summaryrefslogtreecommitdiffstats
path: root/drivers/lightnvm/pblk-recovery.c
blob: cb556e06673e7465bf856cab8e3329867e676382 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
/*
 * Copyright (C) 2016 CNEX Labs
 * Initial: Javier Gonzalez <javier@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-recovery.c - pblk's recovery path
 */

#include "pblk.h"

void pblk_submit_rec(struct work_struct *work)
{
	struct pblk_rec_ctx *recovery =
			container_of(work, struct pblk_rec_ctx, ws_rec);
	struct pblk *pblk = recovery->pblk;
	struct nvm_tgt_dev *dev = pblk->dev;
	struct nvm_rq *rqd = recovery->rqd;
	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
	int max_secs = nvm_max_phys_sects(dev);
	struct bio *bio;
	unsigned int nr_rec_secs;
	unsigned int pgs_read;
	int ret;

	nr_rec_secs = bitmap_weight((unsigned long int *)&rqd->ppa_status,
								max_secs);

	bio = bio_alloc(GFP_KERNEL, nr_rec_secs);
	if (!bio) {
		pr_err("pblk: not able to create recovery bio\n");
		return;
	}

	bio->bi_iter.bi_sector = 0;
	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
	rqd->bio = bio;
	rqd->nr_ppas = nr_rec_secs;

	pgs_read = pblk_rb_read_to_bio_list(&pblk->rwb, bio, &recovery->failed,
								nr_rec_secs);
	if (pgs_read != nr_rec_secs) {
		pr_err("pblk: could not read recovery entries\n");
		goto err;
	}

	if (pblk_setup_w_rec_rq(pblk, rqd, c_ctx)) {
		pr_err("pblk: could not setup recovery request\n");
		goto err;
	}

#ifdef CONFIG_NVM_DEBUG
	atomic_long_add(nr_rec_secs, &pblk->recov_writes);
#endif

	ret = pblk_submit_io(pblk, rqd);
	if (ret) {
		pr_err("pblk: I/O submission failed: %d\n", ret);
		goto err;
	}

	mempool_free(recovery, pblk->rec_pool);
	return;

err:
	bio_put(bio);
	pblk_free_rqd(pblk, rqd, WRITE);
}

int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
			struct pblk_rec_ctx *recovery, u64 *comp_bits,
			unsigned int comp)
{
	struct nvm_tgt_dev *dev = pblk->dev;
	int max_secs = nvm_max_phys_sects(dev);
	struct nvm_rq *rec_rqd;
	struct pblk_c_ctx *rec_ctx;
	int nr_entries = c_ctx->nr_valid + c_ctx->nr_padded;

	rec_rqd = pblk_alloc_rqd(pblk, WRITE);
	if (IS_ERR(rec_rqd)) {
		pr_err("pblk: could not create recovery req.\n");
		return -ENOMEM;
	}

	rec_ctx = nvm_rq_to_pdu(rec_rqd);

	/* Copy completion bitmap, but exclude the first X completed entries */
	bitmap_shift_right((unsigned long int *)&rec_rqd->ppa_status,
				(unsigned long int *)comp_bits,
				comp, max_secs);

	/* Save the context for the entries that need to be re-written and
	 * update current context with the completed entries.
	 */
	rec_ctx->sentry = pblk_rb_wrap_pos(&pblk->rwb, c_ctx->sentry + comp);
	if (comp >= c_ctx->nr_valid) {
		rec_ctx->nr_valid = 0;
		rec_ctx->nr_padded = nr_entries - comp;

		c_ctx->nr_padded = comp - c_ctx->nr_valid;
	} else {
		rec_ctx->nr_valid = c_ctx->nr_valid - comp;
		rec_ctx->nr_padded = c_ctx->nr_padded;

		c_ctx->nr_valid = comp;
		c_ctx->nr_padded = 0;
	}

	recovery->rqd = rec_rqd;
	recovery->pblk = pblk;

	return 0;
}

__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta_buf)
{
	u32 crc;

	crc = pblk_calc_emeta_crc(pblk, emeta_buf);
	if (le32_to_cpu(emeta_buf->crc) != crc)
		return NULL;

