forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathraid5.c
4755 lines (4198 loc) · 133 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->bm_write is the number of the last batch successfully written.
* conf->bm_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 bm_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/module.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/bitops.h>
#include <linux/kthread.h>
#include <asm/atomic.h>
#include "raid6.h"
#include <linux/raid/bitmap.h>
#include <linux/async_tx.h>
/*
* 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 NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
#define stripe_hash(conf, sect) (&((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK]))
/* 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 macro is used to determine the 'next' bio in the list, given the sector
* of the current stripe+device
*/
#define r5_next_bio(bio, sect) ( ( (bio)->bi_sector + ((bio)->bi_size>>9) < sect + STRIPE_SECTORS) ? (bio)->bi_next : NULL)
/*
* The following can be used to debug the driver
*/
#define RAID5_PARANOIA 1
#if RAID5_PARANOIA && defined(CONFIG_SMP)
# define CHECK_DEVLOCK() assert_spin_locked(&conf->device_lock)
#else
# define CHECK_DEVLOCK()
#endif
#ifdef DEBUG
#define inline
#define __inline__
#endif
#if !RAID6_USE_EMPTY_ZERO_PAGE
/* In .bss so it's zeroed */
const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
#endif
static inline int raid6_next_disk(int disk, int raid_disks)
{
disk++;
return (disk < raid_disks) ? disk : 0;
}
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_size = 0;
bi->bi_end_io(bi,
test_bit(BIO_UPTODATE, &bi->bi_flags)
? 0 : -EIO);
bi = return_bi;
}
}
static void print_raid5_conf (raid5_conf_t *conf);
static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
{
if (atomic_dec_and_test(&sh->count)) {
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)) {
list_add_tail(&sh->lru, &conf->delayed_list);
blk_plug_device(conf->mddev->queue);
} else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
sh->bm_seq - conf->seq_write > 0) {
list_add_tail(&sh->lru, &conf->bitmap_list);
blk_plug_device(conf->mddev->queue);
} else {
clear_bit(STRIPE_BIT_DELAY, &sh->state);
list_add_tail(&sh->lru, &conf->handle_list);
}
md_wakeup_thread(conf->mddev->thread);
} else {
BUG_ON(sh->ops.pending);
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
atomic_dec(&conf->preread_active_stripes);
if (atomic_read(&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, &conf->inactive_list);
wake_up(&conf->wait_for_stripe);
if (conf->retry_read_aligned)
md_wakeup_thread(conf->mddev->thread);
}
}
}
}
static void release_stripe(struct stripe_head *sh)
{
raid5_conf_t *conf = sh->raid_conf;
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
__release_stripe(conf, sh);
spin_unlock_irqrestore(&conf->device_lock, 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(raid5_conf_t *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);
CHECK_DEVLOCK();
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(raid5_conf_t *conf)
{
struct stripe_head *sh = NULL;
struct list_head *first;
CHECK_DEVLOCK();
if (list_empty(&conf->inactive_list))
goto out;
first = conf->inactive_list.next;
sh = list_entry(first, struct stripe_head, lru);
list_del_init(first);
remove_hash(sh);
atomic_inc(&conf->active_stripes);
out:
return sh;
}
static void shrink_buffers(struct stripe_head *sh, int num)
{
struct page *p;
int i;
for (i=0; i<num ; i++) {
p = sh->dev[i].page;
if (!p)
continue;
sh->dev[i].page = NULL;
put_page(p);
}
}
static int grow_buffers(struct stripe_head *sh, int num)
{
int i;
for (i=0; i<num; i++) {
struct page *page;
if (!(page = alloc_page(GFP_KERNEL))) {
return 1;
}
sh->dev[i].page = page;
}
return 0;
}
static void raid5_build_block (struct stripe_head *sh, int i);
static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int disks)
{
raid5_conf_t *conf = sh->raid_conf;
int i;
BUG_ON(atomic_read(&sh->count) != 0);
BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
