diff --git a/block/blk-mq.c b/block/blk-mq.c
index 7106c94ea58fe35c6d3118cccb4cffc7ce58a11c..55c81dcafbdc28aa6672e14ef4d151bd446fa7d0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -600,6 +600,20 @@ void blk_mq_force_complete_rq(struct request *rq)
 	if (rq->internal_tag != -1)
 		blk_mq_sched_completed_request(rq);
 
+	/*
+	 * Most of single queue controllers, there is only one irq vector
+	 * for handling IO completion, and the only irq's affinity is set
+	 * as all possible CPUs. On most of ARCHs, this affinity means the
+	 * irq is handled on one specific CPU.
+	 *
+	 * So complete IO reqeust in softirq context in case of single queue
+	 * for not degrading IO performance by irqsoff latency.
+	 */
+	if (rq->q->nr_hw_queues == 1) {
+		__blk_complete_request(rq);
+		return;
+	}
+
 	if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
 		rq->q->softirq_done_fn(rq);
 		return;
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 15c1f5e12eb89460bc42eb7f5807eaa03254e51d..e47a2f751884ddb7821fededef643693db752393 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -97,8 +97,8 @@ static int blk_softirq_cpu_dead(unsigned int cpu)
 
 void __blk_complete_request(struct request *req)
 {
-	int ccpu, cpu;
 	struct request_queue *q = req->q;
+	int cpu, ccpu = q->mq_ops ? req->mq_ctx->cpu : req->cpu;
 	unsigned long flags;
 	bool shared = false;
 
@@ -110,8 +110,7 @@ void __blk_complete_request(struct request *req)
 	/*
 	 * Select completion CPU
 	 */
-	if (req->cpu != -1) {
-		ccpu = req->cpu;
+	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) {
 		if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
 			shared = cpus_share_cache(cpu, ccpu);
 	} else