1/* SPDX-License-Identifier: GPL-2.0 */
2/*
3 * Copyright (C) 2015 IT University of Copenhagen (rrpc.h)
4 * Copyright (C) 2016 CNEX Labs
5 * Initial release: Matias Bjorling <matias@cnexlabs.com>
6 * Write buffering: Javier Gonzalez <javier@cnexlabs.com>
7 *
8 * This program is free software; you can redistribute it and/or
9 * modify it under the terms of the GNU General Public License version
10 * 2 as published by the Free Software Foundation.
11 *
12 * This program is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
15 * General Public License for more details.
16 *
17 * Implementation of a Physical Block-device target for Open-channel SSDs.
18 *
19 */
20
21#ifndef PBLK_H_
22#define PBLK_H_
23
24#include <linux/blkdev.h>
25#include <linux/blk-mq.h>
26#include <linux/bio.h>
27#include <linux/module.h>
28#include <linux/kthread.h>
29#include <linux/vmalloc.h>
30#include <linux/crc32.h>
31#include <linux/uuid.h>
32
33#include <linux/lightnvm.h>
34
35/* Run only GC if less than 1/X blocks are free */
36#define GC_LIMIT_INVERSE 5
37#define GC_TIME_MSECS 1000
38
39#define PBLK_SECTOR (512)
40#define PBLK_EXPOSED_PAGE_SIZE (4096)
41
42#define PBLK_NR_CLOSE_JOBS (4)
43
44#define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16)
45
46/* Max 512 LUNs per device */
47#define PBLK_MAX_LUNS_BITMAP (4)
48
49#define NR_PHY_IN_LOG (PBLK_EXPOSED_PAGE_SIZE / PBLK_SECTOR)
50
51/* Static pool sizes */
52#define PBLK_GEN_WS_POOL_SIZE (2)
53
54#define PBLK_DEFAULT_OP (11)
55
56enum {
57	PBLK_READ		= READ,
58	PBLK_WRITE		= WRITE,/* Write from write buffer */
59	PBLK_WRITE_INT,			/* Internal write - no write buffer */
60	PBLK_READ_RECOV,		/* Recovery read - errors allowed */
61	PBLK_ERASE,
62};
63
64enum {
65	/* IO Types */
66	PBLK_IOTYPE_USER	= 1 << 0,
67	PBLK_IOTYPE_GC		= 1 << 1,
68
69	/* Write buffer flags */
70	PBLK_FLUSH_ENTRY	= 1 << 2,
71	PBLK_WRITTEN_DATA	= 1 << 3,
72	PBLK_SUBMITTED_ENTRY	= 1 << 4,
73	PBLK_WRITABLE_ENTRY	= 1 << 5,
74};
75
76enum {
77	PBLK_BLK_ST_OPEN =	0x1,
78	PBLK_BLK_ST_CLOSED =	0x2,
79};
80
81enum {
82	PBLK_CHUNK_RESET_START,
83	PBLK_CHUNK_RESET_DONE,
84	PBLK_CHUNK_RESET_FAILED,
85};
86
87struct pblk_sec_meta {
88	u64 reserved;
89	__le64 lba;
90};
91
92/* The number of GC lists and the rate-limiter states go together. This way the
93 * rate-limiter can dictate how much GC is needed based on resource utilization.
94 */
95#define PBLK_GC_NR_LISTS 4
96
97enum {
98	PBLK_RL_OFF = 0,
99	PBLK_RL_WERR = 1,
100	PBLK_RL_HIGH = 2,
101	PBLK_RL_MID = 3,
102	PBLK_RL_LOW = 4
103};
104
105#define pblk_dma_ppa_size (sizeof(u64) * NVM_MAX_VLBA)
106
107/* write buffer completion context */
108struct pblk_c_ctx {
109	struct list_head list;		/* Head for out-of-order completion */
110
111	unsigned long *lun_bitmap;	/* Luns used on current request */
112	unsigned int sentry;
113	unsigned int nr_valid;
114	unsigned int nr_padded;
115};
116
117/* read context */
118struct pblk_g_ctx {
119	void *private;
120	unsigned long start_time;
121	u64 lba;
122};
123
124/* Pad context */
125struct pblk_pad_rq {
126	struct pblk *pblk;
127	struct completion wait;
128	struct kref ref;
129};
130
131/* Recovery context */
132struct pblk_rec_ctx {
133	struct pblk *pblk;
134	struct nvm_rq *rqd;
135	struct work_struct ws_rec;
136};
137
138/* Write context */
139struct pblk_w_ctx {
140	struct bio_list bios;		/* Original bios - used for completion
141					 * in REQ_FUA, REQ_FLUSH case
142					 */
143	u64 lba;			/* Logic addr. associated with entry */
144	struct ppa_addr ppa;		/* Physic addr. associated with entry */
145	int flags;			/* Write context flags */
146};
147
148struct pblk_rb_entry {
149	struct ppa_addr cacheline;	/* Cacheline for this entry */
150	void *data;			/* Pointer to data on this entry */
151	struct pblk_w_ctx w_ctx;	/* Context for this entry */
152	struct list_head index;		/* List head to enable indexes */
153};
154
155#define EMPTY_ENTRY (~0U)
156
157struct pblk_rb_pages {
158	struct page *pages;
159	int order;
160	struct list_head list;
161};
162
163struct pblk_rb {
164	struct pblk_rb_entry *entries;	/* Ring buffer entries */
165	unsigned int mem;		/* Write offset - points to next
166					 * writable entry in memory
167					 */
168	unsigned int subm;		/* Read offset - points to last entry
169					 * that has been submitted to the media
170					 * to be persisted
171					 */
172	unsigned int sync;		/* Synced - backpointer that signals
173					 * the last submitted entry that has
174					 * been successfully persisted to media
175					 */
176	unsigned int flush_point;	/* Sync point - last entry that must be
177					 * flushed to the media. Used with
178					 * REQ_FLUSH and REQ_FUA
179					 */
180	unsigned int l2p_update;	/* l2p update point - next entry for
181					 * which l2p mapping will be updated to
182					 * contain a device ppa address (instead
183					 * of a cacheline
184					 */
185	unsigned int nr_entries;	/* Number of entries in write buffer -
186					 * must be a power of two
187					 */
188	unsigned int seg_size;		/* Size of the data segments being
189					 * stored on each entry. Typically this
190					 * will be 4KB
191					 */
192
193	unsigned int back_thres;	/* Threshold that shall be maintained by
194					 * the backpointer in order to respect
195					 * geo->mw_cunits on a per chunk basis
196					 */
197
198	struct list_head pages;		/* List of data pages */
199
200	spinlock_t w_lock;		/* Write lock */
201	spinlock_t s_lock;		/* Sync lock */
202
203#ifdef CONFIG_NVM_PBLK_DEBUG
204	atomic_t inflight_flush_point;	/* Not served REQ_FLUSH | REQ_FUA */
205#endif
206};
207
208#define PBLK_RECOVERY_SECTORS 16
209
210struct pblk_lun {
211	struct ppa_addr bppa;
212	struct semaphore wr_sem;
213};
214
215struct pblk_gc_rq {
216	struct pblk_line *line;
217	void *data;
218	u64 paddr_list[NVM_MAX_VLBA];
219	u64 lba_list[NVM_MAX_VLBA];
220	int nr_secs;
221	int secs_to_gc;
222	struct list_head list;
223};
224
225struct pblk_gc {
226	/* These states are not protected by a lock since (i) they are in the
227	 * fast path, and (ii) they are not critical.
