forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
raid5-ppl.c
1271 lines (1056 loc) · 35.6 KB
/
raid5-ppl.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
/*
* Partial Parity Log for closing the RAID5 write hole
* Copyright (c) 2017, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*/
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/crc32c.h>
#include <linux/flex_array.h>
#include <linux/async_tx.h>
#include <linux/raid/md_p.h>
#include "md.h"
#include "raid5.h"
/*
* PPL consists of a 4KB header (struct ppl_header) and at least 128KB for
* partial parity data. The header contains an array of entries
* (struct ppl_header_entry) which describe the logged write requests.
* Partial parity for the entries comes after the header, written in the same
* sequence as the entries:
*
* Header
* entry0
* ...
* entryN
* PP data
* PP for entry0
* ...
* PP for entryN
*
* An entry describes one or more consecutive stripe_heads, up to a full
* stripe. The modifed raid data chunks form an m-by-n matrix, where m is the
* number of stripe_heads in the entry and n is the number of modified data
* disks. Every stripe_head in the entry must write to the same data disks.
* An example of a valid case described by a single entry (writes to the first
* stripe of a 4 disk array, 16k chunk size):
*
* sh->sector dd0 dd1 dd2 ppl
* +-----+-----+-----+
* 0 | --- | --- | --- | +----+
* 8 | -W- | -W- | --- | | pp | data_sector = 8
* 16 | -W- | -W- | --- | | pp | data_size = 3 * 2 * 4k
* 24 | -W- | -W- | --- | | pp | pp_size = 3 * 4k
* +-----+-----+-----+ +----+
*
* data_sector is the first raid sector of the modified data, data_size is the
* total size of modified data and pp_size is the size of partial parity for
* this entry. Entries for full stripe writes contain no partial parity
* (pp_size = 0), they only mark the stripes for which parity should be
* recalculated after an unclean shutdown. Every entry holds a checksum of its
* partial parity, the header also has a checksum of the header itself.
*
* A write request is always logged to the PPL instance stored on the parity
* disk of the corresponding stripe. For each member disk there is one ppl_log
* used to handle logging for this disk, independently from others. They are
* grouped in child_logs array in struct ppl_conf, which is assigned to
* r5conf->log_private.
*
* ppl_io_unit represents a full PPL write, header_page contains the ppl_header.
* PPL entries for logged stripes are added in ppl_log_stripe(). A stripe_head
* can be appended to the last entry if it meets the conditions for a valid
* entry described above, otherwise a new entry is added. Checksums of entries
* are calculated incrementally as stripes containing partial parity are being
* added. ppl_submit_iounit() calculates the checksum of the header and submits
* a bio containing the header page and partial parity pages (sh->ppl_page) for
* all stripes of the io_unit. When the PPL write completes, the stripes
* associated with the io_unit are released and raid5d starts writing their data
* and parity. When all stripes are written, the io_unit is freed and the next
* can be submitted.
*
* An io_unit is used to gather stripes until it is submitted or becomes full
* (if the maximum number of entries or size of PPL is reached). Another io_unit
* can't be submitted until the previous has completed (PPL and stripe
* data+parity is written). The log->io_list tracks all io_units of a log
* (for a single member disk). New io_units are added to the end of the list
* and the first io_unit is submitted, if it is not submitted already.
* The current io_unit accepting new stripes is always at the end of the list.
