scsi: make sure that request queue queiesce and unquiesce balanced

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 <[email protected]>
Fixes: e70feb8 ("blk-mq: support concurrent queue quiesce/unquiesce")
Signed-off-by: Ming Lei <[email protected]>
Reviewed-by: Martin K. Petersen <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

Author: Ming Lei

drivers/scsi/scsi_lib.c

@@ -2638,6 +2638,32 @@ static int __scsi_internal_device_block_nowait(struct scsi_device *sdev)
 	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
@@ -2662,7 +2688,7 @@ 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 +2715,12 @@ 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

include/scsi/scsi_device.h

@@ -207,6 +207,7 @@ struct scsi_device {
 					 * creation time */
 	unsigned ignore_media_change:1; /* Ignore MEDIA CHANGE on resume */
 
+	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 */