diff options
Diffstat (limited to 'block/blk-mq.h')
| -rw-r--r-- | block/blk-mq.h | 154 |
1 files changed, 86 insertions, 68 deletions
diff --git a/block/blk-mq.h b/block/blk-mq.h index 1743857e0b01..aa15d31aaae9 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -6,6 +6,7 @@ #include "blk-stat.h" struct blk_mq_tag_set; +struct elevator_tags; struct blk_mq_ctxs { struct kobject kobj; @@ -36,6 +37,8 @@ enum { BLK_MQ_TAG_MAX = BLK_MQ_NO_TAG - 1, }; +#define BLK_MQ_CPU_WORK_BATCH (8) + typedef unsigned int __bitwise blk_insert_t; #define BLK_MQ_INSERT_AT_HEAD ((__force blk_insert_t)0x01) @@ -43,10 +46,12 @@ void blk_mq_submit_bio(struct bio *bio); int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob, unsigned int flags); void blk_mq_exit_queue(struct request_queue *q); -int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); +struct elevator_tags *blk_mq_update_nr_requests(struct request_queue *q, + struct elevator_tags *tags, + unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *, - unsigned int); + bool); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); @@ -57,7 +62,7 @@ void blk_mq_put_rq_ref(struct request *rq); */ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); -void blk_mq_free_rq_map(struct blk_mq_tags *tags); +void blk_mq_free_rq_map(struct blk_mq_tag_set *set, struct blk_mq_tags *tags); struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int depth); void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, @@ -79,7 +84,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue * enum hctx_type type, unsigned int cpu) { - return xa_load(&q->hctx_table, q->tag_set->map[type].mq_map[cpu]); + return queue_hctx((q), (q->tag_set->map[type].mq_map[cpu])); } static inline enum hctx_type blk_mq_get_hctx_type(blk_opf_t opf) @@ -98,18 +103,27 @@ static inline enum hctx_type blk_mq_get_hctx_type(blk_opf_t opf) /* * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue - * @q: request queue * @opf: operation type (REQ_OP_*) and flags (e.g. REQ_POLLED). * @ctx: software queue cpu ctx */ -static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, - blk_opf_t opf, +static inline struct blk_mq_hw_ctx *blk_mq_map_queue(blk_opf_t opf, struct blk_mq_ctx *ctx) { return ctx->hctxs[blk_mq_get_hctx_type(opf)]; } /* + * Default to double of smaller one between hw queue_depth and + * 128, since we don't split into sync/async like the old code + * did. Additionally, this is a per-hw queue depth. + */ +static inline unsigned int blk_mq_default_nr_requests( + struct blk_mq_tag_set *set) +{ + return 2 * min_t(unsigned int, set->queue_depth, BLKDEV_DEFAULT_RQ); +} + +/* * sysfs helpers */ extern void blk_mq_sysfs_init(struct request_queue *q); @@ -153,7 +167,7 @@ struct blk_mq_alloc_data { /* allocate multiple requests/tags in one go */ unsigned int nr_tags; - struct request **cached_rq; + struct rq_list *cached_rqs; /* input & output parameter */ struct blk_mq_ctx *ctx; @@ -161,11 +175,8 @@ struct blk_mq_alloc_data { }; struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, - unsigned int reserved_tags, int node, int alloc_policy); -void blk_mq_free_tags(struct blk_mq_tags *tags); -int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, - struct sbitmap_queue *breserved_tags, unsigned int queue_depth, - unsigned int reserved, int node, int alloc_policy); + unsigned int reserved_tags, unsigned int flags, int node); +void blk_mq_free_tags(struct blk_mq_tag_set *set, struct blk_mq_tags *tags); unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, @@ -173,11 +184,10 @@ unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags); -int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, - struct blk_mq_tags **tags, unsigned int depth, bool can_grow); void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size); -void blk_mq_tag_update_sched_shared_tags(struct request_queue *q); +void blk_mq_tag_update_sched_shared_tags(struct request_queue *q, + unsigned int nr); void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn, @@ -228,6 +238,19 @@ static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx) { + /* Fast path: hardware queue is not stopped most of the time. */ + if (likely(!test_bit(BLK_MQ_S_STOPPED, &hctx->state))) + return false; + + /* + * This barrier is used to order adding of dispatch list before and + * the test of BLK_MQ_S_STOPPED below. Pairs with the memory barrier + * in blk_mq_start_stopped_hw_queue() so that dispatch code could + * either see BLK_MQ_S_STOPPED is cleared or dispatch list is not + * empty to avoid missing dispatching requests. + */ + smp_mb(); + return test_bit(BLK_MQ_S_STOPPED, &hctx->state); } @@ -236,10 +259,7 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) return hctx->nr_ctx && hctx->tags; } -unsigned int blk_mq_in_flight(struct request_queue *q, - struct block_device *part); -void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, - unsigned