forked from openbmc/linux
-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathpblk-core.c
1907 lines (1558 loc) · 45.5 KB
/
pblk-core.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright (C) 2016 CNEX Labs
* Initial release: Javier Gonzalez <javier@cnexlabs.com>
* Matias Bjorling <matias@cnexlabs.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License version
* 2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that 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.
*
* pblk-core.c - pblk's core functionality
*
*/
#include "pblk.h"
static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
struct ppa_addr *ppa)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
int pos = pblk_dev_ppa_to_pos(geo, *ppa);
pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
atomic_long_inc(&pblk->erase_failed);
atomic_dec(&line->blk_in_line);
if (test_and_set_bit(pos, line->blk_bitmap))
pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
line->id, pos);
pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb, pblk->bb_wq);
}
static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
{
struct pblk_line *line;
line = &pblk->lines[pblk_dev_ppa_to_line(rqd->ppa_addr)];
atomic_dec(&line->left_seblks);
if (rqd->error) {
struct ppa_addr *ppa;
ppa = kmalloc(sizeof(struct ppa_addr), GFP_ATOMIC);
if (!ppa)
return;
*ppa = rqd->ppa_addr;
pblk_mark_bb(pblk, line, ppa);
}
atomic_dec(&pblk->inflight_io);
}
/* Erase completion assumes that only one block is erased at the time */
static void pblk_end_io_erase(struct nvm_rq *rqd)
{
struct pblk *pblk = rqd->private;
__pblk_end_io_erase(pblk, rqd);
mempool_free(rqd, pblk->g_rq_pool);
}
void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
u64 paddr)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct list_head *move_list = NULL;
/* Lines being reclaimed (GC'ed) cannot be invalidated. Before the L2P
* table is modified with reclaimed sectors, a check is done to endure
* that newer updates are not overwritten.
*/
spin_lock(&line->lock);
if (line->state == PBLK_LINESTATE_GC ||
line->state == PBLK_LINESTATE_FREE) {
spin_unlock(&line->lock);
return;
}
if (test_and_set_bit(paddr, line->invalid_bitmap)) {
WARN_ONCE(1, "pblk: double invalidate\n");
spin_unlock(&line->lock);
return;
}
le32_add_cpu(line->vsc, -1);
if (line->state == PBLK_LINESTATE_CLOSED)
move_list = pblk_line_gc_list(pblk, line);
spin_unlock(&line->lock);
if (move_list) {
spin_lock(&l_mg->gc_lock);
spin_lock(&line->lock);
/* Prevent moving a line that has just been chosen for GC */
if (line->state == PBLK_LINESTATE_GC ||
line->state == PBLK_LINESTATE_FREE) {
spin_unlock(&line->lock);
spin_unlock(&l_mg->gc_lock);
return;
}
spin_unlock(&line->lock);
list_move_tail(&line->list, move_list);
spin_unlock(&l_mg->gc_lock);
}
}
void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
{
struct pblk_line *line;
u64 paddr;
int line_id;
#ifdef CONFIG_NVM_DEBUG
/* Callers must ensure that the ppa points to a device address */
