blk-mq.c

/*
 * Block multiqueue core code
 *
 * Copyright (C) 2013-2014 Jens Axboe
 * Copyright (C) 2013-2014 Christoph Hellwig
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/kmemleak.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/smp.h>
#include <linux/llist.h>
#include <linux/list_sort.h>
#include <linux/cpu.h>
#include <linux/cache.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/topology.h>
#include <linux/sched/signal.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/prefetch.h>

#include <trace/events/block.h>

#include <linux/blk-mq.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-mq-tag.h"
#include "blk-stat.h"
#include "blk-wbt.h"
#include "blk-mq-sched.h"

static DEFINE_MUTEX(all_q_mutex);
static LIST_HEAD(all_q_list);

static void blk_mq_poll_stats_start(struct request_queue *q);
static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);

static int blk_mq_poll_stats_bkt(const struct request *rq)
{
	int ddir, bytes, bucket;

	ddir = rq_data_dir(rq);
	bytes = blk_rq_bytes(rq);

	bucket = ddir + 2*(ilog2(bytes) - 9);

	if (bucket < 0)
		return -1;
	else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
		return ddir + BLK_MQ_POLL_STATS_BKTS - 2;

	return bucket;
}

/*
 * Check if any of the ctx's have pending work in this hardware queue
 */
bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
	return sbitmap_any_bit_set(&hctx->ctx_map) ||
			!list_empty_careful(&hctx->dispatch) ||
			blk_mq_sched_has_work(hctx);
}

/*
 * Mark this ctx as having pending work in this hardware queue
 */
static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
				     struct blk_mq_ctx *ctx)
{
	if (!sbitmap_test_bit(&hctx->ctx_map, ctx->index_hw))
		sbitmap_set_bit(&hctx->ctx_map, ctx->index_hw);
}

static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
				      struct blk_mq_ctx *ctx)
{
	sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);
}

void blk_freeze_queue_start(struct request_queue *q)
{
	int freeze_depth;

	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
	if (freeze_depth == 1) {
		percpu_ref_kill(&q->q_usage_counter);
		blk_mq_run_hw_queues(q, false);
	}
}
EXPORT_SYMBOL_GPL(blk_freeze_queue_start);

void blk_mq_freeze_queue_wait(struct request_queue *q)
{
	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait);

int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
				     unsigned long timeout)
{
	return wait_event_timeout(q->mq_freeze_wq,
					percpu_ref_is_zero(&q->q_usage_counter),
					timeout);
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);

/*
 * Guarantee no request is in use, so we can change any data structure of
 * the queue afterward.
 */
void blk_freeze_queue(struct request_queue *q)
{
	/*
	 * In the !blk_mq case we are only calling this to kill the
	 * q_usage_counter, otherwise this increases the freeze depth
	 * and waits for it to return to zero.  For this reason there is
	 * no blk_unfreeze_queue(), and blk_freeze_queue() is not
	 * exported to drivers as the only user for unfreeze is blk_mq.
	 */
	blk_freeze_queue_start(q);
	blk_mq_freeze_queue_wait(q);
}

void blk_mq_freeze_queue(struct request_queue *q)
{
	/*
	 * ...just an alias to keep freeze and unfreeze actions balanced
	 * in the blk_mq_* namespace
	 */
	blk_freeze_queue(q);
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);

void blk_mq_unfreeze_queue(struct request_queue *q)
{
	int freeze_depth;

	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
	WARN_ON_ONCE(freeze_depth < 0);
	if (!freeze_depth) {
		percpu_ref_reinit(&q->q_usage_counter);
		wake_up_all(&q->mq_freeze_wq);
	}
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);