*/
struct ppl_conf {
struct mddev *mddev;
/* array of child logs, one for each raid disk */
struct ppl_log *child_logs;
int count;
int block_size; /* the logical block size used for data_sector
* in ppl_header_entry */
u32 signature; /* raid array identifier */
atomic64_t seq; /* current log write sequence number */
struct kmem_cache *io_kc;
mempool_t *io_pool;
struct bio_set *bs;
/* used only for recovery */
int recovered_entries;
int mismatch_count;
/* stripes to retry if failed to allocate io_unit */
struct list_head no_mem_stripes;
spinlock_t no_mem_stripes_lock;
};
struct ppl_log {
struct ppl_conf *ppl_conf; /* shared between all log instances */
struct md_rdev *rdev; /* array member disk associated with
* this log instance */
struct mutex io_mutex;
struct ppl_io_unit *current_io; /* current io_unit accepting new data
* always at the end of io_list */
spinlock_t io_list_lock;
struct list_head io_list; /* all io_units of this log */
};
#define PPL_IO_INLINE_BVECS 32
struct ppl_io_unit {
struct ppl_log *log;
struct page *header_page; /* for ppl_header */
unsigned int entries_count; /* number of entries in ppl_header */
unsigned int pp_size; /* total size current of partial parity */
u64 seq; /* sequence number of this log write */
struct list_head log_sibling; /* log->io_list */
struct list_head stripe_list; /* stripes added to the io_unit */
atomic_t pending_stripes; /* how many stripes not written to raid */
bool submitted; /* true if write to log started */
/* inline bio and its biovec for submitting the iounit */
struct bio bio;
struct bio_vec biovec[PPL_IO_INLINE_BVECS];
};
struct dma_async_tx_descriptor *
ops_run_partial_parity(struct stripe_head *sh, struct raid5_percpu *percpu,
struct dma_async_tx_descriptor *tx)
{
int disks = sh->disks;
struct page **srcs = flex_array_get(percpu->scribble, 0);
int count = 0, pd_idx = sh->pd_idx, i;
struct async_submit_ctl submit;
pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector);
/*
* Partial parity is the XOR of stripe data chunks that are not changed
* during the write request. Depending on available data
* (read-modify-write vs. reconstruct-write case) we calculate it
* differently.
*/
if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
/*
* rmw: xor old data and parity from updated disks
* This is calculated earlier by ops_run_prexor5() so just copy
* the parity dev page.
*/
srcs[count++] = sh->dev[pd_idx].page;
} else if (sh->reconstruct_state == reconstruct_state_drain_run) {
/* rcw: xor data from all not updated disks */
for (i = disks; i--;) {
struct r5dev *dev = &sh->dev[i];
if (test_bit(R5_UPTODATE, &dev->flags))
srcs[count++] = dev->page;
}
} else {
return tx;
}
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, tx,
NULL, sh, flex_array_get(percpu->scribble, 0)
+ sizeof(struct page *) * (sh->disks + 2));
if (count == 1)
tx = async_memcpy(sh->ppl_page, srcs[0], 0, 0, PAGE_SIZE,
&submit);
else
tx = async_xor(sh->ppl_page, srcs, 0, count, PAGE_SIZE,
&submit);
return tx;
}
static void *ppl_io_pool_alloc(gfp_t gfp_mask, void *pool_data)
{
struct kmem_cache *kc = pool_data;
struct ppl_io_unit *io;
io = kmem_cache_alloc(kc, gfp_mask);
if (!io)
return NULL;
io->header_page = alloc_page(gfp_mask);
if (!io->header_page) {
kmem_cache_free(kc, io);
return NULL;
}
return io;
}
static void ppl_io_pool_free(void *element, void *pool_data)
{
struct kmem_cache *kc = pool_data;
struct ppl_io_unit *io = element;
