diff options
Diffstat (limited to 'include/linux/blk-mq.h')
| -rw-r--r-- | include/linux/blk-mq.h | 577 |
1 files changed, 316 insertions, 261 deletions
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d319ffa59354..cae9e857aea4 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -7,6 +7,9 @@ #include <linux/lockdep.h> #include <linux/scatterlist.h> #include <linux/prefetch.h> +#include <linux/srcu.h> +#include <linux/rw_hint.h> +#include <linux/rwsem.h> struct blk_mq_tags; struct blk_flush_queue; @@ -14,53 +17,76 @@ struct blk_flush_queue; #define BLKDEV_MIN_RQ 4 #define BLKDEV_DEFAULT_RQ 128 -typedef void (rq_end_io_fn)(struct request *, blk_status_t); +enum rq_end_io_ret { + RQ_END_IO_NONE, + RQ_END_IO_FREE, +}; + +typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t); /* * request flags */ typedef __u32 __bitwise req_flags_t; -/* drive already may have started this one */ -#define RQF_STARTED ((__force req_flags_t)(1 << 1)) -/* may not be passed by ioscheduler */ -#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) -/* request for flush sequence */ -#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) -/* merge of different types, fail separately */ -#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) -/* track inflight for MQ */ -#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) -/* don't call prep for this one */ -#define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) -/* vaguely specified driver internal error. Ignored by the block layer */ -#define RQF_FAILED ((__force req_flags_t)(1 << 10)) -/* don't warn about errors */ -#define RQF_QUIET ((__force req_flags_t)(1 << 11)) -/* elevator private data attached */ -#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) -/* account into disk and partition IO statistics */ -#define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) -/* runtime pm request */ -#define RQF_PM ((__force req_flags_t)(1 << 15)) -/* on IO scheduler merge hash */ -#define RQF_HASHED ((__force req_flags_t)(1 << 16)) -/* track IO completion time */ -#define RQF_STATS ((__force req_flags_t)(1 << 17)) -/* Look at ->special_vec for the actual data payload instead of the - bio chain. */ -#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) -/* The per-zone write lock is held for this request */ -#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) -/* already slept for hybrid poll */ -#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) -/* ->timeout has been called, don't expire again */ -#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) -/* queue has elevator attached */ -#define RQF_ELV ((__force req_flags_t)(1 << 22)) +/* Keep rqf_name[] in sync with the definitions below */ +enum rqf_flags { + /* drive already may have started this one */ + __RQF_STARTED, + /* request for flush sequence */ + __RQF_FLUSH_SEQ, + /* merge of different types, fail separately */ + __RQF_MIXED_MERGE, + /* don't call prep for this one */ + __RQF_DONTPREP, + /* use hctx->sched_tags */ + __RQF_SCHED_TAGS, + /* use an I/O scheduler for this request */ + __RQF_USE_SCHED, + /* vaguely specified driver internal error. Ignored by block layer */ + __RQF_FAILED, + /* don't warn about errors */ + __RQF_QUIET, + /* account into disk and partition IO statistics */ + __RQF_IO_STAT, + /* runtime pm request */ + __RQF_PM, + /* on IO scheduler merge hash */ + __RQF_HASHED, + /* track IO completion time */ + __RQF_STATS, + /* Look at ->special_vec for the actual data payload instead of the + bio chain. */ + __RQF_SPECIAL_PAYLOAD, + /* request completion needs to be signaled to zone write plugging. */ + __RQF_ZONE_WRITE_PLUGGING, + /* ->timeout has been called, don't expire again */ + __RQF_TIMED_OUT, + __RQF_RESV, + __RQF_BITS +}; + +#define RQF_STARTED ((__force req_flags_t)(1 << __RQF_STARTED)) +#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << __RQF_FLUSH_SEQ)) +#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << __RQF_MIXED_MERGE)) +#define RQF_DONTPREP ((__force req_flags_t)(1 << __RQF_DONTPREP)) +#define RQF_SCHED_TAGS ((__force req_flags_t)(1 << __RQF_SCHED_TAGS)) +#define RQF_USE_SCHED ((__force req_flags_t)(1 << __RQF_USE_SCHED)) +#define RQF_FAILED ((__force req_flags_t)(1 << __RQF_FAILED)) +#define RQF_QUIET ((__force req_flags_t)(1 << __RQF_QUIET)) +#define RQF_IO_STAT ((__force req_flags_t)(1 << __RQF_IO_STAT)) +#define RQF_PM ((__force req_flags_t)(1 << __RQF_PM)) +#define RQF_HASHED ((__force req_flags_t)(1 << __RQF_HASHED)) +#define RQF_STATS ((__force req_flags_t)(1 << __RQF_STATS)) +#define RQF_SPECIAL_PAYLOAD \ + ((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD)) +#define RQF_ZONE_WRITE_PLUGGING \ + ((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING)) +#define RQF_TIMED_OUT ((__force req_flags_t)(1 << __RQF_TIMED_OUT)) +#define RQF_RESV ((__force req_flags_t)(1 << __RQF_RESV)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ - (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) + (RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) enum mq_rq_state { MQ_RQ_IDLE = 0, @@ -79,7 +105,7 @@ struct request { struct blk_mq_ctx *mq_ctx; struct blk_mq_hw_ctx *mq_hctx; - unsigned int cmd_flags; /* op and common flags */ + blk_opf_t cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; @@ -124,19 +150,21 @@ struct request { * physical address coalescing is performed. */ unsigned short nr_phys_segments; - -#ifdef CONFIG_BLK_DEV_INTEGRITY unsigned short nr_integrity_segments; -#endif + + /* + * The lowest set bit for address gaps between physical segments. This + * provides information necessary for dma optimization opprotunities, + * like for testing if the segments can be coalesced against the + * device's iommu granule. + */ + unsigned char phys_gap_bit; #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_crypto_keyslot *crypt_keyslot; #endif - unsigned short write_hint; - unsigned short ioprio; - enum mq_rq_state state; atomic_t ref; @@ -156,40 +184,30 @@ struct request { /* * The rb_node is only used inside the io scheduler, requests - * are pruned when moved to the dispatch queue. So let the - * completion_data share space with the rb_node. + * are pruned when moved to the dispatch queue. special_vec must + * only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be + * insert into an IO scheduler. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; - void *completion_data; - int error_count; /* for legacy drivers, don't use */ }; - /* * Three pointers are available for the IO schedulers, if they need - * more they have to dynamically allocate it. Flush requests are - * never put on the IO scheduler. So let the flush fields share - * space with the elevator data. + * more they have to dynamically allocate it. */ - union { - struct { - struct io_cq *icq; - void *priv[2]; - } elv; - - struct { - unsigned int seq; - struct list_head list; - rq_end_io_fn *saved_end_io; - } flush; - }; + struct { + struct io_cq *icq; + void *priv[2]; + } elv; - union { - struct __call_single_data csd; - u64 fifo_time; - }; + struct { + unsigned int seq; + rq_end_io_fn *saved_end_io; + } flush; + + u64 fifo_time; /* * completion callback. @@ -198,17 +216,29 @@ struct request { void *end_io_data; }; -#define req_op(req) \ - ((req)->cmd_flags & REQ_OP_MASK) +/* + * Returns a mask with all bits starting at req->phys_gap_bit set to 1. + */ +static inline unsigned long req_phys_gap_mask(const struct request *req) +{ + return ~(((1 << req->phys_gap_bit) >> 1) - 1); +} + +static inline enum req_op req_op(const struct request *req) +{ + return req->cmd_flags & REQ_OP_MASK; +} static inline bool blk_rq_is_passthrough(struct request *rq) { - return blk_op_is_passthrough(req_op(rq)); + return blk_op_is_passthrough(rq->cmd_flags); } static inline unsigned short req_get_ioprio(struct request *req) { - return req->ioprio; + if (req->bio) + return req->bio->bi_ioprio; + return 0; } #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) @@ -216,64 +246,73 @@ static inline unsigned short req_get_ioprio(struct request *req) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) -#define rq_list_add(listptr, rq) do { \ - (rq)->rq_next = *(listptr); \ - *(listptr) = rq; \ -} while (0) - -#define rq_list_pop(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) { \ - __req = *(listptr); \ - *(listptr) = __req->rq_next; \ - } \ - __req; \ -}) +static inline int rq_list_empty(const struct rq_list *rl) +{ + return rl->head == NULL; +} -#define rq_list_peek(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) \ - __req = *(listptr); \ - __req; \ -}) +static inline void rq_list_init(struct rq_list *rl) +{ + rl->head = NULL; + rl->tail = NULL; +} + +static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq) +{ + rq->rq_next = NULL; + if (rl->tail) + rl->tail->rq_next = rq; + else + rl->head = rq; + rl->tail = rq; +} -#define rq_list_for_each(listptr, pos) \ - for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) +static inline void rq_list_add_head(struct rq_list *rl, struct request *rq) +{ + rq->rq_next = rl->head; + rl->head = rq; + if (!rl->tail) + rl->tail = rq; +} -#define rq_list_for_each_safe(listptr, pos, nxt) \ - for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos); \ - pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL) +static inline struct request *rq_list_pop(struct rq_list *rl) +{ + struct request *rq = rl->head; -#define rq_list_next(rq) (rq)->rq_next -#define rq_list_empty(list) ((list) == (struct request *) NULL) + if (rq) { + rl->head = rl->head->rq_next; + if (!rl->head) + rl->tail = NULL; + rq->rq_next = NULL; + } -/** - * rq_list_move() - move a struct request from one list to another - * @src: The source list @rq is currently in - * @dst: The destination list that @rq will be appended to - * @rq: The request to move - * @prev: The request preceding @rq in @src (NULL if @rq is the head) - */ -static inline void rq_list_move(struct request **src, struct request **dst, - struct request *rq, struct request *prev) + return rq; +} + +static inline struct request *rq_list_peek(struct rq_list *rl) { - if (prev) - prev->rq_next = rq->rq_next; - else - *src = rq->rq_next; - rq_list_add(dst, rq); + return rl->head; } +#define rq_list_for_each(rl, pos) \ + for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next) + +#define rq_list_for_each_safe(rl, pos, nxt) \ + for (pos = rq_list_peek((rl)), nxt = pos->rq_next; \ + pos; pos = nxt, nxt = pos ? pos->rq_next : NULL) + +/** + * enum blk_eh_timer_return - How the timeout handler should proceed + * @BLK_EH_DONE: The block driver completed the command or will complete it at + * a later time. + * @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the + * request to complete. + */ enum blk_eh_timer_return { - BLK_EH_DONE, /* drivers has completed the command */ - BLK_EH_RESET_TIMER, /* reset timer and try again */ + BLK_EH_DONE, + BLK_EH_RESET_TIMER, }; -#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ -#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ - /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device @@ -386,11 +425,6 @@ struct blk_mq_hw_ctx { */ struct blk_mq_tags *sched_tags; - /** @queued: Number of queued requests. */ - unsigned long queued; - /** @run: Number of dispatched requests. */ - unsigned long run; - /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; /** @queue_num: Index of this hardware queue. */ @@ -459,6 +493,7 @@ enum hctx_type { /** * struct blk_mq_tag_set - tag set that can be shared between request queues + * @ops: Pointers to functions that implement block driver behavior. * @map: One or more ctx -> hctx mappings. One map exists for each * hardware queue type (enum hctx_type) that the driver wishes * to support. There are no restrictions on maps being of the @@ -466,7 +501,6 @@ enum hctx_type { * types. * @nr_maps: Number of elements in the @map array. A number in the range * [1, HCTX_MAX_TYPES]. - * @ops: Pointers to functions that implement block driver behavior. * @nr_hw_queues: Number of hardware queues supported by the block driver that * owns this data structure. * @queue_depth: Number of tags per hardware queue, reserved tags included. @@ -487,11 +521,18 @@ enum hctx_type { * @tag_list_lock: Serializes tag_list accesses. * @tag_list: List of the request queues that use this tag set. See also * request_queue.tag_set_list. + * @srcu: Use as lock when type of the request queue is blocking + * (BLK_MQ_F_BLOCKING). + * @tags_srcu: SRCU used to defer freeing of tags page_list to prevent + * use-after-free when iterating tags. + * @update_nr_hwq_lock: + * Synchronize updating nr_hw_queues with add/del disk & + * switching elevator. */ struct blk_mq_tag_set { + const struct blk_mq_ops *ops; struct blk_mq_queue_map map[HCTX_MAX_TYPES]; unsigned int nr_maps; - const struct blk_mq_ops *ops; unsigned int nr_hw_queues; unsigned int queue_depth; unsigned int reserved_tags; @@ -507,6 +548,10 @@ struct blk_mq_tag_set { struct mutex tag_list_lock; struct list_head tag_list; + struct srcu_struct *srcu; + struct srcu_struct tags_srcu; + + struct rw_semaphore update_nr_hwq_lock; }; /** @@ -520,7 +565,7 @@ struct blk_mq_queue_data { bool