/**
 * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
 * @q: request queue.
 *
 * Note: this function does not prevent that the struct request end_io()
 * callback function is invoked. Once this function is returned, we make
 * sure no dispatch can happen until the queue is unquiesced via
 * blk_mq_unquiesce_queue().
 */
void blk_mq_quiesce_queue(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	unsigned int i;
	bool rcu = false;

	blk_mq_quiesce_queue_nowait(q);

	queue_for_each_hw_ctx(q, hctx, i) {
		if (hctx->flags & BLK_MQ_F_BLOCKING)
			synchronize_srcu(hctx->queue_rq_srcu);
		else
			rcu = true;
	}
	if (rcu)
		synchronize_rcu();
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);

/*
 * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
 * @q: request queue.
 *
 * This function recovers queue into the state before quiescing
 * which is done by blk_mq_quiesce_queue.
 */
void blk_mq_unquiesce_queue(struct request_queue *q)
{
	spin_lock_irq(q->queue_lock);
	queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
	spin_unlock_irq(q->queue_lock);

	/* dispatch requests which are inserted during quiescing */
	blk_mq_run_hw_queues(q, true);
}
EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);

void blk_mq_wake_waiters(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	unsigned int i;

	queue_for_each_hw_ctx(q, hctx, i)
		if (blk_mq_hw_queue_mapped(hctx))
			blk_mq_tag_wakeup_all(hctx->tags, true);

	/*
	 * If we are called because the queue has now been marked as
	 * dying, we need to ensure that processes currently waiting on
	 * the queue are notified as well.
	 */
	wake_up_all(&q->mq_freeze_wq);
}

bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
{
	return blk_mq_has_free_tags(hctx->tags);
}
EXPORT_SYMBOL(blk_mq_can_queue);

static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
		unsigned int tag, unsigned int op)
{
	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
	struct request *rq = tags->static_rqs[tag];

	if (data->flags & BLK_MQ_REQ_INTERNAL) {
		rq->tag = -1;
		rq->internal_tag = tag;
	} else {
		if (blk_mq_tag_busy(data->hctx)) {
			rq->rq_flags = RQF_MQ_INFLIGHT;
			atomic_inc(&data->hctx->nr_active);
		}
		rq->tag = tag;
		rq->internal_tag = -1;
		data->hctx->tags->rqs[rq->tag] = rq;
	}

	INIT_LIST_HEAD(&rq->queuelist);
	/* csd/requeue_work/fifo_time is initialized before use */
	rq->q = data->q;
	rq->mq_ctx = data->ctx;
	rq->cmd_flags = op;
	if (blk_queue_io_stat(data->q))
		rq->rq_flags |= RQF_IO_STAT;
	/* do not touch atomic flags, it needs atomic ops against the timer */
	rq->cpu = -1;
	INIT_HLIST_NODE(&rq->hash);
	RB_CLEAR_NODE(&rq->rb_node);
	rq->rq_disk = NULL;
	rq->part = NULL;
	rq->start_time = jiffies;
#ifdef CONFIG_BLK_CGROUP
	rq->rl = NULL;
	set_start_time_ns(rq);
	rq->io_start_time_ns = 0;
#endif
	rq->nr_phys_segments = 0;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
	rq->nr_integrity_segments = 0;
#endif
	rq->special = NULL;
	/* tag was already set */
	rq->extra_len = 0;

	INIT_LIST_HEAD(&rq->timeout_list);
	rq->timeout = 0;

	rq->end_io = NULL;
	rq->end_io_data = NULL;
	rq->next_rq = NULL;

	data->ctx->rq_dispatched[op_is_sync(op)]++;
	return rq;
}

static struct request *blk_mq_get_request(struct request_queue *q,
		struct bio *bio, unsigned int op,
		struct blk_mq_alloc_data *data)
{
	struct elevator_queue *e = q->elevator;
	struct request *rq;
	unsigned int tag;

	blk_queue_enter_live(q);
	data->q = q;
	if (likely(!data->ctx))
		data->ctx = blk_mq_get_ctx(q);
	if (likely(!data->hctx))
		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
	if (op & REQ_NOWAIT)
		data->flags |= BLK_MQ_REQ_NOWAIT;

	if (e) {
		data->flags |= BLK_MQ_REQ_INTERNAL;