__free_page(io->header_page);
kmem_cache_free(kc, io);
}
static struct ppl_io_unit *ppl_new_iounit(struct ppl_log *log,
struct stripe_head *sh)
{
struct ppl_conf *ppl_conf = log->ppl_conf;
struct ppl_io_unit *io;
struct ppl_header *pplhdr;
struct page *header_page;
io = mempool_alloc(ppl_conf->io_pool, GFP_NOWAIT);
if (!io)
return NULL;
header_page = io->header_page;
memset(io, 0, sizeof(*io));
io->header_page = header_page;
io->log = log;
INIT_LIST_HEAD(&io->log_sibling);
INIT_LIST_HEAD(&io->stripe_list);
atomic_set(&io->pending_stripes, 0);
bio_init(&io->bio, io->biovec, PPL_IO_INLINE_BVECS);
pplhdr = page_address(io->header_page);
clear_page(pplhdr);
memset(pplhdr->reserved, 0xff, PPL_HDR_RESERVED);
pplhdr->signature = cpu_to_le32(ppl_conf->signature);
io->seq = atomic64_add_return(1, &ppl_conf->seq);
pplhdr->generation = cpu_to_le64(io->seq);
return io;
}
static int ppl_log_stripe(struct ppl_log *log, struct stripe_head *sh)
{
struct ppl_io_unit *io = log->current_io;
struct ppl_header_entry *e = NULL;
struct ppl_header *pplhdr;
int i;
sector_t data_sector = 0;
int data_disks = 0;
unsigned int entry_space = (log->rdev->ppl.size << 9) - PPL_HEADER_SIZE;
struct r5conf *conf = sh->raid_conf;
pr_debug("%s: stripe: %llu\n", __func__, (unsigned long long)sh->sector);
/* check if current io_unit is full */
if (io && (io->pp_size == entry_space ||
io->entries_count == PPL_HDR_MAX_ENTRIES)) {
pr_debug("%s: add io_unit blocked by seq: %llu\n",
__func__, io->seq);
io = NULL;
}
/* add a new unit if there is none or the current is full */
if (!io) {
io = ppl_new_iounit(log, sh);
if (!io)
return -ENOMEM;
spin_lock_irq(&log->io_list_lock);
list_add_tail(&io->log_sibling, &log->io_list);
spin_unlock_irq(&log->io_list_lock);
log->current_io = io;
}
for (i = 0; i < sh->disks; i++) {
struct r5dev *dev = &sh->dev[i];
if (i != sh->pd_idx && test_bit(R5_Wantwrite, &dev->flags)) {
if (!data_disks || dev->sector < data_sector)
data_sector = dev->sector;
data_disks++;
}
}
BUG_ON(!data_disks);
pr_debug("%s: seq: %llu data_sector: %llu data_disks: %d\n", __func__,
io->seq, (unsigned long long)data_sector, data_disks);
pplhdr = page_address(io->header_page);
if (io->entries_count > 0) {
struct ppl_header_entry *last =
&pplhdr->entries[io->entries_count - 1];
struct stripe_head *sh_last = list_last_entry(
&io->stripe_list, struct stripe_head, log_list);
u64 data_sector_last = le64_to_cpu(last->data_sector);
u32 data_size_last = le32_to_cpu(last->data_size);
/*
* Check if we can append the stripe to the last entry. It must
* be just after the last logged stripe and write to the same
* disks. Use bit shift and logarithm to avoid 64-bit division.
*/
if ((sh->sector == sh_last->sector + STRIPE_SECTORS) &&
(data_sector >> ilog2(conf->chunk_sectors) ==
data_sector_last >> ilog2(conf->chunk_sectors)) &&
((data_sector - data_sector_last) * data_disks ==
data_size_last >> 9))
e = last;
}
if (!e) {
e = &pplhdr->entries[io->entries_count++];
e->data_sector = cpu_to_le64(data_sector);
e->parity_disk = cpu_to_le32(sh->pd_idx);
e->checksum = cpu_to_le32(~0);
}
le32_add_cpu(&e->data_size, data_disks << PAGE_SHIFT);
/* don't write any PP if full stripe write */
if (!test_bit(STRIPE_FULL_WRITE, &sh->state)) {
le32_add_cpu(&e->pp_size, PAGE_SIZE);
io->pp_size += PAGE_SIZE;
e->checksum = cpu_to_le32(crc32c_le(le32_to_cpu(e->checksum),
page_address(sh->ppl_page),
PAGE_SIZE));
}
list_add_tail(&sh->log_list, &io->stripe_list);
atomic_inc(&io->pending_stripes);
