diff --git a/drivers/block/ll_rw_blk.c b/drivers/block/ll_rw_blk.c
index 46e54b441663d501c33944e46411117af9c4da40..11ef9d9ea139316e454cfae3d3b10f7aaab71959 100644
--- a/drivers/block/ll_rw_blk.c
+++ b/drivers/block/ll_rw_blk.c
@@ -1715,6 +1715,15 @@ request_queue_t *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
 	if (blk_init_free_list(q))
 		goto out_init;
 
+	/*
+	 * if caller didn't supply a lock, they get per-queue locking with
+	 * our embedded lock
+	 */
+	if (!lock) {
+		spin_lock_init(&q->__queue_lock);
+		lock = &q->__queue_lock;
+	}
+
 	q->request_fn		= rfn;
 	q->back_merge_fn       	= ll_back_merge_fn;
 	q->front_merge_fn      	= ll_front_merge_fn;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 7cbc4127fb5a6375e870920dd3f7b19199d59a90..d230c699c728e3a8db456034bf5bf30c7b1c5452 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -360,9 +360,9 @@ void scsi_device_unbusy(struct scsi_device *sdev)
 		     shost->host_failed))
 		scsi_eh_wakeup(shost);
 	spin_unlock(shost->host_lock);
-	spin_lock(&sdev->sdev_lock);
+	spin_lock(sdev->request_queue->queue_lock);
 	sdev->device_busy--;
-	spin_unlock_irqrestore(&sdev->sdev_lock, flags);
+	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 }
 
 /*
@@ -1425,7 +1425,7 @@ struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
 	struct Scsi_Host *shost = sdev->host;
 	struct request_queue *q;
 
-	q = blk_init_queue(scsi_request_fn, &sdev->sdev_lock);
+	q = blk_init_queue(scsi_request_fn, NULL);
 	if (!q)
 		return NULL;
 
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index a8a37a338c02f70ea4e04c9cbcab29559c0d3492..287d197a7c17f8527668ee162361b9552f04d948 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -249,7 +249,6 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	 */
 	sdev->borken = 1;
 
-	spin_lock_init(&sdev->sdev_lock);
 	sdev->request_queue = scsi_alloc_queue(sdev);
 	if (!sdev->request_queue) {
 		/* release fn is set up in scsi_sysfs_device_initialise, so
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 70ac2860a605342199b4d68c2215154eb2921645..ef1afc178c0a2df9569daf3312e33911a0e89bf2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -355,8 +355,11 @@ struct request_queue
 	unsigned long		queue_flags;
 
 	/*
-	 * protects queue structures from reentrancy
+	 * protects queue structures from reentrancy. ->__queue_lock should
+	 * _never_ be used directly, it is queue private. always use
+	 * ->queue_lock.
 	 */
+	spinlock_t		__queue_lock;
 	spinlock_t		*queue_lock;
 
 	/*
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 07d974051b0c10b1381ea4b0a675076fe5210e71..f6d051318299c17bf10240b042bca624e96ee97e 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -44,7 +44,6 @@ struct scsi_device {
 	struct list_head    same_target_siblings; /* just the devices sharing same target id */
 
 	volatile unsigned short device_busy;	/* commands actually active on low-level */
-	spinlock_t sdev_lock;           /* also the request queue_lock */
 	spinlock_t list_lock;
 	struct list_head cmd_list;	/* queue of in use SCSI Command structures */
 	struct list_head starved_entry;