		/*
		 * Flush requests are special and go directly to the
		 * dispatch list.
		 */
		if (!op_is_flush(op) && e->type->ops.mq.limit_depth)
			e->type->ops.mq.limit_depth(op, data);
	}

	tag = blk_mq_get_tag(data);
	if (tag == BLK_MQ_TAG_FAIL) {
		blk_queue_exit(q);
		return NULL;
	}

	rq = blk_mq_rq_ctx_init(data, tag, op);
	if (!op_is_flush(op)) {
		rq->elv.icq = NULL;
		if (e && e->type->ops.mq.prepare_request) {
			if (e->type->icq_cache && rq_ioc(bio))
				blk_mq_sched_assign_ioc(rq, bio);

			e->type->ops.mq.prepare_request(rq, bio);
			rq->rq_flags |= RQF_ELVPRIV;
		}
	}
	data->hctx->queued++;
	return rq;
}

struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
		unsigned int flags)
{
	struct blk_mq_alloc_data alloc_data = { .flags = flags };
	struct request *rq;
	int ret;

	ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);
	if (ret)
		return ERR_PTR(ret);

	rq = blk_mq_get_request(q, NULL, op, &alloc_data);

	blk_mq_put_ctx(alloc_data.ctx);
	blk_queue_exit(q);

	if (!rq)
		return ERR_PTR(-EWOULDBLOCK);

	rq->__data_len = 0;
	rq->__sector = (sector_t) -1;
	rq->bio = rq->biotail = NULL;
	return rq;
}
EXPORT_SYMBOL(blk_mq_alloc_request);

struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
		unsigned int op, unsigned int flags, unsigned int hctx_idx)
{
	struct blk_mq_alloc_data alloc_data = { .flags = flags };
	struct request *rq;
	unsigned int cpu;
	int ret;

	/*
	 * If the tag allocator sleeps we could get an allocation for a
	 * different hardware context.  No need to complicate the low level
	 * allocator for this for the rare use case of a command tied to
	 * a specific queue.
	 */
	if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)))
		return ERR_PTR(-EINVAL);

	if (hctx_idx >= q->nr_hw_queues)
		return ERR_PTR(-EIO);

	ret = blk_queue_enter(q, true);
	if (ret)
		return ERR_PTR(ret);

	/*
	 * Check if the hardware context is actually mapped to anything.
	 * If not tell the caller that it should skip this queue.
	 */
	alloc_data.hctx = q->queue_hw_ctx[hctx_idx];
	if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) {
		blk_queue_exit(q);
		return ERR_PTR(-EXDEV);
	}
	cpu = cpumask_first(alloc_data.hctx->cpumask);
	alloc_data.ctx = __blk_mq_get_ctx(q, cpu);

	rq = blk_mq_get_request(q, NULL, op, &alloc_data);

	blk_queue_exit(q);

	if (!rq)
		return ERR_PTR(-EWOULDBLOCK);

	return rq;
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);

void blk_mq_free_request(struct request *rq)
{
	struct request_queue *q = rq->q;
	struct elevator_queue *e = q->elevator;
	struct blk_mq_ctx *ctx = rq->mq_ctx;
	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
	const int sched_tag = rq->internal_tag;

	if (rq->rq_flags & RQF_ELVPRIV) {
		if (e && e->type->ops.mq.finish_request)
			e->type->ops.mq.finish_request(rq);
		if (rq->elv.icq) {
			put_io_context(rq->elv.icq->ioc);
			rq->elv.icq = NULL;
		}
	}

	ctx->rq_completed[rq_is_sync(rq)]++;
	if (rq->rq_flags & RQF_MQ_INFLIGHT)
		atomic_dec(&hctx->nr_active);

	wbt_done(q->rq_wb, &rq->issue_stat);
	rq->rq_flags = 0;

