Merge tag 'iommu-updates-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - Make the dma-iommu code more generic so that it can be used outside
   of the ARM context with other IOMMU drivers. Goal is to make use of
   it on x86 too.

 - Generic IOMMU domain support for the Intel VT-d driver. This driver
   now makes more use of common IOMMU code to allocate default domains
   for the devices it handles.

 - An IOMMU fault reporting API to userspace. With that the IOMMU fault
   handling can be done in user-space, for example to forward the faults
   to a VM.

 - Better handling for reserved regions requested by the firmware. These
   can be 'relaxed' now, meaning that those don't prevent a device being
   attached to a VM.

 - Suspend/Resume support for the Renesas IOMMU driver.

 - Added support for dumping SVA related fields of the DMAR table in the
   Intel VT-d driver via debugfs.

 - A pile of smaller fixes and cleanups.

* tag 'iommu-updates-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (90 commits)
  iommu/omap: No need to check return value of debugfs_create functions
  iommu/arm-smmu-v3: Invalidate ATC when detaching a device
  iommu/arm-smmu-v3: Fix compilation when CONFIG_CMA=n
  iommu/vt-d: Cleanup unused variable
  iommu/amd: Flush not present cache in iommu_map_page
  iommu/amd: Only free resources once on init error
  iommu/amd: Move gart fallback to amd_iommu_init
  iommu/amd: Make iommu_disable safer
  iommu/io-pgtable: Support non-coherent page tables
  iommu/io-pgtable: Replace IO_PGTABLE_QUIRK_NO_DMA with specific flag
  iommu/io-pgtable-arm: Add support to use system cache
  iommu/arm-smmu-v3: Increase maximum size of queues
  iommu/vt-d: Silence a variable set but not used
  iommu/vt-d: Remove an unused variable "length"
  iommu: Fix integer truncation
  iommu: Add padding to struct iommu_fault
  iommu/vt-d: Consolidate domain_init() to avoid duplication
  iommu/vt-d: Cleanup after delegating DMA domain to generic iommu
  iommu/vt-d: Fix suspicious RCU usage in probe_acpi_namespace_devices()
  iommu/vt-d: Allow DMA domain attaching to rmrr locked device
  ...

26 files changed, 1772 insertions, 1301 deletions

diff --git a/Documentation/ABI/testing/sysfs-kernel-iommu_groups b/Documentation/ABI/testing/sysfs-kernel-iommu_groups
index 35c64e00b35c..017f5bc3920c 100644
--- a/Documentation/ABI/testing/sysfs-kernel-iommu_groups
+++ b/Documentation/ABI/testing/sysfs-kernel-iommu_groups
@@ -24,3 +24,12 @@ Description:    /sys/kernel/iommu_groups/reserved_regions list IOVA
 		region is described on a single line: the 1st field is
 		the base IOVA, the second is the end IOVA and the third
 		field describes the type of the region.
+
+What:		/sys/kernel/iommu_groups/reserved_regions
+Date: 		June 2019
+KernelVersion:  v5.3
+Contact: 	Eric Auger <eric.auger@redhat.com>
+Description:    In case an RMRR is used only by graphics or USB devices
+		it is now exposed as "direct-relaxable" instead of "direct".
+		In device assignment use case, for instance, those RMRR
+		are considered to be relaxable and safe.
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 1d17dbeafe76..1d3f0b5a9940 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -1,24 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * SWIOTLB-based DMA API implementation
- *
  * Copyright (C) 2012 ARM Ltd.
  * Author: Catalin Marinas <catalin.marinas@arm.com>
  */
 
 #include <linux/gfp.h>
-#include <linux/acpi.h>
-#include <linux/memblock.h>
 #include <linux/cache.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-#include <linux/genalloc.h>
-#include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
-#include <linux/vmalloc.h>
-#include <linux/swiotlb.h>
-#include <linux/pci.h>
+#include <linux/dma-iommu.h>
 
 #include <asm/cacheflush.h>
 
@@ -47,37 +36,6 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 	__dma_flush_area(page_address(page), size);
 }
 
-#ifdef CONFIG_IOMMU_DMA
-static int __swiotlb_get_sgtable_page(struct sg_table *sgt,
-				      struct page *page, size_t size)
-{
-	int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
-
-	if (!ret)
-		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
-
-	return ret;
-}
-
-static int __swiotlb_mmap_pfn(struct vm_area_struct *vma,
-			      unsigned long pfn, size_t size)
-{
-	int ret = -ENXIO;
-	unsigned long nr_vma_pages = vma_pages(vma);
-	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long off = vma->vm_pgoff;
-
-	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
-		ret = remap_pfn_range(vma, vma->vm_start,
-				      pfn + off,
-				      vma->vm_end - vma->vm_start,
-				      vma->vm_page_prot);
-	}
-
-	return ret;
-}
-#endif /* CONFIG_IOMMU_DMA */
-
 static int __init arm64_dma_init(void)
 {
 	return dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC));
@@ -85,374 +43,11 @@ static int __init arm64_dma_init(void)
 arch_initcall(arm64_dma_init);
 