int inflight[2]); +void blk_mq_in_driver_rw(struct block_device *part, unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct request_queue *q, int budget_token) @@ -271,12 +291,18 @@ static inline int blk_mq_get_rq_budget_token(struct request *rq) return -1; } -static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) +static inline void __blk_mq_add_active_requests(struct blk_mq_hw_ctx *hctx, + int val) { if (blk_mq_is_shared_tags(hctx->flags)) - atomic_inc(&hctx->queue->nr_active_requests_shared_tags); + atomic_add(val, &hctx->queue->nr_active_requests_shared_tags); else - atomic_inc(&hctx->nr_active); + atomic_add(val, &hctx->nr_active); +} + +static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) +{ + __blk_mq_add_active_requests(hctx, 1); } static inline void __blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx, @@ -293,6 +319,32 @@ static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) __blk_mq_sub_active_requests(hctx, 1); } +static inline void blk_mq_add_active_requests(struct blk_mq_hw_ctx *hctx, + int val) +{ + if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) + __blk_mq_add_active_requests(hctx, val); +} + +static inline void blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) +{ + if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) + __blk_mq_inc_active_requests(hctx); +} + +static inline void blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx, + int val) +{ + if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) + __blk_mq_sub_active_requests(hctx, val); +} + +static inline void blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) +{ + if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) + __blk_mq_dec_active_requests(hctx); +} + static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_shared_tags(hctx->flags)) @@ -302,13 +354,9 @@ static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx) static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { + blk_mq_dec_active_requests(hctx); blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag); rq->tag = BLK_MQ_NO_TAG; - - if (rq->rq_flags & RQF_MQ_INFLIGHT) { - rq->rq_flags &= ~RQF_MQ_INFLIGHT; - __blk_mq_dec_active_requests(hctx); - } } static inline void blk_mq_put_driver_tag(struct request *rq) @@ -319,19 +367,14 @@ static inline void blk_mq_put_driver_tag(struct request *rq) __blk_mq_put_driver_tag(rq->mq_hctx, rq); } -bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq); +bool __blk_mq_alloc_driver_tag(struct request *rq); static inline bool blk_mq_get_driver_tag(struct request *rq) { - struct blk_mq_hw_ctx *hctx = rq->mq_hctx; + if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_alloc_driver_tag(rq)) + return false; - if (rq->tag != BLK_MQ_NO_TAG && - !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { - hctx->tags->rqs[rq->tag] = rq; - return true; - } - - return __blk_mq_get_driver_tag(hctx, rq); + return true; } static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) @@ -342,37 +385,6 @@ static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) qmap->mq_map[cpu] = 0; } -/* - * blk_mq_plug() - Get caller context plug - * @bio : the bio being submitted by the caller context - * - * Plugging, by design, may delay the insertion of BIOs into the elevator in - * order to increase BIO merging opportunities. This however can cause BIO - * insertion order to change from the order in which submit_bio() is being - * executed in the case of multiple contexts concurrently issuing BIOs to a - * device, even if these context are synchronized to tightly control BIO issuing - * order. While this is not a problem with regular block devices, this ordering - * change can cause write BIO failures with zoned block devices as these - * require sequential write patterns to zones. Prevent this from happening by - * ignoring the plug state of a BIO issuing context if it is for a zoned block - * device and the BIO to plug is a write operation. - * - * Return current->plug if the bio can be plugged and NULL otherwise - */ -static inline struct blk_plug *blk_mq_plug( struct bio *bio) -{ - /* Zoned block device write operation case: do not plug the BIO */ - if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && - bdev_op_is_zoned_write(bio->bi_bdev, bio_op(bio))) - return NULL; - - /* - * For regular block devices or read operations, use the context plug - * which may be NULL if blk_start_plug() was not executed. - */ - return current->plug; -} - /* Free all requests on the list */ static inline void blk_mq_free_requests(struct list_head *list) { @@ -444,4 +456,10 @@ do { \ #define blk_mq_run_dispatch_ops(q, dispatch_ops) \ __blk_mq_run_dispatch_ops(q, true, dispatch_ops) \ +static inline bool blk_mq_can_poll(struct request_queue *q) +{ + return (q->limits.features & BLK_FEAT_POLL) && + q->tag_set->map[HCTX_TYPE_POLL].nr_queues; +} + #endif |