->state);
/*
* Don't worry the bit is set here, because if the bit is set
* again, the count is always > 1. This is true for
* STRIPE_ON_UNPLUG_LIST bit too.
*/
hash = sh->hash_lock_index;
__release_stripe(conf, sh, &temp_inactive_list[hash]);
count++;
}
return count;
}
static void release_stripe(struct stripe_head *sh)
{
struct r5conf *conf = sh->raid_conf;
unsigned long flags;
struct list_head list;
int hash;
bool wakeup;
/* Avoid release_list until the last reference.
*/
if (atomic_add_unless(&sh->count, -1, 1))
return;
if (unlikely(!conf->mddev->thread) ||
test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state))
goto slow_path;
wakeup = llist_add(&sh->release_list, &conf->released_stripes);
if (wakeup)
md_wakeup_thread(conf->mddev->thread);
return;
slow_path:
local_irq_save(flags);
/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
INIT_LIST_HEAD(&list);
hash = sh->hash_lock_index;
do_release_stripe(conf, sh, &list);
spin_unlock(&conf->device_lock);
release_inactive_stripe_list(conf, &list, hash);
}
local_irq_restore(flags);
}
static inline void remove_hash(struct stripe_head *sh)
{
pr_debug("remove_hash(), stripe %llu\n",
(unsigned long long)sh->sector);
hlist_del_init(&sh->hash);
}
static inline void insert_hash(struct r5conf *conf, struct stripe_head *sh)
{
struct hlist_head *hp = stripe_hash(conf, sh->sector);
pr_debug("insert_hash(), stripe %llu\n",
(unsigned long long)sh->sector);
hlist_add_head(&sh->hash, hp);
}
/* find an idle stripe, make sure it is unhashed, and return it. */
static struct stripe_head *get_free_stripe(struct r5conf *conf, int hash)
{
struct stripe_head *sh = NULL;
struct list_head *first;
if (list_empty(conf->inactive_list + hash))
goto out;
first = (conf->inactive_list + hash)->next;
sh = list_entry(first, struct stripe_head, lru);
list_del_init(first);
remove_hash(sh);
atomic_inc(&conf->active_stripes);
BUG_ON(hash != sh->hash_lock_index);
if (list_empty(conf->inactive_list + hash))
atomic_inc(&conf->empty_inactive_list_nr);
out:
return sh;
}
static void shrink_buffers(struct stripe_head *sh)
{
struct page *p;
int i;
int num = sh->raid_conf->pool_size;
for (i = 0; i < num ; i++) {
WARN_ON(sh->dev[i].page != sh->dev[i].orig_page);
p = sh->dev[i].page;
if (!p)
continue;
sh->dev[i].page = NULL;
put_page(p);
}
}
static int grow_buffers(struct stripe_head *sh, gfp_t gfp)
{
int i;
int num = sh->raid_conf->pool_size;
for (i = 0; i < num; i++) {
struct page *page;
if (!(page = alloc_page(gfp))) {
return 1;
}
sh->dev[i].page = page;
sh->dev[i].orig_page = page;
}
return 0;
}
static void raid5_build_block(struct stripe_head *sh, int i, int previous);
static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
struct stripe_head *sh);
static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
{
struct r5conf *conf = sh->raid_conf;
int i, seq;
BUG_ON(atomic_read(&sh->count) != 0);
BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
BUG_ON(stripe_operations_active(sh));
BUG_ON(sh->batch_head);
pr_debug("init_stripe called, stripe %llu\n",
(unsigned long long)sector);
retry:
seq = read_seqcount_begin(&conf->gen_lock);
sh->generation = conf->generation - previous;
sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks;
sh->sector = sector;
stripe_set_idx(sector, conf, previous, sh);
sh->state = 0;
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->toread || dev->read || dev->towrite || dev->written ||
test_bit(R5_LOCKED, &dev->flags)) {
printk(KERN_ERR "sector=%llx i=%d %p %p %p %p %d\n",
(unsigned long long)sh->sector, i, dev->toread,
dev->read, dev->towrite, dev->written,
test_bit(R5_LOCKED, &dev->flags));
WARN_ON(1);
}
dev->flags = 0;
raid5_build_block(sh, i, previous);
}
if (read_seqcount_retry(&conf->gen_lock, seq))
goto retry;
sh->overwrite_disks = 0;
insert_hash(conf, sh);
sh->cpu = smp_processor_id();
set_bit(STRIPE_BATCH_READY, &sh->state);
}
static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector,
short generation)
{
struct stripe_head *sh;
pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector);
hlist_for_each_entry(sh, stripe_hash(conf, sector), hash)
if (sh->sector == sector && sh->generation == generation)
return sh;
pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector);
return NULL;
}
/*
* Need to check if array has failed when deciding whether to:
* - start an array
* - remove non-faulty devices
* - add a spare
* - allow a reshape
* This determination is simple when no reshape is happening.