sh->ppl_io = io;
return 0;
}
int ppl_write_stripe(struct r5conf *conf, struct stripe_head *sh)
{
struct ppl_conf *ppl_conf = conf->log_private;
struct ppl_io_unit *io = sh->ppl_io;
struct ppl_log *log;
if (io || test_bit(STRIPE_SYNCING, &sh->state) || !sh->ppl_page ||
!test_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags) ||
!test_bit(R5_Insync, &sh->dev[sh->pd_idx].flags)) {
clear_bit(STRIPE_LOG_TRAPPED, &sh->state);
return -EAGAIN;
}
log = &ppl_conf->child_logs[sh->pd_idx];
mutex_lock(&log->io_mutex);
if (!log->rdev || test_bit(Faulty, &log->rdev->flags)) {
mutex_unlock(&log->io_mutex);
return -EAGAIN;
}
set_bit(STRIPE_LOG_TRAPPED, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
atomic_inc(&sh->count);
if (ppl_log_stripe(log, sh)) {
spin_lock_irq(&ppl_conf->no_mem_stripes_lock);
list_add_tail(&sh->log_list, &ppl_conf->no_mem_stripes);
spin_unlock_irq(&ppl_conf->no_mem_stripes_lock);
}
mutex_unlock(&log->io_mutex);
return 0;
}
static void ppl_log_endio(struct bio *bio)
{
struct ppl_io_unit *io = bio->bi_private;
struct ppl_log *log = io->log;
struct ppl_conf *ppl_conf = log->ppl_conf;
struct stripe_head *sh, *next;
pr_debug("%s: seq: %llu\n", __func__, io->seq);
if (bio->bi_error)
md_error(ppl_conf->mddev, log->rdev);
list_for_each_entry_safe(sh, next, &io->stripe_list, log_list) {
list_del_init(&sh->log_list);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
}
}
static void ppl_submit_iounit_bio(struct ppl_io_unit *io, struct bio *bio)
{
char b[BDEVNAME_SIZE];
pr_debug("%s: seq: %llu size: %u sector: %llu dev: %s\n",
__func__, io->seq, bio->bi_iter.bi_size,
(unsigned long long)bio->bi_iter.bi_sector,
bdevname(bio->bi_bdev, b));
submit_bio(bio);
}
static void ppl_submit_iounit(struct ppl_io_unit *io)
{
struct ppl_log *log = io->log;
struct ppl_conf *ppl_conf = log->ppl_conf;
struct ppl_header *pplhdr = page_address(io->header_page);
struct bio *bio = &io->bio;
struct stripe_head *sh;
int i;
bio->bi_private = io;
if (!log->rdev || test_bit(Faulty, &log->rdev->flags)) {
ppl_log_endio(bio);
return;
}
for (i = 0; i < io->entries_count; i++) {
struct ppl_header_entry *e = &pplhdr->entries[i];
pr_debug("%s: seq: %llu entry: %d data_sector: %llu pp_size: %u data_size: %u\n",
__func__, io->seq, i, le64_to_cpu(e->data_sector),
le32_to_cpu(e->pp_size), le32_to_cpu(e->data_size));
e->data_sector = cpu_to_le64(le64_to_cpu(e->data_sector) >>
ilog2(ppl_conf->block_size >> 9));
e->checksum = cpu_to_le32(~le32_to_cpu(e->checksum));
}
pplhdr->entries_count = cpu_to_le32(io->entries_count);
pplhdr->checksum = cpu_to_le32(~crc32c_le(~0, pplhdr, PPL_HEADER_SIZE));
bio->bi_end_io = ppl_log_endio;
bio->bi_opf = REQ_OP_WRITE | REQ_FUA;
bio->bi_bdev = log->rdev->bdev;
bio->bi_iter.bi_sector = log->rdev->ppl.sector;
bio_add_page(bio, io->header_page, PAGE_SIZE, 0);
list_for_each_entry(sh, &io->stripe_list, log_list) {
/* entries for full stripe writes have no partial parity */
if (test_bit(STRIPE_FULL_WRITE, &sh->state))
continue;
if (!bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0)) {
struct bio *prev = bio;
bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES,
ppl_conf->bs);
bio->bi_opf = prev->bi_opf;
bio->bi_bdev = prev->bi_bdev;
bio->bi_iter.bi_sector = bio_end_sector(prev);
bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0);
bio_chain(bio, prev);
ppl_submit_iounit_bio(io, prev);
}
}
ppl_submit_iounit_bio(io, bio);
}
static void ppl_submit_current_io(struct ppl_log *log)
