iommu/vt-d: Preset Access/Dirty bits for IOVA over FL

The Access/Dirty bits in the first level page table entry will be set
whenever a page table entry was used for address translation or write
permission was successfully translated. This is always true when using
the first-level page table for kernel IOVA. Instead of wasting hardware
cycles to update the certain bits, it's better to set them up at the
beginning.
Suggested-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20210115004202.953965-1-baolu.lu@linux.intel.comSigned-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/intel/iommu.c

@@ -1017,8 +1017,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 
 			domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
 			pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
-			if (domain_use_first_level(domain))
+			if (domain_use_first_level(domain)) {
 				pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US;
+				if (domain->domain.type == IOMMU_DOMAIN_DMA)
+					pteval |= DMA_FL_PTE_ACCESS;
+			}
 			if (cmpxchg64(&pte->val, 0ULL, pteval))
 				/* Someone else set it while we were thinking; use theirs. */
 				free_pgtable_page(tmp_page);
@@ -2310,9 +2313,16 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		return -EINVAL;
 
 	attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
-	if (domain_use_first_level(domain))
+	if (domain_use_first_level(domain)) {
 		attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD | DMA_FL_PTE_US;
 
+		if (domain->domain.type == IOMMU_DOMAIN_DMA) {
+			attr |= DMA_FL_PTE_ACCESS;
+			if (prot & DMA_PTE_WRITE)
+				attr |= DMA_FL_PTE_DIRTY;
+		}
+	}
+
 	pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
 
 	while (nr_pages > 0) {

include/linux/intel-iommu.h

@@ -42,6 +42,8 @@
 
 #define DMA_FL_PTE_PRESENT	BIT_ULL(0)
 #define DMA_FL_PTE_US		BIT_ULL(2)
+#define DMA_FL_PTE_ACCESS	BIT_ULL(5)
+#define DMA_FL_PTE_DIRTY	BIT_ULL(6)
 #define DMA_FL_PTE_XD		BIT_ULL(63)
 
 #define ADDR_WIDTH_5LEVEL	(57)