* However if there is a reshape, we need to carefully check
* both the before and after sections.
* This is because some failed devices may only affect one
* of the two sections, and some non-in_sync devices may
* be insync in the section most affected by failed devices.
*/
static int calc_degraded(struct r5conf *conf)
{
int degraded, degraded2;
int i;
rcu_read_lock();
degraded = 0;
for (i = 0; i < conf->previous_raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && test_bit(Faulty, &rdev->flags))
rdev = rcu_dereference(conf->disks[i].replacement);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded++;
else if (test_bit(In_sync, &rdev->flags))
;
else
/* not in-sync or faulty.
* If the reshape increases the number of devices,
* this is being recovered by the reshape, so
* this 'previous' section is not in_sync.
* If the number of devices is being reduced however,
* the device can only be part of the array if
* we are reverting a reshape, so this section will
* be in-sync.
*/
if (conf->raid_disks >= conf->previous_raid_disks)
degraded++;
}
rcu_read_unlock();
if (conf->raid_disks == conf->previous_raid_disks)
return degraded;
rcu_read_lock();
degraded2 = 0;
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && test_bit(Faulty, &rdev->flags))
rdev = rcu_dereference(conf->disks[i].replacement);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded2++;
else if (test_bit(In_sync, &rdev->flags))
;
else
/* not in-sync or faulty.
* If reshape increases the number of devices, this
* section has already been recovered, else it
* almost certainly hasn't.
*/
if (conf->raid_disks <= conf->previous_raid_disks)
degraded2++;
}
rcu_read_unlock();
if (degraded2 > degraded)
return degraded2;
return degraded;
}
static int has_failed(struct r5conf *conf)
{
int degraded;
if (conf->mddev->reshape_position == MaxSector)
return conf->mddev->degraded > conf->max_degraded;
degraded = calc_degraded(conf);
if (degraded > conf->max_degraded)
return 1;
return 0;
}
static struct stripe_head *
get_active_stripe(struct r5conf *conf, sector_t sector,
int previous, int noblock, int noquiesce)
{
struct stripe_head *sh;
int hash = stripe_hash_locks_hash(sector);
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
spin_lock_irq(conf->hash_locks + hash);
do {
wait_event_lock_irq(conf->wait_for_quiescent,
conf->quiesce == 0 || noquiesce,
*(conf->hash_locks + hash));
sh = __find_stripe(conf, sector, conf->generation - previous);
if (!sh) {
if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) {
sh = get_free_stripe(conf, hash);
if (!sh && !test_bit(R5_DID_ALLOC,
&conf->cache_state))
set_bit(R5_ALLOC_MORE,
&conf->cache_state);
}
if (noblock && sh == NULL)
break;
if (!sh) {
set_bit(R5_INACTIVE_BLOCKED,
&conf->cache_state);
wait_event_exclusive_cmd(
conf->wait_for_stripe[hash],
!list_empty(conf->inactive_list + hash) &&
(atomic_read(&conf->active_stripes)
< (conf->max_nr_stripes * 3 / 4)
|| !test_bit(R5_INACTIVE_BLOCKED,
&conf->cache_state)),
spin_unlock_irq(conf->hash_locks + hash),
spin_lock_irq(conf->hash_locks + hash));
clear_bit(R5_INACTIVE_BLOCKED,
&conf->cache_state);
} else {
init_stripe(sh, sector, previous);
atomic_inc(&sh->count);
}
} else if (!atomic_inc_not_zero(&sh->count)) {
spin_lock(&conf->device_lock);
if (!atomic_read(&sh->count)) {
if (!test_bit(STRIPE_HANDLE, &sh->state))
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&sh->lru) &&
!test_bit(STRIPE_EXPANDING, &sh->state));
list_del_init(&sh->lru);
if (sh->group) {
sh->group->stripes_cnt--;
sh->group = NULL;
}
}
atomic_inc(&sh->count);
spin_unlock(&conf->device_lock);
}
} while (sh == NULL);
if (!list_empty(conf->inactive_list + hash))
