path: root/include/linux/blk-mq.h

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BLK_MQ_H
#define BLK_MQ_H

#include <linux/blkdev.h>
#include <linux/sbitmap.h>
#include <linux/srcu.h>
#include <linux/lockdep.h>
#include <linux/scatterlist.h>

struct blk_mq_tags;
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);

/*
 * 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))

/* 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;

	unsigned int 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 gendisk *rq_disk;
	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_ksm_keyslot *crypt_keyslot;
#endif

	unsigned short write_hint;
	unsigned short ioprio;

	enum mq_rq_state state;
	refcount_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;
		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.
	 */
	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;
};

#define req_op(req) \
	((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)

enum blk_eh_timer_return {
	BLK_EH_DONE,		/* drivers has completed the command */
	BLK_EH_RESET_TIMER,	/* reset timer and try again */
};

#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
 */
struct blk_mq_hw_ctx {
	struct {
		/** @lock: Protects the dispatch list. */
		spinlock_t		lock;
		/**
		 * @dispatch: Used for requests that are ready to be
		 * dispatched to the hardware but for some reason (e.g. lack of
		 * resources) could not be sent to the hardware. As soon as the
		 * driver can send new requests, requests at this list will
		 * be sent first for a fairer dispatch.
		 */
		struct list_head	dispatch;
		 /**
		  * @state: BLK_MQ_S_* flags. Defines the state of the hw
		  * queue (active, scheduled to restart, stopped).
		  */
		unsigned long		state;
	} ____cacheline_aligned_in_smp;

	/**
	 * @run_work: Used for scheduling a hardware queue run at a later time.
	 */
	struct delayed_work	run_work;
	/** @cpumask: Map of available CPUs where this hctx can run. */
	cpumask_var_t		cpumask;
	/**
	 * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU
	 * selection from @cpumask.
	 */
	int			next_cpu;
	/**
	 * @next_cpu_batch: Counter of how many works left in the batch before
	 * changing to the next CPU.
	 */
	int			next_cpu_batch;

	/** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */
	unsigned l