	if (le32_to_cpu(emeta_buf->header.identifier) != PBLK_MAGIC)
		return NULL;

	return emeta_to_lbas(pblk, emeta_buf);
}

static int pblk_recov_l2p_from_emeta(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;
	struct pblk_emeta *emeta = line->emeta;
	struct line_emeta *emeta_buf = emeta->buf;
	__le64 *lba_list;
	int data_start;
	int nr_data_lbas, nr_valid_lbas, nr_lbas = 0;
	int i;

	lba_list = pblk_recov_get_lba_list(pblk, emeta_buf);
	if (!lba_list)
		return 1;

	data_start = pblk_line_smeta_start(pblk, line) + lm->smeta_sec;
	nr_data_lbas = lm->sec_per_line - lm->emeta_sec[0];
	nr_valid_lbas = le64_to_cpu(emeta_buf->nr_valid_lbas);

	for (i = data_start; i < nr_data_lbas && nr_lbas < nr_valid_lbas; i++) {
		struct ppa_addr ppa;
		int pos;

		ppa = addr_to_pblk_ppa(pblk, i, line->id);
		pos = pblk_ppa_to_pos(geo, ppa);

		/* Do not update bad blocks */
		if (test_bit(pos, line->blk_bitmap))
			continue;

		if (le64_to_cpu(lba_list[i]) == ADDR_EMPTY) {
			spin_lock(&line->lock);
			if (test_and_set_bit(i, line->invalid_bitmap))
				WARN_ONCE(1, "pblk: rec. double invalidate:\n");
			else
				le32_add_cpu(line->vsc, -1);
			spin_unlock(&line->lock);

			continue;
		}

		pblk_update_map(pblk, le64_to_cpu(lba_list[i]), ppa);
		nr_lbas++;
	}

	if (nr_valid_lbas != nr_lbas)
		pr_err("pblk: line %d - inconsistent lba list(%llu/%d)\n",
				line->id, emeta_buf->nr_valid_lbas, nr_lbas);

	line->left_msecs = 0;

	return 0;
}

static int pblk_calc_sec_in_line(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 nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);

	return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec[0] -
				nr_bb * geo->sec_per_blk;
}

struct pblk_recov_alloc {
	struct ppa_addr *ppa_list;
	struct pblk_sec_meta *meta_list;
	struct nvm_rq *rqd;
	void *data;
	dma_addr_t dma_ppa_list;
	dma_addr_t dma_meta_list;
};

static int pblk_recov_read_oob(struct pblk *pblk, struct pblk_line *line,
			       struct pblk_recov_alloc p, u64 r_ptr)
{
	struct nvm_tgt_dev *dev = pblk->dev;
	struct nvm_geo *geo = &dev->geo;
	struct ppa_addr *ppa_list;
	struct pblk_sec_meta *meta_list;
	struct nvm_rq *rqd;
	struct bio *bio;
	void *data;
	dma_addr_t dma_ppa_list, dma_meta_list;
	u64 r_ptr_int;
	int left_ppas;
	int rq_ppas, rq_len;
	int i, j;
	int ret = 0;
	DECLARE_COMPLETION_ONSTACK(wait);

	ppa_list = p.ppa_list;
	meta_list = p.meta_list;
	rqd = p.rqd;
	data = p.data;
	dma_ppa_list = p.dma_ppa_list;
	dma_meta_list = p.dma_meta_list;

	left_ppas = line->cur_sec - r_ptr;
	if (!left_ppas)
		return 0;

	r_ptr_int = r_ptr;

next_read_rq:
	memset(rqd, 0, pblk_g_rq_size);