{
struct ppl_io_unit *io;
spin_lock_irq(&log->io_list_lock);
io = list_first_entry_or_null(&log->io_list, struct ppl_io_unit,
log_sibling);
if (io && io->submitted)
io = NULL;
spin_unlock_irq(&log->io_list_lock);
if (io) {
io->submitted = true;
if (io == log->current_io)
log->current_io = NULL;
ppl_submit_iounit(io);
}
}
void ppl_write_stripe_run(struct r5conf *conf)
{
struct ppl_conf *ppl_conf = conf->log_private;
struct ppl_log *log;
int i;
for (i = 0; i < ppl_conf->count; i++) {
log = &ppl_conf->child_logs[i];
mutex_lock(&log->io_mutex);
ppl_submit_current_io(log);
mutex_unlock(&log->io_mutex);
}
}
static void ppl_io_unit_finished(struct ppl_io_unit *io)
{
struct ppl_log *log = io->log;
struct ppl_conf *ppl_conf = log->ppl_conf;
unsigned long flags;
pr_debug("%s: seq: %llu\n", __func__, io->seq);
local_irq_save(flags);
spin_lock(&log->io_list_lock);
list_del(&io->log_sibling);
spin_unlock(&log->io_list_lock);
mempool_free(io, ppl_conf->io_pool);
spin_lock(&ppl_conf->no_mem_stripes_lock);
if (!list_empty(&ppl_conf->no_mem_stripes)) {
struct stripe_head *sh;
sh = list_first_entry(&ppl_conf->no_mem_stripes,
struct stripe_head, log_list);
list_del_init(&sh->log_list);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
}
spin_unlock(&ppl_conf->no_mem_stripes_lock);
local_irq_restore(flags);
}
void ppl_stripe_write_finished(struct stripe_head *sh)
{
struct ppl_io_unit *io;
io = sh->ppl_io;
sh->ppl_io = NULL;
if (io && atomic_dec_and_test(&io->pending_stripes))
ppl_io_unit_finished(io);
}
static void ppl_xor(int size, struct page *page1, struct page *page2)
{
struct async_submit_ctl submit;
struct dma_async_tx_descriptor *tx;
struct page *xor_srcs[] = { page1, page2 };
init_async_submit(&submit, ASYNC_TX_ACK|ASYNC_TX_XOR_DROP_DST,
NULL, NULL, NULL, NULL);
tx = async_xor(page1, xor_srcs, 0, 2, size, &submit);
async_tx_quiesce(&tx);
}
/*
* PPL recovery strategy: xor partial parity and data from all modified data
* disks within a stripe and write the result as the new stripe parity. If all
* stripe data disks are modified (full stripe write), no partial parity is
* available, so just xor the data disks.
*
* Recovery of a PPL entry shall occur only if all modified data disks are
* available and read from all of them succeeds.
*
* A PPL entry applies to a stripe, partial parity size for an entry is at most
* the size of the chunk. Examples of possible cases for a single entry:
*
* case 0: single data disk write:
* data0 data1 data2 ppl parity
* +--------+--------+--------+ +--------------------+
* | ------ | ------ | ------ | +----+ | (no change) |
* | ------ | -data- | ------ | | pp | -> | data1 ^ pp |
* | ------ | -data- | ------ | | pp | -> | data1 ^ pp |
* | ------ | ------ | ------ | +----+ | (no change) |
* +--------+--------+--------+ +--------------------+
* pp_size = data_size
*
* case 1: more than one data disk write:
* data0 data1 data2 ppl parity
* +--------+--------+--------+ +--------------------+
* | ------ | ------ | ------ | +----+ | (no change) |
* | -data- | -data- | ------ | | pp | -> | data0 ^ data1 ^ pp |
* | -data- | -data- | ------ | | pp | -> | data0 ^ data1 ^ pp |
* | ------ | ------ | ------ | +----+ | (no change) |
* +--------+--------+--------+ +--------------------+
* pp_size = data_size / modified_data_disks
*
* case 2: write to all data disks (also full stripe write):
* data0 data1 data2 parity
* +--------+--------+--------+ +--------------------+