last; }; -typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); +typedef bool (busy_tag_iter_fn)(struct request *, void *); /** * struct blk_mq_ops - Callback functions that implements block driver @@ -548,7 +593,7 @@ struct blk_mq_ops { * empty the @rqlist completely, then the rest will be queued * individually by the block layer upon return. */ - void (*queue_rqs)(struct request **rqlist); + void (*queue_rqs)(struct rq_list *rqlist); /** * @get_budget: Reserve budget before queue request, once .queue_rq is @@ -575,7 +620,7 @@ struct blk_mq_ops { /** * @timeout: Called on request timeout. */ - enum blk_eh_timer_return (*timeout)(struct request *, bool); + enum blk_eh_timer_return (*timeout)(struct request *); /** * @poll: Called to poll for completion of a specific tag. @@ -628,7 +673,7 @@ struct blk_mq_ops { * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ - int (*map_queues)(struct blk_mq_tag_set *set); + void (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** @@ -639,8 +684,8 @@ struct blk_mq_ops { #endif }; +/* Keep hctx_flag_name[] in sync with the definitions below */ enum { - BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for @@ -648,49 +693,51 @@ enum { */ BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, - BLK_MQ_F_BLOCKING = 1 << 5, - /* Do not allow an I/O scheduler to be configured. */ - BLK_MQ_F_NO_SCHED = 1 << 6, + BLK_MQ_F_BLOCKING = 1 << 4, + + /* + * Alloc tags on a round-robin base instead of the first available one. + */ + BLK_MQ_F_TAG_RR = 1 << 5, + /* * Select 'none' during queue registration in case of a single hwq * or shared hwqs instead of 'mq-deadline'. */ - BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 7, - BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, - BLK_MQ_F_ALLOC_POLICY_BITS = 1, - - BLK_MQ_S_STOPPED = 0, - BLK_MQ_S_TAG_ACTIVE = 1, - BLK_MQ_S_SCHED_RESTART = 2, - - /* hw queue is inactive after all its CPUs become offline */ - BLK_MQ_S_INACTIVE = 3, + BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 6, - BLK_MQ_MAX_DEPTH = 10240, - - BLK_MQ_CPU_WORK_BATCH = 8, + BLK_MQ_F_MAX = 1 << 7, }; -#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \ - ((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \ - ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) -#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \ - ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ - << BLK_MQ_F_ALLOC_POLICY_START_BIT) +#define BLK_MQ_MAX_DEPTH (10240) #define BLK_MQ_NO_HCTX_IDX (-1U) -struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, +enum { + /* Keep hctx_state_name[] in sync with the definitions below */ + BLK_MQ_S_STOPPED, + BLK_MQ_S_TAG_ACTIVE, + BLK_MQ_S_SCHED_RESTART, + /* hw queue is inactive after all its CPUs become offline */ + BLK_MQ_S_INACTIVE, + BLK_MQ_S_MAX +}; + +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, + struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass); -#define blk_mq_alloc_disk(set, queuedata) \ +#define blk_mq_alloc_disk(set, lim, queuedata) \ ({ \ static struct lock_class_key __key; \ \ - __blk_mq_alloc_disk(set, queuedata, &__key); \ + __blk_mq_alloc_disk(set, lim, queuedata, &__key); \ }) -struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); +struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, + struct lock_class_key *lkclass); +struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, + struct queue_limits *lim, void *queuedata); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); -void blk_mq_unregister_dev(struct device *, struct request_queue *); +void blk_mq_destroy_queue(struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, @@ -699,6 +746,8 @@ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_free_request(struct request *rq); +int blk_rq_poll(struct request *rq, struct io_comp_batch *iob, + unsigned int poll_flags); bool blk_mq_queue_inflight(struct request_queue *q); @@ -711,10 +760,10 @@ enum { BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2), }; -struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, +struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, - unsigned int op, blk_mq_req_flags_t flags, + blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx); /* @@ -723,8 +772,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, struct blk_mq_tags { unsigned int nr_tags; unsigned int nr_reserved_tags; - - atomic_t active_queues; + unsigned int active_queues; struct