wake_up(&conf->wait_for_stripe[hash]);
spin_unlock_irq(conf->hash_locks + hash);
return sh;
}
static bool is_full_stripe_write(struct stripe_head *sh)
{
BUG_ON(sh->overwrite_disks > (sh->disks - sh->raid_conf->max_degraded));
return sh->overwrite_disks == (sh->disks - sh->raid_conf->max_degraded);
}
static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
{
local_irq_disable();
if (sh1 > sh2) {
spin_lock(&sh2->stripe_lock);
spin_lock_nested(&sh1->stripe_lock, 1);
} else {
spin_lock(&sh1->stripe_lock);
spin_lock_nested(&sh2->stripe_lock, 1);
}
}
static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
{
spin_unlock(&sh1->stripe_lock);
spin_unlock(&sh2->stripe_lock);
local_irq_enable();
}
/* Only freshly new full stripe normal write stripe can be added to a batch list */
static bool stripe_can_batch(struct stripe_head *sh)
{
return test_bit(STRIPE_BATCH_READY, &sh->state) &&
!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
is_full_stripe_write(sh);
}
/* we only do back search */
static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh)
{
struct stripe_head *head;
sector_t head_sector, tmp_sec;
int hash;
int dd_idx;
if (!stripe_can_batch(sh))
return;
/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
tmp_sec = sh->sector;
if (!sector_div(tmp_sec, conf->chunk_sectors))
return;
head_sector = sh->sector - STRIPE_SECTORS;
hash = stripe_hash_locks_hash(head_sector);
spin_lock_irq(conf->hash_locks + hash);
head = __find_stripe(conf, head_sector, conf->generation);
if (head && !atomic_inc_not_zero(&head->count)) {
spin_lock(&conf->device_lock);
if (!atomic_read(&head->count)) {
if (!test_bit(STRIPE_HANDLE, &head->state))
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&head->lru) &&
!test_bit(STRIPE_EXPANDING, &head->state));
list_del_init(&head->lru);
if (head->group) {
head->group->stripes_cnt--;
head->group = NULL;
}
}
atomic_inc(&head->count);
spin_unlock(&conf->device_lock);
}
spin_unlock_irq(conf->hash_locks + hash);
if (!head)
return;
if (!stripe_can_batch(head))
goto out;
lock_two_stripes(head, sh);
/* clear_batch_ready clear the flag */
if (!stripe_can_batch(head) || !stripe_can_batch(sh))
goto unlock_out;
if (sh->batch_head)
goto unlock_out;
dd_idx = 0;
while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
dd_idx++;
if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw)
goto unlock_out;
if (head->batch_head) {
spin_lock(&head->batch_head->batch_lock);
/* This batch list is already running */
if (!stripe_can_batch(head)) {
spin_unlock(&head->batch_head->batch_lock);
goto unlock_out;
}
/*
* at this point, head's BATCH_READY could be cleared, but we
* can still add the stripe to batch list
*/
list_add(&sh->batch_list, &head->batch_list);
spin_unlock(&head->batch_head->batch_lock);
sh->batch_head = head->batch_head;
} else {
head->batch_head = head;
sh->batch_head = head->batch_head;
spin_lock(&head->batch_lock);
list_add_tail(&sh->batch_list, &head->batch_list);
spin_unlock(&head->batch_lock);
}
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
if (atomic_dec_return(&conf->preread_active_stripes)
< IO_THRESHOLD)
md_wakeup_thread(conf->mddev->thread);
if (test_and_clear_bit(STRIPE_BIT_DELAY, &sh->state)) {
int seq = sh->bm_seq;
if (test_bit(STRIPE_BIT_DELAY, &sh->batch_head->state) &&
sh->batch_head->bm_seq > seq)
seq = sh->batch_head->bm_seq;
set_bit(STRIPE_BIT_DELAY, &sh->batch_head->state);
sh->batch_head->bm_seq = seq;
}
atomic_inc(&sh->count);
unlock_out:
unlock_two_stripes(head, sh);
out:
release_stripe(head);
}
/* Determine if 'data_offset' or 'new_data_offset' should be used
* in this stripe_head.
