diff options
Diffstat (limited to 'include/linux/blk-mq.h')
| -rw-r--r-- | include/linux/blk-mq.h | 822 |
1 files changed, 729 insertions, 93 deletions
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 11cfd6470b1a..d6119c5d1069 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -4,11 +4,290 @@ #include <linux/blkdev.h> #include <linux/sbitmap.h> -#include <linux/srcu.h> +#include <linux/lockdep.h> +#include <linux/scatterlist.h> +#include <linux/prefetch.h> struct blk_mq_tags; struct blk_flush_queue; +#define BLKDEV_MIN_RQ 4 +#define BLKDEV_DEFAULT_RQ 128 + +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)) +#define RQF_RESV ((__force req_flags_t)(1 << 23)) + +/* flags that prevent us from merging requests: */ +#define RQF_NOMERGE_FLAGS \ + (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) + +enum mq_rq_state { + MQ_RQ_IDLE = 0, + MQ_RQ_IN_FLIGHT = 1, + MQ_RQ_COMPLETE = 2, +}; + +/* + * Try to put the fields that are referenced together in the same cacheline. + * + * If you modify this structure, make sure to update blk_rq_init() and + * especially blk_mq_rq_ctx_init() to take care of the added fields. + */ +struct request { + struct request_queue *q; + struct blk_mq_ctx *mq_ctx; + struct blk_mq_hw_ctx *mq_hctx; + + blk_opf_t cmd_flags; /* op and common flags */ + req_flags_t rq_flags; + + int tag; + int internal_tag; + + unsigned int timeout; + + /* the following two fields are internal, NEVER access directly */ + unsigned int __data_len; /* total data len */ + sector_t __sector; /* sector cursor */ + + struct bio *bio; + struct bio *biotail; + + union { + struct list_head queuelist; + struct request *rq_next; + }; + + struct block_device *part; +#ifdef CONFIG_BLK_RQ_ALLOC_TIME + /* Time that the first bio started allocating this request. */ + u64 alloc_time_ns; +#endif + /* Time that this request was allocated for this IO. */ + u64 start_time_ns; + /* Time that I/O was submitted to the device. */ + u64 io_start_time_ns; + +#ifdef CONFIG_BLK_WBT + unsigned short wbt_flags; +#endif + /* + * rq sectors used for blk stats. It has the same value + * with blk_rq_sectors(rq), except that it never be zeroed + * by completion. + */ + unsigned short stats_sectors; + + /* + * Number of scatter-gather DMA addr+len pairs after + * physical address coalescing is performed. + */ + unsigned short nr_phys_segments; + +#ifdef CONFIG_BLK_DEV_INTEGRITY + unsigned short nr_integrity_segments; +#endif + +#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; + + unsigned long deadline; + + /* + * The hash is used inside the scheduler, and killed once the + * request reaches the dispatch list. The ipi_list is only used + * to queue the request for softirq completion, which is long + * after the request has been unhashed (and even removed from + * the dispatch list). + */ + union { + struct hlist_node hash; /* merge hash */ + struct llist_node ipi_list; + }; + + /* + * 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. + */ + union { + struct rb_node rb_node; /* sort/lookup */ + struct bio_vec special_vec; + void *completion_data; + }; + + + /* + * 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. + */ + 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; + }; + + union { + struct __call_single_data csd; + u64 fifo_time; + }; + + /* + * completion callback. + */ + rq_end_io_fn *end_io; + void *end_io_data; +}; + +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)); +} + +static inline unsigned short req_get_ioprio(struct request *req) +{ + return req->ioprio; +} + +#define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) + +#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; \ +}) + +#define rq_list_peek(listptr) \ +({ \ + struct request *__req = NULL; \ + if ((listptr) && *(listptr)) \ + __req = *(listptr); \ + __req; \ +}) + +#define rq_list_for_each(listptr, pos) \ + for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) + +#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) + +#define rq_list_next(rq) (rq)->rq_next +#define rq_list_empty(list) ((list) == (struct request *) 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) +{ + if (prev) + prev->rq_next = rq->rq_next; + else + *src = rq->rq_next; + rq_list_add(dst, rq); +} + +/** + * 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, + 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 @@ -125,9 +404,6 @@ struct blk_mq_hw_ctx { unsigned long queued; /** @run: Number