 #ifdef CONFIG_IOMMU_DMA
-#include <linux/dma-iommu.h>
-#include <linux/platform_device.h>
-#include <linux/amba/bus.h>
-
-/* Thankfully, all cache ops are by VA so we can ignore phys here */
-static void flush_page(struct device *dev, const void *virt, phys_addr_t phys)
-{
-	__dma_flush_area(virt, PAGE_SIZE);
-}
-
-static void *__iommu_alloc_attrs(struct device *dev, size_t size,
-				 dma_addr_t *handle, gfp_t gfp,
-				 unsigned long attrs)
-{
-	bool coherent = dev_is_dma_coherent(dev);
-	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
-	size_t iosize = size;
-	void *addr;
-
-	if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
-		return NULL;
-
-	size = PAGE_ALIGN(size);
-
-	/*
-	 * Some drivers rely on this, and we probably don't want the
-	 * possibility of stale kernel data being read by devices anyway.
-	 */
-	gfp |= __GFP_ZERO;
-
-	if (!gfpflags_allow_blocking(gfp)) {
-		struct page *page;
-		/*
-		 * In atomic context we can't remap anything, so we'll only
-		 * get the virtually contiguous buffer we need by way of a
-		 * physically contiguous allocation.
-		 */
-		if (coherent) {
-			page = alloc_pages(gfp, get_order(size));
-			addr = page ? page_address(page) : NULL;
-		} else {
-			addr = dma_alloc_from_pool(size, &page, gfp);
-		}
-		if (!addr)
-			return NULL;
-
-		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
-		if (*handle == DMA_MAPPING_ERROR) {
-			if (coherent)
-				__free_pages(page, get_order(size));
-			else
-				dma_free_from_pool(addr, size);
-			addr = NULL;
-		}
-	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
-		pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
-		struct page *page;
-
-		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
-					get_order(size), gfp & __GFP_NOWARN);
-		if (!page)
-			return NULL;
-
-		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
-		if (*handle == DMA_MAPPING_ERROR) {
-			dma_release_from_contiguous(dev, page,
-						    size >> PAGE_SHIFT);
-			return NULL;
-		}
-		addr = dma_common_contiguous_remap(page, size, VM_USERMAP,
-						   prot,
-						   __builtin_return_address(0));
-		if (addr) {
-			if (!coherent)
-				__dma_flush_area(page_to_virt(page), iosize);
-			memset(addr, 0, size);
-		} else {
-			iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs);
-			dma_release_from_contiguous(dev, page,
-						    size >> PAGE_SHIFT);
-		}
-	} else {
-		pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
-		struct page **pages;
-
-		pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
-					handle, flush_page);
-		if (!pages)
-			return NULL;
-
-		addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
-					      __builtin_return_address(0));
-		if (!addr)
-			iommu_dma_free(dev, pages, iosize, handle);
-	}
-	return addr;
-}
-
-static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-			       dma_addr_t handle, unsigned long attrs)
-{
-	size_t iosize = size;
-
-	size = PAGE_ALIGN(size);
-	/*
-	 * @cpu_addr will be one of 4 things depending on how it was allocated:
-	 * - A remapped array of pages for contiguous allocations.
-	 * - A remapped array of pages from iommu_dma_alloc(), for all
-	 *   non-atomic allocations.
-	 * - A non-cacheable alias from the atomic pool, for atomic
-	 *   allocations by non-coherent devices.
-	 * - A normal lowmem address, for atomic allocations by
-	 *   coherent devices.
-	 * Hence how dodgy the below logic looks...
-	 */
-	if (dma_in_atomic_pool(cpu_addr, size)) {
-		iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
-		dma_free_from_pool(cpu_addr, size);
-	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
-		struct page *page = vmalloc_to_page(cpu_addr);
-
-		iommu_dma_unmap_page(dev, handle, iosize, 0, attrs);
-		dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
-		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
-	} else if (is_vmalloc_addr(cpu_addr)){
-		struct vm_struct *area = find_vm_area(cpu_addr);
-
-		if (WARN_ON(!area || !area->pages))
-			return;
-		iommu_dma_free(dev, area->pages, iosize, &handle);
-		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
-	} else {
-		iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
-		__free_pages(virt_to_page(cpu_addr), get_order(size));
-	}
-}
-
-static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
-			      void *cpu_addr, dma_addr_t dma_addr, size_t size,
-			      unsigned long attrs)
-{
-	struct vm_struct *area;
-	int ret;
-
-	vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs);
-
-	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
-		return ret;
-
-	if (!is_vmalloc_addr(cpu_addr)) {
-		unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
-		return __swiotlb_mmap_pfn(vma, pfn, size);
-	}
-
-	if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
-		/*
-		 * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
-		 * hence in the vmalloc space.
-		 */
-		unsigned long pfn = vmalloc_to_pfn(cpu_addr);
-		return __swiotlb_mmap_pfn(vma, pfn, size);
-	}
-
-	area = find_vm_area(cpu_addr);
-	if (WARN_ON(!area || !area->pages))
-		return -ENXIO;
-
-	return iommu_dma_mmap(area->pages, size, vma);
-}
-
-static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
-			       void *cpu_addr, dma_addr_t dma_addr,
-			       size_t size, unsigned long attrs)
-{
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct vm_struct *area = find_vm_area(cpu_addr);
-
-	if (!is_vmalloc_addr(cpu_addr)) {
-		struct page *page = virt_to_page(cpu_addr);
-		return __swiotlb_get_sgtable_page(sgt, page, size);
-	}
-
-	if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
-		/*
-		 * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
-		 * hence in the vmalloc space.
-		 */
-		struct page *page = vmalloc_to_page(cpu_addr);
-		return __swiotlb_get_sgtable_page(sgt, page, size);
-	}
-
-	if (WARN_ON(!area || !area->pages))
-		return -ENXIO;
-
-	return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size,
-					 GFP_KERNEL);
-}
-
-static void __iommu_sync_single_for_cpu(struct device *dev,
-					dma_addr_t dev_addr, size_t size,
-					enum dma_data_direction dir)
-{
-	phys_addr_t phys;
-
-	if (dev_is_dma_coherent(dev))
-		return;
-
-	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr);
-	arch_sync_dma_for_cpu(dev, phys, size, dir);
-}
-
-static void __iommu_sync_single_for_device(struct device *dev,
-					   dma_addr_t dev_addr, size_t size,
-					   enum dma_data_direction dir)
-{
-	phys_addr_t phys;
-
-	if (dev_is_dma_coherent(dev))
-		return;
-
-	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr);
-	arch_sync_dma_for_device(dev, phys, size, dir);
-}
-
-static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
-{
-	bool coherent = dev_is_dma_coherent(dev);
-	int prot = dma_info_to_prot(dir, coherent, attrs);
-	dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
-
-	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-	    dev_addr != DMA_MAPPING_ERROR)
-		__dma_map_area(page_address(page) + offset, size, dir);
-
-	return dev_addr;
-}
-
-static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr,
-			       size_t size, enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__iommu_sync_single_for_cpu(dev, dev_addr, size, dir);
-
-	iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs);
-}
-
-static void __iommu_sync_sg_for_cpu(struct device *dev,
-				    struct scatterlist *sgl, int nelems,
-				    enum dma_data_direction dir)
-{
-	struct scatterlist *sg;
-	int i;
-
-	if (dev_is_dma_coherent(dev))
-		return;
-
-	for_each_sg(sgl, sg, nelems, i)
-		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
-}
-
-static void __iommu_sync_sg_for_device(struct device *dev,
-				       struct scatterlist *sgl, int nelems,
-				       enum dma_data_direction dir)
-{
-	struct scatterlist *sg;
-	int i;
-
-	if (dev_is_dma_coherent(dev))
-		return;
-
-	for_each_sg(sgl, sg, nelems, i)
-		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
-}
-
-static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
-				int nelems, enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	bool coherent = dev_is_dma_coherent(dev);
-
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__iommu_sync_sg_for_device(dev, sgl, nelems, dir);
-
-	return iommu_dma_map_sg(dev, sgl, nelems,
-				dma_info_to_prot(dir, coherent, attrs));
-}
-
-static void __iommu_unmap_sg_attrs(struct device *dev,
-				   struct scatterlist *sgl, int nelems,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
-{
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__iommu_sync_sg_for_cpu(dev, sgl, nelems, dir);
-
-	iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs);
-}
-
-static const struct dma_map_ops iommu_dma_ops = {
-	.alloc = __iommu_alloc_attrs,
-	.free = __iommu_free_attrs,
-	.mmap = __iommu_mmap_attrs,
-	.get_sgtable = __iommu_get_sgtable,
-	.map_page = __iommu_map_page,
-	.unmap_page = __iommu_unmap_page,
-	.map_sg = __iommu_map_sg_attrs,
-	.unmap_sg = __iommu_unmap_sg_attrs,
-	.sync_single_for_cpu = __iommu_sync_single_for_cpu,
-	.sync_single_for_device = __iommu_sync_single_for_device,
-	.sync_sg_for_cpu = __iommu_sync_sg_for_cpu,
-	.sync_sg_for_device = __iommu_sync_sg_for_device,
-	.map_resource = iommu_dma_map_resource,
-	.unmap_resource = iommu_dma_unmap_resource,
-};
-
-static int __init __iommu_dma_init(void)
-{
-	return iommu_dma_init();
-}
-arch_initcall(__iommu_dma_init);
-
-static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				  const struct iommu_ops *ops)
-{
-	struct iommu_domain *domain;
-
-	if (!ops)
-		return;
-
-	/*
-	 * The IOMMU core code allocates the default DMA domain, which the
-	 * underlying IOMMU driver needs to support via the dma-iommu layer.
-	 */
-	domain = iommu_get_domain_for_dev(dev);
-
-	if (!domain)
-		goto out_err;
-
-	if (domain->type == IOMMU_DOMAIN_DMA) {
-		if (iommu_dma_init_domain(domain, dma_base, size, dev))
-			goto out_err;
-
-		dev->dma_ops = &iommu_dma_ops;
-	}
-
-	return;
-
-out_err:
-	 pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
-		 dev_name(dev));
-}
-
 void arch_teardown_dma_ops(struct device *dev)
 {
 	dev->dma_ops = NULL;
 }
-
-#else
-
-static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				  const struct iommu_ops *iommu)
-{ }
-
-#endif  /* CONFIG_IOMMU_DMA */
+#endif
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
@@ -466,7 +61,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		   ARCH_DMA_MINALIGN, cls);
 
 	dev->dma_coherent = coherent;
-	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
+	if (iommu)
+		iommu_setup_dma_ops(dev, dma_base, size);
 
