blk-mq.c

	 * 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, &next);

	if (next != 0) {
		mod_timer(&q->timeout, next);
	} else {
		/*
		 * Request timeouts are handled as a forward rolling timer. If
		 * we end up here it means that no requests are pending and
		 * also that no request has been pending for a while. Mark
		 * each hctx as idle.
		 */
		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];
	enum hctx_type type = hctx->type;

	spin_lock(&ctx->lock);
	list_splice_tail_init(&ctx->rq_lists[type], flush_data->list);
	sbitmap_clear_bit(sb, bitnr);
	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);

struct dispatch_rq_data {
	struct blk_mq_hw_ctx *hctx;
	struct request *rq;
};

static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr,
		void *data)
{
	struct dispatch_rq_data *dispatch_data = data;
	struct blk_mq_hw_ctx *hctx = dispatch_data->hctx;
	struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
	enum hctx_type type = hctx->type;

	spin_lock(&ctx->lock);
	if (!list_empty(&ctx->rq_lists[type])) {
		dispatch_data->rq = list_entry_rq(ctx->rq_lists[type].next);
		list_del_init(&dispatch_data->rq->queuelist);
		if (list_empty(&ctx->rq_lists[type]))
			sbitmap_clear_bit(sb, bitnr);
	}
	spin_unlock(&ctx->lock);

	return !dispatch_data->rq;
}

struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
					struct blk_mq_ctx *start)
{
	unsigned off = start ? start->index_hw[hctx->type] : 0;
	struct dispatch_rq_data data = {
		.hctx = hctx,
		.rq   = NULL,
	};

	__sbitmap_for_each_set(&hctx->ctx_map, off,
			       dispatch_rq_from_ctx, &data);

	return data.rq;
}

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);
}

static bool __blk_mq_get_driver_tag(struct request *rq)
{
	struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
	unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
	int tag;

	blk_mq_tag_busy(rq->mq_hctx);

	if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
		bt = &rq->mq_hctx->tags->breserved_tags;
		tag_offset = 0;
	} else {
		if (!hctx_may_queue(rq->mq_hctx, bt))
			return false;
	}

	tag = __sbitmap_queue_get(bt);
	if (tag == BLK_MQ_NO_TAG)
		return false;

	rq->tag = tag + tag_offset;
	return true;
}

bool blk_mq_get_driver_tag(struct request *rq)
{
	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;

	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
		return false;

	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
		rq->rq_flags |= RQF_MQ_INFLIGHT;
		__blk_mq_inc_active_requests(hctx);
	}
	hctx->tags->rqs[rq->tag] = rq;
	return true;
}

static int blk_mq_dispatch_wake(wait_queue_entry_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);

	spin_lock(&hctx->dispatch_wait_lock);
	if (!list_empty(&wait->entry)) {
		struct sbitmap_queue *sbq;

		list_del_init(&wait->entry);
		sbq = &hctx->tags->bitmap_tags;
		atomic_dec(&sbq->ws_active);
	}
	spin_unlock(&hctx->dispatch_wait_lock);

	blk_mq_run_hw_queue(hctx, true);
	return 1;
}

/*
 * Mark us waiting for a tag. For shared tags, this involves hooking us into
 * the tag wakeups. For non-shared tags, we can simply mark us needing a
 * restart. For both cases, take care to check the condition again after
 * marking us as waiting.
 */
static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
				 struct request *rq)
{
	struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags;
	struct wait_queue_head *wq;
	wait_queue_entry_t *wait;
	bool ret;

	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
		blk_mq_sched_mark_restart_hctx(hctx);

		/*
		 * It's possible that a tag was freed in the window between the
		 * allocation failure and adding the hardware queue to the wait
		 * queue.
		 *
		 * Don't clear RESTART here, someone else could have set it.
		 * At most this will cost an extra queue run.
		 */
		return blk_mq_get_driver_tag(rq);
	}

	wait = &hctx->dispatch_wait;
	if (!list_empty_careful(&wait->entry))
		return false;

	wq = &bt_wait_ptr(sbq, hctx)->wait;

	spin_lock_irq(&wq->lock);
	spin_lock(&hctx->dispatch_wait_lock);
	if (!list_empty(&wait->entry)) {
		spin_unlock(&hctx->dispatch_wait_lock);
		spin_unlock_irq(&wq->lock);
		return false;
	}

	atomic_inc(&sbq->ws_active);
	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
	__add_wait_queue(wq, wait);

