diff --git a/block/blk-core.c b/block/blk-core.c
index e2bacfa..5fa3dd2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -204,7 +204,7 @@
 
 	q = container_of(work, struct request_queue, delay_work.work);
 	spin_lock_irq(q->queue_lock);
-	__blk_run_queue(q, false);
+	__blk_run_queue(q);
 	spin_unlock_irq(q->queue_lock);
 }
 
@@ -239,7 +239,7 @@
 	WARN_ON(!irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
-	__blk_run_queue(q, false);
+	__blk_run_queue(q);
 }
 EXPORT_SYMBOL(blk_start_queue);
 
@@ -296,11 +296,9 @@
  *
  * Description:
  *    See @blk_run_queue. This variant must be called with the queue lock
- *    held and interrupts disabled. If force_kblockd is true, then it is
- *    safe to call this without holding the queue lock.
- *
+ *    held and interrupts disabled.
  */
-void __blk_run_queue(struct request_queue *q, bool force_kblockd)
+void __blk_run_queue(struct request_queue *q)
 {
 	if (unlikely(blk_queue_stopped(q)))
 		return;
@@ -309,7 +307,7 @@
 	 * Only recurse once to avoid overrunning the stack, let the unplug
 	 * handling reinvoke the handler shortly if we already got there.
 	 */
-	if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
+	if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
 		q->request_fn(q);
 		queue_flag_clear(QUEUE_FLAG_REENTER, q);
 	} else
@@ -318,6 +316,20 @@
 EXPORT_SYMBOL(__blk_run_queue);
 
 /**
+ * blk_run_queue_async - run a single device queue in workqueue context
+ * @q:	The queue to run
+ *
+ * Description:
+ *    Tells kblockd to perform the equivalent of @blk_run_queue on behalf
+ *    of us.
+ */
+void blk_run_queue_async(struct request_queue *q)
+{
+	if (likely(!blk_queue_stopped(q)))
+		queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
+}
+
+/**
  * blk_run_queue - run a single device queue
  * @q: The queue to run
  *
@@ -330,7 +342,7 @@
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	__blk_run_queue(q, false);
+	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_run_queue);
@@ -979,7 +991,7 @@
 		blk_queue_end_tag(q, rq);
 
 	add_acct_request(q, rq, where);
-	__blk_run_queue(q, false);
+	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_insert_request);
@@ -1323,7 +1335,7 @@
 	} else {
 		spin_lock_irq(q->queue_lock);
 		add_acct_request(q, req, where);
-		__blk_run_queue(q, false);
+		__blk_run_queue(q);
 out_unlock:
 		spin_unlock_irq(q->queue_lock);
 	}
@@ -2684,9 +2696,9 @@
 	 */
 	if (from_schedule) {
 		spin_unlock(q->queue_lock);
-		__blk_run_queue(q, true);
+		blk_run_queue_async(q);
 	} else {
-		__blk_run_queue(q, false);
+		__blk_run_queue(q);
 		spin_unlock(q->queue_lock);
 	}
 
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 7482b7f..81e3181 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -55,7 +55,7 @@
 	WARN_ON(irqs_disabled());
 	spin_lock_irq(q->queue_lock);
 	__elv_add_request(q, rq, where);
-	__blk_run_queue(q, false);
+	__blk_run_queue(q);
 	/* the queue is stopped so it won't be plugged+unplugged */
 	if (rq->cmd_type == REQ_TYPE_PM_RESUME)
 		q->request_fn(q);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index eba4a27..6c9b5e1 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -218,7 +218,7 @@
 	 * request_fn may confuse the driver.  Always use kblockd.
 	 */
 	if (queued)
-		__blk_run_queue(q, true);
+		blk_run_queue_async(q);
 }
 
 /**
@@ -274,7 +274,7 @@
 	 * the comment in flush_end_io().
 	 */
 	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error))
-		__blk_run_queue(q, true);
+		blk_run_queue_async(q);
 }
 
 /**
diff --git a/block/blk.h b/block/blk.h
index 6126346..c9df8fc 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -22,6 +22,7 @@
 void blk_delete_timer(struct request *);
 void blk_add_timer(struct request *);
 void __generic_unplug_device(struct request_queue *);
+void blk_run_queue_async(struct request_queue *q);
 
 /*
  * Internal atomic flags for request handling
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 3be881e..46b0a1d 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3368,7 +3368,7 @@
 			    cfqd->busy_queues > 1) {
 				cfq_del_timer(cfqd, cfqq);
 				cfq_clear_cfqq_wait_request(cfqq);
-				__blk_run_queue(cfqd->queue, false);
+				__blk_run_queue(cfqd->queue);
 			} else {
 				cfq_blkiocg_update_idle_time_stats(
 						&cfqq->cfqg->blkg);
@@ -3383,7 +3383,7 @@
 		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
-		__blk_run_queue(cfqd->queue, false);
+		__blk_run_queue(cfqd->queue);
 	}
 }
 
@@ -3743,7 +3743,7 @@
 	struct request_queue *q = cfqd->queue;
 
 	spin_lock_irq(q->queue_lock);
-	__blk_run_queue(cfqd->queue, false);
+	__blk_run_queue(cfqd->queue);
 	spin_unlock_irq(q->queue_lock);
 }
 
diff --git a/block/elevator.c b/block/elevator.c
index 0cdb4e7..6f6abc0 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -642,7 +642,7 @@
 	 */
 	elv_drain_elevator(q);
 	while (q->rq.elvpriv) {
-		__blk_run_queue(q, false);
+		__blk_run_queue(q);
 		spin_unlock_irq(q->queue_lock);
 		msleep(10);
 		spin_lock_irq(q->queue_lock);
@@ -695,7 +695,7 @@
 		 *   with anything.  There's no point in delaying queue
 		 *   processing.
 		 */
-		__blk_run_queue(q, false);
+		__blk_run_queue(q);
 		break;
 
 	case ELEVATOR_INSERT_SORT_MERGE:
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 6d5c7ff..ab55c2f 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -443,7 +443,7 @@
 					&sdev->request_queue->queue_flags);
 		if (flagset)
 			queue_flag_set(QUEUE_FLAG_REENTER, sdev->request_queue);
-		__blk_run_queue(sdev->request_queue, false);
+		__blk_run_queue(sdev->request_queue);
 		if (flagset)
 			queue_flag_clear(QUEUE_FLAG_REENTER, sdev->request_queue);
 		spin_unlock(sdev->request_queue->queue_lock);
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index fdf3fa6..28c3350 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -3829,7 +3829,7 @@
 		  !test_bit(QUEUE_FLAG_REENTER, &rport->rqst_q->queue_flags);
 	if (flagset)
 		queue_flag_set(QUEUE_FLAG_REENTER, rport->rqst_q);
-	__blk_run_queue(rport->rqst_q, false);
+	__blk_run_queue(rport->rqst_q);
 	if (flagset)
 		queue_flag_clear(QUEUE_FLAG_REENTER, rport->rqst_q);
 	spin_unlock_irqrestore(rport->rqst_q->queue_lock, flags);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3448d89..cbbfd98 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -697,7 +697,7 @@
 extern void blk_stop_queue(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
 extern void __blk_stop_queue(struct request_queue *q);
-extern void __blk_run_queue(struct request_queue *q, bool force_kblockd);
+extern void __blk_run_queue(struct request_queue *q);
 extern void blk_run_queue(struct request_queue *);
 extern int blk_rq_map_user(struct request_queue *, struct request *,
 			   struct rq_map_data *, void __user *, unsigned long,