 #ifdef CONFIG_XEN
 	if (xen_initial_domain())
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index dce1d8d2e8a4..73740b969e62 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -619,9 +619,9 @@ retry:
 		pasid = ((event[0] >> 16) & 0xFFFF)
 			| ((event[1] << 6) & 0xF0000);
 		tag = event[1] & 0x03FF;
-		dev_err(dev, "Event logged [INVALID_PPR_REQUEST device=%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
+		dev_err(dev, "Event logged [INVALID_PPR_REQUEST device=%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x tag=0x%03x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-			pasid, address, flags);
+			pasid, address, flags, tag);
 		break;
 	default:
 		dev_err(dev, "Event logged [UNKNOWN event[0]=0x%08x event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n",
@@ -1295,6 +1295,16 @@ static void domain_flush_complete(struct protection_domain *domain)
 	}
 }
 
+/* Flush the not present cache if it exists */
+static void domain_flush_np_cache(struct protection_domain *domain,
+		dma_addr_t iova, size_t size)
+{
+	if (unlikely(amd_iommu_np_cache)) {
+		domain_flush_pages(domain, iova, size);
+		domain_flush_complete(domain);
+	}
+}
+
 
 /*
  * This function flushes the DTEs for all devices in domain
@@ -2377,10 +2387,7 @@ static dma_addr_t __map_single(struct device *dev,
 	}
 	address += offset;
 
-	if (unlikely(amd_iommu_np_cache)) {
-		domain_flush_pages(&dma_dom->domain, address, size);
-		domain_flush_complete(&dma_dom->domain);
-	}
+	domain_flush_np_cache(&dma_dom->domain, address, size);
 
 out:
 	return address;
@@ -2559,6 +2566,9 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 		s->dma_length   = s->length;
 	}
 
+	if (s)
+		domain_flush_np_cache(domain, s->dma_address, s->dma_length);
+
 	return nelems;
 
 out_unmap:
@@ -2597,7 +2607,7 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct protection_domain *domain;
 	struct dma_ops_domain *dma_dom;
 	unsigned long startaddr;
-	int npages = 2;
+	int npages;
 
 	domain = get_domain(dev);
 	if (IS_ERR(domain))
@@ -3039,6 +3049,8 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
 	ret = iommu_map_page(domain, iova, paddr, page_size, prot, GFP_KERNEL);
 	mutex_unlock(&domain->api_lock);
 
+	domain_flush_np_cache(domain, iova, page_size);
+
 	return ret;
 }
 
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 07d84dbab564..eb104c719629 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -406,6 +406,9 @@ static void iommu_enable(struct amd_iommu *iommu)
 
 static void iommu_disable(struct amd_iommu *iommu)
 {
+	if (!iommu->mmio_base)
+		return;
+
 	/* Disable command buffer */
 	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
 
@@ -2325,15 +2328,6 @@ static void __init free_iommu_resources(void)
 	amd_iommu_dev_table = NULL;
 
 	free_iommu_all();
-
-#ifdef CONFIG_GART_IOMMU
-	/*
-	 * We failed to initialize the AMD IOMMU - try fallback to GART
-	 * if possible.
-	 */
-	gart_iommu_init();
-
-#endif
 }
 
 /* SB IOAPIC is always on this device in AMD systems */
@@ -2625,8 +2619,6 @@ static int __init state_next(void)
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
 		if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) {
 			pr_info("AMD IOMMU disabled on kernel command-line\n");
-			free_dma_resources();
-			free_iommu_resources();
 			init_state = IOMMU_CMDLINE_DISABLED;
 			ret = -EINVAL;
 		}
@@ -2667,6 +2659,19 @@ static int __init state_next(void)
 		BUG();
 	}
 
+	if (ret) {
+		free_dma_resources();
+		if (!irq_remapping_enabled) {
+			disable_iommus();
+			free_iommu_resources();
+		} else {
+			struct amd_iommu *iommu;
+
+			uninit_device_table_dma();
+			for_each_iommu(iommu)
+				iommu_flush_all_caches(iommu);
+		}
+	}
 	return ret;
 }
 
@@ -2740,17 +2745,15 @@ static int __init amd_iommu_init(void)
 	int ret;
 
 	ret = iommu_go_to_state(IOMMU_INITIALIZED);
-	if (ret) {
-		free_dma_resources();
-		if (!irq_remapping_enabled) {
-			disable_iommus();
-			free_iommu_resources();
-		} else {
-			uninit_device_table_dma();
-			for_each_iommu(iommu)
-				iommu_flush_all_caches(iommu);
-		}
+#ifdef CONFIG_GART_IOMMU
+	if (ret && list_empty(&amd_iommu_list)) {
+		/*
+		 * We failed to initialize the AMD IOMMU - try fallback
+		 * to GART if possible.
+		 */
+		gart_iommu_init();
 	}
+#endif
 
 	for_each_iommu(iommu)
 		amd_iommu_debugfs_setup(iommu);
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 4d5a694f02c2..2d96cf0023dd 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -192,6 +192,13 @@
 #define Q_BASE_ADDR_MASK		GENMASK_ULL(51, 5)
 #define Q_BASE_LOG2SIZE			GENMASK(4, 0)
 
+/* Ensure DMA allocations are naturally aligned */
+#ifdef CONFIG_CMA_ALIGNMENT
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + CONFIG_CMA_ALIGNMENT)
+#else
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER - 1)
+#endif
+
 /*
  * Stream table.
  *
@@ -289,8 +296,9 @@
 					FIELD_GET(ARM64_TCR_##fld, tcr))
 
 /* Command queue */
-#define CMDQ_ENT_DWORDS			2
-#define CMDQ_MAX_SZ_SHIFT		8
+#define CMDQ_ENT_SZ_SHIFT		4
+#define CMDQ_ENT_DWORDS			((1 << CMDQ_ENT_SZ_SHIFT) >> 3)
+#define CMDQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - CMDQ_ENT_SZ_SHIFT)
 
 #define CMDQ_CONS_ERR			GENMASK(30, 24)
 #define CMDQ_ERR_CERROR_NONE_IDX	0
@@ -336,14 +344,16 @@
 #define CMDQ_SYNC_1_MSIADDR_MASK	GENMASK_ULL(51, 2)
 
 /* Event queue */
-#define EVTQ_ENT_DWORDS			4
-#define EVTQ_MAX_SZ_SHIFT		7
+#define EVTQ_ENT_SZ_SHIFT		5
+#define EVTQ_ENT_DWORDS			((1 << EVTQ_ENT_SZ_SHIFT) >> 3)
+#define EVTQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - EVTQ_ENT_SZ_SHIFT)
 
 #define EVTQ_0_ID			GENMASK_ULL(7, 0)
 
 /* PRI queue */
-#define PRIQ_ENT_DWORDS			2
-#define PRIQ_MAX_SZ_SHIFT		8
+#define PRIQ_ENT_SZ_SHIFT		4
+#define PRIQ_ENT_DWORDS			((1 << PRIQ_ENT_SZ_SHIFT) >> 3)
+#define PRIQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - PRIQ_ENT_SZ_SHIFT)
 
 #define PRIQ_0_SID			GENMASK_ULL(31, 0)
 #define PRIQ_0_SSID			GENMASK_ULL(51, 32)
@@ -798,7 +808,7 @@ static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
 /* High-level queue accessors */
 static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 {
-	memset(cmd, 0, CMDQ_ENT_DWORDS << 3);
+	memset(cmd, 0, 1 << CMDQ_ENT_SZ_SHIFT);
 	cmd[0] |= FIELD_PREP(CMDQ_0_OP, ent->opcode);
 
 	switch (ent->opcode) {
@@ -1785,13 +1795,11 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 		.pgsize_bitmap	= smmu->pgsize_bitmap,
 		.ias		= ias,
 		.oas		= oas,
+		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENCY,
 		.tlb		= &arm_smmu_gather_ops,
 		.iommu_dev	= smmu->dev,
 	};
 
-	if (smmu->features & ARM_SMMU_FEAT_COHERENCY)
-		pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_NO_DMA;
-
 	if (smmu_domain->non_strict)
 		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
 
@@ -1884,9 +1892,13 @@ static int arm_smmu_enable_ats(struct arm_smmu_master *master)
 
 static void arm_smmu_disable_ats(struct arm_smmu_master *master)
 {
+	struct arm_smmu_cmdq_ent cmd;
+
 	if (!master->ats_enabled || !dev_is_pci(master->dev))
 		return;
 
