blk-mq.c

	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);
}

bool blk_mq_get_driver_tag(struct request *rq)
{
	struct blk_mq_alloc_data data = {
		.q = rq->q,
		.hctx = rq->mq_hctx,
		.flags = BLK_MQ_REQ_NOWAIT,
		.cmd_flags = rq->cmd_flags,
	};
	bool shared;

	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;

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

done:
	return rq->tag != -1;
}

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);
	list_del_init(&wait->entry);
	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 wait_queue_head *wq;
	wait_queue_entry_t *wait;
	bool ret;

	if (!(hctx->flags & BLK_MQ_F_TAG_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(&hctx->tags->bitmap_tags, 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;
	}

	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);
	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;

	if (hctx->queue->elevator)
		return;

	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 */

/*
 * Returns true if we did some work AND can potentially do more.
 */
bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
			     bool got_budget)
{
	struct blk_mq_hw_ctx *hctx;
	struct request *rq, *nxt;
	bool no_tag = false;
	int errors, queued;
	blk_status_t ret = BLK_STS_OK;

	if (list_empty(list))
		return false;

	WARN_ON(!list_is_singular(list) && got_budget);

	/*
	 * 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);

		hctx = rq->mq_hctx;
		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
			break;

		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)) {
				blk_mq_put_dispatch_budget(hctx);
				/*
				 * For non-shared tags, the RESTART check
				 * will suffice.
				 */
				if (hctx->flags & BLK_MQ_F_TAG_SHARED)
					no_tag = true;
				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);
		}

		ret = q->mq_ops->queue_rq(hctx, &bd);
		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
			/*
			 * If an I/O scheduler has been configured and we got a
			 * driver tag for the next request already, free it
			 * again.
			 */
			if (!list_empty(list)) {
				nxt = list_first_entry(list, struct request, queuelist);
				blk_mq_put_driver_tag(nxt);
			}
			list_add(&rq->queuelist, list);
			__blk_mq_requeue_request(rq);
			break;
		}

		if (unlikely(ret != BLK_STS_OK)) {
			errors++;
			blk_mq_end_request(rq, BLK_STS_IOERR);
			continue;
		}

		queued++;
	} while (!list_empty(list));

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

	/*
	 * 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;

		/*
		 * 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 (q->mq_ops->commit_rqs)
			q->mq_ops->commit_rqs(hctx);

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

		/*
		 * 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.
		 */
		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))
			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);

	/*
	 * If the host/device is unable to accept more work, inform the
	 * caller of that.
	 */
	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
		return false;

	return (queued + errors) != 0;
}

static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
{
	int srcu_idx;

	/*
	 * We should be running this queue from one of the CPUs that
	 * are mapped to it.
	 *
	 * There are at least two related races now between setting
	 * hctx->next_cpu from blk_mq_hctx_next_cpu() and running
	 * __blk_mq_run_hw_queue():
	 *
	 * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(),
	 *   but later it becomes online, then this warning is harmless
	 *   at all
	 *
	 * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(),
	 *   but later it becomes offline, then the warning can't be
	 *   triggered, and we depend on blk-mq timeout handler to
	 *   handle dispatched requests to this hctx
	 */
	if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
		cpu_online(hctx->next_cpu)) {
		printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n",
			raw_smp_processor_id(),
			cpumask_empty(hctx->cpumask) ? "inactive": "active");
		dump_stack();
	}

	/*
	 * 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;
}

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));
}

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);

bool 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);
		return true;
	}

	return false;
}
EXPORT_SYMBOL(blk_mq_run_hw_queue);

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

	queue_for_each_hw_ctx(q, hctx, i) {
		if (blk_mq_hctx_stopped(hctx))
			continue;

		blk_mq_run_hw_queue(hctx, async);
	}
}
EXPORT_SYMBOL(blk_mq_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 (test_bit(BLK_MQ_S_STOPPED, &hctx->state))
		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(hctx->queue, 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);
}

/*
 * 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 run_queue)
{
	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;

	spin_lock(&hctx->lock);
	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(hctx->queue, 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, struct list_head *a, 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 -1;
	else if (rqa->mq_ctx > rqb->mq_ctx)
		return 1;
	else if (rqa->mq_hctx < rqb->mq_hctx)
		return -1;
	else if (rqa->mq_hctx > rqb->mq_hctx)
		return 1;