sbitmap_queue bitmap_tags; struct sbitmap_queue breserved_tags; @@ -738,6 +786,7 @@ struct blk_mq_tags { * request pool */ spinlock_t lock; + struct rcu_head rcu_head; }; static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, @@ -821,25 +870,54 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib); */ static inline bool blk_mq_need_time_stamp(struct request *rq) { - return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); + return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } -/* +static inline bool blk_mq_is_reserved_rq(struct request *rq) +{ + return rq->rq_flags & RQF_RESV; +} + +/** + * blk_mq_add_to_batch() - add a request to the completion batch + * @req: The request to add to batch + * @iob: The batch to add the request + * @is_error: Specify true if the request failed with an error + * @complete: The completaion handler for the request + * * Batched completions only work when there is no I/O error and no special * ->end_io handler. + * + * Return: true when the request was added to the batch, otherwise false */ static inline bool blk_mq_add_to_batch(struct request *req, - struct io_comp_batch *iob, int ioerror, + struct io_comp_batch *iob, bool is_error, void (*complete)(struct io_comp_batch *)) { - if (!iob || (req->rq_flags & RQF_ELV) || req->end_io || ioerror) + /* + * Check various conditions that exclude batch processing: + * 1) No batch container + * 2) Has scheduler data attached + * 3) Not a passthrough request and end_io set + * 4) Not a passthrough request and failed with an error + */ + if (!iob) + return false; + if (req->rq_flags & RQF_SCHED_TAGS) return false; + if (!blk_rq_is_passthrough(req)) { + if (req->end_io) + return false; + if (is_error) + return false; + } + if (!iob->complete) iob->complete = complete; else if (iob->complete != complete) return false; iob->need_ts |= blk_mq_need_time_stamp(req); - rq_list_add(&iob->req_list, req); + rq_list_add_tail(&iob->req_list, req); return true; } @@ -848,7 +926,6 @@ void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); bool blk_mq_complete_request_remote(struct request *rq); -bool blk_mq_queue_stopped(struct request_queue *q); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); @@ -856,7 +933,9 @@ void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); -void blk_mq_wait_quiesce_done(struct request_queue *q); +void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set); +void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set); +void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); @@ -865,14 +944,34 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); -void blk_mq_freeze_queue(struct request_queue *q); -void blk_mq_unfreeze_queue(struct request_queue *q); +void blk_mq_freeze_queue_nomemsave(struct request_queue *q); +void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q); +static inline unsigned int __must_check +blk_mq_freeze_queue(struct request_queue *q) +{ + unsigned int memflags = memalloc_noio_save(); + + blk_mq_freeze_queue_nomemsave(q); + return memflags; +} +static inline void +blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags) +{ + blk_mq_unfreeze_queue_nomemrestore(q); + memalloc_noio_restore(memflags); +} void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); - -int blk_mq_map_queues(struct blk_mq_queue_map *qmap); +void blk_mq_unfreeze_queue_non_owner(struct request_queue *q); +void blk_freeze_queue_start_non_owner(struct request_queue *q); + +unsigned int blk_mq_num_possible_queues(unsigned int max_queues); +unsigned int blk_mq_num_online_queues(unsigned int max_queues); +void blk_mq_map_queues(struct blk_mq_queue_map *qmap); +void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, + struct device *dev, unsigned int offset); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); @@ -916,9 +1015,20 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq) return rq + 1; } +static inline struct blk_mq_hw_ctx *queue_hctx(struct request_queue *q, int id) +{ + struct blk_mq_hw_ctx *hctx; + + rcu_read_lock(); + hctx = rcu_dereference(q->queue_hw_ctx)[id]; + rcu_read_unlock(); + + return hctx; +} + #define queue_for_each_hw_ctx(q, hctx, i) \ for ((i) = 0; (i) < (q)->nr_hw_queues && \ - ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++) + ({ hctx = queue_hctx((q), i); 1; }); (i)++) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ @@ -930,15 +1040,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq) rq->q->mq_ops->cleanup_rq(rq); } -static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, - unsigned int nr_segs) -{ - rq->nr_phys_segments = nr_segs; - rq->__data_len = bio->bi_iter.bi_size; - rq->bio = rq->biotail = bio; - rq->ioprio = bio_prio(bio); -} - void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key); @@ -952,29 +1053,30 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); void blk_rq_unprep_clone(struct request *rq); -blk_status_t blk_insert_cloned_request(struct request_queue *q, - struct request *rq); +blk_status_t blk_insert_cloned_request(struct request *rq); struct rq_map_data { struct page **pages; - int page_order; - int nr_entries; unsigned long offset; - int null_mapped; - int from_user; + unsigned short page_order; + unsigned short nr_entries; + bool null_mapped; + bool from_user; }; int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); +int blk_rq_map_user_io(struct request *, struct rq_map_data *, + void __user *, unsigned long, gfp_t, bool, int, bool, int); int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); int blk_rq_unmap_user(struct bio *); -int blk_rq_map_kern(struct request_queue *, struct request *, void *, - unsigned int, gfp_t); +int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, + gfp_t gfp); int blk_rq_append_bio(struct request *rq, struct bio *bio); -void blk_execute_rq_nowait(struct request *rq, bool at_head, - rq_end_io_fn *end_io); +void blk_execute_rq_nowait(struct request *rq, bool at_head); blk_status_t blk_execute_rq(struct request *rq, bool at_head); +bool blk_rq_is_poll(struct request *rq); struct req_iterator { struct bvec_iter iter; @@ -1111,79 +1213,32 @@ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) return max_t(unsigned short, rq->nr_phys_segments, 1); } -int __blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist, struct scatterlist **last_sg); -static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist) -{ - struct scatterlist *last_sg = NULL; - - return __blk_rq_map_sg(q, rq, sglist, &last_sg); -} -void blk_dump_rq_flags(struct request *, char *); - -#ifdef CONFIG_BLK_DEV_ZONED -static inline unsigned int blk_rq_zone_no(struct request *rq) -{ - return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); -} - -static inline unsigned int blk_rq_zone_is_seq(struct request *rq) -{ - return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); -} - -bool blk_req_needs_zone_write_lock(struct request *rq); -bool blk_req_zone_write_trylock(struct request *rq); -void __blk_req_zone_write_lock(struct request *rq); -void __blk_req_zone_write_unlock(struct request *rq); - -static inline void blk_req_zone_write_lock(struct request *rq) -{ - if (blk_req_needs_zone_write_lock(rq)) - __blk_req_zone_write_lock(rq); -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ - if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) - __blk_req_zone_write_unlock(rq); -} - -static inline bool blk_req_zone_is_write_locked(struct request *rq) +/** + * blk_rq_nr_bvec - return number of bvecs in a request + * @rq: request to calculate bvecs for + * + * Returns the number of bvecs. + */ +static inline unsigned int blk_rq_nr_bvec(struct request *rq) { - return rq->q->seq_zones_wlock && - test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock); -} + struct req_iterator rq_iter; + struct bio_vec bv; + unsigned int nr_bvec = 0; -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - if (!blk_req_needs_zone_write_lock(rq)) - return true; - return !blk_req_zone_is_write_locked(rq); -} -#else /* CONFIG_BLK_DEV_ZONED */ -static inline bool blk_req_needs_zone_write_lock(struct request *rq) -{ - return false; -} + rq_for_each_bvec(bv, rq, rq_iter) + nr_bvec++; -static inline void blk_req_zone_write_lock(struct request *rq) -{ + return nr_bvec; } -static inline void blk_req_zone_write_unlock(struct request *rq) +int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist, + struct scatterlist **last_sg); +static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist) { -} -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return false; -} + struct scatterlist *last_sg = NULL; -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - return true; + return __blk_rq_map_sg(rq, sglist, &last_sg); } -#endif /* CONFIG_BLK_DEV_ZONED */ +void blk_dump_rq_flags(struct request *, char *); #endif /* BLK_MQ_H */ |