228	 */
229	int gc_active;
230	int gc_enabled;
231	int gc_forced;
232
233	struct task_struct *gc_ts;
234	struct task_struct *gc_writer_ts;
235	struct task_struct *gc_reader_ts;
236
237	struct workqueue_struct *gc_line_reader_wq;
238	struct workqueue_struct *gc_reader_wq;
239
240	struct timer_list gc_timer;
241
242	struct semaphore gc_sem;
243	atomic_t read_inflight_gc; /* Number of lines with inflight GC reads */
244	atomic_t pipeline_gc;	   /* Number of lines in the GC pipeline -
245				    * started reads to finished writes
246				    */
247	int w_entries;
248
249	struct list_head w_list;
250	struct list_head r_list;
251
252	spinlock_t lock;
253	spinlock_t w_lock;
254	spinlock_t r_lock;
255};
256
257struct pblk_rl {
258	unsigned int high;	/* Upper threshold for rate limiter (free run -
259				 * user I/O rate limiter
260				 */
261	unsigned int high_pw;	/* High rounded up as a power of 2 */
262
263#define PBLK_USER_HIGH_THRS 8	/* Begin write limit at 12% available blks */
264#define PBLK_USER_LOW_THRS 10	/* Aggressive GC at 10% available blocks */
265
266	int rb_windows_pw;	/* Number of rate windows in the write buffer
267				 * given as a power-of-2. This guarantees that
268				 * when user I/O is being rate limited, there
269				 * will be reserved enough space for the GC to
270				 * place its payload. A window is of
271				 * pblk->max_write_pgs size, which in NVMe is
272				 * 64, i.e., 256kb.
273				 */
274	int rb_budget;		/* Total number of entries available for I/O */
275	int rb_user_max;	/* Max buffer entries available for user I/O */
276	int rb_gc_max;		/* Max buffer entries available for GC I/O */
277	int rb_gc_rsv;		/* Reserved buffer entries for GC I/O */
278	int rb_state;		/* Rate-limiter current state */
279	int rb_max_io;		/* Maximum size for an I/O giving the config */
280
281	atomic_t rb_user_cnt;	/* User I/O buffer counter */
282	atomic_t rb_gc_cnt;	/* GC I/O buffer counter */
283	atomic_t rb_space;	/* Space limit in case of reaching capacity */
284
285	int rsv_blocks;		/* Reserved blocks for GC */
286
287	int rb_user_active;
288	int rb_gc_active;
289
290	atomic_t werr_lines;	/* Number of write error lines that needs gc */
291
292	struct timer_list u_timer;
293
294	unsigned long total_blocks;
295
296	atomic_t free_blocks;		/* Total number of free blocks (+ OP) */
297	atomic_t free_user_blocks;	/* Number of user free blocks (no OP) */
298};
299
300#define PBLK_LINE_EMPTY (~0U)
301
302enum {
303	/* Line Types */
304	PBLK_LINETYPE_FREE = 0,
305	PBLK_LINETYPE_LOG = 1,
306	PBLK_LINETYPE_DATA = 2,
307
308	/* Line state */
309	PBLK_LINESTATE_NEW = 9,
310	PBLK_LINESTATE_FREE = 10,
311	PBLK_LINESTATE_OPEN = 11,
312	PBLK_LINESTATE_CLOSED = 12,
313	PBLK_LINESTATE_GC = 13,
314	PBLK_LINESTATE_BAD = 14,
315	PBLK_LINESTATE_CORRUPT = 15,
316
317	/* GC group */
318	PBLK_LINEGC_NONE = 20,
319	PBLK_LINEGC_EMPTY = 21,
320	PBLK_LINEGC_LOW = 22,
321	PBLK_LINEGC_MID = 23,
322	PBLK_LINEGC_HIGH = 24,
323	PBLK_LINEGC_FULL = 25,
324	PBLK_LINEGC_WERR = 26
325};
326
327#define PBLK_MAGIC 0x70626c6b /*pblk*/
328
329/* emeta/smeta persistent storage format versions:
330 * Changes in major version requires offline migration.
331 * Changes in minor version are handled automatically during
332 * recovery.