+	arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd);
+	arm_smmu_atc_inv_master(master, &cmd);
 	pci_disable_ats(to_pci_dev(master->dev));
 	master->ats_enabled = false;
 }
@@ -1906,7 +1918,6 @@ static void arm_smmu_detach_dev(struct arm_smmu_master *master)
 	master->domain = NULL;
 	arm_smmu_install_ste_for_dev(master);
 
-	/* Disabling ATS invalidates all ATC entries */
 	arm_smmu_disable_ats(master);
 }
 
@@ -2270,17 +2281,32 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
 				   struct arm_smmu_queue *q,
 				   unsigned long prod_off,
 				   unsigned long cons_off,
-				   size_t dwords)
+				   size_t dwords, const char *name)
 {
-	size_t qsz = ((1 << q->max_n_shift) * dwords) << 3;
+	size_t qsz;
+
+	do {
+		qsz = ((1 << q->max_n_shift) * dwords) << 3;
+		q->base = dmam_alloc_coherent(smmu->dev, qsz, &q->base_dma,
+					      GFP_KERNEL);
+		if (q->base || qsz < PAGE_SIZE)
+			break;
+
+		q->max_n_shift--;
+	} while (1);
 
-	q->base = dmam_alloc_coherent(smmu->dev, qsz, &q->base_dma, GFP_KERNEL);
 	if (!q->base) {
-		dev_err(smmu->dev, "failed to allocate queue (0x%zx bytes)\n",
-			qsz);
+		dev_err(smmu->dev,
+			"failed to allocate queue (0x%zx bytes) for %s\n",
+			qsz, name);
 		return -ENOMEM;
 	}
 
+	if (!WARN_ON(q->base_dma & (qsz - 1))) {
+		dev_info(smmu->dev, "allocated %u entries for %s\n",
+			 1 << q->max_n_shift, name);
+	}
+
 	q->prod_reg	= arm_smmu_page1_fixup(prod_off, smmu);
 	q->cons_reg	= arm_smmu_page1_fixup(cons_off, smmu);
 	q->ent_dwords	= dwords;
@@ -2300,13 +2326,15 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
 	/* cmdq */
 	spin_lock_init(&smmu->cmdq.lock);
 	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
-				      ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS);
+				      ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS,
+				      "cmdq");
 	if (ret)
 		return ret;
 
 	/* evtq */
 	ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, ARM_SMMU_EVTQ_PROD,
-				      ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS);
+				      ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS,
+				      "evtq");
 	if (ret)
 		return ret;
 
@@ -2315,7 +2343,8 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
 		return 0;
 
 	return arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD,
-				       ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS);
+				       ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS,
+				       "priq");
 }
 
 static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
@@ -2879,7 +2908,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 		return -ENXIO;
 	}
 
-	/* Queue sizes, capped at 4k */
+	/* Queue sizes, capped to ensure natural alignment */
 	smmu->cmdq.q.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT,
 					 FIELD_GET(IDR1_CMDQS, reg));
 	if (!smmu->cmdq.q.max_n_shift) {
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 586dd5a46d9f..653b6b3dcafb 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -892,13 +892,11 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.pgsize_bitmap	= smmu->pgsize_bitmap,
 		.ias		= ias,
 		.oas		= oas,
+		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENT_WALK,
 		.tlb		= smmu_domain->tlb_ops,
 		.iommu_dev	= smmu->dev,
 	};
 
-	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
-		pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_NO_DMA;
-
 	if (smmu_domain->non_strict)
 		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
 
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 379318266468..f802255219d3 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -10,7 +10,9 @@
 
 #include <linux/acpi_iort.h>
 #include <linux/device.h>
+#include <linux/dma-contiguous.h>
 #include <linux/dma-iommu.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
 #include <linux/huge_mm.h>
 #include <linux/iommu.h>
@@ -67,11 +69,6 @@ static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
 	return cookie;
 }
 
-int iommu_dma_init(void)
-{
-	return iova_cache_get();
-}
-
 /**
  * iommu_get_dma_cookie - Acquire DMA-API resources for a domain
  * @domain: IOMMU domain to prepare for DMA-API usage
@@ -229,8 +226,8 @@ resv_iova:
 		start = window->res->end - window->offset + 1;
 		/* If window is last entry */
 		if (window->node.next == &bridge->dma_ranges &&
-		    end != ~(dma_addr_t)0) {
-			end = ~(dma_addr_t)0;
+		    end != ~(phys_addr_t)0) {
+			end = ~(phys_addr_t)0;
 			goto resv_iova;
 		}
 	}
@@ -302,7 +299,7 @@ static void iommu_dma_flush_iotlb_all(struct iova_domain *iovad)
  * to ensure it is an invalid IOVA. It is safe to reinitialise a domain, but
  * any change which could make prior IOVAs invalid will fail.
  */
-int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
+static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		u64 size, struct device *dev)
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
@@ -353,7 +350,6 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 
 	return iova_reserve_iommu_regions(dev, domain);
 }
-EXPORT_SYMBOL(iommu_dma_init_domain);
 
 /**
  * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API
@@ -364,7 +360,7 @@ EXPORT_SYMBOL(iommu_dma_init_domain);
  *
  * Return: corresponding IOMMU API page protection flags
  */
-int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
+static int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
 		     unsigned long attrs)
 {
 	int prot = coherent ? IOMMU_CACHE : 0;
@@ -441,9 +437,10 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
 				size >> iova_shift(iovad));
 }
 
-static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr,
+static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 		size_t size)
 {
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	size_t iova_off = iova_offset(iovad, dma_addr);
@@ -457,6 +454,30 @@ static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr,
 	iommu_dma_free_iova(cookie, dma_addr, size);
 }
 
+static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
+		size_t size, int prot)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	size_t iova_off = 0;
+	dma_addr_t iova;
+
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE) {
+		iova_off = iova_offset(&cookie->iovad, phys);
+		size = iova_align(&cookie->iovad, size + iova_off);
+	}
+
+	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
+	if (!iova)
+		return DMA_MAPPING_ERROR;
+
+	if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
+		iommu_dma_free_iova(cookie, iova, size);
+		return DMA_MAPPING_ERROR;
+	}
+	return iova + iova_off;
+}
+
 static void __iommu_dma_free_pages(struct page **pages, int count)
 {
 	while (count--)
@@ -522,55 +543,45 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	return pages;
 }
 
-/**
- * iommu_dma_free - Free a buffer allocated by iommu_dma_alloc()
- * @dev: Device which owns this buffer
- * @pages: Array of buffer pages as returned by iommu_dma_alloc()
- * @size: Size of buffer in bytes
- * @handle: DMA address of buffer
- *
- * Frees both the pages associated with the buffer, and the array
- * describing them
- */
-void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
-		dma_addr_t *handle)
+static struct page **__iommu_dma_get_pages(void *cpu_addr)
 {
-	__iommu_dma_unmap(iommu_get_dma_domain(dev), *handle, size);
-	__iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
-	*handle = DMA_MAPPING_ERROR;
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || !area->pages)
+		return NULL;
+	return area->pages;
 }
 
 /**
- * iommu_dma_alloc - Allocate and map a buffer contiguous in IOVA space
+ * iommu_dma_alloc_remap - Allocate and map a buffer contiguous in IOVA space
  * @dev: Device to allocate memory for. Must be a real device
  *	 attached to an iommu_dma_domain
  * @size: Size of buffer in bytes
+ * @dma_handle: Out argument for allocated DMA handle
  * @gfp: Allocation flags
  * @attrs: DMA attributes for this allocation
- * @prot: IOMMU mapping flags
- * @handle: Out argument for allocated DMA handle
- * @flush_page: Arch callback which must ensure PAGE_SIZE bytes from the
- *		given VA/PA are visible to the given non-coherent device.
  *
  * If @size is less than PAGE_SIZE, then a full CPU page will be allocated,
  * but an IOMMU which supports smaller pages might not map the whole thing.
  *
- * Return: Array of struct page pointers describing the buffer,
- *	   or NULL on failure.
+ * Return: Mapped virtual address, or NULL on failure.
  */
-struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
-		unsigned long attrs, int prot, dma_addr_t *handle,
-		void (*flush_page)(struct device *, const void *, phys_addr_t))
+static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
+	bool coherent = dev_is_dma_coherent(dev);
+	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
+	pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
+	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 	struct page **pages;
 	struct sg_table sgt;
 	dma_addr_t iova;
-	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
+	void *vaddr;
 
