Commit 7cedffec authored by Bart Van Assche's avatar Bart Van Assche Committed by Jens Axboe
Browse files

block: Make blk_get_request() block for non-PM requests while suspended 



Instead of allowing requests that are not power management requests
to enter the queue in runtime suspended status (RPM_SUSPENDED), make
the blk_get_request() caller block. This change fixes a starvation
issue: it is now guaranteed that power management requests will be
executed no matter how many blk_get_request() callers are waiting.
For blk-mq, instead of maintaining the q->nr_pending counter, rely
on q->q_usage_counter. Call pm_runtime_mark_last_busy() every time a
request finishes instead of only if the queue depth drops to zero.

Signed-off-by: default avatarBart Van Assche <bvanassche@acm.org>
Reviewed-by: default avatarMing Lei <ming.lei@redhat.com>
Reviewed-by: default avatarChristoph Hellwig <hch@lst.de>
Cc: Jianchao Wang <jianchao.w.wang@oracle.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent bdd63160

block/blk-core.c

+8 −29
Original line number Diff line number Diff line
@@ -2746,30 +2746,6 @@ void blk_account_io_done(struct request *req, u64 now) 
	}

}



#ifdef CONFIG_PM

/*

 * Don't process normal requests when queue is suspended

 * or in the process of suspending/resuming

 */

static bool blk_pm_allow_request(struct request *rq)

{

	switch (rq->q->rpm_status) {

	case RPM_RESUMING:

	case RPM_SUSPENDING:

		return rq->rq_flags & RQF_PM;

	case RPM_SUSPENDED:

		return false;

	default:

		return true;

	}

}

#else

static bool blk_pm_allow_request(struct request *rq)

{

	return true;

}

#endif



void blk_account_io_start(struct request *rq, bool new_io)

{

	struct hd_struct *part;
@@ -2815,11 +2791,14 @@ static struct request *elv_next_request(struct request_queue *q) 


	while (1) {

		list_for_each_entry(rq, &q->queue_head, queuelist) {

			if (blk_pm_allow_request(rq))

#ifdef CONFIG_PM

			/*

			 * If a request gets queued in state RPM_SUSPENDED

			 * then that's a kernel bug.

			 */

			WARN_ON_ONCE(q->rpm_status == RPM_SUSPENDED);

#endif

			return rq;



			if (rq->rq_flags & RQF_SOFTBARRIER)

				break;

		}



		/*

block/blk-pm.c

+39 −5
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0



#include <linux/blk-mq.h>

#include <linux/blk-pm.h>

#include <linux/blkdev.h>

#include <linux/pm_runtime.h>

#include "blk-mq.h"

#include "blk-mq-tag.h"



/**

 * blk_pm_runtime_init - Block layer runtime PM initialization routine
@@ -68,14 +71,40 @@ int blk_pre_runtime_suspend(struct request_queue *q) 
	if (!q->dev)

		return ret;



	spin_lock_irq(q->queue_lock);

	if (q->nr_pending) {

	WARN_ON_ONCE(q->rpm_status != RPM_ACTIVE);



	/*

	 * Increase the pm_only counter before checking whether any

	 * non-PM blk_queue_enter() calls are in progress to avoid that any

	 * new non-PM blk_queue_enter() calls succeed before the pm_only

	 * counter is decreased again.

	 */

	blk_set_pm_only(q);

	ret = -EBUSY;

	/* Switch q_usage_counter from per-cpu to atomic mode. */

	blk_freeze_queue_start(q);

	/*

	 * Wait until atomic mode has been reached. Since that

	 * involves calling call_rcu(), it is guaranteed that later

	 * blk_queue_enter() calls see the pm-only state. See also

	 * http://lwn.net/Articles/573497/.

	 */

	percpu_ref_switch_to_atomic_sync(&q->q_usage_counter);

	if (percpu_ref_is_zero(&q->q_usage_counter))

		ret = 0;

	/* Switch q_usage_counter back to per-cpu mode. */

	blk_mq_unfreeze_queue(q);



	spin_lock_irq(q->queue_lock);

	if (ret < 0)

		pm_runtime_mark_last_busy(q->dev);

	} else {

	else

		q->rpm_status = RPM_SUSPENDING;

	}

	spin_unlock_irq(q->queue_lock);



	if (ret)

		blk_clear_pm_only(q);



	return ret;

}

EXPORT_SYMBOL(blk_pre_runtime_suspend);
@@ -106,6 +135,9 @@ void blk_post_runtime_suspend(struct request_queue *q, int err) 
		pm_runtime_mark_last_busy(q->dev);

	}

	spin_unlock_irq(q->queue_lock);



	if (err)

		blk_clear_pm_only(q);

}

EXPORT_SYMBOL(blk_post_runtime_suspend);
@@ -153,13 +185,15 @@ void blk_post_runtime_resume(struct request_queue *q, int err) 
	spin_lock_irq(q->queue_lock);

	if (!err) {

		q->rpm_status = RPM_ACTIVE;

		__blk_run_queue(q);

		pm_runtime_mark_last_busy(q->dev);

		pm_request_autosuspend(q->dev);

	} else {

		q->rpm_status = RPM_SUSPENDED;

	}

	spin_unlock_irq(q->queue_lock);



	if (!err)

		blk_clear_pm_only(q);

}

EXPORT_SYMBOL(blk_post_runtime_resume);

CRA Git | Maintained and supported by SUSTech CRA and CCSE