333 */
334
335#define SMETA_VERSION_MAJOR (0)
336#define SMETA_VERSION_MINOR (1)
337
338#define EMETA_VERSION_MAJOR (0)
339#define EMETA_VERSION_MINOR (2)
340
341struct line_header {
342	__le32 crc;
343	__le32 identifier;	/* pblk identifier */
344	__u8 uuid[16];		/* instance uuid */
345	__le16 type;		/* line type */
346	__u8 version_major;	/* version major */
347	__u8 version_minor;	/* version minor */
348	__le32 id;		/* line id for current line */
349};
350
351struct line_smeta {
352	struct line_header header;
353
354	__le32 crc;		/* Full structure including struct crc */
355	/* Previous line metadata */
356	__le32 prev_id;		/* Line id for previous line */
357
358	/* Current line metadata */
359	__le64 seq_nr;		/* Sequence number for current line */
360
361	/* Active writers */
362	__le32 window_wr_lun;	/* Number of parallel LUNs to write */
363
364	__le32 rsvd[2];
365
366	__le64 lun_bitmap[];
367};
368
369
370/*
371 * Metadata layout in media:
372 *	First sector:
373 *		1. struct line_emeta
374 *		2. bad block bitmap (u64 * window_wr_lun)
375 *		3. write amplification counters
376 *	Mid sectors (start at lbas_sector):
377 *		3. nr_lbas (u64) forming lba list
378 *	Last sectors (start at vsc_sector):
379 *		4. u32 valid sector count (vsc) for all lines (~0U: free line)
380 */
381struct line_emeta {
382	struct line_header header;
383
384	__le32 crc;		/* Full structure including struct crc */
385
386	/* Previous line metadata */
387	__le32 prev_id;		/* Line id for prev line */
388
389	/* Current line metadata */
390	__le64 seq_nr;		/* Sequence number for current line */
391
392	/* Active writers */
393	__le32 window_wr_lun;	/* Number of parallel LUNs to write */
394
395	/* Bookkeeping for recovery */
396	__le32 next_id;		/* Line id for next line */
397	__le64 nr_lbas;		/* Number of lbas mapped in line */
398	__le64 nr_valid_lbas;	/* Number of valid lbas mapped in line */
399	__le64 bb_bitmap[];     /* Updated bad block bitmap for line */
400};
401
402
403/* Write amplification counters stored on media */
404struct wa_counters {
405	__le64 user;		/* Number of user written sectors */
406	__le64 gc;		/* Number of sectors written by GC*/
407	__le64 pad;		/* Number of padded sectors */
408};
409
410struct pblk_emeta {
411	struct line_emeta *buf;		/* emeta buffer in media format */
412	int mem;			/* Write offset - points to next
413					 * writable entry in memory
414					 */
415	atomic_t sync;			/* Synced - backpointer that signals the
416					 * last entry that has been successfully
417					 * persisted to media
418					 */
419	unsigned int nr_entries;	/* Number of emeta entries */
420};
421
422struct pblk_smeta {
423	struct line_smeta *buf;		/* smeta buffer in persistent format */
424};
425
426struct pblk_w_err_gc {
427	int has_write_err;
428	int has_gc_err;
429	__le64 *lba_list;
430};
431
432struct pblk_line {
433	struct pblk *pblk;
434	unsigned int id;		/* Line number corresponds to the
435					 * block line
436					 */
437	unsigned int seq_nr;		/* Unique line sequence number */
438
439	int state;			/* PBLK_LINESTATE_X */
440	int type;			/* PBLK_LINETYPE_X */
441	int gc_group;			/* PBLK_LINEGC_X */
442	struct list_head list;		/* Free, GC lists */
443
444	unsigned long *lun_bitmap;	/* Bitmap for LUNs mapped in line */
445
446	struct nvm_chk_meta *chks;	/* Chunks forming line */
447
448	struct pblk_smeta *smeta;	/* Start metadata */
449	struct pblk_emeta *emeta;	/* End medatada */
450
451	int meta_line;			/* Metadata line id */
452	int meta_distance;		/* Distance between data and metadata */
453
454	u64 emeta_ssec;			/* Sector where emeta starts */
455
456	unsigned int sec_in_line;	/* Number of usable secs in line */
457
458	atomic_t blk_in_line;		/* Number of good blocks in line */
459	unsigned long *blk_bitmap;	/* Bitmap for valid/invalid blocks */
460	unsigned long *erase_bitmap;	/* Bitmap for erased blocks */
461
462	unsigned long *map_bitmap;	/* Bitmap for mapped sectors in line */
463	unsigned long *invalid_bitmap;	/* Bitmap for invalid sectors in line */
464
465	atomic_t left_eblks;		/* Blocks left for erasing */
466	atomic_t left_seblks;		/* Blocks left for sync erasing */
467
468	int left_msecs;			/* Sectors left for mapping */
469	unsigned int cur_sec;		/* Sector map pointer */
470	unsigned int nr_valid_lbas;	/* Number of valid lbas in line */
471
472	__le32 *vsc;			/* Valid sector count in line */
473
474	struct kref ref;		/* Write buffer L2P references */
475	atomic_t sec_to_update;         /* Outstanding L2P updates to ppa */
476
477	struct pblk_w_err_gc *w_err_gc;	/* Write error gc recovery metadata */
478
479	spinlock_t lock;		/* Necessary for invalid_bitmap only */
480};
481
482#define PBLK_DATA_LINES 4
483
484enum {
485	PBLK_EMETA_TYPE_HEADER = 1,	/* struct line_emeta first sector */
486	PBLK_EMETA_TYPE_LLBA = 2,	/* lba list - type: __le64 */
487	PBLK_EMETA_TYPE_VSC = 3,	/* vsc list - type: __le32 */
488};
489
490struct pblk_line_mgmt {
491	int nr_lines;			/* Total number of full lines */
492	int nr_free_lines;		/* Number of full lines in free list */
493
494	/* Free lists - use free_lock */
495	struct list_head free_list;	/* Full lines ready to use */
496	struct list_head corrupt_list;	/* Full lines corrupted */
497	struct list_head bad_list;	/* Full lines bad */
498
499	/* GC lists - use gc_lock */
500	struct list_head *gc_lists[PBLK_GC_NR_LISTS];
501	struct list_head gc_high_list;	/* Full lines ready to GC, high isc */
502	struct list_head gc_mid_list;	/* Full lines ready to GC, mid isc */
503	struct list_head gc_low_list;	/* Full lines ready to GC, low isc */
504
505	struct list_head gc_werr_list;  /* Write err recovery list */
506
507	struct list_head gc_full_list;	/* Full lines ready to GC, no valid */
508	struct list_head gc_empty_list;	/* Full lines close, all valid */
509
510	struct pblk_line *log_line;	/* Current FTL log line */
