diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 4afb9cb99ea31bb52ca3157c1871ec199ed49a68..9ae3678844ebf0fda278eb631247aa1750a310d1 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -688,7 +688,13 @@ static void queue_inc_cons(struct arm_smmu_queue *q)
 	u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;
 
 	q->cons = Q_OVF(q, q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
-	writel(q->cons, q->cons_reg);
+
+	/*
+	 * Ensure that all CPU accesses (reads and writes) to the queue
+	 * are complete before we update the cons pointer.
+	 */
+	mb();
+	writel_relaxed(q->cons, q->cons_reg);
 }
 
 static int queue_sync_prod(struct arm_smmu_queue *q)