	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
	if (!rq_ppas)
		rq_ppas = pblk->min_write_pgs;
	rq_len = rq_ppas * geo->sec_size;

	bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
	if (IS_ERR(bio))
		return PTR_ERR(bio);

	bio->bi_iter.bi_sector = 0; /* internal bio */
	bio_set_op_attrs(bio, REQ_OP_READ, 0);

	rqd->bio = bio;
	rqd->opcode = NVM_OP_PREAD;
	rqd->meta_list = meta_list;
	rqd->nr_ppas = rq_ppas;
	rqd->ppa_list = ppa_list;
	rqd->dma_ppa_list = dma_ppa_list;
	rqd->dma_meta_list = dma_meta_list;
	rqd->end_io = pblk_end_io_sync;
	rqd->private = &wait;

	if (pblk_io_aligned(pblk, rq_ppas))
		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
	else
		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);

	for (i = 0; i < rqd->nr_ppas; ) {
		struct ppa_addr ppa;
		int pos;

		ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
		pos = pblk_dev_ppa_to_pos(geo, ppa);

		while (test_bit(pos, line->blk_bitmap)) {
			r_ptr_int += pblk->min_write_pgs;
			ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
			pos = pblk_dev_ppa_to_pos(geo, ppa);
		}

		for (j = 0; j < pblk->min_write_pgs; j++, i++, r_ptr_int++)
			rqd->ppa_list[i] =
				addr_to_gen_ppa(pblk, r_ptr_int, line->id);
	}

	/* If read fails, more padding is needed */
	ret = pblk_submit_io(pblk, rqd);
	if (ret) {
		pr_err("pblk: I/O submission failed: %d\n", ret);
		return ret;
	}

	if (!wait_for_completion_io_timeout(&wait,
				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
		pr_err("pblk: L2P recovery read timed out\n");
		return -EINTR;
	}
	atomic_dec(&pblk->inflight_io);
	reinit_completion(&wait);

	/* At this point, the read should not fail. If it does, it is a problem
	 * we cannot recover from here. Need FTL log.
	 */
	if (rqd->error) {
		pr_err("pblk: L2P recovery failed (%d)\n", rqd->error);
		return -EINTR;
	}

	for (i = 0; i < rqd->nr_ppas; i++) {
		u64 lba = le64_to_cpu(meta_list[i].lba);

		if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
			continue;

		pblk_update_map(pblk, lba, rqd->ppa_list[i]);
	}

	left_ppas -= rq_ppas;
	if (left_ppas > 0)
		goto next_read_rq;

	return 0;
}

static void pblk_recov_complete(struct kref *ref)
{
	struct pblk_pad_rq *pad_rq = container_of(ref, struct pblk_pad_rq, ref);

	complete(&pad_rq->wait);
}

static void pblk_end_io_recov(struct nvm_rq *rqd)
{
	struct pblk_pad_rq *pad_rq = rqd->private;
	struct pblk *pblk = pad_rq->pblk;
	struct nvm_tgt_dev *dev = pblk->dev;

	pblk_up_page(pblk, rqd->ppa_list, rqd->nr_ppas);

	bio_put(rqd->bio);
	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
	pblk_free_rqd(pblk, rqd, WRITE);

	atomic_dec(&pblk->inflight_io);
	kref_put(&pad_rq->ref, pblk_recov_complete);
}

static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
			      int left_ppas)
{
	struct nvm_tgt_dev *dev = pblk->dev;
	struct nvm_geo *geo = &dev->geo;
	struct ppa_addr *ppa_list;
	struct pblk_sec_meta *meta_list;
	struct pblk_pad_rq *pad_rq;
	struct nvm_rq *rqd;
	struct bio *bio;
	void *data;
	dma_addr_t dma_ppa_list, dma_meta_list;
	__le64 *lba_list = emeta_to_lbas(pblk, line->emeta->buf);
	u64 w_ptr = line->cur_sec;
	int left_line_ppas, rq_ppas, rq_len;
	int i, j;
	int ret = 0;

	spin_lock(&line->lock);
	left_line_ppas = line->left_msecs;
	spin_unlock(&line->lock);

	pad_rq = kmalloc(sizeof(struct pblk_pad_rq), GFP_KERNEL);
	if (!pad_rq)
		return -ENOMEM;

	data = vzalloc(pblk->max_write_pgs * geo->sec_size);
	if (!data) {
		ret = -ENOMEM;
		goto free_rq;
	}

	pad_rq->pblk = pblk;
	init_completion(&pad_rq->wait);
	kref_init(&pad_rq->ref);

next_pad_rq:
	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
	if (rq_ppas < pblk->min_write_pgs) {
		pr_err("pblk: corrupted pad line %d\n", line->id);
		goto fail_free_pad;
	}

	rq_len = rq_ppas * geo->sec_size;

	meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
	if (!meta_list) {
		ret = -ENOMEM;
		goto fail_free_pad;
	}

	ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;

	rqd = pblk_alloc_rqd(pblk, WRITE);
	if (IS_ERR(rqd)) {
		ret = PTR_ERR(rqd);
		goto fail_free_meta;
	}

	bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
						PBLK_VMALLOC_META, GFP_KERNEL);
	if (IS_ERR(bio)) {
		ret = PTR_ERR(bio);
		goto fail_free_rqd;
	}

	bio->bi_iter.bi_sector = 0; /* internal bio */
	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);

	rqd->bio = bio;
	rqd->opcode = NVM_OP_PWRITE;
	rqd->flags = pblk_set_progr_mode(pblk, WRITE);
	rqd->meta_list = meta_list;
	rqd->nr_ppas = rq_ppas;
	rqd->ppa_list = ppa_list;
	rqd->dma_ppa_list = dma_ppa_list;
	rqd->dma_meta_list = dma_meta_list;
	rqd->end_io = pblk_end_io_recov;
	rqd->private = pad_rq;

	for (i = 0; i < rqd->nr_ppas; ) {
		struct ppa_addr ppa;
		int pos;

		w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
		ppa = addr_to_pblk_ppa(pblk, w_ptr, line->id);
		pos = pblk_ppa_to_pos(geo, ppa);

		while (test_bit(pos, line->blk_bitmap)) {
			w_ptr += pblk->min_write_pgs;
			ppa = addr_to_pblk_ppa(pblk, w_ptr, line->id);
			pos = pblk_ppa_to_pos(geo, ppa);
		}

		for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++) {
			struct ppa_addr dev_ppa;
			__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);

			dev_ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);

			pblk_map_invalidate(pblk, dev_ppa);
			lba_list[w_ptr] = meta_list[i].lba = addr_empty;
			rqd->ppa_list[i] = dev_ppa;
		}
	}

	kref_get(&pad_rq->ref);
	pblk_down_page(pblk, rqd->ppa_list, rqd->nr_ppas);

	ret = pblk_submit_io(pblk, rqd);
	if (ret) {
		pr_err("pblk: I/O submission failed: %d\n", ret);
		pblk_up_page(pblk, rqd->ppa_list, rqd->nr_ppas);
		goto fail_free_bio;
	}

	left_line_ppas -= rq_ppas;
	left_ppas -= rq_ppas;
	if (left_ppas && left_line_ppas)
		goto next_pad_rq;

	kref_put(&pad_rq->ref, pblk_recov_complete);

	if (!wait_for_completion_io_timeout(&pad_rq->wait,
				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
		pr_err("pblk: pad write timed out\n");
		ret = -ETIME;
	}

	if (!pblk_line_is_full(line))
		pr_err("pblk: corrupted padded line: %d\n", line->id);

	vfree(data);
free_rq:
	kfree(pad_rq);
	return ret;

fail_free_bio:
	bio_put(bio);
fail_free_rqd:
	pblk_free_rqd(pblk, rqd, WRITE);
fail_free_meta:
	nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
fail_free_pad:
	kfree(pad_rq);
	vfree(data);
	return ret;
}

