diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index b6acb519fea5..340ae2150f91 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3167,26 +3167,44 @@ const struct iommu_ops amd_iommu_ops = {
 static struct irq_chip amd_ir_chip;
 static DEFINE_SPINLOCK(iommu_table_lock);
 
+static int iommu_flush_dev_irt(struct pci_dev *unused, u16 devid, void *data)
+{
+	int ret;
+	struct iommu_cmd cmd;
+	struct amd_iommu *iommu = data;
+
+	build_inv_irt(&cmd, devid);
+	ret = __iommu_queue_command_sync(iommu, &cmd, true);
+	return ret;
+}
+
 static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid)
 {
 	int ret;
 	u64 data;
 	unsigned long flags;
-	struct iommu_cmd cmd, cmd2;
+	struct iommu_cmd cmd;
+	struct pci_dev *pdev = NULL;
+	struct iommu_dev_data *dev_data = search_dev_data(iommu, devid);
 
 	if (iommu->irtcachedis_enabled)
 		return;
 
-	build_inv_irt(&cmd, devid);
+	if (dev_data && dev_data->dev && dev_is_pci(dev_data->dev))
+		pdev = to_pci_dev(dev_data->dev);
 
 	raw_spin_lock_irqsave(&iommu->lock, flags);
 	data = get_cmdsem_val(iommu);
-	build_completion_wait(&cmd2, iommu, data);
+	build_completion_wait(&cmd, iommu, data);
 
-	ret = __iommu_queue_command_sync(iommu, &cmd, true);
+	if (pdev)
+		ret = pci_for_each_dma_alias(pdev, iommu_flush_dev_irt, iommu);
+	else
+		ret = iommu_flush_dev_irt(NULL, devid, iommu);
 	if (ret)
 		goto out_err;
-	ret = __iommu_queue_command_sync(iommu, &cmd2, false);
+
+	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
 		goto out_err;
 	raw_spin_unlock_irqrestore(&iommu->lock, flags);