	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
	clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
	if (rq->tag != -1)
		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
	if (sched_tag != -1)
		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
	blk_mq_sched_restart(hctx);
	blk_queue_exit(q);
}
EXPORT_SYMBOL_GPL(blk_mq_free_request);

inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
{
	blk_account_io_done(rq);

	if (rq->end_io) {
		wbt_done(rq->q->rq_wb, &rq->issue_stat);
		rq->end_io(rq, error);
	} else {
		if (unlikely(blk_bidi_rq(rq)))
			blk_mq_free_request(rq->next_rq);
		blk_mq_free_request(rq);
	}
}
EXPORT_SYMBOL(__blk_mq_end_request);

void blk_mq_end_request(struct request *rq, blk_status_t error)
{
	if (blk_update_request(rq, error, blk_rq_bytes(rq)))
		BUG();
	__blk_mq_end_request(rq, error);
}
EXPORT_SYMBOL(blk_mq_end_request);

static void __blk_mq_complete_request_remote(void *data)
{
	struct request *rq = data;

	rq->q->softirq_done_fn(rq);
}

static void __blk_mq_complete_request(struct request *rq)
{
	struct blk_mq_ctx *ctx = rq->mq_ctx;
	bool shared = false;
	int cpu;

	if (rq->internal_tag != -1)
		blk_mq_sched_completed_request(rq);
	if (rq->rq_flags & RQF_STATS) {
		blk_mq_poll_stats_start(rq->q);
		blk_stat_add(rq);
	}

	if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
		rq->q->softirq_done_fn(rq);
		return;
	}

	cpu = get_cpu();
	if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags))
		shared = cpus_share_cache(cpu, ctx->cpu);

	if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
		rq->csd.func = __blk_mq_complete_request_remote;
		rq->csd.info = rq;
		rq->csd.flags = 0;
		smp_call_function_single_async(ctx->cpu, &rq->csd);
	} else {
		rq->q->softirq_done_fn(rq);
	}
	put_cpu();
}

/**
 * blk_mq_complete_request - end I/O on a request
 * @rq:		the request being processed
 *
 * Description:
 *	Ends all I/O on a request. It does not handle partial completions.
 *	The actual completion happens out-of-order, through a IPI handler.
 **/
void blk_mq_complete_request(struct request *rq)
{
	struct request_queue *q = rq->q;

	if (unlikely(blk_should_fake_timeout(q)))
		return;
	if (!blk_mark_rq_complete(rq))
		__blk_mq_complete_request(rq);
}
EXPORT_SYMBOL(blk_mq_complete_request);

int blk_mq_request_started(struct request *rq)
{
	return test_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
}
EXPORT_SYMBOL_GPL(blk_mq_request_started);

void blk_mq_start_request(struct request *rq)
{
	struct request_queue *q = rq->q;

	blk_mq_sched_started_request(rq);

	trace_block_rq_issue(q, rq);

	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
		blk_stat_set_issue(&rq->issue_stat, blk_rq_sectors(rq));
		rq->rq_flags |= RQF_STATS;
		wbt_issue(q->rq_wb, &rq->issue_stat);
	}

	blk_add_timer(rq);

	/*
	 * Ensure that ->deadline is visible before set the started
	 * flag and clear the completed flag.
	 */
	smp_mb__before_atomic();

	/*
	 * Mark us as started and clear complete. Complete might have been
	 * set if requeue raced with timeout, which then marked it as
	 * complete. So be sure to clear complete again when we start
	 * the request, otherwise we'll ignore the completion event.
	 */
	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
		set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
	if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags))
		clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);

	if (q->dma_drain_size && blk_rq_bytes(rq)) {
		/*
		 * Make sure space for the drain appears.  We know we can do
		 * this because max_hw_segments has been adjusted to be one
		 * fewer than the device can handle.
		 */
		rq->nr_phys_segments++;
	}
}
EXPORT_SYMBOL(blk_mq_start_request);