/* When this function is called, it means that not all upper pages have been
 * written in a page that contains valid data. In order to recover this data, we
 * first find the write pointer on the device, then we pad all necessary
 * sectors, and finally attempt to read the valid data
 */
static int pblk_recov_scan_all_oob(struct pblk *pblk, struct pblk_line *line,
				   struct pblk_recov_alloc p)
{
	struct nvm_tgt_dev *dev = pblk->dev;
	struct nvm_geo *geo = &dev->geo;
	struct ppa_addr *ppa_list;
	struct pblk_sec_meta *meta_list;
	struct nvm_rq *rqd;
	struct bio *bio;
	void *data;
	dma_addr_t dma_ppa_list, dma_meta_list;
	u64 w_ptr = 0, r_ptr;
	int rq_ppas, rq_len;
	int i, j;
	int ret = 0;
	int rec_round;
	int left_ppas = pblk_calc_sec_in_line(pblk, line) - line->cur_sec;
	DECLARE_COMPLETION_ONSTACK(wait);

	ppa_list = p.ppa_list;
	meta_list = p.meta_list;
	rqd = p.rqd;
	data = p.data;
	dma_ppa_list = p.dma_ppa_list;
	dma_meta_list = p.dma_meta_list;

	/* we could recover up until the line write pointer */
	r_ptr = line->cur_sec;
	rec_round = 0;

next_rq:
	memset(rqd, 0, pblk_g_rq_size);

	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
	if (!rq_ppas)
		rq_ppas = pblk->min_write_pgs;
	rq_len = rq_ppas * geo->sec_size;

	bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
	if (IS_ERR(bio))
		return PTR_ERR(bio);

	bio->bi_iter.bi_sector = 0; /* internal bio */
	bio_set_op_attrs(bio, REQ_OP_READ, 0);

	rqd->bio = bio;
	rqd->opcode = NVM_OP_PREAD;
	rqd->meta_list = meta_list;
	rqd->nr_ppas = rq_ppas;
	rqd->ppa_list = ppa_list;
	rqd->dma_ppa_list = dma_ppa_list;
	rqd->dma_meta_list = dma_meta_list;
	rqd->end_io = pblk_end_io_sync;
	rqd->private = &wait;

	if (pblk_io_aligned(pblk, rq_ppas))
		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
	else
		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);

	for (i = 0; i < rqd->nr_ppas; ) {
		struct ppa_addr ppa;
		int pos;

		w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
		ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
		pos = pblk_dev_ppa_to_pos(geo, ppa);

		while (test_bit(pos, line->blk_bitmap)) {
			w_ptr += pblk->min_write_pgs;
			ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
			pos = pblk_dev_ppa_to_pos(geo, ppa);
		}

		for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++)
			rqd->ppa_list[i] =
				addr_to_gen_ppa(pblk, w_ptr, line->id);
	}

	ret = pblk_submit_io(pblk, rqd);
	if (ret) {
		pr_err("pblk: I/O submission failed: %d\n", ret);
		return ret;
	}

	if (!wait_for_completion_io_timeout(&wait,
				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
		pr_err("pblk: L2P recovery read timed out\n");
	}
	atomic_dec(&pblk->inflight_io);
	reinit_completion(&wait);

	/* This should not happen since the read failed during normal recovery,
	 * but the media works funny sometimes...
	 */
	if (!rec_round++ && !rqd->error) {
		rec_round = 0;
		for (i = 0; i < rqd->nr_ppas; i++, r_ptr++) {
			u64 lba = le64_to_cpu(meta_list[i].lba);

			if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
				continue;

			pblk_update_map(pblk, lba, rqd->ppa_list[i]);
		}
	}

	/* Reached the end of the written line */
	if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) {
		int pad_secs, nr_error_bits, bit;
		int ret;

		bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
		nr_error_bits = rqd->nr_ppas - bit;

		/* Roll back failed sectors */
		line->cur_sec -= nr_error_bits;
		line->left_msecs += nr_error_bits;
		bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);

		pad_secs = pblk_pad_distance(pblk);
		if (pad_secs > line->left_msecs)
			pad_secs = line->left_msecs;

		ret = pblk_recov_pad_oob(pblk, line, pad_secs);
		if (ret)
			pr_err("pblk: OOB padding failed (err:%d)\n", ret);

		ret = pblk_recov_read_oob(pblk, line, p, r_ptr);
		if (ret)
			pr_err("pblk: OOB read failed (err:%d)\n", ret);