-	*handle = DMA_MAPPING_ERROR;
+	*dma_handle = DMA_MAPPING_ERROR;
 
 	min_size = alloc_sizes & -alloc_sizes;
 	if (min_size < PAGE_SIZE) {
@@ -596,26 +607,29 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
 	if (sg_alloc_table_from_pages(&sgt, pages, count, 0, size, GFP_KERNEL))
 		goto out_free_iova;
 
-	if (!(prot & IOMMU_CACHE)) {
-		struct sg_mapping_iter miter;
-		/*
-		 * The CPU-centric flushing implied by SG_MITER_TO_SG isn't
-		 * sufficient here, so skip it by using the "wrong" direction.
-		 */
-		sg_miter_start(&miter, sgt.sgl, sgt.orig_nents, SG_MITER_FROM_SG);
-		while (sg_miter_next(&miter))
-			flush_page(dev, miter.addr, page_to_phys(miter.page));
-		sg_miter_stop(&miter);
+	if (!(ioprot & IOMMU_CACHE)) {
+		struct scatterlist *sg;
+		int i;
+
+		for_each_sg(sgt.sgl, sg, sgt.orig_nents, i)
+			arch_dma_prep_coherent(sg_page(sg), sg->length);
 	}
 
-	if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, prot)
+	if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
 			< size)
 		goto out_free_sg;
 
-	*handle = iova;
+	vaddr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
+			__builtin_return_address(0));
+	if (!vaddr)
+		goto out_unmap;
+
+	*dma_handle = iova;
 	sg_free_table(&sgt);
-	return pages;
+	return vaddr;
 
+out_unmap:
+	__iommu_dma_unmap(dev, iova, size);
 out_free_sg:
 	sg_free_table(&sgt);
 out_free_iova:
@@ -626,54 +640,94 @@ out_free_pages:
 }
 
 /**
- * iommu_dma_mmap - Map a buffer into provided user VMA
- * @pages: Array representing buffer from iommu_dma_alloc()
+ * __iommu_dma_mmap - Map a buffer into provided user VMA
+ * @pages: Array representing buffer from __iommu_dma_alloc()
  * @size: Size of buffer in bytes
  * @vma: VMA describing requested userspace mapping
  *
  * Maps the pages of the buffer in @pages into @vma. The caller is responsible
  * for verifying the correct size and protection of @vma beforehand.
  */
-
-int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma)
+static int __iommu_dma_mmap(struct page **pages, size_t size,
+		struct vm_area_struct *vma)
 {
 	return vm_map_pages(vma, pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
 }
 
-static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
-		size_t size, int prot, struct iommu_domain *domain)
+static void iommu_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
 {
-	struct iommu_dma_cookie *cookie = domain->iova_cookie;
-	size_t iova_off = 0;
-	dma_addr_t iova;
+	phys_addr_t phys;
 
-	if (cookie->type == IOMMU_DMA_IOVA_COOKIE) {
-		iova_off = iova_offset(&cookie->iovad, phys);
-		size = iova_align(&cookie->iovad, size + iova_off);
-	}
+	if (dev_is_dma_coherent(dev))
+		return;
 
-	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
-	if (!iova)
-		return DMA_MAPPING_ERROR;
+	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
+	arch_sync_dma_for_cpu(dev, phys, size, dir);
+}
 
-	if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
-		iommu_dma_free_iova(cookie, iova, size);
-		return DMA_MAPPING_ERROR;
-	}
-	return iova + iova_off;
+static void iommu_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t phys;
+
+	if (dev_is_dma_coherent(dev))
+		return;
+
+	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
+	arch_sync_dma_for_device(dev, phys, size, dir);
+}
+
+static void iommu_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nelems,
+		enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	if (dev_is_dma_coherent(dev))
+		return;
+
+	for_each_sg(sgl, sg, nelems, i)
+		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+}
+
+static void iommu_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nelems,
+		enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	if (dev_is_dma_coherent(dev))
+		return;
+
+	for_each_sg(sgl, sg, nelems, i)
+		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
 }
 
-dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, int prot)
+static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
 {
-	return __iommu_dma_map(dev, page_to_phys(page) + offset, size, prot,
-			iommu_get_dma_domain(dev));
+	phys_addr_t phys = page_to_phys(page) + offset;
+	bool coherent = dev_is_dma_coherent(dev);
+	int prot = dma_info_to_prot(dir, coherent, attrs);
+	dma_addr_t dma_handle;
+
+	dma_handle =__iommu_dma_map(dev, phys, size, prot);
+	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+	    dma_handle != DMA_MAPPING_ERROR)
+		arch_sync_dma_for_device(dev, phys, size, dir);
+	return dma_handle;
 }
 
-void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
+static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	__iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		iommu_dma_sync_single_for_cpu(dev, dma_handle, size, dir);
+	__iommu_dma_unmap(dev, dma_handle, size);
 }
 
 /*
@@ -758,18 +812,22 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
  * impedance-matching, to be able to hand off a suitably-aligned list,
  * but still preserve the original offsets and sizes for the caller.
  */
-int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, int prot)
+static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	struct scatterlist *s, *prev = NULL;
+	int prot = dma_info_to_prot(dir, dev_is_dma_coherent(dev), attrs);
 	dma_addr_t iova;
 	size_t iova_len = 0;
 	unsigned long mask = dma_get_seg_boundary(dev);
 	int i;
 
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
+
 	/*
 	 * Work out how much IOVA space we need, and align the segments to
 	 * IOVA granules for the IOMMU driver to handle. With some clever
@@ -829,12 +887,16 @@ out_restore_sg:
 	return 0;
 }
 
-void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir, unsigned long attrs)
+static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	dma_addr_t start, end;
 	struct scatterlist *tmp;
 	int i;
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
+
 	/*
 	 * The scatterlist segments are mapped into a single
 	 * contiguous IOVA allocation, so this is incredibly easy.
@@ -846,21 +908,231 @@ void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 		sg = tmp;
 	}
 	end = sg_dma_address(sg) + sg_dma_len(sg);
-	__iommu_dma_unmap(iommu_get_dma_domain(dev), start, end - start);
+	__iommu_dma_unmap(dev, start, end - start);
 }
 
-dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
+static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	return __iommu_dma_map(dev, phys, size,
-			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
-			iommu_get_dma_domain(dev));
+			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO);
 }
 