BUG_ON(sh->ops.pending || sh->ops.ack || sh->ops.complete);
CHECK_DEVLOCK();
pr_debug("init_stripe called, stripe %llu\n",
(unsigned long long)sh->sector);
remove_hash(sh);
sh->sector = sector;
sh->pd_idx = pd_idx;
sh->state = 0;
sh->disks = disks;
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));
BUG();
}
dev->flags = 0;
raid5_build_block(sh, i);
}
insert_hash(conf, sh);
}
static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, int disks)
{
struct stripe_head *sh;
struct hlist_node *hn;
CHECK_DEVLOCK();
pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector);
hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
if (sh->sector == sector && sh->disks == disks)
return sh;
pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector);
return NULL;
}
static void unplug_slaves(mddev_t *mddev);
static void raid5_unplug_device(struct request_queue *q);
static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector, int disks,
int pd_idx, int noblock)
{
struct stripe_head *sh;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
spin_lock_irq(&conf->device_lock);
do {
wait_event_lock_irq(conf->wait_for_stripe,
conf->quiesce == 0,
conf->device_lock, /* nothing */);
sh = __find_stripe(conf, sector, disks);
if (!sh) {
if (!conf->inactive_blocked)
sh = get_free_stripe(conf);
if (noblock && sh == NULL)
break;
if (!sh) {
conf->inactive_blocked = 1;
wait_event_lock_irq(conf->wait_for_stripe,
!list_empty(&conf->inactive_list) &&
(atomic_read(&conf->active_stripes)
< (conf->max_nr_stripes *3/4)
|| !conf->inactive_blocked),
conf->device_lock,
raid5_unplug_device(conf->mddev->queue)
);
conf->inactive_blocked = 0;
} else
init_stripe(sh, sector, pd_idx, disks);
} else {
if (atomic_read(&sh->count)) {
BUG_ON(!list_empty(&sh->lru));
} else {
if (!test_bit(STRIPE_HANDLE, &sh->state))
atomic_inc(&conf->active_stripes);
if (list_empty(&sh->lru) &&
!test_bit(STRIPE_EXPANDING, &sh->state))
BUG();
list_del_init(&sh->lru);
}
}
} while (sh == NULL);
if (sh)
atomic_inc(&sh->count);
spin_unlock_irq(&conf->device_lock);
return sh;
}
/* test_and_ack_op() ensures that we only dequeue an operation once */
#define test_and_ack_op(op, pend) \
do { \
if (test_bit(op, &sh->ops.pending) && \
!test_bit(op, &sh->ops.complete)) { \
if (test_and_set_bit(op, &sh->ops.ack)) \
clear_bit(op, &pend); \
else \
ack++; \
} else \
clear_bit(op, &pend); \
} while (0)
/* find new work to run, do not resubmit work that is already
* in flight
*/
static unsigned long get_stripe_work(struct stripe_head *sh)
{
unsigned long pending;
int ack = 0;
pending = sh->ops.pending;
test_and_ack_op(STRIPE_OP_BIOFILL, pending);
test_and_ack_op(STRIPE_OP_COMPUTE_BLK, pending);
test_and_ack_op(STRIPE_OP_PREXOR, pending);
test_and_ack_op(STRIPE_OP_BIODRAIN, pending);
test_and_ack_op(STRIPE_OP_POSTXOR, pending);
test_and_ack_op(STRIPE_OP_CHECK, pending);
if (test_and_clear_bit(STRIPE_OP_IO, &sh->ops.pending))
ack++;
sh->ops.count -= ack;
if (unlikely(sh->ops.count < 0)) {
printk(KERN_ERR "pending: %#lx ops.pending: %#lx ops.ack: %#lx "
"ops.complete: %#lx\n", pending, sh->ops.pending,
sh->ops.ack, sh->ops.complete);
BUG();
}
return pending;
}
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)
{
raid5_conf_t *conf = sh->raid_conf;
int i, disks = sh->disks;
might_sleep();
for (i = disks; i--; ) {
int rw;
struct bio *bi;
mdk_rdev_t *rdev;
if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
rw = WRITE;
else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
rw = READ;
else
continue;
bi = &sh->dev[i].req;
bi->bi_rw = rw;
if (rw == WRITE)
bi->bi_end_io = raid5_end_write_request;
else
bi->bi_end_io = raid5_end_read_request;
rcu_read_lock();
rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && test_bit(Faulty, &rdev->flags))
rdev = NULL;
if (rdev)
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
if (rdev) {
if (test_bit(STRIPE_SYNCING, &sh->state) ||
test_bit(STRIPE_EXPAND_SOURCE, &sh->state) ||
test_bit(STRIPE_EXPAND_READY, &sh->state))
md_sync_acct(rdev->bdev, STRIPE_SECTORS);