	/*
	 * It's possible that a tag was freed in the window between the
	 * allocation failure and adding the hardware queue to the wait
	 * queue.
	 */
	ret = blk_mq_get_driver_tag(rq);
	if (!ret) {
		spin_unlock(&hctx->dispatch_wait_lock);
		spin_unlock_irq(&wq->lock);
		return false;
	}

	/*
	 * We got a tag, remove ourselves from the wait queue to ensure
	 * someone else gets the wakeup.
	 */
	list_del_init(&wait->entry);
	atomic_dec(&sbq->ws_active);
	spin_unlock(&hctx->dispatch_wait_lock);
	spin_unlock_irq(&wq->lock);

	return true;
}

#define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT  8
#define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR  4
/*
 * Update dispatch busy with the Exponential Weighted Moving Average(EWMA):
 * - EWMA is one simple way to compute running average value
 * - weight(7/8 and 1/8) is applied so that it can decrease exponentially
 * - take 4 as factor for avoiding to get too small(0) result, and this
 *   factor doesn't matter because EWMA decreases exponentially
 */
static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
{
	unsigned int ewma;

	ewma = hctx->dispatch_busy;

	if (!ewma && !busy)
		return;

	ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1;
	if (busy)
		ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR;
	ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT;

	hctx->dispatch_busy = ewma;
}

#define BLK_MQ_RESOURCE_DELAY	3		/* ms units */

static void blk_mq_handle_dev_resource(struct request *rq,
				       struct list_head *list)
{
	struct request *next =
		list_first_entry_or_null(list, struct request, queuelist);

	/*
	 * If an I/O scheduler has been configured and we got a driver tag for
	 * the next request already, free it.
	 */
	if (next)
		blk_mq_put_driver_tag(next);

	list_add(&rq->queuelist, list);
	__blk_mq_requeue_request(rq);
}

static void blk_mq_handle_zone_resource(struct request *rq,
					struct list_head *zone_list)
{
	/*
	 * If we end up here it is because we cannot dispatch a request to a
	 * specific zone due to LLD level zone-write locking or other zone
	 * related resource not being available. In this case, set the request
	 * aside in zone_list for retrying it later.
	 */
	list_add(&rq->queuelist, zone_list);
	__blk_mq_requeue_request(rq);
}

enum prep_dispatch {
	PREP_DISPATCH_OK,
	PREP_DISPATCH_NO_TAG,
	PREP_DISPATCH_NO_BUDGET,
};

static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq,
						  bool need_budget)
{
	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
	int budget_token = -1;

	if (need_budget) {
		budget_token = blk_mq_get_dispatch_budget(rq->q);
		if (budget_token < 0) {
			blk_mq_put_driver_tag(rq);
			return PREP_DISPATCH_NO_BUDGET;
		}
		blk_mq_set_rq_budget_token(rq, budget_token);
	}

	if (!blk_mq_get_driver_tag(rq)) {
		/*
		 * The initial allocation attempt failed, so we need to
		 * rerun the hardware queue when a tag is freed. The
		 * waitqueue takes care of that. If the queue is run
		 * before we add this entry back on the dispatch list,
		 * we'll re-run it below.
		 */
		if (!blk_mq_mark_tag_wait(hctx, rq)) {
			/*
			 * All budgets not got from this function will be put
			 * together during handling partial dispatch
			 */
			if (need_budget)
				blk_mq_put_dispatch_budget(rq->q, budget_token);
			return PREP_DISPATCH_NO_TAG;
		}
	}

	return PREP_DISPATCH_OK;
}

/* release all allocated budgets before calling to blk_mq_dispatch_rq_list */
static void blk_mq_release_budgets(struct request_queue *q,
		struct list_head *list)
{
	struct request *rq;

	list_for_each_entry(rq, list, queuelist) {
		int budget_token = blk_mq_get_rq_budget_token(rq);

		if (budget_token >= 0)
			blk_mq_put_dispatch_budget(q, budget_token);
	}
}

/*
 * Returns true if we did some work AND can potentially do more.
 */
bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
			     unsigned int nr_budgets)
{
	enum prep_dispatch prep;
	struct request_queue *q = hctx->queue;
	struct request *rq, *nxt;
	int errors, queued;
	blk_status_t ret = BLK_STS_OK;
	LIST_HEAD(zone_list);

	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;

		rq = list_first_entry(list, struct request, queuelist);

		WARN_ON_ONCE(hctx != rq->mq_hctx);
		prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets);
		if (prep != PREP_DISPATCH_OK)
			break;

		list_del_init(&rq->queuelist);

		bd.rq = rq;