-void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
+static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	__iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size);
+	__iommu_dma_unmap(dev, handle, size);
+}
+
+static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
+{
+	size_t alloc_size = PAGE_ALIGN(size);
+	int count = alloc_size >> PAGE_SHIFT;
+	struct page *page = NULL, **pages = NULL;
+
+	/* Non-coherent atomic allocation? Easy */
+	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_free_from_pool(cpu_addr, alloc_size))
+		return;
+
+	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+		/*
+		 * If it the address is remapped, then it's either non-coherent
+		 * or highmem CMA, or an iommu_dma_alloc_remap() construction.
+		 */
+		pages = __iommu_dma_get_pages(cpu_addr);
+		if (!pages)
+			page = vmalloc_to_page(cpu_addr);
+		dma_common_free_remap(cpu_addr, alloc_size, VM_USERMAP);
+	} else {
+		/* Lowmem means a coherent atomic or CMA allocation */
+		page = virt_to_page(cpu_addr);
+	}
+
+	if (pages)
+		__iommu_dma_free_pages(pages, count);
+	if (page && !dma_release_from_contiguous(dev, page, count))
+		__free_pages(page, get_order(alloc_size));
+}
+
+static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t handle, unsigned long attrs)
+{
+	__iommu_dma_unmap(dev, handle, size);
+	__iommu_dma_free(dev, size, cpu_addr);
+}
+
+static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
+		struct page **pagep, gfp_t gfp, unsigned long attrs)
+{
+	bool coherent = dev_is_dma_coherent(dev);
+	size_t alloc_size = PAGE_ALIGN(size);
+	struct page *page = NULL;
+	void *cpu_addr;
+
+	if (gfpflags_allow_blocking(gfp))
+		page = dma_alloc_from_contiguous(dev, alloc_size >> PAGE_SHIFT,
+						 get_order(alloc_size),
+						 gfp & __GFP_NOWARN);
+	if (!page)
+		page = alloc_pages(gfp, get_order(alloc_size));
+	if (!page)
+		return NULL;
+
+	if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) {
+		pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
+
+		cpu_addr = dma_common_contiguous_remap(page, alloc_size,
+				VM_USERMAP, prot, __builtin_return_address(0));
+		if (!cpu_addr)
+			goto out_free_pages;
+
+		if (!coherent)
+			arch_dma_prep_coherent(page, size);
+	} else {
+		cpu_addr = page_address(page);
+	}
+
+	*pagep = page;
+	memset(cpu_addr, 0, alloc_size);
+	return cpu_addr;
+out_free_pages:
+	if (!dma_release_from_contiguous(dev, page, alloc_size >> PAGE_SHIFT))
+		__free_pages(page, get_order(alloc_size));
+	return NULL;
+}
+
+static void *iommu_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
+{
+	bool coherent = dev_is_dma_coherent(dev);
+	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
+	struct page *page = NULL;
+	void *cpu_addr;
+
+	gfp |= __GFP_ZERO;
+
+	if (IS_ENABLED(CONFIG_DMA_REMAP) && gfpflags_allow_blocking(gfp) &&
+	    !(attrs & DMA_ATTR_FORCE_CONTIGUOUS))
+		return iommu_dma_alloc_remap(dev, size, handle, gfp, attrs);
+
+	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !gfpflags_allow_blocking(gfp) && !coherent)
+		cpu_addr = dma_alloc_from_pool(PAGE_ALIGN(size), &page, gfp);
+	else
+		cpu_addr = iommu_dma_alloc_pages(dev, size, &page, gfp, attrs);
+	if (!cpu_addr)
+		return NULL;
+
+	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot);
+	if (*handle == DMA_MAPPING_ERROR) {
+		__iommu_dma_free(dev, size, cpu_addr);
+		return NULL;
+	}
+
+	return cpu_addr;
+}
+
+static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn, off = vma->vm_pgoff;
+	int ret;
+
+	vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off >= nr_pages || vma_pages(vma) > nr_pages - off)
+		return -ENXIO;
+
+	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+		struct page **pages = __iommu_dma_get_pages(cpu_addr);
+
+		if (pages)
+			return __iommu_dma_mmap(pages, size, vma);
+		pfn = vmalloc_to_pfn(cpu_addr);
+	} else {
+		pfn = page_to_pfn(virt_to_page(cpu_addr));
+	}
+
+	return remap_pfn_range(vma, vma->vm_start, pfn + off,
+			       vma->vm_end - vma->vm_start,
+			       vma->vm_page_prot);
+}
+
+static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	struct page *page;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+		struct page **pages = __iommu_dma_get_pages(cpu_addr);
+
+		if (pages) {
+			return sg_alloc_table_from_pages(sgt, pages,
+					PAGE_ALIGN(size) >> PAGE_SHIFT,
+					0, size, GFP_KERNEL);
+		}
+
+		page = vmalloc_to_page(cpu_addr);
+	} else {
+		page = virt_to_page(cpu_addr);
+	}
+
+	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+	if (!ret)
+		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	return ret;
+}
+
+static const struct dma_map_ops iommu_dma_ops = {
+	.alloc			= iommu_dma_alloc,
+	.free			= iommu_dma_free,
+	.mmap			= iommu_dma_mmap,
+	.get_sgtable		= iommu_dma_get_sgtable,
+	.map_page		= iommu_dma_map_page,
+	.unmap_page		= iommu_dma_unmap_page,
+	.map_sg			= iommu_dma_map_sg,
+	.unmap_sg		= iommu_dma_unmap_sg,
+	.sync_single_for_cpu	= iommu_dma_sync_single_for_cpu,
+	.sync_single_for_device	= iommu_dma_sync_single_for_device,
+	.sync_sg_for_cpu	= iommu_dma_sync_sg_for_cpu,
+	.sync_sg_for_device	= iommu_dma_sync_sg_for_device,
+	.map_resource		= iommu_dma_map_resource,
+	.unmap_resource		= iommu_dma_unmap_resource,
+};
+
+/*
+ * The IOMMU core code allocates the default DMA domain, which the underlying
+ * IOMMU driver needs to support via the dma-iommu layer.
+ */
+void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size)
+{
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+
+	if (!domain)
+		goto out_err;
+
+	/*
+	 * The IOMMU core code allocates the default DMA domain, which the
+	 * underlying IOMMU driver needs to support via the dma-iommu layer.
+	 */
+	if (domain->type == IOMMU_DOMAIN_DMA) {
+		if (iommu_dma_init_domain(domain, dma_base, size, dev))
+			goto out_err;
+		dev->dma_ops = &iommu_dma_ops;
+	}
+
+	return;
+out_err:
+	 pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+		 dev_name(dev));
 }
 
 static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
@@ -881,7 +1153,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	if (!msi_page)
 		return NULL;
 
-	iova = __iommu_dma_map(dev, msi_addr, size, prot, domain);
+	iova = __iommu_dma_map(dev, msi_addr, size, prot);
 	if (iova == DMA_MAPPING_ERROR)
 		goto out_free_page;
 
@@ -943,3 +1215,9 @@ void iommu_dma_compose_msi_msg(struct msi_desc *desc,
 	msg->address_lo &= cookie_msi_granule(domain->iova_cookie) - 1;
 	msg->address_lo += lower_32_bits(msi_page->iova);
 }
+
+static int iommu_dma_init(void)
+{
+	return iova_cache_get();
+}
+arch_initcall(iommu_dma_init);
diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c
index 7fabf9b1c2dc..73a552914455 100644
--- a/drivers/iommu/intel-iommu-debugfs.c
+++ b/drivers/iommu/intel-iommu-debugfs.c
@@ -14,6 +14,17 @@
 
 #include <asm/irq_remapping.h>
 
+#include "intel-pasid.h"
+
+struct tbl_walk {
+	u16 bus;
+	u16 devfn;
+	u32 pasid;
+	struct root_entry *rt_entry;
+	struct context_entry *ctx_entry;
+	struct pasid_entry *pasid_tbl_entry;
+};
+
 struct iommu_regset {
 	int offset;
 	const char *regs;
@@ -131,16 +142,86 @@ out:
 }
 DEFINE_SHOW_ATTRIBUTE(iommu_regset);
 
-static void ctx_tbl_entry_show(struct seq_file *m, struct intel_iommu *iommu,
-			       int bus)
+static inline void print_tbl_walk(struct seq_file *m)
 {
-	struct context_entry *context;
-	int devfn;
+	struct tbl_walk *tbl_wlk = m->private;
+
+	seq_printf(m, "%02x:%02x.%x\t0x%016llx:0x%016llx\t0x%016llx:0x%016llx\t",
+		   tbl_wlk->bus, PCI_SLOT(tbl_wlk->devfn),
+		   PCI_FUNC(tbl_wlk->devfn), tbl_wlk->rt_entry->hi,
+		   tbl_wlk->rt_entry->lo, tbl_wlk->ctx_entry->hi,
+		   tbl_wlk->ctx_entry->lo);
+
+	/*
+	 * A legacy mode DMAR doesn't support PASID, hence default it to -1
+	 * indicating that it's invalid. Also, default all PASID related fields
+	 * to 0.
+	 */
+	if (!tbl_wlk->pasid_tbl_entry)
+		seq_printf(m, "%-6d\t0x%016llx:0x%016llx:0x%016llx\n", -1,
+			   (u64)0, (u64)0, (u64)0);
+	else
+		seq_printf(m, "%-6d\t0x%016llx:0x%016llx:0x%016llx\n",
+			   tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[0],
+			   tbl_wlk->pasid_tbl_entry->val[1],
+			   tbl_wlk->pasid_tbl_entry->val[2]);
+}
 