BUG_ON(pblk_addr_in_cache(ppa));
BUG_ON(pblk_ppa_empty(ppa));
#endif
line_id = pblk_tgt_ppa_to_line(ppa);
line = &pblk->lines[line_id];
paddr = pblk_dev_ppa_to_line_addr(pblk, ppa);
__pblk_map_invalidate(pblk, line, paddr);
}
static void pblk_invalidate_range(struct pblk *pblk, sector_t slba,
unsigned int nr_secs)
{
sector_t lba;
spin_lock(&pblk->trans_lock);
for (lba = slba; lba < slba + nr_secs; lba++) {
struct ppa_addr ppa;
ppa = pblk_trans_map_get(pblk, lba);
if (!pblk_addr_in_cache(ppa) && !pblk_ppa_empty(ppa))
pblk_map_invalidate(pblk, ppa);
pblk_ppa_set_empty(&ppa);
pblk_trans_map_set(pblk, lba, ppa);
}
spin_unlock(&pblk->trans_lock);
}
struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw)
{
mempool_t *pool;
struct nvm_rq *rqd;
int rq_size;
if (rw == WRITE) {
pool = pblk->w_rq_pool;
rq_size = pblk_w_rq_size;
} else {
pool = pblk->g_rq_pool;
rq_size = pblk_g_rq_size;
}
rqd = mempool_alloc(pool, GFP_KERNEL);
memset(rqd, 0, rq_size);
return rqd;
}
void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw)
{
mempool_t *pool;
if (rw == WRITE)
pool = pblk->w_rq_pool;
else
pool = pblk->g_rq_pool;
mempool_free(rqd, pool);
}
void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
int nr_pages)
{
struct bio_vec bv;
int i;
WARN_ON(off + nr_pages != bio->bi_vcnt);
bio_advance(bio, off * PBLK_EXPOSED_PAGE_SIZE);
for (i = off; i < nr_pages + off; i++) {
bv = bio->bi_io_vec[i];
mempool_free(bv.bv_page, pblk->page_pool);
}
}
int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
int nr_pages)
{
struct request_queue *q = pblk->dev->q;
struct page *page;
int i, ret;
for (i = 0; i < nr_pages; i++) {
page = mempool_alloc(pblk->page_pool, flags);
if (!page)
goto err;
ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
if (ret != PBLK_EXPOSED_PAGE_SIZE) {
pr_err("pblk: could not add page to bio\n");
mempool_free(page, pblk->page_pool);
goto err;
}
}
return 0;
err:
pblk_bio_free_pages(pblk, bio, 0, i - 1);
return -1;
}
static void pblk_write_kick(struct pblk *pblk)
{
wake_up_process(pblk->writer_ts);
mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(1000));
}
void pblk_write_timer_fn(unsigned long data)
{
struct pblk *pblk = (struct pblk *)data;
/* kick the write thread every tick to flush outstanding data */
pblk_write_kick(pblk);
}
void pblk_write_should_kick(struct pblk *pblk)
{
unsigned int secs_avail = pblk_rb_read_count(&pblk->rwb);
if (secs_avail >= pblk->min_write_pgs)
pblk_write_kick(pblk);
}
void pblk_end_bio_sync(struct bio *bio)
{
struct completion *waiting = bio->bi_private;
complete(waiting);
}
void pblk_end_io_sync(struct nvm_rq *rqd)
{
struct completion *waiting = rqd->private;
complete(waiting);
}
void pblk_wait_for_meta(struct pblk *pblk)
{
do {
if (!atomic_read(&pblk->inflight_io))
break;
schedule();
} while (1);
}
static void pblk_flush_writer(struct pblk *pblk)
{
pblk_rb_flush(&pblk->rwb);
do {
if (!pblk_rb_sync_count(&pblk->rwb))
break;
pblk_write_kick(pblk);
schedule();
} while (1);
}
struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
{
struct pblk_line_meta *lm = &pblk->lm;
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct list_head *move_list = NULL;
int vsc = le32_to_cpu(*line->vsc);
lockdep_assert_held(&line->lock);
if (!vsc) {
if (line->gc_group != PBLK_LINEGC_FULL) {
line->gc_group = PBLK_LINEGC_FULL;
move_list = &l_mg->gc_full_list;
}
} else if (vsc < lm->high_thrs) {
if (line->gc_group != PBLK_LINEGC_HIGH) {
line->gc_group = PBLK_LINEGC_HIGH;
move_list = &l_mg->gc_high_list;
}
} else if (vsc < lm->mid_thrs) {
if (line->gc_group != PBLK_LINEGC_MID) {
line->gc_group = PBLK_LINEGC_MID;
move_list = &l_mg->gc_mid_list;
}
} else if (vsc < line->sec_in_line) {
if (line->gc_group != PBLK_LINEGC_LOW) {
line->gc_group = PBLK_LINEGC_LOW;
move_list = &l_mg->gc_low_list;
}
} else if (vsc == line->sec_in_line) {
if (line->gc_group != PBLK_LINEGC_EMPTY) {
line->gc_group = PBLK_LINEGC_EMPTY;
move_list = &l_mg->gc_empty_list;
}
} else {
line->state = PBLK_LINESTATE_CORRUPT;
line->gc_group = PBLK_LINEGC_NONE;
move_list = &l_mg->corrupt_list;
pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
line->id, vsc,
line->sec_in_line,
lm->high_thrs, lm->mid_thrs);
}
return move_list;
}
void pblk_discard(struct pblk *pblk, struct bio *bio)
{
sector_t slba = pblk_get_lba(bio);
sector_t nr_secs = pblk_get_secs(bio);
pblk_invalidate_range(pblk, slba, nr_secs);
}
struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba)
{
struct ppa_addr ppa;
spin_lock(&pblk->trans_lock);
ppa = pblk_trans_map_get(pblk, lba);
spin_unlock(&pblk->trans_lock);
return ppa;
}
void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd)
{
atomic_long_inc(&pblk->write_failed);
#ifdef CONFIG_NVM_DEBUG
pblk_print_failed_rqd(pblk, rqd, rqd->error);
#endif
}
void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
{
/* Empty page read is not necessarily an error (e.g., L2P recovery) */
if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) {
atomic_long_inc(&pblk->read_empty);
return;
}
switch (rqd->error) {
case NVM_RSP_WARN_HIGHECC:
atomic_long_inc(&pblk->read_high_ecc);
break;
case NVM_RSP_ERR_FAILECC:
case NVM_RSP_ERR_FAILCRC:
atomic_long_inc(&pblk->read_failed);
break;
default:
pr_err("pblk: unknown read error:%d\n", rqd->error);
}
#ifdef CONFIG_NVM_DEBUG
pblk_print_failed_rqd(pblk, rqd, rqd->error);
#endif
}
void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write)
{
pblk->sec_per_write = sec_per_write;
}
int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
{
struct nvm_tgt_dev *dev = pblk->dev;
#ifdef CONFIG_NVM_DEBUG
struct ppa_addr *ppa_list;
ppa_list = (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr;
if (pblk_boundary_ppa_checks(dev, ppa_list, rqd->nr_ppas)) {
WARN_ON(1);
return -EINVAL;
}
if (rqd->opcode == NVM_OP_PWRITE) {
struct pblk_line *line;
struct ppa_addr ppa;
int i;
for (i = 0; i < rqd->nr_ppas; i++) {
ppa = ppa_list[i];
line = &pblk->lines[pblk_dev_ppa_to_line(ppa)];
spin_lock(&line->lock);