		/*
		 * Flag last if we have no more requests, or if we have more
		 * but can't assign a driver tag to it.
		 */
		if (list_empty(list))
			bd.last = true;
		else {
			nxt = list_first_entry(list, struct request, queuelist);
			bd.last = !blk_mq_get_driver_tag(nxt);
		}

		/*
		 * once the request is queued to lld, no need to cover the
		 * budget any more
		 */
		if (nr_budgets)
			nr_budgets--;
		ret = q->mq_ops->queue_rq(hctx, &bd);
		switch (ret) {
		case BLK_STS_OK:
			queued++;
			break;
		case BLK_STS_RESOURCE:
		case BLK_STS_DEV_RESOURCE:
			blk_mq_handle_dev_resource(rq, list);
			goto out;
		case BLK_STS_ZONE_RESOURCE:
			/*
			 * Move the request to zone_list and keep going through
			 * the dispatch list to find more requests the drive can
			 * accept.
			 */
			blk_mq_handle_zone_resource(rq, &zone_list);
			break;
		default:
			errors++;
			blk_mq_end_request(rq, ret);
		}
	} while (!list_empty(list));
out:
	if (!list_empty(&zone_list))
		list_splice_tail_init(&zone_list, list);

	hctx->dispatched[queued_to_index(queued)]++;

	/* If we didn't flush the entire list, we could have told the driver
	 * there was more coming, but that turned out to be a lie.
	 */
	if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued)
		q->mq_ops->commit_rqs(hctx);
	/*
	 * Any items that need requeuing? Stuff them into hctx->dispatch,
	 * that is where we will continue on next queue run.
	 */
	if (!list_empty(list)) {
		bool needs_restart;
		/* For non-shared tags, the RESTART check will suffice */
		bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
			(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
		bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;

		if (nr_budgets)
			blk_mq_release_budgets(q, list);

		spin_lock(&hctx->lock);
		list_splice_tail_init(list, &hctx->dispatch);
		spin_unlock(&hctx->lock);

		/*
		 * Order adding requests to hctx->dispatch and checking
		 * SCHED_RESTART flag. The pair of this smp_mb() is the one
		 * in blk_mq_sched_restart(). Avoid restart code path to
		 * miss the new added requests to hctx->dispatch, meantime
		 * SCHED_RESTART is observed here.
		 */
		smp_mb();

		/*
		 * If SCHED_RESTART was set by the caller of this function and
		 * it is no longer set that means that it was cleared by another
		 * thread and hence that a queue rerun is needed.
		 *
		 * If 'no_tag' is set, that means that we failed getting
		 * a driver tag with an I/O scheduler attached. If our dispatch
		 * waitqueue is no longer active, ensure that we run the queue
		 * AFTER adding our entries back to the list.
		 *
		 * If no I/O scheduler has been configured it is possible that
		 * the hardware queue got stopped and restarted before requests
		 * were pushed back onto the dispatch list. Rerun the queue to
		 * avoid starvation. Notes:
		 * - blk_mq_run_hw_queue() checks whether or not a queue has
		 *   been stopped before rerunning a queue.
		 * - Some but not all block drivers stop a queue before
		 *   returning BLK_STS_RESOURCE. Two exceptions are scsi-mq
		 *   and dm-rq.
		 *
		 * If driver returns BLK_STS_RESOURCE and SCHED_RESTART
		 * bit is set, run queue after a delay to avoid IO stalls
		 * that could otherwise occur if the queue is idle.  We'll do
		 * similar if we couldn't get budget and SCHED_RESTART is set.
		 */
		needs_restart = blk_mq_sched_needs_restart(hctx);
		if (!needs_restart ||
		    (no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
			blk_mq_run_hw_queue(hctx, true);
		else if (needs_restart && (ret == BLK_STS_RESOURCE ||
					   no_budget_avail))
			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);

		blk_mq_update_dispatch_busy(hctx, true);
		return false;
	} else
		blk_mq_update_dispatch_busy(hctx, false);

	return (queued + errors) != 0;
}

/**
 * __blk_mq_run_hw_queue - Run a hardware queue.
 * @hctx: Pointer to the hardware queue to run.
 *
 * Send pending requests to the hardware.
 */
static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
{
	int srcu_idx;

	/*
	 * We can't run the queue inline with ints disabled. Ensure that
	 * we catch bad users of this early.
	 */
	WARN_ON_ONCE(in_interrupt());