-	seq_printf(m, " Context Table Entries for Bus: %d\n", bus);
-	seq_puts(m, "  Entry\tB:D.F\tHigh\tLow\n");
+static void pasid_tbl_walk(struct seq_file *m, struct pasid_entry *tbl_entry,
+			   u16 dir_idx)
+{
+	struct tbl_walk *tbl_wlk = m->private;
+	u8 tbl_idx;
+
+	for (tbl_idx = 0; tbl_idx < PASID_TBL_ENTRIES; tbl_idx++) {
+		if (pasid_pte_is_present(tbl_entry)) {
+			tbl_wlk->pasid_tbl_entry = tbl_entry;
+			tbl_wlk->pasid = (dir_idx << PASID_PDE_SHIFT) + tbl_idx;
+			print_tbl_walk(m);
+		}
+
+		tbl_entry++;
+	}
+}
+
+static void pasid_dir_walk(struct seq_file *m, u64 pasid_dir_ptr,
+			   u16 pasid_dir_size)
+{
+	struct pasid_dir_entry *dir_entry = phys_to_virt(pasid_dir_ptr);
+	struct pasid_entry *pasid_tbl;
+	u16 dir_idx;
+
+	for (dir_idx = 0; dir_idx < pasid_dir_size; dir_idx++) {
+		pasid_tbl = get_pasid_table_from_pde(dir_entry);
+		if (pasid_tbl)
+			pasid_tbl_walk(m, pasid_tbl, dir_idx);
+
+		dir_entry++;
+	}
+}
+
+static void ctx_tbl_walk(struct seq_file *m, struct intel_iommu *iommu, u16 bus)
+{
+	struct context_entry *context;
+	u16 devfn, pasid_dir_size;
+	u64 pasid_dir_ptr;
 
 	for (devfn = 0; devfn < 256; devfn++) {
+		struct tbl_walk tbl_wlk = {0};
+
+		/*
+		 * Scalable mode root entry points to upper scalable mode
+		 * context table and lower scalable mode context table. Each
+		 * scalable mode context table has 128 context entries where as
+		 * legacy mode context table has 256 context entries. So in
+		 * scalable mode, the context entries for former 128 devices are
+		 * in the lower scalable mode context table, while the latter
+		 * 128 devices are in the upper scalable mode context table.
+		 * In scalable mode, when devfn > 127, iommu_context_addr()
+		 * automatically refers to upper scalable mode context table and
+		 * hence the caller doesn't have to worry about differences
+		 * between scalable mode and non scalable mode.
+		 */
 		context = iommu_context_addr(iommu, bus, devfn, 0);
 		if (!context)
 			return;
@@ -148,33 +229,41 @@ static void ctx_tbl_entry_show(struct seq_file *m, struct intel_iommu *iommu,
 		if (!context_present(context))
 			continue;
 
-		seq_printf(m, "  %-5d\t%02x:%02x.%x\t%-6llx\t%llx\n", devfn,
-			   bus, PCI_SLOT(devfn), PCI_FUNC(devfn),
-			   context[0].hi, context[0].lo);
+		tbl_wlk.bus = bus;
+		tbl_wlk.devfn = devfn;
+		tbl_wlk.rt_entry = &iommu->root_entry[bus];
+		tbl_wlk.ctx_entry = context;
+		m->private = &tbl_wlk;
+
+		if (pasid_supported(iommu) && is_pasid_enabled(context)) {
+			pasid_dir_ptr = context->lo & VTD_PAGE_MASK;
+			pasid_dir_size = get_pasid_dir_size(context);
+			pasid_dir_walk(m, pasid_dir_ptr, pasid_dir_size);
+			continue;
+		}
+
+		print_tbl_walk(m);
 	}
 }
 
-static void root_tbl_entry_show(struct seq_file *m, struct intel_iommu *iommu)
+static void root_tbl_walk(struct seq_file *m, struct intel_iommu *iommu)
 {
 	unsigned long flags;
-	int bus;
+	u16 bus;
 
 	spin_lock_irqsave(&iommu->lock, flags);
-	seq_printf(m, "IOMMU %s: Root Table Address:%llx\n", iommu->name,
+	seq_printf(m, "IOMMU %s: Root Table Address: 0x%llx\n", iommu->name,
 		   (u64)virt_to_phys(iommu->root_entry));
-	seq_puts(m, "Root Table Entries:\n");
+	seq_puts(m, "B.D.F\tRoot_entry\t\t\t\tContext_entry\t\t\t\tPASID\tPASID_table_entry\n");
 
-	for (bus = 0; bus < 256; bus++) {
-		if (!(iommu->root_entry[bus].lo & 1))
-			continue;
+	/*
+	 * No need to check if the root entry is present or not because
+	 * iommu_context_addr() performs the same check before returning
+	 * context entry.
+	 */
+	for (bus = 0; bus < 256; bus++)
+		ctx_tbl_walk(m, iommu, bus);
 
-		seq_printf(m, " Bus: %d H: %llx L: %llx\n", bus,
-			   iommu->root_entry[bus].hi,
-			   iommu->root_entry[bus].lo);
-
-		ctx_tbl_entry_show(m, iommu, bus);
-		seq_putc(m, '\n');
-	}
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
@@ -185,7 +274,7 @@ static int dmar_translation_struct_show(struct seq_file *m, void *unused)
 
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
-		root_tbl_entry_show(m, iommu);
+		root_tbl_walk(m, iommu);
 		seq_putc(m, '\n');
 	}
 	rcu_read_unlock();
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 162b3236e72c..ac4172c02244 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -294,14 +294,16 @@ static inline void context_clear_entry(struct context_entry *context)
 static struct dmar_domain *si_domain;
 static int hw_pass_through = 1;
 
+/* si_domain contains mulitple devices */
+#define DOMAIN_FLAG_STATIC_IDENTITY		BIT(0)
+
 /*
- * Domain represents a virtual machine, more than one devices
- * across iommus may be owned in one domain, e.g. kvm guest.
+ * This is a DMA domain allocated through the iommu domain allocation
+ * interface. But one or more devices belonging to this domain have
+ * been chosen to use a private domain. We should avoid to use the
+ * map/unmap/iova_to_phys APIs on it.
  */
-#define DOMAIN_FLAG_VIRTUAL_MACHINE	(1 << 0)
-
-/* si_domain contains mulitple devices */
-#define DOMAIN_FLAG_STATIC_IDENTITY	(1 << 1)
+#define DOMAIN_FLAG_LOSE_CHILDREN		BIT(1)
 
 #define for_each_domain_iommu(idx, domain)			\
 	for (idx = 0; idx < g_num_of_iommus; idx++)		\
@@ -314,7 +316,6 @@ struct dmar_rmrr_unit {
 	u64	end_address;		/* reserved end address */
 	struct dmar_dev_scope *devices;	/* target devices */
 	int	devices_cnt;		/* target device count */
-	struct iommu_resv_region *resv; /* reserved region handle */
 };
 
 struct dmar_atsr_unit {
@@ -342,6 +343,9 @@ static void domain_context_clear(struct intel_iommu *iommu,
 				 struct device *dev);
 static int domain_detach_iommu(struct dmar_domain *domain,
 			       struct intel_iommu *iommu);
+static bool device_is_rmrr_locked(struct device *dev);
+static int intel_iommu_attach_device(struct iommu_domain *domain,
+				     struct device *dev);
 
 #ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
 int dmar_disabled = 0;
@@ -349,6 +353,7 @@ int dmar_disabled = 0;
 int dmar_disabled = 1;
 #endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/
 