bi->bi_bdev = rdev->bdev;
pr_debug("%s: for %llu schedule op %ld on disc %d\n",
__FUNCTION__, (unsigned long long)sh->sector,
bi->bi_rw, i);
atomic_inc(&sh->count);
bi->bi_sector = sh->sector + rdev->data_offset;
bi->bi_flags = 1 << BIO_UPTODATE;
bi->bi_vcnt = 1;
bi->bi_max_vecs = 1;
bi->bi_idx = 0;
bi->bi_io_vec = &sh->dev[i].vec;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
bi->bi_next = NULL;
if (rw == WRITE &&
test_bit(R5_ReWrite, &sh->dev[i].flags))
atomic_add(STRIPE_SECTORS,
&rdev->corrected_errors);
generic_make_request(bi);
} else {
if (rw == WRITE)
set_bit(STRIPE_DEGRADED, &sh->state);
pr_debug("skip op %ld on disc %d for sector %llu\n",
bi->bi_rw, i, (unsigned long long)sh->sector);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
}
}
}
static struct dma_async_tx_descriptor *
async_copy_data(int frombio, struct bio *bio, struct page *page,
sector_t sector, struct dma_async_tx_descriptor *tx)
{
struct bio_vec *bvl;
struct page *bio_page;
int i;
int page_offset;
if (bio->bi_sector >= sector)
page_offset = (signed)(bio->bi_sector - sector) * 512;
else
page_offset = (signed)(sector - bio->bi_sector) * -512;
bio_for_each_segment(bvl, bio, i) {
int len = bio_iovec_idx(bio, i)->bv_len;
int clen;
int b_offset = 0;
if (page_offset < 0) {
b_offset = -page_offset;
page_offset += b_offset;
len -= b_offset;
}
if (len > 0 && page_offset + len > STRIPE_SIZE)
clen = STRIPE_SIZE - page_offset;
else
clen = len;
if (clen > 0) {
b_offset += bio_iovec_idx(bio, i)->bv_offset;
bio_page = bio_iovec_idx(bio, i)->bv_page;
if (frombio)
tx = async_memcpy(page, bio_page, page_offset,
b_offset, clen,
ASYNC_TX_DEP_ACK,
tx, NULL, NULL);
else
tx = async_memcpy(bio_page, page, b_offset,
page_offset, clen,
ASYNC_TX_DEP_ACK,
tx, NULL, NULL);
}
if (clen < len) /* hit end of page */
break;
page_offset += len;
}
return tx;
}
static void ops_complete_biofill(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
struct bio *return_bi = NULL;
raid5_conf_t *conf = sh->raid_conf;
int i;
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
/* clear completed biofills */
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
/* acknowledge completion of a biofill operation */
/* and check if we need to reply to a read request,
* new R5_Wantfill requests are held off until
* !test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending)
*/
if (test_and_clear_bit(R5_Wantfill, &dev->flags)) {
struct bio *rbi, *rbi2;
/* The access to dev->read is outside of the
* spin_lock_irq(&conf->device_lock), but is protected
* by the STRIPE_OP_BIOFILL pending bit
*/
BUG_ON(!dev->read);
rbi = dev->read;
dev->read = NULL;
while (rbi && rbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
rbi2 = r5_next_bio(rbi, dev->sector);
spin_lock_irq(&conf->device_lock);
if (--rbi->bi_phys_segments == 0) {
rbi->bi_next = return_bi;
return_bi = rbi;
}
spin_unlock_irq(&conf->device_lock);
rbi = rbi2;
}
}
}
set_bit(STRIPE_OP_BIOFILL, &sh->ops.complete);
return_io(return_bi);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static void ops_run_biofill(struct stripe_head *sh)
{
struct dma_async_tx_descriptor *tx = NULL;
raid5_conf_t *conf = sh->raid_conf;
int i;
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (test_bit(R5_Wantfill, &dev->flags)) {
struct bio *rbi;
spin_lock_irq(&conf->device_lock);
dev->read = rbi = dev->toread;
dev->toread = NULL;
spin_unlock_irq(&conf->device_lock);
while (rbi && rbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
tx = async_copy_data(0, rbi, dev->page,
dev->sector, tx);
rbi = r5_next_bio(rbi, dev->sector);
}
}
}
atomic_inc(&sh->count);
async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
ops_complete_biofill, sh);
}
static void ops_complete_compute5(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
int target = sh->ops.target;
struct r5dev *tgt = &sh->dev[target];
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
set_bit(R5_UPTODATE, &tgt->flags);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
clear_bit(R5_Wantcompute, &tgt->flags);