if (line->state != PBLK_LINESTATE_OPEN) {
pr_err("pblk: bad ppa: line:%d,state:%d\n",
line->id, line->state);
WARN_ON(1);
spin_unlock(&line->lock);
return -EINVAL;
}
spin_unlock(&line->lock);
}
}
#endif
atomic_inc(&pblk->inflight_io);
return nvm_submit_io(dev, rqd);
}
struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
unsigned int nr_secs, unsigned int len,
int alloc_type, gfp_t gfp_mask)
{
struct nvm_tgt_dev *dev = pblk->dev;
void *kaddr = data;
struct page *page;
struct bio *bio;
int i, ret;
if (alloc_type == PBLK_KMALLOC_META)
return bio_map_kern(dev->q, kaddr, len, gfp_mask);
bio = bio_kmalloc(gfp_mask, nr_secs);
if (!bio)
return ERR_PTR(-ENOMEM);
for (i = 0; i < nr_secs; i++) {
page = vmalloc_to_page(kaddr);
if (!page) {
pr_err("pblk: could not map vmalloc bio\n");
bio_put(bio);
bio = ERR_PTR(-ENOMEM);
goto out;
}
ret = bio_add_pc_page(dev->q, bio, page, PAGE_SIZE, 0);
if (ret != PAGE_SIZE) {
pr_err("pblk: could not add page to bio\n");
bio_put(bio);
bio = ERR_PTR(-ENOMEM);
goto out;
}
kaddr += PAGE_SIZE;
}
out:
return bio;
}
int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
unsigned long secs_to_flush)
{
int max = pblk->sec_per_write;
int min = pblk->min_write_pgs;
int secs_to_sync = 0;
if (secs_avail >= max)
secs_to_sync = max;
else if (secs_avail >= min)
secs_to_sync = min * (secs_avail / min);
else if (secs_to_flush)
secs_to_sync = min;
return secs_to_sync;
}
void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
{
u64 addr;
int i;
addr = find_next_zero_bit(line->map_bitmap,
pblk->lm.sec_per_line, line->cur_sec);
line->cur_sec = addr - nr_secs;
for (i = 0; i < nr_secs; i++, line->cur_sec--)
WARN_ON(!test_and_clear_bit(line->cur_sec, line->map_bitmap));
}
u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
{
u64 addr;
int i;
lockdep_assert_held(&line->lock);
/* logic error: ppa out-of-bounds. Prevent generating bad address */
if (line->cur_sec + nr_secs > pblk->lm.sec_per_line) {
WARN(1, "pblk: page allocation out of bounds\n");
nr_secs = pblk->lm.sec_per_line - line->cur_sec;
}
line->cur_sec = addr = find_next_zero_bit(line->map_bitmap,
pblk->lm.sec_per_line, line->cur_sec);
for (i = 0; i < nr_secs; i++, line->cur_sec++)
WARN_ON(test_and_set_bit(line->cur_sec, line->map_bitmap));
return addr;
}
u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
{
u64 addr;
/* Lock needed in case a write fails and a recovery needs to remap
* failed write buffer entries
*/
spin_lock(&line->lock);
addr = __pblk_alloc_page(pblk, line, nr_secs);
line->left_msecs -= nr_secs;
WARN(line->left_msecs < 0, "pblk: page allocation out of bounds\n");
spin_unlock(&line->lock);
return addr;
}
u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line)
{
u64 paddr;
spin_lock(&line->lock);
paddr = find_next_zero_bit(line->map_bitmap,
pblk->lm.sec_per_line, line->cur_sec);
spin_unlock(&line->lock);
return paddr;
}
/*
* Submit emeta to one LUN in the raid line at the time to avoid a deadlock when
* taking the per LUN semaphore.
*/
static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
void *emeta_buf, u64 paddr, int dir)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line_meta *lm = &pblk->lm;
void *ppa_list, *meta_list;
struct bio *bio;
struct nvm_rq rqd;
dma_addr_t dma_ppa_list, dma_meta_list;
int min = pblk->min_write_pgs;
int left_ppas = lm->emeta_sec[0];
int id = line->id;
int rq_ppas, rq_len;
int cmd_op, bio_op;
int i, j;
int ret;
DECLARE_COMPLETION_ONSTACK(wait);
if (dir == WRITE) {
bio_op = REQ_OP_WRITE;
cmd_op = NVM_OP_PWRITE;
} else if (dir == READ) {
bio_op = REQ_OP_READ;
cmd_op = NVM_OP_PREAD;
} else
return -EINVAL;
meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
&dma_meta_list);
if (!meta_list)
return -ENOMEM;
ppa_list = meta_list + pblk_dma_meta_size;
dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
next_rq:
memset(&rqd, 0, sizeof(struct nvm_rq));
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
rq_len = rq_ppas * geo->sec_size;
bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len,
l_mg->emeta_alloc_type, GFP_KERNEL);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
goto free_rqd_dma;
}
bio->bi_iter.bi_sector = 0; /* internal bio */
bio_set_op_attrs(bio, bio_op, 0);
rqd.bio = bio;
rqd.meta_list = meta_list;
rqd.ppa_list = ppa_list;
rqd.dma_meta_list = dma_meta_list;
rqd.dma_ppa_list = dma_ppa_list;
rqd.opcode = cmd_op;
rqd.nr_ppas = rq_ppas;
rqd.end_io = pblk_end_io_sync;
rqd.private = &wait;
if (dir == WRITE) {
struct pblk_sec_meta *meta_list = rqd.meta_list;
rqd.flags = pblk_set_progr_mode(pblk, WRITE);
for (i = 0; i < rqd.nr_ppas; ) {
spin_lock(&line->lock);
paddr = __pblk_alloc_page(pblk, line, min);
spin_unlock(&line->lock);
for (j = 0; j < min; j++, i++, paddr++) {
meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
rqd.ppa_list[i] =
addr_to_gen_ppa(pblk, paddr, id);
}
}
} else {
for (i = 0; i < rqd.nr_ppas; ) {
struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, id);
int pos = pblk_dev_ppa_to_pos(geo, ppa);
int read_type = PBLK_READ_RANDOM;
if (pblk_io_aligned(pblk, rq_ppas))
read_type = PBLK_READ_SEQUENTIAL;
rqd.flags = pblk_set_read_mode(pblk, read_type);
while (test_bit(pos, line->blk_bitmap)) {
paddr += min;
if (pblk_boundary_paddr_checks(pblk, paddr)) {
pr_err("pblk: corrupt emeta line:%d\n",
line->id);
bio_put(bio);
ret = -EINTR;
goto free_rqd_dma;
}
ppa = addr_to_gen_ppa(pblk, paddr, id);
pos = pblk_dev_ppa_to_pos(geo, ppa);
}
if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
pr_err("pblk: corrupt emeta line:%d\n",
line->id);
bio_put(bio);
ret = -EINTR;
goto free_rqd_dma;
}
for (j = 0; j < min; j++, i++, paddr++)
rqd.ppa_list[i] =
addr_to_gen_ppa(pblk, paddr, line->id);
}
}
ret = pblk_submit_io(pblk, &rqd);
if (ret) {
pr_err("pblk: emeta I/O submission failed: %d\n", ret);
bio_put(bio);
goto free_rqd_dma;
}
if (!wait_for_completion_io_timeout(&wait,
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: emeta I/O timed out\n");
}
atomic_dec(&pblk->inflight_io);
reinit_completion(&wait);
if (likely(pblk->l_mg.emeta_alloc_type == PBLK_VMALLOC_META))
bio_put(bio);
if (rqd.error) {
if (dir == WRITE)
pblk_log_write_err(pblk, &rqd);
else
pblk_log_read_err(pblk, &rqd);
}
emeta_buf += rq_len;
left_ppas -= rq_ppas;
if (left_ppas)
goto next_rq;
free_rqd_dma:
nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list);
return ret;
}
u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
struct pblk_line_meta *lm = &pblk->lm;
int bit;
/* This usually only happens on bad lines */
bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
if (bit >= lm->blk_per_line)
return -1;
return bit * geo->sec_per_pl;
}
static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
u64 paddr, int dir)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct pblk_line_meta *lm = &pblk->lm;
struct bio *bio;
struct nvm_rq rqd;
__le64 *lba_list = NULL;
int i, ret;
int cmd_op, bio_op;
int flags;
DECLARE_COMPLETION_ONSTACK(wait);
if (dir == WRITE) {
bio_op = REQ_OP_WRITE;
cmd_op = NVM_OP_PWRITE;
flags = pblk_set_progr_mode(pblk, WRITE);
lba_list = emeta_to_lbas(pblk, line->emeta->buf);
} else if (dir == READ) {
bio_op = REQ_OP_READ;
cmd_op = NVM_OP_PREAD;
flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
} else
return -EINVAL;
memset(&rqd, 0, sizeof(struct nvm_rq));
rqd.meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
&rqd.dma_meta_list);
if (!rqd.meta_list)
return -ENOMEM;
rqd.ppa_list = rqd.meta_list + pblk_dma_meta_size;
rqd.dma_ppa_list = rqd.dma_meta_list + pblk_dma_meta_size;
bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
goto free_ppa_list;
}
bio->bi_iter.bi_sector = 0; /* internal bio */
bio_set_op_attrs(bio, bio_op, 0);
rqd.bio = bio;
rqd.opcode = cmd_op;
rqd.flags = flags;
rqd.nr_ppas = lm->smeta_sec;
rqd.end_io = pblk_end_io_sync;
rqd.private = &wait;
for (i = 0; i < lm->smeta_sec; i++, paddr++) {
struct pblk_sec_meta *meta_list = rqd.meta_list;
rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
if (dir == WRITE) {
__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
meta_list[i].lba = lba_list[paddr] = addr_empty;
}
}
/*
* This I/O is sent by the write thread when a line is replace. Since
* the write thread is the only one sending write and erase commands,
* there is no need to take the LUN semaphore.
*/
ret = pblk_submit_io(pblk, &rqd);
if (ret) {
pr_err("pblk: smeta I/O submission failed: %d\n", ret);
bio_put(bio);
goto free_ppa_list;
}
if (!wait_for_completion_io_timeout(&wait,
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: smeta I/O timed out\n");
}
atomic_dec(&pblk->inflight_io);
if (rqd.error) {
if (dir == WRITE)
pblk_log_write_err(pblk, &rqd);
else
pblk_log_read_err(pblk, &rqd);
}
free_ppa_list:
nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list);
return ret;
}
int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line)
{
u64 bpaddr = pblk_line_smeta_start(pblk, line);
return pblk_line_submit_smeta_io(pblk, line, bpaddr, READ);
}
int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line,
void *emeta_buf)
{
return pblk_line_submit_emeta_io(pblk, line, emeta_buf,
line->emeta_ssec, READ);
}
static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
struct ppa_addr ppa)
{
rqd->opcode = NVM_OP_ERASE;
rqd->ppa_addr = ppa;
rqd->nr_ppas = 1;
rqd->flags = pblk_set_progr_mode(pblk, ERASE);
rqd->bio = NULL;
}
static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
{
struct nvm_rq rqd;
int ret = 0;
DECLARE_COMPLETION_ONSTACK(wait);
memset(&rqd, 0, sizeof(struct nvm_rq));
pblk_setup_e_rq(pblk, &rqd, ppa);
rqd.end_io = pblk_end_io_sync;
rqd.private = &wait;
/* The write thread schedules erases so that it minimizes disturbances
* with writes. Thus, there is no need to take the LUN semaphore.
