diff --git a/block/blk-core.c b/block/blk-core.c
index 7af4a4898dcb..0bc030aff0d0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1307,7 +1307,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 		struct request_list *rl = blk_rq_rl(req);
 
 		BUG_ON(!list_empty(&req->queuelist));
-		BUG_ON(!hlist_unhashed(&req->hash));
+		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
 		freed_request(rl, flags);
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index ebd6b6f1bdeb..53b1737e978d 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -30,8 +30,8 @@ static void blk_done_softirq(struct softirq_action *h)
 	while (!list_empty(&local_list)) {
 		struct request *rq;
 
-		rq = list_entry(local_list.next, struct request, queuelist);
-		list_del_init(&rq->queuelist);
+		rq = list_entry(local_list.next, struct request, ipi_list);
+		list_del_init(&rq->ipi_list);
 		rq->q->softirq_done_fn(rq);
 	}
 }
@@ -45,14 +45,9 @@ static void trigger_softirq(void *data)
 
 	local_irq_save(flags);
 	list = this_cpu_ptr(&blk_cpu_done);
-	/*
-	 * We reuse queuelist for a list of requests to process. Since the
-	 * queuelist is used by the block layer only for requests waiting to be
-	 * submitted to the device it is unused now.
-	 */
-	list_add_tail(&rq->queuelist, list);
+	list_add_tail(&rq->ipi_list, list);
 
-	if (list->next == &rq->queuelist)
+	if (list->next == &rq->ipi_list)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 
 	local_irq_restore(flags);
@@ -141,7 +136,7 @@ void __blk_complete_request(struct request *req)
 		struct list_head *list;
 do_local:
 		list = this_cpu_ptr(&blk_cpu_done);
-		list_add_tail(&req->queuelist, list);
+		list_add_tail(&req->ipi_list, list);
 
 		/*
 		 * if the list only contains our just added request,
@@ -149,7 +144,7 @@ do_local:
 		 * entries there, someone already raised the irq but it
 		 * hasn't run yet.
 		 */
-		if (list->next == &req->queuelist)
+		if (list->next == &req->ipi_list)
 			raise_softirq_irqoff(BLOCK_SOFTIRQ);
 	} else if (raise_blk_irq(ccpu, req))
 		goto do_local;
diff --git a/block/blk.h b/block/blk.h
index d23b415b8a28..1d880f1f957f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -78,7 +78,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
 /*
  * Internal elevator interface
  */
-#define ELV_ON_HASH(rq) hash_hashed(&(rq)->hash)
+#define ELV_ON_HASH(rq) ((rq)->cmd_flags & REQ_HASHED)
 
 void blk_insert_flush(struct request *rq);
 void blk_abort_flushes(struct request_queue *q);
diff --git a/block/elevator.c b/block/elevator.c
index 42c45a7d6714..1e01b66a0b92 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -247,6 +247,7 @@ EXPORT_SYMBOL(elevator_exit);
 static inline void __elv_rqhash_del(struct request *rq)
 {
 	hash_del(&rq->hash);
+	rq->cmd_flags &= ~REQ_HASHED;
 }
 
 static void elv_rqhash_del(struct request_queue *q, struct request *rq)
@@ -261,6 +262,7 @@ static void elv_rqhash_add(struct request_queue *q, struct request *rq)
 
 	BUG_ON(ELV_ON_HASH(rq));
 	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
+	rq->cmd_flags |= REQ_HASHED;
 }
 
 static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index bbc3a6c88fce..aa0eaa2d0bd8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -189,6 +189,7 @@ enum rq_flag_bits {
 	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_PM,		/* runtime pm request */
 	__REQ_END,		/* last of chain of requests */
+	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -241,5 +242,6 @@ enum rq_flag_bits {
 #define REQ_KERNEL		(1ULL << __REQ_KERNEL)
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_END			(1ULL << __REQ_END)
+#define REQ_HASHED		(1ULL << __REQ_HASHED)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5a31307c5ded..e402f8421c0c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -118,7 +118,18 @@ struct request {
 	struct bio *bio;
 	struct bio *biotail;
 
-	struct hlist_node hash;	/* merge hash */
+	/*
+	 * The hash is used inside the scheduler, and killed once the
+	 * request reaches the dispatch list. The ipi_list is only used
+	 * to queue the request for softirq completion, which is long
+	 * after the request has been unhashed (and even removed from
+	 * the dispatch list).
+	 */
+	union {
+		struct hlist_node hash;	/* merge hash */
+		struct list_head ipi_list;
+	};
+
 	/*
 	 * The rb_node is only used inside the io scheduler, requests
 	 * are pruned when moved to the dispatch queue. So let the