/*
 * When we reach here because queue is busy, REQ_ATOM_COMPLETE
 * flag isn't set yet, so there may be race with timeout handler,
 * but given rq->deadline is just set in .queue_rq() under
 * this situation, the race won't be possible in reality because
 * rq->timeout should be set as big enough to cover the window
 * between blk_mq_start_request() called from .queue_rq() and
 * clearing REQ_ATOM_STARTED here.
 */
static void __blk_mq_requeue_request(struct request *rq)
{
	struct request_queue *q = rq->q;

	trace_block_rq_requeue(q, rq);
	wbt_requeue(q->rq_wb, &rq->issue_stat);
	blk_mq_sched_requeue_request(rq);

	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
		if (q->dma_drain_size && blk_rq_bytes(rq))
			rq->nr_phys_segments--;
	}
}

void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
{
	__blk_mq_requeue_request(rq);

	BUG_ON(blk_queued_rq(rq));
	blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
}
EXPORT_SYMBOL(blk_mq_requeue_request);

static void blk_mq_requeue_work(struct work_struct *work)
{
	struct request_queue *q =
		container_of(work, struct request_queue, requeue_work.work);
	LIST_HEAD(rq_list);
	struct request *rq, *next;
	unsigned long flags;

	spin_lock_irqsave(&q->requeue_lock, flags);
	list_splice_init(&q->requeue_list, &rq_list);
	spin_unlock_irqrestore(&q->requeue_lock, flags);

	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
		if (!(rq->rq_flags & RQF_SOFTBARRIER))
			continue;

		rq->rq_flags &= ~RQF_SOFTBARRIER;
		list_del_init(&rq->queuelist);
		blk_mq_sched_insert_request(rq, true, false, false, true);
	}

	while (!list_empty(&rq_list)) {
		rq = list_entry(rq_list.next, struct request, queuelist);
		list_del_init(&rq->queuelist);
		blk_mq_sched_insert_request(rq, false, false, false, true);
	}

	blk_mq_run_hw_queues(q, false);
}

void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
				bool kick_requeue_list)
{
	struct request_queue *q = rq->q;
	unsigned long flags;

	/*
	 * We abuse this flag that is otherwise used by the I/O scheduler to
	 * request head insertation from the workqueue.
	 */
	BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);

	spin_lock_irqsave(&q->requeue_lock, flags);
	if (at_head) {
		rq->rq_flags |= RQF_SOFTBARRIER;
		list_add(&rq->queuelist, &q->requeue_list);
	} else {
		list_add_tail(&rq->queuelist, &q->requeue_list);
	}
	spin_unlock_irqrestore(&q->requeue_lock, flags);

	if (kick_requeue_list)
		blk_mq_kick_requeue_list(q);
}
EXPORT_SYMBOL(blk_mq_add_to_requeue_list);

void blk_mq_kick_requeue_list(struct request_queue *q)
{
	kblockd_schedule_delayed_work(&q->requeue_work, 0);
}
EXPORT_SYMBOL(blk_mq_kick_requeue_list);

void blk_mq_delay_kick_requeue_list(struct request_queue *q,
				    unsigned long msecs)
{
	kblockd_schedule_delayed_work(&q->requeue_work,
				      msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);

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;
}
EXPORT_SYMBOL(blk_mq_tag_to_rq);

struct blk_mq_timeout_data {
	unsigned long next;
	unsigned int next_set;
};

void blk_mq_rq_timed_out(struct request *req, bool reserved)
{
	const struct blk_mq_ops *ops = req->q->mq_ops;
	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;