of dispatched requests. */ unsigned long run; -#define BLK_MQ_MAX_DISPATCH_ORDER 7 - /** @dispatched: Number of dispatch requests by queue. */ - unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; @@ -140,18 +416,13 @@ struct blk_mq_hw_ctx { */ atomic_t nr_active; + /** @cpuhp_online: List to store request if CPU is going to die */ + struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ struct kobject kobj; - /** @poll_considered: Count times blk_poll() was called. */ - unsigned long poll_considered; - /** @poll_invoked: Count how many requests blk_poll() polled. */ - unsigned long poll_invoked; - /** @poll_success: Count how many polled requests were completed. */ - unsigned long poll_success; - #ifdef CONFIG_BLK_DEBUG_FS /** * @debugfs_dir: debugfs directory for this hardware queue. Named @@ -162,15 +433,11 @@ struct blk_mq_hw_ctx { struct dentry *sched_debugfs_dir; #endif - /** @hctx_list: List of all hardware queues. */ - struct list_head hctx_list; - /** - * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is - * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also - * blk_mq_hw_ctx_size(). + * @hctx_list: if this hctx is not in use, this is an entry in + * q->unused_hctx_list. */ - struct srcu_struct srcu[0]; + struct list_head hctx_list; }; /** @@ -228,6 +495,9 @@ enum hctx_type { * tag set. * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. + * @shared_tags: + * Shared set of tags. Has @nr_hw_queues elements. If set, + * shared by all @tags. * @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. @@ -247,6 +517,8 @@ struct blk_mq_tag_set { struct blk_mq_tags **tags; + struct blk_mq_tags *shared_tags; + struct mutex tag_list_lock; struct list_head tag_list; }; @@ -262,27 +534,7 @@ struct blk_mq_queue_data { bool last; }; -typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, - const struct blk_mq_queue_data *); -typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *); -typedef bool (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); -typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *, - unsigned int, unsigned int); -typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *, - unsigned int); - -typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, - bool); -typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); -typedef int (poll_fn)(struct blk_mq_hw_ctx *); -typedef int (map_queues_fn)(struct blk_mq_tag_set *set); -typedef bool (busy_fn)(struct request_queue *); -typedef void (complete_fn)(struct request *); -typedef void (cleanup_rq_fn)(struct request *); +typedef bool (busy_tag_iter_fn)(struct request *, void *); /** * struct blk_mq_ops - Callback functions that implements block driver @@ -292,7 +544,8 @@ struct blk_mq_ops { /** * @queue_rq: Queue a new request from block IO. */ - queue_rq_fn *queue_rq; + blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *, + const struct blk_mq_queue_data *); /** * @commit_rqs: If a driver uses bd->last to judge when to submit @@ -301,7 +554,15 @@ struct blk_mq_ops { * purpose of kicking the hardware (which the last request otherwise * would have done). */ - commit_rqs_fn *commit_rqs; + void (*commit_rqs)(struct blk_mq_hw_ctx *); + + /** + * @queue_rqs: Queue a list of new requests. Driver is guaranteed + * that each request belongs to the same queue. If the driver doesn't + * empty the @rqlist completely, then the rest will be queued + * individually by the block layer upon return. + */ + void (*queue_rqs)(struct request **rqlist); /** * @get_budget: Reserve budget before queue request, once .queue_rq is @@ -309,37 +570,47 @@ struct blk_mq_ops { * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ - get_budget_fn *get_budget; + int (*get_budget)(struct request_queue *); + /** * @put_budget: Release the reserved budget. */ - put_budget_fn *put_budget; + void (*put_budget)(struct request_queue *, int); + + /** + * @set_rq_budget_token: store rq's budget token + */ + void (*set_rq_budget_token)(struct request *, int); + /** + * @get_rq_budget_token: retrieve rq's budget token + */ + int (*get_rq_budget_token)(struct request *); /** * @timeout: Called on request timeout. */ - timeout_fn *timeout; + enum blk_eh_timer_return (*timeout)(struct request *); /** * @poll: Called to poll for completion of a specific tag. */ - poll_fn *poll; + int (*poll)(struct blk_mq_hw_ctx *, struct io_comp_batch *); /** * @complete: Mark the request as complete. */ - complete_fn *complete; + void (*complete)(struct request *); /** * @init_hctx: Called when the block layer side of a hardware queue has * been set up, allowing the driver to allocate/init matching * structures. */ - init_hctx_fn *init_hctx; + int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int); /** * @exit_hctx: Ditto for exit/teardown. */ - exit_hctx_fn *exit_hctx; + void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); /** * @init_request: Called for every command allocated by the block layer @@ -348,33 +619,30 @@ struct blk_mq_ops { * Tag greater than or equal to queue_depth is for setting up * flush request. */ - init_request_fn *init_request; + int (*init_request)(struct blk_mq_tag_set *set, struct request *, + unsigned int, unsigned int); /** * @exit_request: Ditto for exit/teardown. */ - exit_request_fn *exit_request; - - /** - * @initialize_rq_fn: Called from inside blk_get_request(). - */ - void (*initialize_rq_fn)(struct request *rq); + void (*exit_request)(struct blk_mq_tag_set *set, struct request *, + unsigned int); /** * @cleanup_rq: Called before freeing one request which isn't completed * yet, and usually for freeing the driver private data. */ - cleanup_rq_fn *cleanup_rq; + void (*cleanup_rq)(struct request *); /** * @busy: If set, returns whether or not this queue currently is busy. */ - busy_fn *busy; + bool (*busy)(struct request_queue *); /** * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ - map_queues_fn *map_queues; + void (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** @@ -387,9 +655,21 @@ struct blk_mq_ops { enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, - BLK_MQ_F_TAG_SHARED = 1 << 1, + BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, + /* + * Set when this device requires underlying blk-mq device for + * completing IO: + */ + 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, + /* + * 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, @@ -397,6 +677,9 @@ enum { 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_MAX_DEPTH = 10240, BLK_MQ_CPU_WORK_BATCH = 8, @@ -408,21 +691,29 @@ enum { ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) +#define BLK_MQ_NO_HCTX_IDX (-1U) + +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, + struct lock_class_key *lkclass); +#define blk_mq_alloc_disk(set, queuedata) \ +({ \ + static struct lock_class_key __key; \ + \ + __blk_mq_alloc_disk(set, queuedata, &__key); \ +}) +struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, + struct lock_class_key *lkclass); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); -struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, - struct request_queue *q, - bool elevator_init); -struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, - const struct blk_mq_ops *ops, - unsigned int queue_depth, - unsigned int set_flags); -void blk_mq_unregister_dev(struct device *, struct request_queue *); +int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, + struct request_queue *q); +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, + const struct blk_mq_ops *ops, unsigned int queue_depth, + unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); -void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); - void blk_mq_free_request(struct request *rq); bool blk_mq_queue_inflight(struct request_queue *q); @@ -432,18 +723,49 @@ enum { BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), - /* allocate internal/sched tag */ - BLK_MQ_REQ_INTERNAL = (__force blk_mq_req_flags_t)(1 << 2), - /* set RQF_PREEMPT */ - BLK_MQ_REQ_PREEMPT = (__force blk_mq_req_flags_t)(1 << 3), + /* set RQF_PM */ + 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); -struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); + +/* + * Tag address space map. + */ +struct blk_mq_tags { + unsigned int nr_tags; + unsigned int nr_reserved_tags; + + atomic_t active_queues; + + struct sbitmap_queue bitmap_tags; + struct sbitmap_queue breserved_tags; + + struct request **rqs; + struct request **static_rqs; + struct list_head page_list; + + /* + * used to clear request reference in rqs[] before freeing one + * request pool + */ + spinlock_t lock; +}; + +static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, + unsigned int tag) +{ + if (tag < tags->nr_tags) { + prefetch(tags->rqs[tag]); + return tags->rqs[tag]; + } + + return NULL; +} enum { BLK_MQ_UNIQUE_TAG_BITS = 16, @@ -481,17 +803,74 @@ static inline int blk_mq_request_completed(struct