		left_ppas = 0;
	}

	left_ppas -= rq_ppas;
	if (left_ppas > 0)
		goto next_rq;

	return ret;
}

static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
			       struct pblk_recov_alloc p, int *done)
{
	struct nvm_tgt_dev *dev = pblk->dev;
	struct nvm_geo *geo = &dev->geo;
	struct ppa_addr *ppa_list;
	struct pblk_sec_meta *meta_list;
	struct nvm_rq *rqd;
	struct bio *bio;
	void *data;
	dma_addr_t dma_ppa_list, dma_meta_list;
	u64 paddr;
	int rq_ppas, rq_len;
	int i, j;
	int ret = 0;
	int left_ppas = pblk_calc_sec_in_line(pblk, line);
	DECLARE_COMPLETION_ONSTACK(wait);

	ppa_list = p.ppa_list;
	meta_list = p.meta_list;
	rqd = p.rqd;
	data = p.data;
	dma_ppa_list = p.dma_ppa_list;
	dma_meta_list = p.dma_meta_list;

	*done = 1;

next_rq:
	memset(rqd, 0, pblk_g_rq_size);

	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
	if (!rq_ppas)
		rq_ppas = pblk->min_write_pgs;
	rq_len = rq_ppas * geo->sec_size;

	bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
	if (IS_ERR(bio))
		return PTR_ERR(bio);

	bio->bi_iter.bi_sector = 0; /* internal bio */
	bio_set_op_attrs(bio, REQ_OP_READ, 0);

	rqd->bio = bio;
	rqd->opcode = NVM_OP_PREAD;
	rqd->meta_list = meta_list;
	rqd->nr_ppas = rq_ppas;
	rqd->ppa_list = ppa_list;
	rqd->dma_ppa_list = dma_ppa_list;
	rqd->dma_meta_list = dma_meta_list;
	rqd->end_io = pblk_end_io_sync;
	rqd->private = &wait;

	if (pblk_io_aligned(pblk, rq_ppas))
		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
	else
		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);

	for (i = 0; i < rqd->nr_ppas; ) {
		struct ppa_addr ppa;
		int pos;

		paddr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
		ppa = addr_to_gen_ppa(pblk, paddr, line->id);
		pos = pblk_dev_ppa_to_pos(geo, ppa);

		while (test_bit(pos, line->blk_bitmap)) {
			paddr += pblk->min_write_pgs;
			ppa = addr_to_gen_ppa(pblk, paddr, line->id);
			pos = pblk_dev_ppa_to_pos(geo, ppa);
		}

		for (j = 0; j < pblk->min_write_pgs; 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: I/O submission failed: %d\n", ret);
		bio_put(bio);
		return ret;
	}

	if (!wait_for_completion_io_timeout(&wait,
				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
		pr_err("pblk: L2P recovery read timed out\n");
	}
	atomic_dec(&pblk->inflight_io);
	reinit_completion(&wait);

	/* Reached the end of the written line */
	if (rqd->error) {
		int nr_error_bits, bit;

		bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
		nr_error_bits = rqd->nr_ppas - bit;

		/* Roll back failed sectors */
		line->cur_sec -= nr_error_bits;
		line->left_msecs += nr_error_bits;
		bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);

		left_ppas = 0;
		rqd->nr_ppas = bit;

		if (rqd->error != NVM_RSP_ERR_EMPTYPAGE)
			*done = 0;
	}

	for (i = 0; i < rqd->nr_ppas; i++) {
		u64 lba = le64_to_cpu(meta_list[i].lba);

		if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
			continue;

		pblk_update_map(pblk, lba, rqd->ppa_list[i]);
	}

	left_ppas -= rq_ppas;
	if (left_ppas > 0)
		goto next_rq;

	return ret;
}

/* Scan line for lbas on out of bound area */
static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
{
	struct nvm_tgt_dev *dev = pblk->dev;
	struct nvm_geo *geo = &dev->geo;
	struct nvm_rq *rqd;
	struct ppa_addr *ppa_list;
	struct pblk_sec_meta *meta_list;
	struct pblk_recov_alloc p;
	void *data;
	dma_addr_t dma_ppa_list, dma_meta_list;
	int done, ret = 0;

	rqd = pblk_alloc_rqd(pblk, READ);
	if (IS_ERR(rqd))
		return PTR_ERR(rqd);

	meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
	if (!meta_list) {
		ret = -ENOMEM;
		goto free_rqd;
	}

	ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;

	data = kcalloc(pblk->max_write_pgs, geo->sec_size, GFP_KERNEL);
	if (!data) {
		ret = -ENOMEM;
		goto free_meta_list;
	}

	p.ppa_list = ppa_list;
	p.meta_list = meta_list;
	p.rqd = rqd;
	p.data = data;
	p.dma_ppa_list = dma_ppa_list;
	p.dma_meta_list = dma_meta_list;

	ret = pblk_recov_scan_oob(pblk, line, p, &done);
	if (ret) {
		pr_err("pblk: could not recover L2P from OOB\n");
		goto out;
	}

	if (!done) {
		ret = pblk_recov_scan_all_oob(pblk, line, p);
		if (ret) {
			pr_err("pblk: could not recover L2P from OOB\n");
			goto out;
		}
	}

	if (pblk_line_is_full(line))
		pblk_line_recov_close(pblk, line);

out:
	kfree(data);
free_meta_list:
	nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
free_rqd:
	pblk_free_rqd(pblk, rqd, READ);

	return ret;
}

/* Insert lines ordered by sequence number (seq_num) on list */
static void pblk_recov_line_add_ordered(struct list_head *head,
					struct pblk_line *line)
{
	struct pblk_line *t = NULL;

	list_for_each_entry(t, head, list)
		if (t->seq_nr > line->seq_nr)
			break;

	__list_add(&line->list, t->list.prev, &t->list);
}

struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
{
	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_line *line, *tline, *data_line = NULL;
	struct pblk_smeta *smeta;
	struct pblk_emeta *emeta;
	struct line_smeta *smeta_buf;
	int found_lines = 0, recovered_lines = 0, open_lines = 0;
	int is_next = 0;
	int meta_line;
	int i, valid_uuid = 0;
	LIST_HEAD(recov_list);

	/* TODO: Implement FTL snapshot */

	/* Scan recovery - takes place when FTL snapshot fails */
	spin_lock(&l_mg->free_lock);
	meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
	set_bit(meta_line, &l_mg->meta_bitmap);
	smeta = l_mg->sline_meta[meta_line];
	emeta = l_mg->eline_meta[meta_line];
	smeta_buf = (struct line_smeta *)smeta;
	spin_unlock(&l_mg->free_lock);

	/* Order data lines using their sequence number */
	for (i = 0; i < l_mg->nr_lines; i++) {
		u32 crc;

		line = &pblk->lines[i];

		memset(smeta, 0, lm->smeta_len);
		line->smeta = smeta;
		line->lun_bitmap = ((void *)(smeta_buf)) +
						sizeof(struct line_smeta);

		/* Lines that cannot be read are assumed as not written here */
		if (pblk_line_read_smeta(pblk, line))
			continue;

		crc = pblk_calc_smeta_crc(pblk, smeta_buf);
		if (le32_to_cpu(smeta_buf->crc) != crc)
			continue;

		if (le32_to_cpu(smeta_buf->header.identifier) != PBLK_MAGIC)
			continue;

		if (le16_to_cpu(smeta_buf->header.version) != 1) {
			pr_err("pblk: found incompatible line version %u\n",
					smeta_buf->header.version);
			return ERR_PTR(-EINVAL);
		}

		/* The first valid instance uuid is used for initialization */
		if (!valid_uuid) {
			memcpy(pblk->instance_uuid, smeta_buf->header.uuid, 16);
			valid_uuid = 1;
		}

		if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) {
			pr_debug("pblk: ignore line %u due to uuid mismatch\n",
					i);
			continue;
		}

		/* Update line metadata */
		spin_lock(&line->lock);
		line->id = le32_to_cpu(smeta_buf->header.id);
		line->type = le16_to_cpu(smeta_buf->header.type);
		line->seq_nr = le64_to_cpu(smeta_buf->seq_nr);
		spin_unlock(&line->lock);

