[dm-devel] [PATCH 2/3] scsi: make sure that request queue queiesce and unquiesce balanced

[Ming Lei]

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
bit flag & global spinlock, basically zero cost since request queue quiesce
is seldom triggered.

Reported-by: Yi Zhang <yi.zhang at redhat.com>
Fixes: e70feb8b3e68 ("blk-mq: support concurrent queue quiesce/unquiesce")
Signed-off-by: Ming Lei <ming.lei at redhat.com>
---
 drivers/scsi/scsi_lib.c    | 45 ++++++++++++++++++++++++++++++--------
 include/scsi/scsi_device.h |  1 +
 2 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 51fcd46be265..414f4daf8005 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2638,6 +2638,40 @@ static int __scsi_internal_device_block_nowait(struct scsi_device *sdev)
 	return 0;
 }
 
+static DEFINE_SPINLOCK(sdev_queue_stop_lock);
+
+void scsi_start_queue(struct scsi_device *sdev)
+{
+	bool need_start;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sdev_queue_stop_lock, flags);
+	need_start = sdev->queue_stopped;
+	sdev->queue_stopped = 0;
+	spin_unlock_irqrestore(&sdev_queue_stop_lock, flags);
+
+	if (need_start)
+		blk_mq_unquiesce_queue(sdev->request_queue);
+}
+
+static void scsi_stop_queue(struct scsi_device *sdev, bool nowait)
+{
+	bool need_stop;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sdev_queue_stop_lock, flags);
+	need_stop = !sdev->queue_stopped;
+	sdev->queue_stopped = 1;
+	spin_unlock_irqrestore(&sdev_queue_stop_lock, flags);
+
+	if (need_stop) {
+		if (nowait)
+			blk_mq_quiesce_queue_nowait(sdev->request_queue);
+		else
+			blk_mq_quiesce_queue(sdev->request_queue);
+	}
+}
+
 /**
  * scsi_internal_device_block_nowait - try to transition to the SDEV_BLOCK state
  * @sdev: device to block
@@ -2662,7 +2696,7 @@ int scsi_internal_device_block_nowait(struct scsi_device *sdev)
 	 * 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);
@@ -2689,19 +2723,12 @@ static int scsi_internal_device_block(struct scsi_device *sdev)
 	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
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 430b73bd02ac..ac74beccffa2 100644
--- 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 ignore_media_change:1; /* Ignore MEDIA CHANGE on resume */
+	unsigned queue_stopped:1;	/* request queue is quiesced */
 
 	bool offline_already;		/* Device offline message logged */
 
-- 
2.31.1