	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);

	hctx_lock(hctx, &srcu_idx);
	blk_mq_sched_dispatch_requests(hctx);
	hctx_unlock(hctx, srcu_idx);
}

static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
{
	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);

	if (cpu >= nr_cpu_ids)
		cpu = cpumask_first(hctx->cpumask);
	return cpu;
}

/*
 * It'd be great if the workqueue API had a way to pass
 * in a mask and had some smarts for more clever placement.
 * For now we just round-robin here, switching for every
 * BLK_MQ_CPU_WORK_BATCH queued items.
 */
static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
{
	bool tried = false;
	int next_cpu = hctx->next_cpu;

	if (hctx->queue->nr_hw_queues == 1)
		return WORK_CPU_UNBOUND;

	if (--hctx->next_cpu_batch <= 0) {
select_cpu:
		next_cpu = cpumask_next_and(next_cpu, hctx->cpumask,
				cpu_online_mask);
		if (next_cpu >= nr_cpu_ids)
			next_cpu = blk_mq_first_mapped_cpu(hctx);
		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
	}

	/*
	 * Do unbound schedule if we can't find a online CPU for this hctx,
	 * and it should only happen in the path of handling CPU DEAD.
	 */
	if (!cpu_online(next_cpu)) {
		if (!tried) {
			tried = true;
			goto select_cpu;
		}

		/*
		 * Make sure to re-select CPU next time once after CPUs
		 * in hctx->cpumask become online again.
		 */
		hctx->next_cpu = next_cpu;
		hctx->next_cpu_batch = 1;
		return WORK_CPU_UNBOUND;
	}

	hctx->next_cpu = next_cpu;
	return next_cpu;
}

/**
 * __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue.
 * @hctx: Pointer to the hardware queue to run.
 * @async: If we want to run the queue asynchronously.
 * @msecs: Milliseconds of delay to wait before running the queue.
 *
 * If !@async, try to run the queue now. Else, run the queue asynchronously and
 * with a delay of @msecs.
 */
static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
					unsigned long msecs)
{
	if (unlikely(blk_mq_hctx_stopped(hctx)))
		return;

	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
		int cpu = get_cpu();
		if (cpumask_test_cpu(cpu, hctx->cpumask)) {
			__blk_mq_run_hw_queue(hctx);
			put_cpu();
			return;
		}

		put_cpu();
	}

	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
				    msecs_to_jiffies(msecs));
}

/**
 * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
 * @hctx: Pointer to the hardware queue to run.
 * @msecs: Milliseconds of delay to wait before running the queue.
 *
 * Run a hardware queue asynchronously with a delay of @msecs.
 */
void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
{
	__blk_mq_delay_run_hw_queue(hctx, true, msecs);
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);

/**
 * blk_mq_run_hw_queue - Start to run a hardware queue.
 * @hctx: Pointer to the hardware queue to run.
 * @async: If we want to run the queue asynchronously.
 *
 * Check if the request queue is not in a quiesced state and if there are
 * pending requests to be sent. If this is true, run the queue to send requests
 * to hardware.
 */
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
	int srcu_idx;
	bool need_run;

	/*
	 * When queue is quiesced, we may be switching io scheduler, or
	 * updating nr_hw_queues, or other things, and we can't run queue
	 * any more, even __blk_mq_hctx_has_pending() can't be called safely.
	 *
	 * And queue will be rerun in blk_mq_unquiesce_queue() if it is
	 * quiesced.
	 */
	hctx_lock(hctx, &srcu_idx);
	need_run = !blk_queue_quiesced(hctx->queue) &&
		blk_mq_hctx_has_pending(hctx);
	hctx_unlock(hctx, srcu_idx);

	if (need_run)
		__blk_mq_delay_run_hw_queue(hctx, async, 0);
}
EXPORT_SYMBOL(blk_mq_run_hw_queue);

/*
 * Is the request queue handled by an IO scheduler that does not respect
 * hardware queues when dispatching?
 */
static bool blk_mq_has_sqsched(struct request_queue *q)
{
	struct elevator_queue *e = q->elevator;

	if (e && e->type->ops.dispatch_request &&
	    !(e->type->elevator_features & ELEVATOR_F_MQ_AWARE))
		return true;
	return false;
}

/*
 * Return prefered queue to dispatch from (if any) for non-mq aware IO
 * scheduler.
 */
static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;