set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static struct dma_async_tx_descriptor *
ops_run_compute5(struct stripe_head *sh, unsigned long pending)
{
/* kernel stack size limits the total number of disks */
int disks = sh->disks;
struct page *xor_srcs[disks];
int target = sh->ops.target;
struct r5dev *tgt = &sh->dev[target];
struct page *xor_dest = tgt->page;
int count = 0;
struct dma_async_tx_descriptor *tx;
int i;
pr_debug("%s: stripe %llu block: %d\n",
__FUNCTION__, (unsigned long long)sh->sector, target);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
for (i = disks; i--; )
if (i != target)
xor_srcs[count++] = sh->dev[i].page;
atomic_inc(&sh->count);
if (unlikely(count == 1))
tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
0, NULL, ops_complete_compute5, sh);
else
tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
ASYNC_TX_XOR_ZERO_DST, NULL,
ops_complete_compute5, sh);
/* ack now if postxor is not set to be run */
if (tx && !test_bit(STRIPE_OP_POSTXOR, &pending))
async_tx_ack(tx);
return tx;
}
static void ops_complete_prexor(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
set_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
}
static struct dma_async_tx_descriptor *
ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
{
/* kernel stack size limits the total number of disks */
int disks = sh->disks;
struct page *xor_srcs[disks];
int count = 0, pd_idx = sh->pd_idx, i;
/* existing parity data subtracted */
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
/* Only process blocks that are known to be uptodate */
if (dev->towrite && test_bit(R5_Wantprexor, &dev->flags))
xor_srcs[count++] = dev->page;
}
tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
ASYNC_TX_DEP_ACK | ASYNC_TX_XOR_DROP_DST, tx,
ops_complete_prexor, sh);
return tx;
}
static struct dma_async_tx_descriptor *
ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
unsigned long pending)
{
int disks = sh->disks;
int pd_idx = sh->pd_idx, i;
/* check if prexor is active which means only process blocks
* that are part of a read-modify-write (Wantprexor)
*/
int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
struct bio *chosen;
int towrite;
towrite = 0;
if (prexor) { /* rmw */
if (dev->towrite &&
test_bit(R5_Wantprexor, &dev->flags))
towrite = 1;
} else { /* rcw */
if (i != pd_idx && dev->towrite &&
test_bit(R5_LOCKED, &dev->flags))
towrite = 1;
}
if (towrite) {
struct bio *wbi;
spin_lock(&sh->lock);
chosen = dev->towrite;
dev->towrite = NULL;
BUG_ON(dev->written);
wbi = dev->written = chosen;
spin_unlock(&sh->lock);
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
tx = async_copy_data(1, wbi, dev->page,
dev->sector, tx);
wbi = r5_next_bio(wbi, dev->sector);
}
}
}
return tx;
}
static void ops_complete_postxor(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static void ops_complete_write(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
int disks = sh->disks, i, pd_idx = sh->pd_idx;
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->written || i == pd_idx)
set_bit(R5_UPTODATE, &dev->flags);
}
set_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static void
ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
unsigned long pending)
{
/* kernel stack size limits the total number of disks */
int disks = sh->disks;
struct page *xor_srcs[disks];
int count = 0, pd_idx = sh->pd_idx, i;
struct page *xor_dest;
int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
unsigned long flags;
dma_async_tx_callback callback;
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
/* check if prexor is active which means only process blocks
* that are part of a read-modify-write (written)
*/
if (prexor) {
xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->written)
xor_srcs[count++] = dev->page;
}
} else {
xor_dest = sh->dev[pd_idx].page;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (i != pd_idx)
xor_srcs[count++] = dev->page;
}
}
/* check whether this postxor is part of a write */
callback = test_bit(STRIPE_OP_BIODRAIN, &pending) ?
