Merge git://git.infradead.org/iommu-2.6

* git://git.infradead.org/iommu-2.6:
  intel-iommu: Fix off-by-one in RMRR setup
  intel-iommu: Add domain check in domain_remove_one_dev_info
  intel-iommu: Remove Host Bridge devices from identity mapping
  intel-iommu: Use coherent DMA mask when requested
  intel-iommu: Dont cache iova above 32bit
  intel-iommu: Speed up processing of the identity_mapping function
  intel-iommu: Check for identity mapping candidate using system dma mask
  intel-iommu: Only unlink device domains from iommu
  intel-iommu: Enable super page (2MiB, 1GiB, etc.) support
  intel-iommu: Flush unmaps at domain_exit
  intel-iommu: Remove obsolete comment from detect_intel_iommu
  intel-iommu: fix VT-d PMR disable for TXT on S3 resume

Documentation/kernel-parameters.txt

@@ -999,7 +999,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			With this option on every unmap_single operation will
 			result in a hardware IOTLB flush operation as opposed
 			to batching them for performance.
-
+		sp_off [Default Off]
+			By default, super page will be supported if Intel IOMMU
+			has the capability. With this option, super page will
+			not be supported.
 	intremap=	[X86-64, Intel-IOMMU]
 			Format: { on (default) | off | nosid }
 			on	enable Interrupt Remapping (default)

drivers/pci/dmar.c

@@ -698,12 +698,7 @@ int __init detect_intel_iommu(void)
 	{
 #ifdef CONFIG_INTR_REMAP
 		struct acpi_table_dmar *dmar;
-		/*
-		 * for now we will disable dma-remapping when interrupt
-		 * remapping is enabled.
-		 * When support for queued invalidation for IOTLB invalidation
-		 * is added, we will not need this any more.
-		 */
+
 		dmar = (struct acpi_table_dmar *) dmar_tbl;
 		if (ret && cpu_has_x2apic && dmar->flags & 0x1)
 			printk(KERN_INFO

drivers/pci/iova.c

@@ -63,8 +63,16 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 	curr = iovad->cached32_node;
 	cached_iova = container_of(curr, struct iova, node);
 
-	if (free->pfn_lo >= cached_iova->pfn_lo)
-		iovad->cached32_node = rb_next(&free->node);
+	if (free->pfn_lo >= cached_iova->pfn_lo) {
+		struct rb_node *node = rb_next(&free->node);
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* only cache if it's below 32bit pfn */
+		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
+			iovad->cached32_node = node;
+		else
+			iovad->cached32_node = NULL;
+	}
 }
 
 /* Computes the padding size required, to make the

include/linux/dma_remapping.h

@@ -9,8 +9,12 @@
 #define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
 #define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
 
+#define VTD_STRIDE_SHIFT        (9)
+#define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
+
 #define DMA_PTE_READ (1)
 #define DMA_PTE_WRITE (2)
+#define DMA_PTE_LARGE_PAGE (1 << 7)
 #define DMA_PTE_SNP (1 << 11)
 
 #define CONTEXT_TT_MULTI_LEVEL	0