+int intel_iommu_sm;
 int intel_iommu_enabled = 0;
 EXPORT_SYMBOL_GPL(intel_iommu_enabled);
 
@@ -356,21 +361,17 @@ static int dmar_map_gfx = 1;
 static int dmar_forcedac;
 static int intel_iommu_strict;
 static int intel_iommu_superpage = 1;
-static int intel_iommu_sm;
 static int iommu_identity_mapping;
 
 #define IDENTMAP_ALL		1
 #define IDENTMAP_GFX		2
 #define IDENTMAP_AZALIA		4
 
-#define sm_supported(iommu)	(intel_iommu_sm && ecap_smts((iommu)->ecap))
-#define pasid_supported(iommu)	(sm_supported(iommu) &&			\
-				 ecap_pasid((iommu)->ecap))
-
 int intel_iommu_gfx_mapped;
 EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
 
 #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
+#define DEFER_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-2))
 static DEFINE_SPINLOCK(device_domain_lock);
 static LIST_HEAD(device_domain_list);
 
@@ -535,22 +536,11 @@ static inline void free_devinfo_mem(void *vaddr)
 	kmem_cache_free(iommu_devinfo_cache, vaddr);
 }
 
-static inline int domain_type_is_vm(struct dmar_domain *domain)
-{
-	return domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE;
-}
-
 static inline int domain_type_is_si(struct dmar_domain *domain)
 {
 	return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY;
 }
 
-static inline int domain_type_is_vm_or_si(struct dmar_domain *domain)
-{
-	return domain->flags & (DOMAIN_FLAG_VIRTUAL_MACHINE |
-				DOMAIN_FLAG_STATIC_IDENTITY);
-}
-
 static inline int domain_pfn_supported(struct dmar_domain *domain,
 				       unsigned long pfn)
 {
@@ -598,7 +588,9 @@ struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
 	int iommu_id;
 
 	/* si_domain and vm domain should not get here. */
-	BUG_ON(domain_type_is_vm_or_si(domain));
+	if (WARN_ON(domain->domain.type != IOMMU_DOMAIN_DMA))
+		return NULL;
+
 	for_each_domain_iommu(iommu_id, domain)
 		break;
 
@@ -729,12 +721,39 @@ static int iommu_dummy(struct device *dev)
 	return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
 }
 
+/**
+ * is_downstream_to_pci_bridge - test if a device belongs to the PCI
+ *				 sub-hierarchy of a candidate PCI-PCI bridge
+ * @dev: candidate PCI device belonging to @bridge PCI sub-hierarchy
+ * @bridge: the candidate PCI-PCI bridge
+ *
+ * Return: true if @dev belongs to @bridge PCI sub-hierarchy, else false.
+ */
+static bool
+is_downstream_to_pci_bridge(struct device *dev, struct device *bridge)
+{
+	struct pci_dev *pdev, *pbridge;
+
+	if (!dev_is_pci(dev) || !dev_is_pci(bridge))
+		return false;
+
+	pdev = to_pci_dev(dev);
+	pbridge = to_pci_dev(bridge);
+
+	if (pbridge->subordinate &&
+	    pbridge->subordinate->number <= pdev->bus->number &&
+	    pbridge->subordinate->busn_res.end >= pdev->bus->number)
+		return true;
+
+	return false;
+}
+
 static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
 	struct intel_iommu *iommu;
 	struct device *tmp;
-	struct pci_dev *ptmp, *pdev = NULL;
+	struct pci_dev *pdev = NULL;
 	u16 segment = 0;
 	int i;
 
@@ -780,13 +799,7 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 				goto out;
 			}
 
-			if (!pdev || !dev_is_pci(tmp))
-				continue;
-
-			ptmp = to_pci_dev(tmp);
-			if (ptmp->subordinate &&
-			    ptmp->subordinate->number <= pdev->bus->number &&
-			    ptmp->subordinate->busn_res.end >= pdev->bus->number)
+			if (is_downstream_to_pci_bridge(dev, tmp))
 				goto got_pdev;
 		}
 
@@ -908,7 +921,6 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 	return pte;
 }
 
-
 /* return address's pte at specific level */
 static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
 					 unsigned long pfn,
@@ -1577,7 +1589,6 @@ static void iommu_disable_translation(struct intel_iommu *iommu)
 	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
 }
 
-
 static int iommu_init_domains(struct intel_iommu *iommu)
 {
 	u32 ndomains, nlongs;
@@ -1615,8 +1626,6 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 		return -ENOMEM;
 	}
 
-
-
 	/*
 	 * If Caching mode is set, then invalid translations are tagged
 	 * with domain-id 0, hence we need to pre-allocate it. We also
@@ -1646,32 +1655,15 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
 	if (!iommu->domains || !iommu->domain_ids)
 		return;
 
-again:
 	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_entry_safe(info, tmp, &device_domain_list, global) {
-		struct dmar_domain *domain;
-
 		if (info->iommu != iommu)
 			continue;
 
 		if (!info->dev || !info->domain)
 			continue;
 
-		domain = info->domain;
-
 		__dmar_remove_one_dev_info(info);
-
-		if (!domain_type_is_vm_or_si(domain)) {
-			/*
-			 * The domain_exit() function  can't be called under
-			 * device_domain_lock, as it takes this lock itself.
-			 * So release the lock here and re-run the loop
-			 * afterwards.
-			 */
-			spin_unlock_irqrestore(&device_domain_lock, flags);
-			domain_exit(domain);
-			goto again;
-		}
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
@@ -1841,71 +1833,12 @@ static inline int guestwidth_to_adjustwidth(int gaw)
 	return agaw;
 }
 
-static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu,
-		       int guest_width)
-{
-	int adjust_width, agaw;
-	unsigned long sagaw;
-	int err;
-
-	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
-
-	err = init_iova_flush_queue(&domain->iovad,
-				    iommu_flush_iova, iova_entry_free);
-	if (err)
-		return err;
-
-	domain_reserve_special_ranges(domain);
-
-	/* calculate AGAW */
-	if (guest_width > cap_mgaw(iommu->cap))
-		guest_width = cap_mgaw(iommu->cap);
-	domain->gaw = guest_width;
-	adjust_width = guestwidth_to_adjustwidth(guest_width);
-	agaw = width_to_agaw(adjust_width);
-	sagaw = cap_sagaw(iommu->cap);
-	if (!test_bit(agaw, &sagaw)) {
-		/* hardware doesn't support it, choose a bigger one */
-		pr_debug("Hardware doesn't support agaw %d\n", agaw);
-		agaw = find_next_bit(&sagaw, 5, agaw);
-		if (agaw >= 5)
-			return -ENODEV;
-	}
-	domain->agaw = agaw;
-
-	if (ecap_coherent(iommu->ecap))
-		domain->iommu_coherency = 1;
-	else
-		domain->iommu_coherency = 0;
-
-	if (ecap_sc_support(iommu->ecap))
-		domain->iommu_snooping = 1;
-	else
-		domain->iommu_snooping = 0;
-
-	if (intel_iommu_superpage)
-		domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
-	else
-		domain->iommu_superpage = 0;
-
-	domain->nid = iommu->node;
-
-	/* always allocate the top pgd */
-	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
-	if (!domain->pgd)
-		return -ENOMEM;
-	__iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE);
-	return 0;
-}
-
 static void domain_exit(struct dmar_domain *domain)
 {
 	struct page *freelist;
 
 	/* Remove associated devices and clear attached or cached domains */
-	rcu_read_lock();
 	domain_remove_dev_info(domain);
-	rcu_read_unlock();
 
 	/* destroy iovas */
 	put_iova_domain(&domain->iovad);
@@ -2336,7 +2269,7 @@ static int domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			  struct scatterlist *sg, unsigned long phys_pfn,
 			  unsigned long nr_pages, int prot)
 {
-	int ret;
+	int iommu_id, ret;
 	struct intel_iommu *iommu;
 
 	/* Do the real mapping first */
@@ -2344,18 +2277,8 @@ static int domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	if (ret)
 		return ret;
 
-	/* