#define PBLK_MAX_REQ_ADDRS (64)
#define PBLK_MAX_REQ_ADDRS_PW (6)
+#define PBLK_WS_POOL_SIZE (128)
+#define PBLK_META_POOL_SIZE (128)
+#define PBLK_READ_REQ_POOL_SIZE (1024)
+
+#define PBLK_NR_CLOSE_JOBS (4)
+
#define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16)
#define PBLK_COMMAND_TIMEOUT_MS 30000
PBLK_BLK_ST_CLOSED = 0x2,
};
+struct pblk_sec_meta {
+ u64 reserved;
+ __le64 lba;
+};
+
/* The number of GC lists and the rate-limiter states go together. This way the
* rate-limiter can dictate how much GC is needed based on resource utilization.
*/
-#define PBLK_NR_GC_LISTS 3
-#define PBLK_MAX_GC_JOBS 32
+#define PBLK_GC_NR_LISTS 3
enum {
PBLK_RL_HIGH = 1,
PBLK_RL_LOW = 3,
};
-struct pblk_sec_meta {
- u64 reserved;
- __le64 lba;
-};
-
#define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * PBLK_MAX_REQ_ADDRS)
/* write buffer completion context */
void *private;
};
+/* Pad context */
+struct pblk_pad_rq {
+ struct pblk *pblk;
+ struct completion wait;
+ struct kref ref;
+};
+
/* Recovery context */
struct pblk_rec_ctx {
struct pblk *pblk;
struct pblk_gc_rq {
struct pblk_line *line;
void *data;
- u64 *lba_list;
+ u64 lba_list[PBLK_MAX_REQ_ADDRS];
int nr_secs;
int secs_to_gc;
struct list_head list;
};
struct pblk_gc {
+ /* These states are not protected by a lock since (i) they are in the
+ * fast path, and (ii) they are not critical.
+ */
int gc_active;
int gc_enabled;
int gc_forced;
- int gc_jobs_active;
- atomic_t inflight_gc;
struct task_struct *gc_ts;
struct task_struct *gc_writer_ts;
+ struct task_struct *gc_reader_ts;
+
+ struct workqueue_struct *gc_line_reader_wq;
struct workqueue_struct *gc_reader_wq;
+
struct timer_list gc_timer;
+ struct semaphore gc_sem;
+ atomic_t inflight_gc;
int w_entries;
+
struct list_head w_list;
+ struct list_head r_list;
spinlock_t lock;
spinlock_t w_lock;
+ spinlock_t r_lock;
};
struct pblk_rl {
*/
unsigned int high_pw; /* High rounded up as a power of 2 */
-#define PBLK_USER_HIGH_THRS 2 /* Begin write limit at 50 percent
- * available blks
- */
-#define PBLK_USER_LOW_THRS 20 /* Aggressive GC at 5% available blocks */
+#define PBLK_USER_HIGH_THRS 8 /* Begin write limit at 12% available blks */
+#define PBLK_USER_LOW_THRS 10 /* Aggressive GC at 10% available blocks */
int rb_windows_pw; /* Number of rate windows in the write buffer
* given as a power-of-2. This guarantees that
*/
int rb_budget; /* Total number of entries available for I/O */
int rb_user_max; /* Max buffer entries available for user I/O */
- atomic_t rb_user_cnt; /* User I/O buffer counter */
int rb_gc_max; /* Max buffer entries available for GC I/O */
int rb_gc_rsv; /* Reserved buffer entries for GC I/O */
int rb_state; /* Rate-limiter current state */
+
+ atomic_t rb_user_cnt; /* User I/O buffer counter */
atomic_t rb_gc_cnt; /* GC I/O buffer counter */
+ atomic_t rb_space; /* Space limit in case of reaching capacity */
+
+ int rsv_blocks; /* Reserved blocks for GC */
int rb_user_active;
+ int rb_gc_active;
+
struct timer_list u_timer;
unsigned long long nr_secs;
struct list_head bad_list; /* Full lines bad */
/* GC lists - use gc_lock */
- struct list_head *gc_lists[PBLK_NR_GC_LISTS];
+ struct list_head *gc_lists[PBLK_GC_NR_LISTS];
struct list_head gc_high_list; /* Full lines ready to GC, high isc */
struct list_head gc_mid_list; /* Full lines ready to GC, mid isc */
struct list_head gc_low_list; /* Full lines ready to GC, low isc */
u8 sec_offset;
};
+enum {
+ PBLK_STATE_RUNNING = 0,
+ PBLK_STATE_STOPPING = 1,
+ PBLK_STATE_RECOVERING = 2,
+ PBLK_STATE_STOPPED = 3,
+};
+
struct pblk {
struct nvm_tgt_dev *dev;
struct gendisk *disk;
struct pblk_rb rwb;
+ int state; /* pblk line state */
+
int min_write_pgs; /* Minimum amount of pages required by controller */
int max_write_pgs; /* Maximum amount of pages supported by controller */
int pgs_in_buffer; /* Number of pages that need to be held in buffer to
atomic_long_t write_failed;
atomic_long_t erase_failed;
+ atomic_t inflight_io; /* General inflight I/O counter */
+
struct task_struct *writer_ts;
/* Simple translation map of logical addresses to physical addresses.
