iommu/amd: Optimize alloc_new_range for new fetch_pte interface

Now that fetch_pte returns the page-size of the pte, the
call in this function can also be optimized a little bit.
Tested-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/amd_iommu.c

@@ -1591,7 +1591,7 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
 {
 	int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
 	struct amd_iommu *iommu;
-	unsigned long i, old_size;
+	unsigned long i, old_size, pte_pgsize;
 
 #ifdef CONFIG_IOMMU_STRESS
 	populate = false;
@@ -1664,13 +1664,13 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
 	 */
 	for (i = dma_dom->aperture[index]->offset;
 	     i < dma_dom->aperture_size;
-	     i += PAGE_SIZE) {
-		unsigned long pte_pgsize;
+	     i += pte_pgsize) {
 		u64 *pte = fetch_pte(&dma_dom->domain, i, &pte_pgsize);
 		if (!pte || !IOMMU_PTE_PRESENT(*pte))
 			continue;
 
-		dma_ops_reserve_addresses(dma_dom, i >> PAGE_SHIFT, 1);
+		dma_ops_reserve_addresses(dma_dom, i >> PAGE_SHIFT,
+					  pte_pgsize >> 12);
 	}
 
 	update_domain(&dma_dom->domain);