511	struct pblk_line *data_line;	/* Current data line */
512	struct pblk_line *log_next;	/* Next FTL log line */
513	struct pblk_line *data_next;	/* Next data line */
514
515	struct list_head emeta_list;	/* Lines queued to schedule emeta */
516
517	__le32 *vsc_list;		/* Valid sector counts for all lines */
518
519	/* Pre-allocated metadata for data lines */
520	struct pblk_smeta *sline_meta[PBLK_DATA_LINES];
521	struct pblk_emeta *eline_meta[PBLK_DATA_LINES];
522	unsigned long meta_bitmap;
523
524	/* Cache and mempool for map/invalid bitmaps */
525	struct kmem_cache *bitmap_cache;
526	mempool_t *bitmap_pool;
527
528	/* Helpers for fast bitmap calculations */
529	unsigned long *bb_template;
530	unsigned long *bb_aux;
531
532	unsigned long d_seq_nr;		/* Data line unique sequence number */
533	unsigned long l_seq_nr;		/* Log line unique sequence number */
534
535	spinlock_t free_lock;
536	spinlock_t close_lock;
537	spinlock_t gc_lock;
538};
539
540struct pblk_line_meta {
541	unsigned int smeta_len;		/* Total length for smeta */
542	unsigned int smeta_sec;		/* Sectors needed for smeta */
543
544	unsigned int emeta_len[4];	/* Lengths for emeta:
545					 *  [0]: Total
546					 *  [1]: struct line_emeta +
547					 *       bb_bitmap + struct wa_counters
548					 *  [2]: L2P portion
549					 *  [3]: vsc
550					 */
551	unsigned int emeta_sec[4];	/* Sectors needed for emeta. Same layout
552					 * as emeta_len
553					 */
554
555	unsigned int emeta_bb;		/* Boundary for bb that affects emeta */
556
557	unsigned int vsc_list_len;	/* Length for vsc list */
558	unsigned int sec_bitmap_len;	/* Length for sector bitmap in line */
559	unsigned int blk_bitmap_len;	/* Length for block bitmap in line */
560	unsigned int lun_bitmap_len;	/* Length for lun bitmap in line */
561
562	unsigned int blk_per_line;	/* Number of blocks in a full line */
563	unsigned int sec_per_line;	/* Number of sectors in a line */
564	unsigned int dsec_per_line;	/* Number of data sectors in a line */
565	unsigned int min_blk_line;	/* Min. number of good blocks in line */
566
567	unsigned int mid_thrs;		/* Threshold for GC mid list */
568	unsigned int high_thrs;		/* Threshold for GC high list */
569
570	unsigned int meta_distance;	/* Distance between data and metadata */
571};
572
573enum {
574	PBLK_STATE_RUNNING = 0,
575	PBLK_STATE_STOPPING = 1,
576	PBLK_STATE_RECOVERING = 2,
577	PBLK_STATE_STOPPED = 3,
578};
579
580/* Internal format to support not power-of-2 device formats */
581struct pblk_addrf {
582	/* gen to dev */
583	int sec_stripe;
584	int ch_stripe;
585	int lun_stripe;
586
587	/* dev to gen */
588	int sec_lun_stripe;
589	int sec_ws_stripe;
590};
591
592struct pblk {
593	struct nvm_tgt_dev *dev;
594	struct gendisk *disk;
595
596	struct kobject kobj;
597
598	struct pblk_lun *luns;
599
600	struct pblk_line *lines;		/* Line array */
601	struct pblk_line_mgmt l_mg;		/* Line management */
602	struct pblk_line_meta lm;		/* Line metadata */
603
604	struct nvm_addrf addrf;		/* Aligned address format */
605	struct pblk_addrf uaddrf;	/* Unaligned address format */
606	int addrf_len;
607
608	struct pblk_rb rwb;
609
610	int state;			/* pblk line state */
611
612	int min_write_pgs; /* Minimum amount of pages required by controller */
613	int min_write_pgs_data; /* Minimum amount of payload pages */
614	int max_write_pgs; /* Maximum amount of pages supported by controller */
615	int oob_meta_size; /* Size of OOB sector metadata */
616
617	sector_t capacity; /* Device capacity when bad blocks are subtracted */
618
619	int op;      /* Percentage of device used for over-provisioning */
620	int op_blks; /* Number of blocks used for over-provisioning */
621
622	/* pblk provisioning values. Used by rate limiter */
623	struct pblk_rl rl;
624
625	int sec_per_write;
626
627	guid_t instance_uuid;
628
629	/* Persistent write amplification counters, 4kb sector I/Os */
630	atomic64_t user_wa;		/* Sectors written by user */
631	atomic64_t gc_wa;		/* Sectors written by GC */
632	atomic64_t pad_wa;		/* Padded sectors written */
633
634	/* Reset values for delta write amplification measurements */
635	u64 user_rst_wa;
636	u64 gc_rst_wa;
637	u64 pad_rst_wa;
638
639	/* Counters used for calculating padding distribution */
640	atomic64_t *pad_dist;		/* Padding distribution buckets */
641	u64 nr_flush_rst;		/* Flushes reset value for pad dist.*/
642	atomic64_t nr_flush;		/* Number of flush/fua I/O */
643
644#ifdef CONFIG_NVM_PBLK_DEBUG
645	/* Non-persistent debug counters, 4kb sector I/Os */
646	atomic_long_t inflight_writes;	/* Inflight writes (user and gc) */
647	atomic_long_t padded_writes;	/* Sectors padded due to flush/fua */
648	atomic_long_t padded_wb;	/* Sectors padded in write buffer */
649	atomic_long_t req_writes;	/* Sectors stored on write buffer */
650	atomic_long_t sub_writes;	/* Sectors submitted from buffer */
651	atomic_long_t sync_writes;	/* Sectors synced to media */
652	atomic_long_t inflight_reads;	/* Inflight sector read requests */
653	atomic_long_t cache_reads;	/* Read requests that hit the cache */
654	atomic_long_t sync_reads;	/* Completed sector read requests */
655	atomic_long_t recov_writes;	/* Sectors submitted from recovery */
656	atomic_long_t recov_gc_writes;	/* Sectors submitted from write GC */
657	atomic_long_t recov_gc_reads;	/* Sectors submitted from read GC */
658#endif
659
660	spinlock_t lock;
661
662	atomic_long_t read_failed;
663	atomic_long_t read_empty;
664	atomic_long_t read_high_ecc;
665	atomic_long_t read_failed_gc;
666	atomic_long_t write_failed;
667	atomic_long_t erase_failed;
668
669	atomic_t inflight_io;		/* General inflight I/O counter */
670
671	struct task_struct *writer_ts;
672
673	/* Simple translation map of logical addresses to physical addresses.
674	 * The logical addresses is known by the host system, while the physical
675	 * addresses are used when writing to the disk block device.
676	 */
677	unsigned char *trans_map;
678	spinlock_t trans_lock;
679
680	struct list_head compl_list;
681
682	spinlock_t resubmit_lock;	 /* Resubmit list lock */
683	struct list_head resubmit_list; /* Resubmit list for failed writes*/
684
685	mempool_t page_bio_pool;
686	mempool_t gen_ws_pool;
687	mempool_t rec_pool;
688	mempool_t r_rq_pool;
689	mempool_t w_rq_pool;
690	mempool_t e_rq_pool;
691
692	struct workqueue_struct *close_wq;
693	struct workqueue_struct *bb_wq;
694	struct workqueue_struct *r_end_wq;
695
696	struct timer_list wtimer;
697
698	struct pblk_gc gc;
699};
700
701struct pblk_line_ws {
702	struct pblk *pblk;
703	struct pblk_line *line;
704	void *priv;
705	struct work_struct ws;
706};
707
708#define pblk_g_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_g_ctx))
709#define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx))
710
711#define pblk_err(pblk, fmt, ...)			\
712	pr_err("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
713#define pblk_info(pblk, fmt, ...)			\
714	pr_info("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
715#define pblk_warn(pblk, fmt, ...)			\
716	pr_warn("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
717#define pblk_debug(pblk, fmt, ...)			\
718	pr_debug("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
719
720/*
721 * pblk ring buffer operations
722 */
723int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold,
724		 unsigned int seg_sz);
725int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
726			   unsigned int nr_entries, unsigned int *pos);
727int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries,
728			 unsigned int *pos);
729void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
730			      struct pblk_w_ctx w_ctx, unsigned int pos);
731void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
732			    struct pblk_w_ctx w_ctx, struct pblk_line *line,
733			    u64 paddr, unsigned int pos);
734struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos);
735void pblk_rb_flush(struct pblk_rb *rb);
736
737void pblk_rb_sync_l2p(struct pblk_rb *rb);
738unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
739				 unsigned int pos, unsigned int nr_entries,
740				 unsigned int count);
741int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
742			struct ppa_addr ppa);
743unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries);
744
745unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags);
746unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries);
747unsigned int pblk_rb_ptr_wrap(struct pblk_rb *rb, unsigned int p,
748			      unsigned int nr_entries);
749void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags);
750unsigned int pblk_rb_flush_point_count(struct pblk_rb *rb);
751
752unsigned int pblk_rb_read_count(struct pblk_rb *rb);
753unsigned int pblk_rb_sync_count(struct pblk_rb *rb);
754unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos);
755
756int pblk_rb_tear_down_check(struct pblk_rb *rb);
757int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos);
758void pblk_rb_free(struct pblk_rb *rb);
759ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf);
760
761/*
762 * pblk core
763 */
764struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type);
765void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type);
766int pblk_alloc_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd);
767void pblk_free_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd);
768void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write);
769int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
770			struct pblk_c_ctx *c_ctx);
771void pblk_discard(struct pblk *pblk, struct bio *bio);
772struct nvm_chk_meta *pblk_get_chunk_meta(struct pblk *pblk);
773struct nvm_chk_meta *pblk_chunk_get_off(struct pblk *pblk,
774					      struct nvm_chk_meta *lp,
775					      struct ppa_addr ppa);
776void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd);
777void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd);
778int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd, void *buf);
779int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd, void *buf);
780int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line);
781void pblk_check_chunk_state_update(struct pblk *pblk, struct nvm_rq *rqd);
782struct pblk_line *pblk_line_get(struct pblk *pblk);
783struct pblk_line *pblk_line_get_first_data(struct pblk *pblk);
784struct pblk_line *pblk_line_replace_data(struct pblk *pblk);
785void pblk_ppa_to_line_put(struct pblk *pblk, struct ppa_addr ppa);
786void pblk_rq_to_line_put(struct pblk *pblk, struct nvm_rq *rqd);
787int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line);
788void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line);
789struct pblk_line *pblk_line_get_data(struct pblk *pblk);
790struct pblk_line *pblk_line_get_erase(struct pblk *pblk);
791int pblk_line_erase(struct pblk *pblk, struct pblk_line *line);
792int pblk_line_is_full(struct pblk_line *line);
793void pblk_line_free(struct pblk_line *line);
794void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line);
795void pblk_line_close(struct pblk *pblk, struct pblk_line *line);
796void pblk_line_close_ws(struct work_struct *work);
797void pblk_pipeline_stop(struct pblk *pblk);
798void __pblk_pipeline_stop(struct pblk *pblk);
799void __pblk_pipeline_flush(struct pblk *pblk);
800void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
801		     void (*work)(struct work_struct *), gfp_t gfp_mask,
802		     struct workqueue_struct *wq);
803u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line);
804int pblk_line_smeta_read(struct pblk *pblk, struct pblk_line *line);
805int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line,
806			 void *emeta_buf);
807int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr erase_ppa);
808void pblk_line_put(struct kref *ref);
809void pblk_line_put_wq(struct kref *ref);
810struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line);
811u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line);
812void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
813u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
814u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
815int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
816		   unsigned long secs_to_flush, bool skip_meta);
817void pblk_down_rq(struct pblk *pblk, struct ppa_addr ppa,
818		  unsigned long *lun_bitmap);
819void pblk_down_chunk(struct pblk *pblk, struct ppa_addr ppa);
820void pblk_up_chunk(struct pblk *pblk, struct ppa_addr ppa);
821void pblk_up_rq(struct pblk *pblk, unsigned long *lun_bitmap);
822int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
823		       int nr_pages);
824void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
825			 int nr_pages);
826void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa);
827void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
828			   u64 paddr);
829void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa);
830void pblk_update_map_cache(struct pblk *pblk, sector_t lba,
831			   struct ppa_addr ppa);
832void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
833			 struct ppa_addr ppa, struct ppa_addr entry_line);
834int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
835		       struct pblk_line *gc_line, u64 paddr);
836void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
837			  u64 *lba_list, int nr_secs);
838int pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
839			 sector_t blba, int nr_secs, bool *from_cache);
840void *pblk_get_meta_for_writes(struct pblk *pblk, struct nvm_rq *rqd);
841void pblk_get_packed_meta(struct pblk *pblk, struct nvm_rq *rqd);
842
843/*
844 * pblk user I/O write path
845 */
846void pblk_write_to_cache(struct pblk *pblk, struct bio *bio,
847			unsigned long flags);
848int pblk_write_gc_to_cache(struct pblk *pblk, struct pblk_gc_rq *gc_rq);
849
850/*
851 * pblk map
852 */
853int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
854		       unsigned int sentry, unsigned long *lun_bitmap,
855		       unsigned int valid_secs, struct ppa_addr *erase_ppa);
856int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
857		 unsigned long *lun_bitmap, unsigned int valid_secs,
858		 unsigned int off);
859
860/*
861 * pblk write thread
862 */
863int pblk_write_ts(void *data);
864void pblk_write_timer_fn(struct timer_list *t);
865void pblk_write_should_kick(struct pblk *pblk);
866void pblk_write_kick(struct pblk *pblk);
867
868/*
869 * pblk read path
870 */
871extern struct bio_set pblk_bio_set;
872void pblk_submit_read(struct pblk *pblk, struct bio *bio);
873int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq);
874/*
875 * pblk recovery
876 */
877struct pblk_line *pblk_recov_l2p(struct pblk *pblk);
878int pblk_recov_pad(struct pblk *pblk);
879int pblk_recov_check_emeta(struct pblk *pblk, struct line_emeta *emeta);
880
881/*
882 * pblk gc
883 */
884#define PBLK_GC_MAX_READERS 8	/* Max number of outstanding GC reader jobs */
885#define PBLK_GC_RQ_QD 128	/* Queue depth for inflight GC requests */
886#define PBLK_GC_L_QD 4		/* Queue depth for inflight GC lines */
887
888int pblk_gc_init(struct pblk *pblk);
889void pblk_gc_exit(struct pblk *pblk, bool graceful);
890void pblk_gc_should_start(struct pblk *pblk);
891void pblk_gc_should_stop(struct pblk *pblk);
892void pblk_gc_should_kick(struct pblk *pblk);
893void pblk_gc_free_full_lines(struct pblk *pblk);
894void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
895			      int *gc_active);
896int pblk_gc_sysfs_force(struct pblk *pblk, int force);
897void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line);
898
899/*
900 * pblk rate limiter
901 */
902void pblk_rl_init(struct pblk_rl *rl, int budget, int threshold);
903void pblk_rl_free(struct pblk_rl *rl);
904void pblk_rl_update_rates(struct pblk_rl *rl);
905int pblk_rl_high_thrs(struct pblk_rl *rl);
906unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl);
907unsigned long pblk_rl_nr_user_free_blks(struct pblk_rl *rl);
908int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries);
909void pblk_rl_inserted(struct pblk_rl *rl, int nr_entries);
910void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries);
911int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries);
912void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries);
913void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc);
914int pblk_rl_max_io(struct pblk_rl *rl);
915void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line);
916void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line,
917			    bool used);
918int pblk_rl_is_limit(struct pblk_rl *rl);
919
920void pblk_rl_werr_line_in(struct pblk_rl *rl);
921void pblk_rl_werr_line_out(struct pblk_rl *rl);
922
923/*
924 * pblk sysfs
925 */
926int pblk_sysfs_init(struct gendisk *tdisk);
927void pblk_sysfs_exit(struct gendisk *tdisk);
928
929static inline struct nvm_rq *nvm_rq_from_c_ctx(void *c_ctx)
930{
931	return c_ctx - sizeof(struct nvm_rq);
932}
933
934static inline void *emeta_to_bb(struct line_emeta *emeta)
935{
936	return emeta->bb_bitmap;
937}
938
939static inline void *emeta_to_wa(struct pblk_line_meta *lm,
940				struct line_emeta *emeta)
941{
942	return emeta->bb_bitmap + lm->blk_bitmap_len;
943}
944