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

void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
	struct blk_mq_hw_ctx *this_hctx;
	struct blk_mq_ctx *this_ctx;
	struct request_queue *this_q;
	struct request *rq;
	LIST_HEAD(list);
	LIST_HEAD(rq_list);
	unsigned int depth;

	list_splice_init(&plug->mq_list, &list);
	plug->rq_count = 0;

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

	this_q = NULL;
	this_hctx = NULL;
	this_ctx = NULL;
	depth = 0;

	while (!list_empty(&list)) {
		rq = list_entry_rq(list.next);
		list_del_init(&rq->queuelist);
		BUG_ON(!rq->q);
		if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx) {
			if (this_hctx) {
				trace_block_unplug(this_q, depth, !from_schedule);
				blk_mq_sched_insert_requests(this_hctx, this_ctx,
								&rq_list,
								from_schedule);
			}

			this_q = rq->q;
			this_ctx = rq->mq_ctx;
			this_hctx = rq->mq_hctx;
			depth = 0;
		}

		depth++;
		list_add_tail(&rq->queuelist, &rq_list);
	}

	/*
	 * If 'this_hctx' is set, we know we have entries to complete
	 * on 'rq_list'. Do those.
	 */
	if (this_hctx) {
		trace_block_unplug(this_q, depth, !from_schedule);
		blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list,
						from_schedule);
	}
}

static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
{
	blk_init_request_from_bio(rq, bio);

	blk_account_io_start(rq, true);
}

static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
					    struct request *rq,
					    blk_qc_t *cookie, bool last)
{
	struct request_queue *q = rq->q;
	struct blk_mq_queue_data bd = {
		.rq = rq,
		.last = last,
	};
	blk_qc_t new_cookie;
	blk_status_t ret;

	new_cookie = request_to_qc_t(hctx, rq);

	/*
	 * For OK queue, we are done. For error, caller may kill it.
	 * Any other error (busy), just add it to our list as we
	 * previously would have done.
	 */
	ret = q->mq_ops->queue_rq(hctx, &bd);
	switch (ret) {
	case BLK_STS_OK:
		blk_mq_update_dispatch_busy(hctx, false);
		*cookie = new_cookie;
		break;
	case BLK_STS_RESOURCE:
	case BLK_STS_DEV_RESOURCE:
		blk_mq_update_dispatch_busy(hctx, true);
		__blk_mq_requeue_request(rq);
		break;
	default:
		blk_mq_update_dispatch_busy(hctx, false);
		*cookie = BLK_QC_T_NONE;
		break;
	}

	return ret;
}

blk_status_t blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
						struct request *rq,
						blk_qc_t *cookie,
						bool bypass, bool last)
{
	struct request_queue *q = rq->q;
	bool run_queue = true;
	blk_status_t ret = BLK_STS_RESOURCE;
	int srcu_idx;
	bool force = false;

	hctx_lock(hctx, &srcu_idx);
	/*
	 * hctx_lock is needed before checking quiesced flag.
	 *
	 * When queue is stopped or quiesced, ignore 'bypass', insert
	 * and return BLK_STS_OK to caller, and avoid driver to try to
	 * dispatch again.
	 */
	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) {
		run_queue = false;
		bypass = false;
		goto out_unlock;
	}

	if (unlikely(q->elevator && !bypass))
		goto out_unlock;

	if (!blk_mq_get_dispatch_budget(hctx))
		goto out_unlock;

	if (!blk_mq_get_driver_tag(rq)) {
		blk_mq_put_dispatch_budget(hctx);
		goto out_unlock;
	}

	/*
	 * Always add a request that has been through
	 *.queue_rq() to the hardware dispatch list.
	 */
	force = true;
	ret = __blk_mq_issue_directly(hctx, rq, cookie, last);
out_unlock:
	hctx_unlock(hctx, srcu_idx);
	switch (ret) {
	case BLK_STS_OK:
		break;
	case BLK_STS_DEV_RESOURCE:
	case BLK_STS_RESOURCE:
		if (force) {
			blk_mq_request_bypass_insert(rq, run_queue);
			/*
			 * We have to return BLK_STS_OK for the DM
			 * to avoid livelock. Otherwise, we return
			 * the real result to indicate whether the
			 * request is direct-issued successfully.
			 */
			ret = bypass ? BLK_STS_OK : ret;
		} else if (!bypass) {
			blk_mq_sched_insert_request(rq, false,
						    run_queue, false);
		}
		break;
	default:
		if (!bypass)
			blk_mq_end_request(rq, ret);
		break;
	}