* | ------ | ------ | ------ | | (no change) |
* | -data- | -data- | -data- | --------> | xor all data |
* | ------ | ------ | ------ | --------> | (no change) |
* | ------ | ------ | ------ | | (no change) |
* +--------+--------+--------+ +--------------------+
* pp_size = 0
*
* The following cases are possible only in other implementations. The recovery
* code can handle them, but they are not generated at runtime because they can
* be reduced to cases 0, 1 and 2:
*
* case 3:
* data0 data1 data2 ppl parity
* +--------+--------+--------+ +----+ +--------------------+
* | ------ | -data- | -data- | | pp | | data1 ^ data2 ^ pp |
* | ------ | -data- | -data- | | pp | -> | data1 ^ data2 ^ pp |
* | -data- | -data- | -data- | | -- | -> | xor all data |
* | -data- | -data- | ------ | | pp | | data0 ^ data1 ^ pp |
* +--------+--------+--------+ +----+ +--------------------+
* pp_size = chunk_size
*
* case 4:
* data0 data1 data2 ppl parity
* +--------+--------+--------+ +----+ +--------------------+
* | ------ | -data- | ------ | | pp | | data1 ^ pp |
* | ------ | ------ | ------ | | -- | -> | (no change) |
* | ------ | ------ | ------ | | -- | -> | (no change) |
* | -data- | ------ | ------ | | pp | | data0 ^ pp |
* +--------+--------+--------+ +----+ +--------------------+
* pp_size = chunk_size
*/
static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
sector_t ppl_sector)
{
struct ppl_conf *ppl_conf = log->ppl_conf;
struct mddev *mddev = ppl_conf->mddev;
struct r5conf *conf = mddev->private;
int block_size = ppl_conf->block_size;
struct page *page1;
struct page *page2;
sector_t r_sector_first;
sector_t r_sector_last;
int strip_sectors;
int data_disks;
int i;
int ret = 0;
char b[BDEVNAME_SIZE];
unsigned int pp_size = le32_to_cpu(e->pp_size);
unsigned int data_size = le32_to_cpu(e->data_size);
page1 = alloc_page(GFP_KERNEL);
page2 = alloc_page(GFP_KERNEL);
if (!page1 || !page2) {
ret = -ENOMEM;
goto out;
}
r_sector_first = le64_to_cpu(e->data_sector) * (block_size >> 9);
if ((pp_size >> 9) < conf->chunk_sectors) {
if (pp_size > 0) {
data_disks = data_size / pp_size;
strip_sectors = pp_size >> 9;
} else {
data_disks = conf->raid_disks - conf->max_degraded;
strip_sectors = (data_size >> 9) / data_disks;
}
r_sector_last = r_sector_first +
(data_disks - 1) * conf->chunk_sectors +
strip_sectors;
} else {
data_disks = conf->raid_disks - conf->max_degraded;
strip_sectors = conf->chunk_sectors;
r_sector_last = r_sector_first + (data_size >> 9);
}
pr_debug("%s: array sector first: %llu last: %llu\n", __func__,
(unsigned long long)r_sector_first,
(unsigned long long)r_sector_last);
/* if start and end is 4k aligned, use a 4k block */
if (block_size == 512 &&
(r_sector_first & (STRIPE_SECTORS - 1)) == 0 &&
(r_sector_last & (STRIPE_SECTORS - 1)) == 0)
block_size = STRIPE_SIZE;
/* iterate through blocks in strip */
for (i = 0; i < strip_sectors; i += (block_size >> 9)) {
bool update_parity = false;
sector_t parity_sector;
struct md_rdev *parity_rdev;
struct stripe_head sh;
int disk;
int indent = 0;
pr_debug("%s:%*s iter %d start\n", __func__, indent, "", i);
indent += 2;
memset(page_address(page1), 0, PAGE_SIZE);
/* iterate through data member disks */
for (disk = 0; disk < data_disks; disk++) {
int dd_idx;
struct md_rdev *rdev;
sector_t sector;
sector_t r_sector = r_sector_first + i +
(disk * conf->chunk_sectors);
pr_debug("%s:%*s data member disk %d start\n",
__func__, indent, "", disk);
indent += 2;