945static inline void *emeta_to_lbas(struct pblk *pblk, struct line_emeta *emeta)
946{
947	return ((void *)emeta + pblk->lm.emeta_len[1]);
948}
949
950static inline void *emeta_to_vsc(struct pblk *pblk, struct line_emeta *emeta)
951{
952	return (emeta_to_lbas(pblk, emeta) + pblk->lm.emeta_len[2]);
953}
954
955static inline int pblk_line_vsc(struct pblk_line *line)
956{
957	return le32_to_cpu(*line->vsc);
958}
959
960static inline int pblk_ppa_to_line_id(struct ppa_addr p)
961{
962	return p.a.blk;
963}
964
965static inline struct pblk_line *pblk_ppa_to_line(struct pblk *pblk,
966						 struct ppa_addr p)
967{
968	return &pblk->lines[pblk_ppa_to_line_id(p)];
969}
970
971static inline int pblk_ppa_to_pos(struct nvm_geo *geo, struct ppa_addr p)
972{
973	return p.a.lun * geo->num_ch + p.a.ch;
974}
975
976static inline struct ppa_addr addr_to_gen_ppa(struct pblk *pblk, u64 paddr,
977					      u64 line_id)
978{
979	struct nvm_tgt_dev *dev = pblk->dev;
980	struct nvm_geo *geo = &dev->geo;
981	struct ppa_addr ppa;
982
983	if (geo->version == NVM_OCSSD_SPEC_12) {
984		struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf;
985
986		ppa.ppa = 0;
987		ppa.g.blk = line_id;
988		ppa.g.pg = (paddr & ppaf->pg_mask) >> ppaf->pg_offset;
989		ppa.g.lun = (paddr & ppaf->lun_mask) >> ppaf->lun_offset;
990		ppa.g.ch = (paddr & ppaf->ch_mask) >> ppaf->ch_offset;
991		ppa.g.pl = (paddr & ppaf->pln_mask) >> ppaf->pln_offset;
992		ppa.g.sec = (paddr & ppaf->sec_mask) >> ppaf->sec_offset;
993	} else {
994		struct pblk_addrf *uaddrf = &pblk->uaddrf;
995		int secs, chnls, luns;
996
997		ppa.ppa = 0;
998
999		ppa.m.chk = line_id;
1000
1001		paddr = div_u64_rem(paddr, uaddrf->sec_stripe, &secs);
1002		ppa.m.sec = secs;
1003
1004		paddr = div_u64_rem(paddr, uaddrf->ch_stripe, &chnls);
1005		ppa.m.grp = chnls;
1006
1007		paddr = div_u64_rem(paddr, uaddrf->lun_stripe, &luns);
1008		ppa.m.pu = luns;
1009
1010		ppa.m.sec += uaddrf->sec_stripe * paddr;
1011	}
1012
1013	return ppa;
1014}
1015
1016static inline struct nvm_chk_meta *pblk_dev_ppa_to_chunk(struct pblk *pblk,
1017							struct ppa_addr p)
1018{
1019	struct nvm_tgt_dev *dev = pblk->dev;
1020	struct nvm_geo *geo = &dev->geo;
1021	struct pblk_line *line = pblk_ppa_to_line(pblk, p);
1022	int pos = pblk_ppa_to_pos(geo, p);
1023
1024	return &line->chks[pos];
1025}
1026
1027static inline u64 pblk_dev_ppa_to_chunk_addr(struct pblk *pblk,
1028							struct ppa_addr p)
1029{
1030	struct nvm_tgt_dev *dev = pblk->dev;
1031
1032	return dev_to_chunk_addr(dev->parent, &pblk->addrf, p);
1033}
1034
1035static inline u64 pblk_dev_ppa_to_line_addr(struct pblk *pblk,
1036							struct ppa_addr p)
1037{
1038	struct nvm_tgt_dev *dev = pblk->dev;
1039	struct nvm_geo *geo = &dev->geo;
1040	u64 paddr;
1041
1042	if (geo->version == NVM_OCSSD_SPEC_12) {
1043		struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf;
1044
1045		paddr = (u64)p.g.ch << ppaf->ch_offset;
1046		paddr |= (u64)p.g.lun << ppaf->lun_offset;
1047		paddr |= (u64)p.g.pg << ppaf->pg_offset;
1048		paddr |= (u64)p.g.pl << ppaf->pln_offset;
1049		paddr |= (u64)p.g.sec << ppaf->sec_offset;
1050	} else {
1051		struct pblk_addrf *uaddrf = &pblk->uaddrf;
1052		u64 secs = p.m.sec;
1053		int sec_stripe;
1054
1055		paddr = (u64)p.m.grp * uaddrf->sec_stripe;
1056		paddr += (u64)p.m.pu * uaddrf->sec_lun_stripe;
1057
1058		secs = div_u64_rem(secs, uaddrf->sec_stripe, &sec_stripe);
1059		paddr += secs * uaddrf->sec_ws_stripe;
1060		paddr += sec_stripe;
1061	}
1062
1063	return paddr;
1064}
1065
1066static inline struct ppa_addr pblk_ppa32_to_ppa64(struct pblk *pblk, u32 ppa32)
1067{
1068	struct nvm_tgt_dev *dev = pblk->dev;
1069
1070	return nvm_ppa32_to_ppa64(dev->parent, &pblk->addrf, ppa32);
1071}
1072
1073static inline u32 pblk_ppa64_to_ppa32(struct pblk *pblk, struct ppa_addr ppa64)
1074{
1075	struct nvm_tgt_dev *dev = pblk->dev;
1076
1077	return nvm_ppa64_to_ppa32(dev->parent, &pblk->addrf, ppa64);
1078}
1079
1080static inline struct ppa_addr pblk_trans_map_get(struct pblk *pblk,
1081								sector_t lba)
1082{
1083	struct ppa_addr ppa;
1084
1085	if (pblk->addrf_len < 32) {
1086		u32 *map = (u32 *)pblk->trans_map;
1087
1088		ppa = pblk_ppa32_to_ppa64(pblk, map[lba]);
1089	} else {
1090		struct ppa_addr *map = (struct ppa_addr *)pblk->trans_map;
1091
1092		ppa = map[lba];
1093	}
1094
1095	return ppa;
1096}
1097
1098static inline void pblk_trans_map_set(struct pblk *pblk, sector_t lba,
1099						struct ppa_addr ppa)
1100{
1101	if (pblk->addrf_len < 32) {
1102		u32 *map = (u32 *)pblk->trans_map;
1103
1104		map[lba] = pblk_ppa64_to_ppa32(pblk, ppa);
1105	} else {
1106		u64 *map = (u64 *)pblk->trans_map;
1107
1108		map[lba] = ppa.ppa;
1109	}
1110}
1111
1112static inline int pblk_ppa_empty(struct ppa_addr ppa_addr)
1113{
1114	return (ppa_addr.ppa == ADDR_EMPTY);
1115}
1116
1117static inline void pblk_ppa_set_empty(struct ppa_addr *ppa_addr)
1118{
1119	ppa_addr->ppa = ADDR_EMPTY;
1120}
1121
1122static inline bool pblk_ppa_comp(struct ppa_addr lppa, struct ppa_addr rppa)
1123{
1124	return (lppa.ppa == rppa.ppa);
1125}
1126
1127static inline int pblk_addr_in_cache(struct ppa_addr ppa)
1128{
1129	return (ppa.ppa != ADDR_EMPTY && ppa.c.is_cached);
1130}
1131
1132static inline int pblk_addr_to_cacheline(struct ppa_addr ppa)
1133{
1134	return ppa.c.line;
1135}
1136
1137static inline struct ppa_addr pblk_cacheline_to_addr(int addr)
1138{
1139	struct ppa_addr p;
1140
1141	p.c.line = addr;
1142	p.c.is_cached = 1;
1143
1144	return p;
1145}
1146
1147static inline u32 pblk_calc_meta_header_crc(struct pblk *pblk,
1148					    struct line_header *header)
1149{
1150	u32 crc = ~(u32)0;
1151
