From: Ming Lei <ming.lei@redhat.com>

Date: Tue, 9 Nov 2021 15:11:43 +0800

Subject: scsi: make sure that request queue queiesce and unquiesce balanced

Patch-mainline: v5.16-rc1

Git-commit: 93542fbfa7b726d053c01a9399577c03968c4f6b

References: bsc#1201651

For fixing queue quiesce race between driver and block layer(elevator

switch, update nr_requests, ...), we need to support concurrent quiesce

and unquiesce, which requires the two call balanced.

It isn't easy to audit that in all scsi drivers, especially the two may

be called from different contexts, so do it in scsi core with one

per-device atomic variable to balance quiesce and unquiesce.

Reported-by: Yi Zhang <yi.zhang@redhat.com>

Fixes: e70feb8b3e68 ("blk-mq: support concurrent queue quiesce/unquiesce")

Signed-off-by: Ming Lei <ming.lei@redhat.com>

Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>

Link: https://lore.kernel.org/r/20211109071144.181581-4-ming.lei@redhat.com

Signed-off-by: Jens Axboe <axboe@kernel.dk>

Acked-by: Daniel Wagner <dwagner@suse.de>

---

 drivers/scsi/scsi_lib.c    |   37 ++++++++++++++++++++++++++++---------

 include/scsi/scsi_device.h |    1 +

 2 files changed, 29 insertions(+), 9 deletions(-)

--- a/drivers/scsi/scsi_lib.c

+++ b/drivers/scsi/scsi_lib.c

@@ -2632,6 +2632,32 @@ static int __scsi_internal_device_block_

 	return 0;

 }

+void scsi_start_queue(struct scsi_device *sdev)

+{

+	if (cmpxchg(&sdev->queue_stopped, 1, 0))

+		blk_mq_unquiesce_queue(sdev->request_queue);

+}

+

+static void scsi_stop_queue(struct scsi_device *sdev, bool nowait)

+{

+	/*

+	 * The atomic variable of ->queue_stopped covers that

+	 * blk_mq_quiesce_queue* is balanced with blk_mq_unquiesce_queue.

+	 *

+	 * However, we still need to wait until quiesce is done

+	 * in case that queue has been stopped.

+	 */

+	if (!cmpxchg(&sdev->queue_stopped, 0, 1)) {

+		if (nowait)

+			blk_mq_quiesce_queue_nowait(sdev->request_queue);

+		else

+			blk_mq_quiesce_queue(sdev->request_queue);

+	} else {

+		if (!nowait)

+			blk_mq_wait_quiesce_done(sdev->request_queue);

+	}

+}

+

 /**

  * scsi_internal_device_block_nowait - try to transition to the SDEV_BLOCK state

  * @sdev: device to block

@@ -2656,7 +2682,7 @@ int scsi_internal_device_block_nowait(st

 	 * request queue.

 	 */

 	if (!ret)

-		blk_mq_quiesce_queue_nowait(sdev->request_queue);

+		scsi_stop_queue(sdev, true);

 	return ret;

 }

 EXPORT_SYMBOL_GPL(scsi_internal_device_block_nowait);

@@ -2683,19 +2709,12 @@ static int scsi_internal_device_block(st

 	mutex_lock(&sdev->state_mutex);

 	err = __scsi_internal_device_block_nowait(sdev);

 	if (err == 0)

-		blk_mq_quiesce_queue(sdev->request_queue);

+		scsi_stop_queue(sdev, false);

 	mutex_unlock(&sdev->state_mutex);

 	return err;

 }

-void scsi_start_queue(struct scsi_device *sdev)

-{

-	struct request_queue *q = sdev->request_queue;

-

-	blk_mq_unquiesce_queue(q);

-}

-

 /**

  * scsi_internal_device_unblock_nowait - resume a device after a block request

  * @sdev:	device to resume

--- a/include/scsi/scsi_device.h

+++ b/include/scsi/scsi_device.h

@@ -206,6 +206,7 @@ struct scsi_device {

 	unsigned rpm_autosuspend:1;	/* Enable runtime autosuspend at device

 					 * creation time */

+	unsigned int queue_stopped;	/* request queue is quiesced */

 	bool offline_already;		/* Device offline message logged */

 	atomic_t disk_events_disable_depth; /* disable depth for disk events */