	/*
	 * We know that complete is set at this point. If STARTED isn't set
	 * anymore, then the request isn't active and the "timeout" should
	 * just be ignored. This can happen due to the bitflag ordering.
	 * Timeout first checks if STARTED is set, and if it is, assumes
	 * the request is active. But if we race with completion, then
	 * both flags will get cleared. So check here again, and ignore
	 * a timeout event with a request that isn't active.
	 */
	if (!test_bit(REQ_ATOM_STARTED, &req->atomic_flags))
		return;

	if (ops->timeout)
		ret = ops->timeout(req, reserved);

	switch (ret) {
	case BLK_EH_HANDLED:
		__blk_mq_complete_request(req);
		break;
	case BLK_EH_RESET_TIMER:
		blk_add_timer(req);
		blk_clear_rq_complete(req);
		break;
	case BLK_EH_NOT_HANDLED:
		break;
	default:
		printk(KERN_ERR "block: bad eh return: %d\n", ret);
		break;
	}
}

static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
		struct request *rq, void *priv, bool reserved)
{
	struct blk_mq_timeout_data *data = priv;

	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
		return;

	/*
	 * The rq being checked may have been freed and reallocated
	 * out already here, we avoid this race by checking rq->deadline
	 * and REQ_ATOM_COMPLETE flag together:
	 *
	 * - if rq->deadline is observed as new value because of
	 *   reusing, the rq won't be timed out because of timing.
	 * - if rq->deadline is observed as previous value,
	 *   REQ_ATOM_COMPLETE flag won't be cleared in reuse path
	 *   because we put a barrier between setting rq->deadline
	 *   and clearing the flag in blk_mq_start_request(), so
	 *   this rq won't be timed out too.
	 */
	if (time_after_eq(jiffies, rq->deadline)) {
		if (!blk_mark_rq_complete(rq))
			blk_mq_rq_timed_out(rq, reserved);
	} else if (!data->next_set || time_after(data->next, rq->deadline)) {
		data->next = rq->deadline;
		data->next_set = 1;
	}
}

static void blk_mq_timeout_work(struct work_struct *work)
{
	struct request_queue *q =
		container_of(work, struct request_queue, timeout_work);
	struct blk_mq_timeout_data data = {
		.next		= 0,
		.next_set	= 0,
	};
	int i;

	/* A deadlock might occur if a request is stuck requiring a
	 * timeout at the same time a queue freeze is waiting
	 * completion, since the timeout code would not be able to
	 * acquire the queue reference here.
	 *
	 * That's why we don't use blk_queue_enter here; instead, we use
	 * percpu_ref_tryget directly, because we need to be able to
	 * obtain a reference even in the short window between the queue
	 * starting to freeze, by dropping the first reference in
	 * blk_freeze_queue_start, and the moment the last request is
	 * consumed, marked by the instant q_usage_counter reaches
	 * zero.
	 */
	if (!percpu_ref_tryget(&q->q_usage_counter))
		return;

	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);

	if (data.next_set) {
		data.next = blk_rq_timeout(round_jiffies_up(data.next));
		mod_timer(&q->timeout, data.next);
	} else {
		struct blk_mq_hw_ctx *hctx;

		queue_for_each_hw_ctx(q, hctx, i) {
			/* the hctx may be unmapped, so check it here */
			if (blk_mq_hw_queue_mapped(hctx))
				blk_mq_tag_idle(hctx);
		}
	}
	blk_queue_exit(q);
}

struct flush_busy_ctx_data {
	struct blk_mq_hw_ctx *hctx;
	struct list_head *list;
};

static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
{
	struct flush_busy_ctx_data *flush_data = data;
	struct blk_mq_hw_ctx *hctx = flush_data->hctx;
	struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];

	sbitmap_clear_bit(sb, bitnr);
	spin_lock(&ctx->lock);
	list_splice_tail_init(&ctx->rq_list, flush_data->list);
	spin_unlock(&ctx->lock);
	return true;
}

/*
 * Process software queues that have been marked busy, splicing them
 * to the for-dispatch
 */
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
{
	struct flush_busy_ctx_data data = {
		.hctx = hctx,
		.list = list,
	};

	sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data);
}
EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs);

static inline unsigned int queued_to_index(unsigned int queued)
{
	if (!queued)
		return 0;

	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
}

bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
			   bool wait)
{
	struct blk_mq_alloc_data data = {
		.q = rq->q,
		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
	};

	might_sleep_if(wait);

	if (rq->tag != -1)
		goto done;