	return ret;
}

void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
		struct list_head *list)
{
	blk_qc_t unused;
	blk_status_t ret = BLK_STS_OK;

	while (!list_empty(list)) {
		struct request *rq = list_first_entry(list, struct request,
				queuelist);

		list_del_init(&rq->queuelist);
		if (ret == BLK_STS_OK)
			ret = blk_mq_try_issue_directly(hctx, rq, &unused,
							false,
							list_empty(list));
		else
			blk_mq_sched_insert_request(rq, false, true, false);
	}

	/*
	 * 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 (ret != BLK_STS_OK && hctx->queue->mq_ops->commit_rqs)
		hctx->queue->mq_ops->commit_rqs(hctx);
}

static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
{
	list_add_tail(&rq->queuelist, &plug->mq_list);
	plug->rq_count++;
	if (!plug->multiple_queues && !list_is_singular(&plug->mq_list)) {
		struct request *tmp;

		tmp = list_first_entry(&plug->mq_list, struct request,
						queuelist);
		if (tmp->q != rq->q)
			plug->multiple_queues = true;
	}
}

static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
{
	const int is_sync = op_is_sync(bio->bi_opf);
	const int is_flush_fua = op_is_flush(bio->bi_opf);
	struct blk_mq_alloc_data data = { .flags = 0};
	struct request *rq;
	struct blk_plug *plug;
	struct request *same_queue_rq = NULL;
	blk_qc_t cookie;

	blk_queue_bounce(q, &bio);

	blk_queue_split(q, &bio);

	if (!bio_integrity_prep(bio))
		return BLK_QC_T_NONE;

	if (!is_flush_fua && !blk_queue_nomerges(q) &&
	    blk_attempt_plug_merge(q, bio, &same_queue_rq))
		return BLK_QC_T_NONE;

	if (blk_mq_sched_bio_merge(q, bio))
		return BLK_QC_T_NONE;

	rq_qos_throttle(q, bio);

	data.cmd_flags = bio->bi_opf;
	rq = blk_mq_get_request(q, bio, &data);
	if (unlikely(!rq)) {
		rq_qos_cleanup(q, bio);
		if (bio->bi_opf & REQ_NOWAIT)
			bio_wouldblock_error(bio);
		return BLK_QC_T_NONE;
	}

	trace_block_getrq(q, bio, bio->bi_opf);

	rq_qos_track(q, rq, bio);

	cookie = request_to_qc_t(data.hctx, rq);

	plug = current->plug;
	if (unlikely(is_flush_fua)) {
		blk_mq_put_ctx(data.ctx);
		blk_mq_bio_to_request(rq, bio);

		/* bypass scheduler for flush rq */
		blk_insert_flush(rq);
		blk_mq_run_hw_queue(data.hctx, true);
	} else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) {
		/*
		 * Use plugging if we have a ->commit_rqs() hook as well, as
		 * we know the driver uses bd->last in a smart fashion.
		 */
		unsigned int request_count = plug->rq_count;
		struct request *last = NULL;

		blk_mq_put_ctx(data.ctx);
		blk_mq_bio_to_request(rq, bio);

		if (!request_count)
			trace_block_plug(q);
		else
			last = list_entry_rq(plug->mq_list.prev);

		if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
		    blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
			blk_flush_plug_list(plug, false);
			trace_block_plug(q);
		}

		blk_add_rq_to_plug(plug, rq);
	} else if (plug && !blk_queue_nomerges(q)) {
		blk_mq_bio_to_request(rq, bio);

		/*
		 * We do limited plugging. If the bio can be merged, do that.
		 * Otherwise the existing request in the plug list will be
		 * issued. So the plug list will have one request at most
		 * The plug list might get flushed before this. If that happens,
		 * the plug list is empty, and same_queue_rq is invalid.
		 */
		if (list_empty(&plug->mq_list))
			same_queue_rq = NULL;
		if (same_queue_rq) {
			list_del_init(&same_queue_rq->queuelist);
			plug->rq_count--;
		}
		blk_add_rq_to_plug(plug, rq);

		blk_mq_put_ctx(data.ctx);

		if (same_queue_rq) {
			data.hctx = same_queue_rq->mq_hctx;