diff options
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/backing-dev-defs.h | 23 | ||||
-rw-r--r-- | include/linux/backing-dev.h | 2 | ||||
-rw-r--r-- | include/linux/blk-mq.h | 13 | ||||
-rw-r--r-- | include/linux/blk_types.h | 5 | ||||
-rw-r--r-- | include/linux/blkdev.h | 16 | ||||
-rw-r--r-- | include/linux/elevator.h | 1 | ||||
-rw-r--r-- | include/linux/lightnvm.h | 11 | ||||
-rw-r--r-- | include/linux/sbitmap.h | 64 | ||||
-rw-r--r-- | include/linux/writeback.h | 26 | ||||
-rw-r--r-- | include/trace/events/writeback.h | 1 |
10 files changed, 91 insertions, 71 deletions
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 420de5c7c7f9..b7c7be6f5986 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -45,6 +45,28 @@ enum wb_stat_item { #define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) /* + * why some writeback work was initiated + */ +enum wb_reason { + WB_REASON_BACKGROUND, + WB_REASON_VMSCAN, + WB_REASON_SYNC, + WB_REASON_PERIODIC, + WB_REASON_LAPTOP_TIMER, + WB_REASON_FREE_MORE_MEM, + WB_REASON_FS_FREE_SPACE, + /* + * There is no bdi forker thread any more and works are done + * by emergency worker, however, this is TPs userland visible + * and we'll be exposing exactly the same information, + * so it has a mismatch name. + */ + WB_REASON_FORKER_THREAD, + + WB_REASON_MAX, +}; + +/* * For cgroup writeback, multiple wb's may map to the same blkcg. Those * wb's can operate mostly independently but should share the congested * state. To facilitate such sharing, the congested state is tracked using @@ -116,6 +138,7 @@ struct bdi_writeback { struct fprop_local_percpu completions; int dirty_exceeded; + enum wb_reason start_all_reason; spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 157e950a70dc..872afa41abc2 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -172,8 +172,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) long congestion_wait(int sync, long timeout); long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout); -int pdflush_proc_obsolete(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index cfd64e500d82..f2e3079eecdd 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -30,6 +30,8 @@ struct blk_mq_hw_ctx { struct sbitmap ctx_map; + struct blk_mq_ctx *dispatch_from; + struct blk_mq_ctx **ctxs; unsigned int nr_ctx; @@ -90,6 +92,8 @@ struct blk_mq_queue_data { typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +typedef blk_status_t (get_budget_fn)(struct blk_mq_hw_ctx *); +typedef void (put_budget_fn)(struct blk_mq_hw_ctx *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); @@ -112,6 +116,15 @@ struct blk_mq_ops { queue_rq_fn *queue_rq; /* + * Reserve budget before queue request, once .queue_rq is + * run, it is driver's responsibility to release the + * reserved budget. Also we have to handle failure case + * of .get_budget for avoiding I/O deadlock. + */ + get_budget_fn *get_budget; + put_budget_fn *put_budget; + + /* * Called on request timeout */ timeout_fn *timeout; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index a2d2aa709cef..3385c89f402e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -329,11 +329,10 @@ static inline bool blk_qc_t_is_internal(blk_qc_t cookie) } struct blk_rq_stat { - s64 mean; + u64 mean; u64 min; u64 max; - s32 nr_samples; - s32 nr_batch; + u32 nr_samples; u64 batch; }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 02fa42d24b52..72637028f3c9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -609,7 +609,6 @@ struct request_queue { #define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ -#define QUEUE_FLAG_STACKABLE 8 /* supports request stacking */ #define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 10 /* do IO stats */ @@ -633,12 +632,10 @@ struct request_queue { #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_ADD_RANDOM)) #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_POLL)) @@ -722,8 +719,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_stackable(q) \ - test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) @@ -922,17 +917,6 @@ static inline void rq_flush_dcache_pages(struct request *rq) } #endif -#ifdef CONFIG_PRINTK -#define vfs_msg(sb, level, fmt, ...) \ - __vfs_msg(sb, level, fmt, ##__VA_ARGS__) -#else -#define vfs_msg(sb, level, fmt, ...) \ -do { \ - no_printk(fmt, ##__VA_ARGS__); \ - __vfs_msg(sb, "", " "); \ -} while (0) -#endif - extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern blk_qc_t generic_make_request(struct bio *bio); diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 5bc8f8682a3e..6df8b14f1f6a 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -144,6 +144,7 @@ struct elevator_type size_t icq_align; /* ditto */ struct elv_fs_entry *elevator_attrs; char elevator_name[ELV_NAME_MAX]; + const char *elevator_alias; struct module *elevator_owner; bool uses_mq; #ifdef CONFIG_BLK_DEBUG_FS diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 7dfa56ebbc6d..b7f111ff4d3b 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -56,6 +56,7 @@ typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32, typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *); typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int); typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); +typedef int (nvm_submit_io_sync_fn)(struct nvm_dev *, struct nvm_rq *); typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); typedef void (nvm_destroy_dma_pool_fn)(void *); typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t, @@ -69,6 +70,7 @@ struct nvm_dev_ops { nvm_op_set_bb_fn *set_bb_tbl; nvm_submit_io_fn *submit_io; + nvm_submit_io_sync_fn *submit_io_sync; nvm_create_dma_pool_fn *create_dma_pool; nvm_destroy_dma_pool_fn *destroy_dma_pool; @@ -460,10 +462,9 @@ struct nvm_tgt_type { /* For internal use */ struct list_head list; + struct module *owner; }; -extern struct nvm_tgt_type *nvm_find_target_type(const char *, int); - extern int nvm_register_tgt_type(struct nvm_tgt_type *); extern void nvm_unregister_tgt_type(struct nvm_tgt_type *); @@ -478,10 +479,8 @@ extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *, int, int); extern int nvm_max_phys_sects(struct nvm_tgt_dev *); extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *); +extern int nvm_submit_io_sync(struct nvm_tgt_dev *, struct nvm_rq *); extern int nvm_erase_sync(struct nvm_tgt_dev *, struct ppa_addr *, int); -extern int nvm_set_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *, - const struct ppa_addr *, int, int); -extern void nvm_free_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *); extern int nvm_get_l2p_tbl(struct nvm_tgt_dev *, u64, u32, nvm_l2p_update_fn *, void *); extern int nvm_get_area(struct nvm_tgt_dev *, sector_t *, sector_t); @@ -490,8 +489,6 @@ extern void nvm_end_io(struct nvm_rq *); extern int nvm_bb_tbl_fold(struct nvm_dev *, u8 *, int); extern int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr, u8 *); -extern int nvm_dev_factory(struct nvm_dev *, int flags); - extern void nvm_part_to_tgt(struct nvm_dev *, sector_t *, int); #else /* CONFIG_NVM */ diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index a1904aadbc45..0dcc60e820de 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -211,10 +211,14 @@ bool sbitmap_any_bit_set(const struct sbitmap *sb); */ bool sbitmap_any_bit_clear(const struct sbitmap *sb); +#define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift) +#define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U)) + typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *); /** - * sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap. + * __sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap. + * @start: Where to start the iteration. * @sb: Bitmap to iterate over. * @fn: Callback. Should return true to continue or false to break early. * @data: Pointer to pass to callback. @@ -222,35 +226,61 @@ typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *); * This is inline even though it's non-trivial so that the function calls to the * callback will hopefully get optimized away. */ -static inline void sbitmap_for_each_set(struct sbitmap *sb, sb_for_each_fn fn, - void *data) +static inline void __sbitmap_for_each_set(struct sbitmap *sb, + unsigned int start, + sb_for_each_fn fn, void *data) { - unsigned int i; + unsigned int index; + unsigned int nr; + unsigned int scanned = 0; - for (i = 0; i < sb->map_nr; i++) { - struct sbitmap_word *word = &sb->map[i]; - unsigned int off, nr; + if (start >= sb->depth) + start = 0; + index = SB_NR_TO_INDEX(sb, start); + nr = SB_NR_TO_BIT(sb, start); - if (!word->word) - continue; + while (scanned < sb->depth) { + struct sbitmap_word *word = &sb->map[index]; + unsigned int depth = min_t(unsigned int, word->depth - nr, + sb->depth - scanned); - nr = 0; - off = i << sb->shift; + scanned += depth; + if (!word->word) + goto next; + + /* + * On the first iteration of the outer loop, we need to add the + * bit offset back to the size of the word for find_next_bit(). + * On all other iterations, nr is zero, so this is a noop. + */ + depth += nr; while (1) { - nr = find_next_bit(&word->word, word->depth, nr); - if (nr >= word->depth) + nr = find_next_bit(&word->word, depth, nr); + if (nr >= depth) break; - - if (!fn(sb, off + nr, data)) + if (!fn(sb, (index << sb->shift) + nr, data)) return; nr++; } +next: + nr = 0; + if (++index >= sb->map_nr) + index = 0; } } -#define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift) -#define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U)) +/** + * sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap. + * @sb: Bitmap to iterate over. + * @fn: Callback. Should return true to continue or false to break early. + * @data: Pointer to pass to callback. + */ +static inline void sbitmap_for_each_set(struct sbitmap *sb, sb_for_each_fn fn, + void *data) +{ + __sbitmap_for_each_set(sb, 0, fn, data); +} static inline unsigned long *__sbitmap_word(struct sbitmap *sb, unsigned int bitnr) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9c0091678af4..e15ec14085ad 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -42,28 +42,6 @@ enum writeback_sync_modes { }; /* - * why some writeback work was initiated - */ -enum wb_reason { - WB_REASON_BACKGROUND, - WB_REASON_VMSCAN, - WB_REASON_SYNC, - WB_REASON_PERIODIC, - WB_REASON_LAPTOP_TIMER, - WB_REASON_FREE_MORE_MEM, - WB_REASON_FS_FREE_SPACE, - /* - * There is no bdi forker thread any more and works are done - * by emergency worker, however, this is TPs userland visible - * and we'll be exposing exactly the same information, - * so it has a mismatch name. - */ - WB_REASON_FORKER_THREAD, - - WB_REASON_MAX, -}; - -/* * A control structure which tells the writeback code what to do. These are * always on the stack, and hence need no locking. They are always initialised * in a manner such that unspecified fields are set to zero. @@ -185,9 +163,7 @@ struct bdi_writeback; void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); -bool try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); -bool try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, - enum wb_reason reason); +void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason); void sync_inodes_sb(struct super_block *); void wakeup_flusher_threads(enum wb_reason reason); void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 9b57f014d79d..19a0ea08e098 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -286,7 +286,6 @@ DEFINE_EVENT(writeback_class, name, \ TP_PROTO(struct bdi_writeback *wb), \ TP_ARGS(wb)) -DEFINE_WRITEBACK_EVENT(writeback_nowork); DEFINE_WRITEBACK_EVENT(writeback_wake_background); TRACE_EVENT(writeback_bdi_register, |