if (r_sector >= r_sector_last) {
pr_debug("%s:%*s array sector %llu doesn't need parity update\n",
__func__, indent, "",
(unsigned long long)r_sector);
indent -= 2;
continue;
}
update_parity = true;
/* map raid sector to member disk */
sector = raid5_compute_sector(conf, r_sector, 0,
&dd_idx, NULL);
pr_debug("%s:%*s processing array sector %llu => data member disk %d, sector %llu\n",
__func__, indent, "",
(unsigned long long)r_sector, dd_idx,
(unsigned long long)sector);
rdev = conf->disks[dd_idx].rdev;
if (!rdev) {
pr_debug("%s:%*s data member disk %d missing\n",
__func__, indent, "", dd_idx);
update_parity = false;
break;
}
pr_debug("%s:%*s reading data member disk %s sector %llu\n",
__func__, indent, "", bdevname(rdev->bdev, b),
(unsigned long long)sector);
if (!sync_page_io(rdev, sector, block_size, page2,
REQ_OP_READ, 0, false)) {
md_error(mddev, rdev);
pr_debug("%s:%*s read failed!\n", __func__,
indent, "");
ret = -EIO;
goto out;
}
ppl_xor(block_size, page1, page2);
indent -= 2;
}
if (!update_parity)
continue;
if (pp_size > 0) {
pr_debug("%s:%*s reading pp disk sector %llu\n",
__func__, indent, "",
(unsigned long long)(ppl_sector + i));
if (!sync_page_io(log->rdev,
ppl_sector - log->rdev->data_offset + i,
block_size, page2, REQ_OP_READ, 0,
false)) {
pr_debug("%s:%*s read failed!\n", __func__,
indent, "");
md_error(mddev, log->rdev);
ret = -EIO;
goto out;
}
ppl_xor(block_size, page1, page2);
}
/* map raid sector to parity disk */
parity_sector = raid5_compute_sector(conf, r_sector_first + i,
0, &disk, &sh);
BUG_ON(sh.pd_idx != le32_to_cpu(e->parity_disk));
parity_rdev = conf->disks[sh.pd_idx].rdev;
BUG_ON(parity_rdev->bdev->bd_dev != log->rdev->bdev->bd_dev);
pr_debug("%s:%*s write parity at sector %llu, disk %s\n",
__func__, indent, "",
(unsigned long long)parity_sector,
bdevname(parity_rdev->bdev, b));
if (!sync_page_io(parity_rdev, parity_sector, block_size,
page1, REQ_OP_WRITE, 0, false)) {
pr_debug("%s:%*s parity write error!\n", __func__,
indent, "");
md_error(mddev, parity_rdev);
ret = -EIO;
goto out;
}
}
out:
if (page1)
__free_page(page1);
if (page2)
__free_page(page2);
return ret;
}
static int ppl_recover(struct ppl_log *log, struct ppl_header *pplhdr)
{
struct ppl_conf *ppl_conf = log->ppl_conf;
struct md_rdev *rdev = log->rdev;
struct mddev *mddev = rdev->mddev;
sector_t ppl_sector = rdev->ppl.sector + (PPL_HEADER_SIZE >> 9);
struct page *page;
int i;
int ret = 0;
page = alloc_page(GFP_KERNEL);
if (!page)
return -ENOMEM;
/* iterate through all PPL entries saved */
for (i = 0; i < le32_to_cpu(pplhdr->entries_count); i++) {
struct ppl_header_entry *e = &pplhdr->entries[i];
u32 pp_size = le32_to_cpu(e->pp_size);
sector_t sector = ppl_sector;
int ppl_entry_sectors = pp_size >> 9;
u32 crc, crc_stored;
pr_debug("%s: disk: %d entry: %d ppl_sector: %llu pp_size: %u\n",
__func__, rdev->raid_disk, i,
(unsigned long long)ppl_sector, pp_size);
crc = ~0;
crc_stored = le32_to_cpu(e->checksum);
/* read parial parity for this entry and calculate its checksum */
while (pp_size) {
int s = pp_size > PAGE_SIZE ? PAGE_SIZE : pp_size;
if (!sync_page_io(rdev, sector - rdev->data_offset,
s, page, REQ_OP_READ, 0, false)) {
md_error(mddev, rdev);
ret = -EIO;
goto out;
}
crc = crc32c_le(crc, page_address(page), s);
pp_size -= s;
sector += s >> 9;
}
crc = ~crc;
if (crc != crc_stored) {
/*
* Don't recover this entry if the checksum does not
* match, but keep going and try to recover other
* entries.