	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
		data.flags |= BLK_MQ_REQ_RESERVED;

	rq->tag = blk_mq_get_tag(&data);
	if (rq->tag >= 0) {
		if (blk_mq_tag_busy(data.hctx)) {
			rq->rq_flags |= RQF_MQ_INFLIGHT;
			atomic_inc(&data.hctx->nr_active);
		}
		data.hctx->tags->rqs[rq->tag] = rq;
	}

done:
	if (hctx)
		*hctx = data.hctx;
	return rq->tag != -1;
}

static void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
				    struct request *rq)
{
	blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
	rq->tag = -1;

	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
		atomic_dec(&hctx->nr_active);
	}
}

static void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
				       struct request *rq)
{
	if (rq->tag == -1 || rq->internal_tag == -1)
		return;

	__blk_mq_put_driver_tag(hctx, rq);
}

static void blk_mq_put_driver_tag(struct request *rq)
{
	struct blk_mq_hw_ctx *hctx;

	if (rq->tag == -1 || rq->internal_tag == -1)
		return;

	hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
	__blk_mq_put_driver_tag(hctx, rq);
}

/*
 * If we fail getting a driver tag because all the driver tags are already
 * assigned and on the dispatch list, BUT the first entry does not have a
 * tag, then we could deadlock. For that case, move entries with assigned
 * driver tags to the front, leaving the set of tagged requests in the
 * same order, and the untagged set in the same order.
 */
static bool reorder_tags_to_front(struct list_head *list)
{
	struct request *rq, *tmp, *first = NULL;

	list_for_each_entry_safe_reverse(rq, tmp, list, queuelist) {
		if (rq == first)
			break;
		if (rq->tag != -1) {
			list_move(&rq->queuelist, list);
			if (!first)
				first = rq;
		}
	}

	return first != NULL;
}

static int blk_mq_dispatch_wake(wait_queue_t *wait, unsigned mode, int flags,
				void *key)
{
	struct blk_mq_hw_ctx *hctx;

	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);

	list_del(&wait->task_list);
	clear_bit_unlock(BLK_MQ_S_TAG_WAITING, &hctx->state);
	blk_mq_run_hw_queue(hctx, true);
	return 1;
}

static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx *hctx)
{
	struct sbq_wait_state *ws;

	/*
	 * The TAG_WAITING bit serves as a lock protecting hctx->dispatch_wait.
	 * The thread which wins the race to grab this bit adds the hardware
	 * queue to the wait queue.
	 */
	if (test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state) ||
	    test_and_set_bit_lock(BLK_MQ_S_TAG_WAITING, &hctx->state))
		return false;

	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
	ws = bt_wait_ptr(&hctx->tags->bitmap_tags, hctx);

	/*
	 * As soon as this returns, it's no longer safe to fiddle with
	 * hctx->dispatch_wait, since a completion can wake up the wait queue
	 * and unlock the bit.
	 */
	add_wait_queue(&ws->wait, &hctx->dispatch_wait);
	return true;
}

bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
{
	struct blk_mq_hw_ctx *hctx;
	struct request *rq;
	int errors, queued;

	if (list_empty(list))
		return false;

	/*
	 * Now process all the entries, sending them to the driver.
	 */
	errors = queued = 0;
	do {
		struct blk_mq_queue_data bd;
		blk_status_t ret;

		rq = list_first_entry(list, struct request, queuelist);
		if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
			if (!queued && reorder_tags_to_front(list))
				continue;

			/*
			 * The initial allocation attempt failed, so we need to
			 * rerun the hardware queue when a tag is freed.
			 */
			if (!blk_mq_dispatch_wait_add(hctx))
				break;

			/*
			 * It's possible that a tag was freed in the window
			 * between the allocation failure and adding the
			 * hardware queue to the wait queue.
			 */
			if (!blk_mq_get_driver_tag(rq, &hctx, false))
				break;