*/
ret = pblk_submit_io(pblk, &rqd);
if (ret) {
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
pr_err("pblk: could not sync erase line:%d,blk:%d\n",
pblk_dev_ppa_to_line(ppa),
pblk_dev_ppa_to_pos(geo, ppa));
rqd.error = ret;
goto out;
}
if (!wait_for_completion_io_timeout(&wait,
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: sync erase timed out\n");
}
out:
rqd.private = pblk;
__pblk_end_io_erase(pblk, &rqd);
return ret;
}
int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
{
struct pblk_line_meta *lm = &pblk->lm;
struct ppa_addr ppa;
int ret, bit = -1;
/* Erase only good blocks, one at a time */
do {
spin_lock(&line->lock);
bit = find_next_zero_bit(line->erase_bitmap, lm->blk_per_line,
bit + 1);
if (bit >= lm->blk_per_line) {
spin_unlock(&line->lock);
break;
}
ppa = pblk->luns[bit].bppa; /* set ch and lun */
ppa.g.blk = line->id;
atomic_dec(&line->left_eblks);
WARN_ON(test_and_set_bit(bit, line->erase_bitmap));
spin_unlock(&line->lock);
ret = pblk_blk_erase_sync(pblk, ppa);
if (ret) {
pr_err("pblk: failed to erase line %d\n", line->id);
return ret;
}
} while (1);
return 0;
}
static void pblk_line_setup_metadata(struct pblk_line *line,
struct pblk_line_mgmt *l_mg,
struct pblk_line_meta *lm)
{
int meta_line;
lockdep_assert_held(&l_mg->free_lock);
retry_meta:
meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
if (meta_line == PBLK_DATA_LINES) {
spin_unlock(&l_mg->free_lock);
io_schedule();
spin_lock(&l_mg->free_lock);
goto retry_meta;
}
set_bit(meta_line, &l_mg->meta_bitmap);
line->meta_line = meta_line;
line->smeta = l_mg->sline_meta[meta_line];
line->emeta = l_mg->eline_meta[meta_line];
memset(line->smeta, 0, lm->smeta_len);
memset(line->emeta->buf, 0, lm->emeta_len[0]);
line->emeta->mem = 0;
atomic_set(&line->emeta->sync, 0);
}
/* For now lines are always assumed full lines. Thus, smeta former and current
* lun bitmaps are omitted.
*/
static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
struct pblk_line *cur)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
struct pblk_line_meta *lm = &pblk->lm;
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_emeta *emeta = line->emeta;
struct line_emeta *emeta_buf = emeta->buf;
struct line_smeta *smeta_buf = (struct line_smeta *)line->smeta;
int nr_blk_line;
/* After erasing the line, new bad blocks might appear and we risk
* having an invalid line
*/
nr_blk_line = lm->blk_per_line -
bitmap_weight(line->blk_bitmap, lm->blk_per_line);
if (nr_blk_line < lm->min_blk_line) {
spin_lock(&l_mg->free_lock);
spin_lock(&line->lock);
line->state = PBLK_LINESTATE_BAD;
spin_unlock(&line->lock);
list_add_tail(&line->list, &l_mg->bad_list);
spin_unlock(&l_mg->free_lock);
pr_debug("pblk: line %d is bad\n", line->id);
return 0;
}
/* Run-time metadata */
line->lun_bitmap = ((void *)(smeta_buf)) + sizeof(struct line_smeta);
/* Mark LUNs allocated in this line (all for now) */
bitmap_set(line->lun_bitmap, 0, lm->lun_bitmap_len);
smeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC);
memcpy(smeta_buf->header.uuid, pblk->instance_uuid, 16);
smeta_buf->header.id = cpu_to_le32(line->id);
smeta_buf->header.type = cpu_to_le16(line->type);
smeta_buf->header.version = cpu_to_le16(1);
/* Start metadata */
smeta_buf->seq_nr = cpu_to_le64(line->seq_nr);
smeta_buf->window_wr_lun = cpu_to_le32(geo->nr_luns);
/* Fill metadata among lines */
if (cur) {
memcpy(line->lun_bitmap, cur->lun_bitmap, lm->lun_bitmap_len);
smeta_buf->prev_id = cpu_to_le32(cur->id);
cur->emeta->buf->next_id = cpu_to_le32(line->id);
} else {
smeta_buf->prev_id = cpu_to_le32(PBLK_LINE_EMPTY);
}
/* All smeta must be set at this point */
smeta_buf->header.crc = cpu_to_le32(
pblk_calc_meta_header_crc(pblk, &smeta_buf->header));
smeta_buf->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta_buf));
/* End metadata */
memcpy(&emeta_buf->header, &smeta_buf->header,