*/
pr_debug("%s: ppl entry crc does not match: stored: 0x%x calculated: 0x%x\n",
__func__, crc_stored, crc);
ppl_conf->mismatch_count++;
} else {
ret = ppl_recover_entry(log, e, ppl_sector);
if (ret)
goto out;
ppl_conf->recovered_entries++;
}
ppl_sector += ppl_entry_sectors;
}
/* flush the disk cache after recovery if necessary */
ret = blkdev_issue_flush(rdev->bdev, GFP_KERNEL, NULL);
out:
__free_page(page);
return ret;
}
static int ppl_write_empty_header(struct ppl_log *log)
{
struct page *page;
struct ppl_header *pplhdr;
struct md_rdev *rdev = log->rdev;
int ret = 0;
pr_debug("%s: disk: %d ppl_sector: %llu\n", __func__,
rdev->raid_disk, (unsigned long long)rdev->ppl.sector);
page = alloc_page(GFP_NOIO | __GFP_ZERO);
if (!page)
return -ENOMEM;
pplhdr = page_address(page);
memset(pplhdr->reserved, 0xff, PPL_HDR_RESERVED);
pplhdr->signature = cpu_to_le32(log->ppl_conf->signature);
pplhdr->checksum = cpu_to_le32(~crc32c_le(~0, pplhdr, PAGE_SIZE));
if (!sync_page_io(rdev, rdev->ppl.sector - rdev->data_offset,
PPL_HEADER_SIZE, page, REQ_OP_WRITE | REQ_FUA, 0,
false)) {
md_error(rdev->mddev, rdev);
ret = -EIO;
}
__free_page(page);
return ret;
}
static int ppl_load_distributed(struct ppl_log *log)
{
struct ppl_conf *ppl_conf = log->ppl_conf;
struct md_rdev *rdev = log->rdev;
struct mddev *mddev = rdev->mddev;
struct page *page;
struct ppl_header *pplhdr;
u32 crc, crc_stored;
u32 signature;
int ret = 0;
pr_debug("%s: disk: %d\n", __func__, rdev->raid_disk);
/* read PPL header */
page = alloc_page(GFP_KERNEL);
if (!page)
return -ENOMEM;
if (!sync_page_io(rdev, rdev->ppl.sector - rdev->data_offset,
PAGE_SIZE, page, REQ_OP_READ, 0, false)) {
md_error(mddev, rdev);
ret = -EIO;
goto out;
}
pplhdr = page_address(page);
/* check header validity */
crc_stored = le32_to_cpu(pplhdr->checksum);
pplhdr->checksum = 0;
crc = ~crc32c_le(~0, pplhdr, PAGE_SIZE);
if (crc_stored != crc) {
pr_debug("%s: ppl header crc does not match: stored: 0x%x calculated: 0x%x\n",
__func__, crc_stored, crc);
ppl_conf->mismatch_count++;
goto out;
}
signature = le32_to_cpu(pplhdr->signature);
if (mddev->external) {
/*
* For external metadata the header signature is set and
* validated in userspace.
*/
ppl_conf->signature = signature;
} else if (ppl_conf->signature != signature) {
pr_debug("%s: ppl header signature does not match: stored: 0x%x configured: 0x%x\n",
__func__, signature, ppl_conf->signature);
ppl_conf->mismatch_count++;
goto out;
}
/* attempt to recover from log if we are starting a dirty array */
if (!mddev->pers && mddev->recovery_cp != MaxSector)
ret = ppl_recover(log, pplhdr);
out:
/* write empty header if we are starting the array */
if (!ret && !mddev->pers)
ret = ppl_write_empty_header(log);
__free_page(page);
pr_debug("%s: return: %d mismatch_count: %d recovered_entries: %d\n",
__func__, ret, ppl_conf->mismatch_count,
ppl_conf->recovered_entries);
return ret;
}
static int ppl_load(struct ppl_conf *ppl_conf)
{
int ret = 0;
u32 signature = 0;
bool signature_set = false;
int i;
for (i = 0; i < ppl_conf->count; i++) {
struct ppl_log *log = &ppl_conf->child_logs[i];
/* skip missing drive */
if (!log->rdev)