mempool_t *w_rq_pool;
mempool_t *line_meta_pool;
- struct workqueue_struct *kw_wq;
+ struct workqueue_struct *close_wq;
+ struct workqueue_struct *bb_wq;
+
struct timer_list wtimer;
struct pblk_gc gc;
struct pblk_w_ctx w_ctx, struct pblk_line *gc_line,
unsigned int pos);
struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos);
+void pblk_rb_flush(struct pblk_rb *rb);
void pblk_rb_sync_l2p(struct pblk_rb *rb);
unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
struct list_head *list,
unsigned int max);
int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
- u64 pos, int bio_iter);
+ struct ppa_addr ppa, int bio_iter);
unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries);
unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags);
unsigned int pblk_rb_sync_point_count(struct pblk_rb *rb);
unsigned int pblk_rb_read_count(struct pblk_rb *rb);
+unsigned int pblk_rb_sync_count(struct pblk_rb *rb);
unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos);
int pblk_rb_tear_down_check(struct pblk_rb *rb);
int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
struct pblk_c_ctx *c_ctx);
void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw);
-void pblk_flush_writer(struct pblk *pblk);
+void pblk_wait_for_meta(struct pblk *pblk);
struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba);
void pblk_discard(struct pblk *pblk, struct bio *bio);
void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd);
int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line);
struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
unsigned int nr_secs, unsigned int len,
- gfp_t gfp_mask);
+ int alloc_type, gfp_t gfp_mask);
struct pblk_line *pblk_line_get(struct pblk *pblk);
struct pblk_line *pblk_line_get_first_data(struct pblk *pblk);
-struct pblk_line *pblk_line_replace_data(struct pblk *pblk);
+void pblk_line_replace_data(struct pblk *pblk);
int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line);
void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line);
struct pblk_line *pblk_line_get_data(struct pblk *pblk);
void pblk_line_free(struct pblk *pblk, struct pblk_line *line);
void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line);
void pblk_line_close(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_close_meta_sync(struct pblk *pblk);
void pblk_line_close_ws(struct work_struct *work);
+void pblk_pipeline_stop(struct pblk *pblk);
void pblk_line_mark_bb(struct work_struct *work);
void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
- void (*work)(struct work_struct *));
+ void (*work)(struct work_struct *),
+ struct workqueue_struct *wq);
u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line);
int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line);
int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line,
*/
void pblk_submit_rec(struct work_struct *work);
struct pblk_line *pblk_recov_l2p(struct pblk *pblk);
-void pblk_recov_pad(struct pblk *pblk);
+int pblk_recov_pad(struct pblk *pblk);
__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta);
int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
struct pblk_rec_ctx *recovery, u64 *comp_bits,
/*
* pblk gc
*/
-#define PBLK_GC_TRIES 3
+#define PBLK_GC_MAX_READERS 8 /* Max number of outstanding GC reader jobs */
+#define PBLK_GC_W_QD 128 /* Queue depth for inflight GC write I/Os */
+#define PBLK_GC_L_QD 4 /* Queue depth for inflight GC lines */
+#define PBLK_GC_RSV_LINE 1 /* Reserved lines for GC */
int pblk_gc_init(struct pblk *pblk);
void pblk_gc_exit(struct pblk *pblk);
void pblk_gc_should_start(struct pblk *pblk);
void pblk_gc_should_stop(struct pblk *pblk);
-int pblk_gc_status(struct pblk *pblk);
+void pblk_gc_should_kick(struct pblk *pblk);
+void pblk_gc_kick(struct pblk *pblk);
void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
int *gc_active);
-void pblk_gc_sysfs_force(struct pblk *pblk, int force);
+int pblk_gc_sysfs_force(struct pblk *pblk, int force);
/*
* pblk rate limiter
*/
void pblk_rl_init(struct pblk_rl *rl, int budget);
void pblk_rl_free(struct pblk_rl *rl);
-int pblk_rl_gc_thrs(struct pblk_rl *rl);
+int pblk_rl_high_thrs(struct pblk_rl *rl);
+int pblk_rl_low_thrs(struct pblk_rl *rl);
unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl);
int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_inserted(struct pblk_rl *rl, int nr_entries);
void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries);
int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries);
void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries);
void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc);
-void pblk_rl_set_gc_rsc(struct pblk_rl *rl, int rsv);
int pblk_rl_sysfs_rate_show(struct pblk_rl *rl);
void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line);
void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line);
+void pblk_rl_set_space_limit(struct pblk_rl *rl, int entries_left);
+int pblk_rl_is_limit(struct pblk_rl *rl);
/*
* pblk sysfs
return (emeta_to_lbas(pblk, emeta) + pblk->lm.emeta_len[2]);
}
+static inline int pblk_line_vsc(struct pblk_line *line)
+{
+ int vsc;
+
+ spin_lock(&line->lock);
+ vsc = le32_to_cpu(*line->vsc);
+ spin_unlock(&line->lock);
+
+ return vsc;
+}
+
#define NVM_MEM_PAGE_WRITE (8)
static inline int pblk_pad_distance(struct pblk *pblk)
ppa_addr->ppa = ADDR_EMPTY;
}
+static inline bool pblk_ppa_comp(struct ppa_addr lppa, struct ppa_addr rppa)
+{
+ if (lppa.ppa == rppa.ppa)
+ return true;
+
+ return false;
+}
+
static inline int pblk_addr_in_cache(struct ppa_addr ppa)
{
return (ppa.ppa != ADDR_EMPTY && ppa.c.is_cached);