	/*
	 * If the IO scheduler does not respect hardware queues when
	 * dispatching, we just don't bother with multiple HW queues and
	 * dispatch from hctx for the current CPU since running multiple queues
	 * just causes lock contention inside the scheduler and pointless cache
	 * bouncing.
	 */
	hctx = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT,
				     raw_smp_processor_id());
	if (!blk_mq_hctx_stopped(hctx))
		return hctx;
	return NULL;
}

/**
 * blk_mq_run_hw_queues - Run all hardware queues in a request queue.
 * @q: Pointer to the request queue to run.
 * @async: If we want to run the queue asynchronously.
 */
void blk_mq_run_hw_queues(struct request_queue *q, bool async)
{
	struct blk_mq_hw_ctx *hctx, *sq_hctx;
	int i;

	sq_hctx = NULL;
	if (blk_mq_has_sqsched(q))
		sq_hctx = blk_mq_get_sq_hctx(q);
	queue_for_each_hw_ctx(q, hctx, i) {
		if (blk_mq_hctx_stopped(hctx))
			continue;
		/*
		 * Dispatch from this hctx either if there's no hctx preferred
		 * by IO scheduler or if it has requests that bypass the
		 * scheduler.
		 */
		if (!sq_hctx || sq_hctx == hctx ||
		    !list_empty_careful(&hctx->dispatch))
			blk_mq_run_hw_queue(hctx, async);
	}
}
EXPORT_SYMBOL(blk_mq_run_hw_queues);

/**
 * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously.
 * @q: Pointer to the request queue to run.
 * @msecs: Milliseconds of delay to wait before running the queues.
 */
void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
{
	struct blk_mq_hw_ctx *hctx, *sq_hctx;
	int i;

	sq_hctx = NULL;
	if (blk_mq_has_sqsched(q))
		sq_hctx = blk_mq_get_sq_hctx(q);
	queue_for_each_hw_ctx(q, hctx, i) {
		if (blk_mq_hctx_stopped(hctx))
			continue;
		/*
		 * Dispatch from this hctx either if there's no hctx preferred
		 * by IO scheduler or if it has requests that bypass the
		 * scheduler.
		 */
		if (!sq_hctx || sq_hctx == hctx ||
		    !list_empty_careful(&hctx->dispatch))
			blk_mq_delay_run_hw_queue(hctx, msecs);
	}
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);

/**
 * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped
 * @q: request queue.
 *
 * The caller is responsible for serializing this function against
 * blk_mq_{start,stop}_hw_queue().
 */
bool blk_mq_queue_stopped(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	int i;

	queue_for_each_hw_ctx(q, hctx, i)
		if (blk_mq_hctx_stopped(hctx))
			return true;

	return false;
}
EXPORT_SYMBOL(blk_mq_queue_stopped);

/*
 * This function is often used for pausing .queue_rq() by driver when
 * there isn't enough resource or some conditions aren't satisfied, and
 * BLK_STS_RESOURCE is usually returned.
 *
 * We do not guarantee that dispatch can be drained or blocked
 * after blk_mq_stop_hw_queue() returns. Please use
 * blk_mq_quiesce_queue() for that requirement.
 */
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
{
	cancel_delayed_work(&hctx->run_work);

	set_bit(BLK_MQ_S_STOPPED, &hctx->state);
}
EXPORT_SYMBOL(blk_mq_stop_hw_queue);

/*
 * This function is often used for pausing .queue_rq() by driver when
 * there isn't enough resource or some conditions aren't satisfied, and
 * BLK_STS_RESOURCE is usually returned.
 *
 * We do not guarantee that dispatch can be drained or blocked
 * after blk_mq_stop_hw_queues() returns. Please use
 * blk_mq_quiesce_queue() for that requirement.
 */
void blk_mq_stop_hw_queues(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	int i;

	queue_for_each_hw_ctx(q, hctx, i)
		blk_mq_stop_hw_queue(hctx);
}
EXPORT_SYMBOL(blk_mq_stop_hw_queues);

void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx)
{
	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);

	blk_mq_run_hw_queue(hctx, false);
}
EXPORT_SYMBOL(blk_mq_start_hw_queue);

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

	queue_for_each_hw_ctx(q, hctx, i)
		blk_mq_start_hw_queue(hctx);
}
EXPORT_SYMBOL(blk_mq_start_hw_queues);

void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
	if (!blk_mq_hctx_stopped(hctx))
		return;