1152	crc = crc32_le(crc, (unsigned char *)header + sizeof(crc),
1153				sizeof(struct line_header) - sizeof(crc));
1154
1155	return crc;
1156}
1157
1158static inline u32 pblk_calc_smeta_crc(struct pblk *pblk,
1159				      struct line_smeta *smeta)
1160{
1161	struct pblk_line_meta *lm = &pblk->lm;
1162	u32 crc = ~(u32)0;
1163
1164	crc = crc32_le(crc, (unsigned char *)smeta +
1165				sizeof(struct line_header) + sizeof(crc),
1166				lm->smeta_len -
1167				sizeof(struct line_header) - sizeof(crc));
1168
1169	return crc;
1170}
1171
1172static inline u32 pblk_calc_emeta_crc(struct pblk *pblk,
1173				      struct line_emeta *emeta)
1174{
1175	struct pblk_line_meta *lm = &pblk->lm;
1176	u32 crc = ~(u32)0;
1177
1178	crc = crc32_le(crc, (unsigned char *)emeta +
1179				sizeof(struct line_header) + sizeof(crc),
1180				lm->emeta_len[0] -
1181				sizeof(struct line_header) - sizeof(crc));
1182
1183	return crc;
1184}
1185
1186static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs)
1187{
1188	return !(nr_secs % pblk->min_write_pgs);
1189}
1190
1191#ifdef CONFIG_NVM_PBLK_DEBUG
1192static inline void print_ppa(struct pblk *pblk, struct ppa_addr *p,
1193			     char *msg, int error)
1194{
1195	struct nvm_geo *geo = &pblk->dev->geo;
1196
1197	if (p->c.is_cached) {
1198		pblk_err(pblk, "ppa: (%s: %x) cache line: %llu\n",
1199				msg, error, (u64)p->c.line);
1200	} else if (geo->version == NVM_OCSSD_SPEC_12) {
1201		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
1202			msg, error,
1203			p->g.ch, p->g.lun, p->g.blk,
1204			p->g.pg, p->g.pl, p->g.sec);
1205	} else {
1206		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n",
1207			msg, error,
1208			p->m.grp, p->m.pu, p->m.chk, p->m.sec);
1209	}
1210}
1211
1212static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd,
1213					 int error)
1214{
1215	int bit = -1;
1216
1217	if (rqd->nr_ppas ==  1) {
1218		print_ppa(pblk, &rqd->ppa_addr, "rqd", error);
1219		return;
1220	}
1221
1222	while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas,
1223						bit + 1)) < rqd->nr_ppas) {
1224		print_ppa(pblk, &rqd->ppa_list[bit], "rqd", error);
1225	}
1226
1227	pblk_err(pblk, "error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
1228}
1229
1230static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
1231				       struct ppa_addr *ppas, int nr_ppas)
1232{
1233	struct nvm_geo *geo = &tgt_dev->geo;
1234	struct ppa_addr *ppa;
1235	int i;
1236
1237	for (i = 0; i < nr_ppas; i++) {
1238		ppa = &ppas[i];
1239
1240		if (geo->version == NVM_OCSSD_SPEC_12) {
1241			if (!ppa->c.is_cached &&
1242					ppa->g.ch < geo->num_ch &&
1243					ppa->g.lun < geo->num_lun &&
1244					ppa->g.pl < geo->num_pln &&
1245					ppa->g.blk < geo->num_chk &&
1246					ppa->g.pg < geo->num_pg &&
1247					ppa->g.sec < geo->ws_min)
1248				continue;
1249		} else {
1250			if (!ppa->c.is_cached &&
1251					ppa->m.grp < geo->num_ch &&
1252					ppa->m.pu < geo->num_lun &&
1253					ppa->m.chk < geo->num_chk &&
1254					ppa->m.sec < geo->clba)
1255				continue;
1256		}
1257
1258		print_ppa(tgt_dev->q->queuedata, ppa, "boundary", i);
1259
1260		return 1;
1261	}
1262	return 0;
1263}
1264
1265static inline int pblk_check_io(struct pblk *pblk, struct nvm_rq *rqd)
1266{
1267	struct nvm_tgt_dev *dev = pblk->dev;
1268	struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
1269
1270	if (pblk_boundary_ppa_checks(dev, ppa_list, rqd->nr_ppas)) {
1271		WARN_ON(1);
1272		return -EINVAL;
1273	}
1274
1275	if (rqd->opcode == NVM_OP_PWRITE) {
1276		struct pblk_line *line;
1277		int i;
1278
1279		for (i = 0; i < rqd->nr_ppas; i++) {
1280			line = pblk_ppa_to_line(pblk, ppa_list[i]);
1281
1282			spin_lock(&line->lock);
1283			if (line->state != PBLK_LINESTATE_OPEN) {
1284				pblk_err(pblk, "bad ppa: line:%d,state:%d\n",
1285							line->id, line->state);
1286				WARN_ON(1);
1287				spin_unlock(&line->lock);
1288				return -EINVAL;
1289			}
1290			spin_unlock(&line->lock);
1291		}
1292	}
1293
1294	return 0;
1295}
1296#endif
1297
1298static inline int pblk_boundary_paddr_checks(struct pblk *pblk, u64 paddr)
1299{
1300	struct pblk_line_meta *lm = &pblk->lm;
1301
1302	if (paddr > lm->sec_per_line)
1303		return 1;
1304
1305	return 0;
1306}
1307
1308static inline unsigned int pblk_get_bi_idx(struct bio *bio)
1309{
1310	return bio->bi_iter.bi_idx;
1311}
1312
1313static inline sector_t pblk_get_lba(struct bio *bio)
1314{
1315	return bio->bi_iter.bi_sector / NR_PHY_IN_LOG;
1316}
1317
1318static inline unsigned int pblk_get_secs(struct bio *bio)
1319{
1320	return  bio->bi_iter.bi_size / PBLK_EXPOSED_PAGE_SIZE;
1321}
1322
1323static inline char *pblk_disk_name(struct pblk *pblk)
1324{
1325	struct gendisk *disk = pblk->disk;
1326
1327	return disk->disk_name;
1328}
1329
1330static inline unsigned int pblk_get_min_chks(struct pblk *pblk)
1331{
1332	struct pblk_line_meta *lm = &pblk->lm;
1333	/* In a worst-case scenario every line will have OP invalid sectors.
1334	 * We will then need a minimum of 1/OP lines to free up a single line
1335	 */
1336
1337	return DIV_ROUND_UP(100, pblk->op) * lm->blk_per_line;
1338}
1339
1340static inline struct pblk_sec_meta *pblk_get_meta(struct pblk *pblk,
1341							 void *meta, int index)
1342{
1343	return meta +
1344	       max_t(int, sizeof(struct pblk_sec_meta), pblk->oob_meta_size)
1345	       * index;
1346}
1347
1348static inline int pblk_dma_meta_size(struct pblk *pblk)
1349{
1350	return max_t(int, sizeof(struct pblk_sec_meta), pblk->oob_meta_size)
1351	       * NVM_MAX_VLBA;
1352}
1353
1354static inline int pblk_is_oob_meta_supported(struct pblk *pblk)
1355{
1356	return pblk->oob_meta_size >= sizeof(struct pblk_sec_meta);
1357}
1358#endif /* PBLK_H_ */
1359