ops_complete_write : ops_complete_postxor;
/* 1/ if we prexor'd then the dest is reused as a source
* 2/ if we did not prexor then we are redoing the parity
* set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST
* for the synchronous xor case
*/
flags = ASYNC_TX_DEP_ACK | ASYNC_TX_ACK |
(prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST);
atomic_inc(&sh->count);
if (unlikely(count == 1)) {
flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST);
tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
flags, tx, callback, sh);
} else
tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
flags, tx, callback, sh);
}
static void ops_complete_check(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
int pd_idx = sh->pd_idx;
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
if (test_and_clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending) &&
sh->ops.zero_sum_result == 0)
set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
set_bit(STRIPE_OP_CHECK, &sh->ops.complete);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static void ops_run_check(struct stripe_head *sh)
{
/* kernel stack size limits the total number of disks */
int disks = sh->disks;
struct page *xor_srcs[disks];
struct dma_async_tx_descriptor *tx;
int count = 0, pd_idx = sh->pd_idx, i;
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
pr_debug("%s: stripe %llu\n", __FUNCTION__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (i != pd_idx)
xor_srcs[count++] = dev->page;
}
tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
&sh->ops.zero_sum_result, 0, NULL, NULL, NULL);
if (tx)
set_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
else
clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
atomic_inc(&sh->count);
tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
ops_complete_check, sh);
}
static void raid5_run_ops(struct stripe_head *sh, unsigned long pending)
{
int overlap_clear = 0, i, disks = sh->disks;
struct dma_async_tx_descriptor *tx = NULL;
if (test_bit(STRIPE_OP_BIOFILL, &pending)) {
ops_run_biofill(sh);
overlap_clear++;
}
if (test_bit(STRIPE_OP_COMPUTE_BLK, &pending))
tx = ops_run_compute5(sh, pending);
if (test_bit(STRIPE_OP_PREXOR, &pending))
tx = ops_run_prexor(sh, tx);
if (test_bit(STRIPE_OP_BIODRAIN, &pending)) {
tx = ops_run_biodrain(sh, tx, pending);
overlap_clear++;
}
if (test_bit(STRIPE_OP_POSTXOR, &pending))
ops_run_postxor(sh, tx, pending);
if (test_bit(STRIPE_OP_CHECK, &pending))
ops_run_check(sh);
if (test_bit(STRIPE_OP_IO, &pending))
ops_run_io(sh);
if (overlap_clear)
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (test_and_clear_bit(R5_Overlap, &dev->flags))
wake_up(&sh->raid_conf->wait_for_overlap);
}
}
static int grow_one_stripe(raid5_conf_t *conf)
{
struct stripe_head *sh;
sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
if (!sh)
return 0;
memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev));
sh->raid_conf = conf;
spin_lock_init(&sh->lock);
if (grow_buffers(sh, conf->raid_disks)) {
shrink_buffers(sh, conf->raid_disks);
kmem_cache_free(conf->slab_cache, sh);
return 0;
}
sh->disks = conf->raid_disks;
/* we just created an active stripe so... */
atomic_set(&sh->count, 1);
atomic_inc(&conf->active_stripes);
INIT_LIST_HEAD(&sh->lru);
release_stripe(sh);
return 1;
}
static int grow_stripes(raid5_conf_t *conf, int num)
{
struct kmem_cache *sc;
int devs = conf->raid_disks;
sprintf(conf->cache_name[0], "raid5-%s", mdname(conf->mddev));
sprintf(conf->cache_name[1], "raid5-%s-alt", mdname(conf->mddev));
conf->active_name = 0;
sc = kmem_cache_create(conf->cache_name[conf->active_name],
sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
0, 0, NULL);
if (!sc)
return 1;
conf->slab_cache = sc;
conf->pool_size = devs;
while (num--)
if (!grow_one_stripe(conf))
return 1;
return 0;
}
#ifdef CONFIG_MD_RAID5_RESHAPE
static int resize_stripes(raid5_conf_t *conf, int newsize)
{
/* Make all the stripes able to hold 'newsize' devices.
* New slots in each stripe get 'page' set to a new page.
*
* This happens in stages:
* 1/ create a new kmem_cache and allocate the required number of
* stripe_heads.
* 2/ gather all the old stripe_heads and tranfer the pages across
* to the new stripe_heads. This will have the side effect of
* freezing the array as once all stripe_heads have been collected,
* no IO will be possible. Old stripe heads are freed once their
* pages have been transferred over, and the old kmem_cache is
* freed when all stripes are done.
* 3/ reallocate conf->disks to be suitable bigger. If this fails,
* we simple return a failre status - no need to clean anything up.
* 4/ allocate new pages for the new slots in the new stripe_heads.
* If this fails, we don't bother trying the shrink the
* stripe_heads down again, we just leave them as they are.
* As each stripe_head is processed the new one is released into
* active service.
*
* Once step2 is started, we cannot afford to wait for a write,
* so we use GFP_NOIO allocations.
*/
struct stripe_head *osh, *nsh;
LIST_HEAD(newstripes);
struct disk_info *ndisks;
int err = 0;
struct kmem_cache *sc;
int i;
if (newsize <= conf->pool_size)