	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
	blk_mq_run_hw_queue(hctx, async);
}
EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue);

void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async)
{
	struct blk_mq_hw_ctx *hctx;
	int i;

	queue_for_each_hw_ctx(q, hctx, i)
		blk_mq_start_stopped_hw_queue(hctx, async);
}
EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);

static void blk_mq_run_work_fn(struct work_struct *work)
{
	struct blk_mq_hw_ctx *hctx;

	hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);

	/*
	 * If we are stopped, don't run the queue.
	 */
	if (blk_mq_hctx_stopped(hctx))
		return;

	__blk_mq_run_hw_queue(hctx);
}

static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
					    struct request *rq,
					    bool at_head)
{
	struct blk_mq_ctx *ctx = rq->mq_ctx;
	enum hctx_type type = hctx->type;

	lockdep_assert_held(&ctx->lock);

	trace_block_rq_insert(rq);

	if (at_head)
		list_add(&rq->queuelist, &ctx->rq_lists[type]);
	else
		list_add_tail(&rq->queuelist, &ctx->rq_lists[type]);
}

void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
			     bool at_head)
{
	struct blk_mq_ctx *ctx = rq->mq_ctx;

	lockdep_assert_held(&ctx->lock);

	__blk_mq_insert_req_list(hctx, rq, at_head);
	blk_mq_hctx_mark_pending(hctx, ctx);
}

/**
 * blk_mq_request_bypass_insert - Insert a request at dispatch list.
 * @rq: Pointer to request to be inserted.
 * @at_head: true if the request should be inserted at the head of the list.
 * @run_queue: If we should run the hardware queue after inserting the request.
 *
 * Should only be used carefully, when the caller knows we want to
 * bypass a potential IO scheduler on the target device.
 */
void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
				  bool run_queue)
{
	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;

	spin_lock(&hctx->lock);
	if (at_head)
		list_add(&rq->queuelist, &hctx->dispatch);
	else
		list_add_tail(&rq->queuelist, &hctx->dispatch);
	spin_unlock(&hctx->lock);

	if (run_queue)
		blk_mq_run_hw_queue(hctx, false);
}

void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
			    struct list_head *list)

{
	struct request *rq;
	enum hctx_type type = hctx->type;

	/*
	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
	 * offline now
	 */
	list_for_each_entry(rq, list, queuelist) {
		BUG_ON(rq->mq_ctx != ctx);
		trace_block_rq_insert(rq);
	}

	spin_lock(&ctx->lock);
	list_splice_tail_init(list, &ctx->rq_lists[type]);
	blk_mq_hctx_mark_pending(hctx, ctx);
	spin_unlock(&ctx->lock);
}

static int plug_rq_cmp(void *priv, const struct list_head *a,
		       const struct list_head *b)
{
	struct request *rqa = container_of(a, struct request, queuelist);
	struct request *rqb = container_of(b, struct request, queuelist);

	if (rqa->mq_ctx != rqb->mq_ctx)
		return rqa->mq_ctx > rqb->mq_ctx;
	if (rqa->mq_hctx != rqb->mq_hctx)
		return rqa->mq_hctx > rqb->mq_hctx;

	return blk_rq_pos(rqa) > blk_rq_pos(rqb);
}

void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
	LIST_HEAD(list);

	if (list_empty(&plug->mq_list))
		return;
	list_splice_init(&plug->mq_list, &list);

	if (plug->rq_count > 2 && plug->multiple_queues)
		list_sort(NULL, &list, plug_rq_cmp);

	plug->rq_count = 0;

	do {
		struct list_head rq_list;
		struct request *rq, *head_rq = list_entry_rq(list.next);
		struct list_head *pos = &head_rq->queuelist; /* skip first */
		struct blk_mq_hw_ctx *this_hctx = head_rq->mq_hctx;
		struct blk_mq_ctx *this_ctx = head_rq->mq_ctx;
		unsigned int depth = 1;

		list_for_each_continue(pos, &list) {
			rq = list_entry_rq(pos);
			BUG_ON(!rq->q);
			if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx)
				break;
			depth++;
		}

		list_cut_before(&rq_list, &list, pos);
		trace_block_unplug(head_rq->q, depth, !from_schedule);
		blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list,
						from_schedule);
	} while(!list_empty(&list));
}

static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
		unsigned int nr_segs)
{
	int err;

	if (bio->bi_opf & REQ_RAHEAD)
		rq->cmd_flags |= REQ_FAILFAST_MASK;

	rq->__sector = bio->bi_iter.bi_sector;
	rq->write_hint = bio->bi_write_hint;
	blk_rq_bio_prep(rq, bio, nr_segs);