*/
static int use_new_offset(struct r5conf *conf, struct stripe_head *sh)
{
sector_t progress = conf->reshape_progress;
/* Need a memory barrier to make sure we see the value
* of conf->generation, or ->data_offset that was set before
* reshape_progress was updated.
*/
smp_rmb();
if (progress == MaxSector)
return 0;
if (sh->generation == conf->generation - 1)
return 0;
/* We are in a reshape, and this is a new-generation stripe,
* so use new_data_offset.
*/
return 1;
}
static void
raid5_end_read_request(struct bio *bi, int error);
static void
raid5_end_write_request(struct bio *bi, int error);
static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
{
struct r5conf *conf = sh->raid_conf;
int i, disks = sh->disks;
struct stripe_head *head_sh = sh;
might_sleep();
for (i = disks; i--; ) {
int rw;
int replace_only = 0;
struct bio *bi, *rbi;
struct md_rdev *rdev, *rrdev = NULL;
sh = head_sh;
if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
rw = WRITE_FUA;
else
rw = WRITE;
if (test_bit(R5_Discard, &sh->dev[i].flags))
rw |= REQ_DISCARD;
} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
rw = READ;
else if (test_and_clear_bit(R5_WantReplace,
&sh->dev[i].flags)) {
rw = WRITE;
replace_only = 1;
} else
continue;
if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags))
rw |= REQ_SYNC;
again:
bi = &sh->dev[i].req;
rbi = &sh->dev[i].rreq; /* For writing to replacement */
rcu_read_lock();
rrdev = rcu_dereference(conf->disks[i].replacement);
smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */
rdev = rcu_dereference(conf->disks[i].rdev);
if (!rdev) {
rdev = rrdev;
rrdev = NULL;
}
if (rw & WRITE) {
if (replace_only)
rdev = NULL;
if (rdev == rrdev)
/* We raced and saw duplicates */
rrdev = NULL;
} else {
if (test_bit(R5_ReadRepl, &head_sh->dev[i].flags) && rrdev)
rdev = rrdev;
rrdev = NULL;
}
if (rdev && test_bit(Faulty, &rdev->flags))
rdev = NULL;
if (rdev)
atomic_inc(&rdev->nr_pending);
if (rrdev && test_bit(Faulty, &rrdev->flags))
rrdev = NULL;
if (rrdev)
atomic_inc(&rrdev->nr_pending);
rcu_read_unlock();
/* We have already checked bad blocks for reads. Now
* need to check for writes. We never accept write errors
* on the replacement, so we don't to check rrdev.
*/
while ((rw & WRITE) && rdev &&
test_bit(WriteErrorSeen, &rdev->flags)) {
sector_t first_bad;
int bad_sectors;
int bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
&first_bad, &bad_sectors);
if (!bad)
break;
if (bad < 0) {
set_bit(BlockedBadBlocks, &rdev->flags);
if (!conf->mddev->external &&
conf->mddev->flags) {
/* It is very unlikely, but we might
* still need to write out the
* bad block log - better give it
* a chance*/
md_check_recovery(conf->mddev);
}
/*
* Because md_wait_for_blocked_rdev
* will dec nr_pending, we must
* increment it first.
*/
atomic_inc(&rdev->nr_pending);
md_wait_for_blocked_rdev(rdev, conf->mddev);
} else {
/* Acknowledged bad block - skip the write */
rdev_dec_pending(rdev, conf->mddev);
rdev = NULL;
}
}
if (rdev) {
if (s->syncing || s->expanding || s->expanded
|| s->replacing)