		/* Update general metadata */
		spin_lock(&l_mg->free_lock);
		if (line->seq_nr >= l_mg->d_seq_nr)
			l_mg->d_seq_nr = line->seq_nr + 1;
		l_mg->nr_free_lines--;
		spin_unlock(&l_mg->free_lock);

		if (pblk_line_recov_alloc(pblk, line))
			goto out;

		pblk_recov_line_add_ordered(&recov_list, line);
		found_lines++;
		pr_debug("pblk: recovering data line %d, seq:%llu\n",
						line->id, smeta_buf->seq_nr);
	}

	if (!found_lines) {
		pblk_setup_uuid(pblk);

		spin_lock(&l_mg->free_lock);
		WARN_ON_ONCE(!test_and_clear_bit(meta_line,
							&l_mg->meta_bitmap));
		spin_unlock(&l_mg->free_lock);

		goto out;
	}

	/* Verify closed blocks and recover this portion of L2P table*/
	list_for_each_entry_safe(line, tline, &recov_list, list) {
		int off, nr_bb;

		recovered_lines++;
		/* Calculate where emeta starts based on the line bb */
		off = lm->sec_per_line - lm->emeta_sec[0];
		nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
		off -= nr_bb * geo->sec_per_pl;

		line->emeta_ssec = off;
		line->emeta = emeta;
		memset(line->emeta->buf, 0, lm->emeta_len[0]);

		if (pblk_line_read_emeta(pblk, line, line->emeta->buf)) {
			pblk_recov_l2p_from_oob(pblk, line);
			goto next;
		}

		if (pblk_recov_l2p_from_emeta(pblk, line))
			pblk_recov_l2p_from_oob(pblk, line);

next:
		if (pblk_line_is_full(line)) {
			struct list_head *move_list;

			spin_lock(&line->lock);
			line->state = PBLK_LINESTATE_CLOSED;
			move_list = pblk_line_gc_list(pblk, line);
			spin_unlock(&line->lock);

			spin_lock(&l_mg->gc_lock);
			list_move_tail(&line->list, move_list);
			spin_unlock(&l_mg->gc_lock);

			mempool_free(line->map_bitmap, pblk->line_meta_pool);
			line->map_bitmap = NULL;
			line->smeta = NULL;
			line->emeta = NULL;
		} else {
			if (open_lines > 1)
				pr_err("pblk: failed to recover L2P\n");

			open_lines++;
			line->meta_line = meta_line;
			data_line = line;
		}
	}

	spin_lock(&l_mg->free_lock);
	if (!open_lines) {
		WARN_ON_ONCE(!test_and_clear_bit(meta_line,
							&l_mg->meta_bitmap));
		pblk_line_replace_data(pblk);
	} else {
		/* Allocate next line for preparation */
		l_mg->data_next = pblk_line_get(pblk);
		if (l_mg->data_next) {
			l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
			l_mg->data_next->type = PBLK_LINETYPE_DATA;
			is_next = 1;
		}
	}
	spin_unlock(&l_mg->free_lock);

	if (is_next) {
		pblk_line_erase(pblk, l_mg->data_next);
		pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
	}

out:
	if (found_lines != recovered_lines)
		pr_err("pblk: failed to recover all found lines %d/%d\n",
						found_lines, recovered_lines);

	return data_line;
}

/*
 * Pad current line
 */
int pblk_recov_pad(struct pblk *pblk)
{
	struct pblk_line *line;
	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
	int left_msecs;
	int ret = 0;

	spin_lock(&l_mg->free_lock);
	line = l_mg->data_line;
	left_msecs = line->left_msecs;
	spin_unlock(&l_mg->free_lock);

	ret = pblk_recov_pad_oob(pblk, line, left_msecs);
	if (ret) {
		pr_err("pblk: Tear down padding failed (%d)\n", ret);
		return ret;
	}

	pblk_line_close_meta(pblk, line);
	return ret;
}