diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 96de97a460791ae70efa8f6b0ff91e736363c5e9..4025291ea0ae9c57370cdb283ae0b9959585f9a3 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -940,15 +940,13 @@ static void build_inv_irt(struct iommu_cmd *cmd, u16 devid)
  * Writes the command to the IOMMUs command buffer and informs the
  * hardware about the new command.
  */
-static int iommu_queue_command_sync(struct amd_iommu *iommu,
-				    struct iommu_cmd *cmd,
-				    bool sync)
+static int __iommu_queue_command_sync(struct amd_iommu *iommu,
+				      struct iommu_cmd *cmd,
+				      bool sync)
 {
 	u32 left, tail, head, next_tail;
-	unsigned long flags;
 
 again:
-	spin_lock_irqsave(&iommu->lock, flags);
 
 	head      = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
 	tail      = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
@@ -957,15 +955,14 @@ static int iommu_queue_command_sync(struct amd_iommu *iommu,
 
 	if (left <= 2) {
 		struct iommu_cmd sync_cmd;
-		volatile u64 sem = 0;
 		int ret;
 
-		build_completion_wait(&sync_cmd, (u64)&sem);
-		copy_cmd_to_buffer(iommu, &sync_cmd, tail);
+		iommu->cmd_sem = 0;
 
-		spin_unlock_irqrestore(&iommu->lock, flags);
+		build_completion_wait(&sync_cmd, (u64)&iommu->cmd_sem);
+		copy_cmd_to_buffer(iommu, &sync_cmd, tail);
 
-		if ((ret = wait_on_sem(&sem)) != 0)
+		if ((ret = wait_on_sem(&iommu->cmd_sem)) != 0)
 			return ret;
 
 		goto again;
@@ -976,9 +973,21 @@ static int iommu_queue_command_sync(struct amd_iommu *iommu,
 	/* We need to sync now to make sure all commands are processed */
 	iommu->need_sync = sync;
 
+	return 0;
+}
+
+static int iommu_queue_command_sync(struct amd_iommu *iommu,
+				    struct iommu_cmd *cmd,
+				    bool sync)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	ret = __iommu_queue_command_sync(iommu, cmd, sync);
 	spin_unlock_irqrestore(&iommu->lock, flags);
 
-	return 0;
+	return ret;
 }
 
 static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
@@ -993,19 +1002,29 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
 static int iommu_completion_wait(struct amd_iommu *iommu)
 {
 	struct iommu_cmd cmd;
-	volatile u64 sem = 0;
+	unsigned long flags;
 	int ret;
 
 	if (!iommu->need_sync)
 		return 0;
 
-	build_completion_wait(&cmd, (u64)&sem);
 
-	ret = iommu_queue_command_sync(iommu, &cmd, false);
+	build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
+
+	spin_lock_irqsave(&iommu->lock, flags);
+
+	iommu->cmd_sem = 0;
+
+	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
-		return ret;
+		goto out_unlock;
+
+	ret = wait_on_sem(&iommu->cmd_sem);
 
-	return wait_on_sem(&sem);
+out_unlock:
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	return ret;
 }
 
 static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid)
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index caf5e3822715f2f2066e15ca040371eac244026b..9652848e315580afeee72e3780e397ebe7d75ec6 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -524,6 +524,8 @@ struct amd_iommu {
 	struct irq_domain *ir_domain;
 	struct irq_domain *msi_domain;
 #endif
+
+	volatile u64 __aligned(8) cmd_sem;
 };
 
 #define ACPIHID_UID_LEN 256