request *rq) return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; } +/* + * + * Set the state to complete when completing a request from inside ->queue_rq. + * This is used by drivers that want to ensure special complete actions that + * need access to the request are called on failure, e.g. by nvme for + * multipathing. + */ +static inline void blk_mq_set_request_complete(struct request *rq) +{ + WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); +} + +/* + * Complete the request directly instead of deferring it to softirq or + * completing it another CPU. Useful in preemptible instead of an interrupt. + */ +static inline void blk_mq_complete_request_direct(struct request *rq, + void (*complete)(struct request *rq)) +{ + WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); + complete(rq); +} + void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); +void blk_mq_end_request_batch(struct io_comp_batch *ib); + +/* + * Only need start/end time stamping if we have iostat or + * blk stats enabled, or using an IO scheduler. + */ +static inline bool blk_mq_need_time_stamp(struct request *rq) +{ + return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); +} + +static inline bool blk_mq_is_reserved_rq(struct request *rq) +{ + return rq->rq_flags & RQF_RESV; +} + +/* + * Batched completions only work when there is no I/O error and no special + * ->end_io handler. + */ +static inline bool blk_mq_add_to_batch(struct request *req, + struct io_comp_batch *iob, int ioerror, + void (*complete)(struct io_comp_batch *)) +{ + if (!iob || (req->rq_flags & RQF_ELV) || ioerror || + (req->end_io && !blk_rq_is_passthrough(req))) + 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); + return true; +} void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); -bool blk_mq_complete_request(struct request *rq); -bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, - struct bio *bio, unsigned int nr_segs); -bool blk_mq_queue_stopped(struct request_queue *q); +void blk_mq_complete_request(struct request *rq); +bool blk_mq_complete_request_remote(struct request *rq); 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); @@ -499,10 +878,12 @@ 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_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); void blk_mq_run_hw_queues(struct request_queue *q, bool async); +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); @@ -513,13 +894,22 @@ 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_map_queues(struct blk_mq_queue_map *qmap); 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); unsigned int blk_mq_rq_cpu(struct request *rq); +bool __blk_should_fake_timeout(struct request_queue *q); +static inline bool blk_should_fake_timeout(struct request_queue *q) +{ + if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) && + test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) + return __blk_should_fake_timeout(q); + return false; +} + /** * blk_mq_rq_from_pdu - cast a PDU to a request * @pdu: the PDU (Protocol Data Unit) to be casted @@ -549,27 +939,273 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq) } #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)++) + xa_for_each(&(q)->hctx_table, (i), (hctx)) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++) -static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, - struct request *rq) +static inline void blk_mq_cleanup_rq(struct request *rq) { - if (rq->tag != -1) - return rq->tag | (hctx->queue_num << BLK_QC_T_SHIFT); + if (rq->q->mq_ops->cleanup_rq) + rq->q->mq_ops->cleanup_rq(rq); +} - return rq->internal_tag | (hctx->queue_num << BLK_QC_T_SHIFT) | - BLK_QC_T_INTERNAL; +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); } -static inline void blk_mq_cleanup_rq(struct request *rq) +void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, + struct lock_class_key *key); + +static inline bool rq_is_sync(struct request *rq) { - if (rq->q->mq_ops->cleanup_rq) - rq->q->mq_ops->cleanup_rq(rq); + return op_is_sync(rq->cmd_flags); } -#endif +void blk_rq_init(struct request_queue *q, struct request *rq); +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 *rq); + +struct rq_map_data { + struct page **pages; + unsigned long offset; + 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_append_bio(struct request *rq, struct bio *bio); +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; + struct bio *bio; +}; + +#define __rq_for_each_bio(_bio, rq) \ + if ((rq->bio)) \ + for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) + +#define rq_for_each_segment(bvl, _rq, _iter) \ + __rq_for_each_bio(_iter.bio, _rq) \ + bio_for_each_segment(bvl, _iter.bio, _iter.iter) + +#define rq_for_each_bvec(bvl, _rq, _iter) \ + __rq_for_each_bio(_iter.bio, _rq) \ + bio_for_each_bvec(bvl, _iter.bio, _iter.iter) + +#define rq_iter_last(bvec, _iter) \ + (_iter.bio->bi_next == NULL && \ + bio_iter_last(bvec, _iter.iter)) + +/* + * blk_rq_pos() : the current sector + * blk_rq_bytes() : bytes left in the entire request + * blk_rq_cur_bytes() : bytes left in the current segment + * blk_rq_sectors() : sectors left in the entire request + * blk_rq_cur_sectors() : sectors left in the current segment + * blk_rq_stats_sectors() : sectors of the entire request used for stats + */ +static inline sector_t blk_rq_pos(const struct request *rq) +{ + return rq->__sector; +} + +static inline unsigned int blk_rq_bytes(const struct request *rq) +{ + return rq->__data_len; +} + +static inline int blk_rq_cur_bytes(const struct request *rq) +{ + if (!rq->bio) + return 0; + if (!bio_has_data(rq->bio)) /* dataless requests such as discard */ + return rq->bio->bi_iter.bi_size; + return bio_iovec(rq->bio).bv_len; +} + +static inline unsigned int blk_rq_sectors(const struct request *rq) +{ + return blk_rq_bytes(rq) >> SECTOR_SHIFT; +} + +static inline unsigned int blk_rq_cur_sectors(const struct request *rq) +{ + return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; +} + +static inline unsigned int blk_rq_stats_sectors(const struct request *rq) +{ + return rq->stats_sectors; +} + +/* + * Some commands like WRITE SAME have a payload or data transfer size which + * is different from the size of the request. Any driver that supports such + * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to + * calculate the data transfer size. + */ +static inline unsigned int blk_rq_payload_bytes(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return rq->special_vec.bv_len; + return blk_rq_bytes(rq); +} + +/* + * Return the first full biovec in the request. The caller needs to check that + * there are any bvecs before calling this helper. + */ +static inline struct bio_vec req_bvec(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return rq->special_vec; + return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); +} + +static inline unsigned int blk_rq_count_bios(struct request *rq) +{ + unsigned int nr_bios = 0; + struct bio *bio; + + __rq_for_each_bio(bio, rq) + nr_bios++; + + return nr_bios; +} + +void blk_steal_bios(struct bio_list *list, struct request *rq); + +/* + * Request completion related functions. + * + * blk_update_request() completes given number of bytes and updates + * the request without completing it. + */ +bool blk_update_request(struct request *rq, blk_status_t error, + unsigned int nr_bytes); +void blk_abort_request(struct request *); + +/* + * Number of physical segments as sent to the device. + * + * Normally this is the number of discontiguous data segments sent by the + * submitter. But for data-less command like discard we might have no + * actual data segments submitted, but the driver might have to add it's + * own special payload. In that case we still return 1 here so that this + * special payload will be mapped. + */ +static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return 1; + return rq->nr_phys_segments; +} + +/* + * Number of discard segments (or ranges) the driver needs to fill in. + * Each discard bio merged into a request is counted as one segment. + */ +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 disk_zone_no(rq->q->disk, blk_rq_pos(rq)); +} + +static inline unsigned int blk_rq_zone_is_seq(struct request *rq) +{ + return disk_zone_is_seq(rq->q->disk, 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) +{ + return rq->q->disk->seq_zones_wlock && + test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock); +} + +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; +} + +static inline void blk_req_zone_write_lock(struct request *rq) +{ +} + +static inline void blk_req_zone_write_unlock(struct request *rq) +{ +} +static inline bool blk_req_zone_is_write_locked(struct request *rq) +{ + return false; +} + +static inline bool blk_req_can_dispatch_to_zone(struct request *rq) +{ + return true; +} +#endif /* CONFIG_BLK_DEV_ZONED */ + +#endif /* BLK_MQ_H */ |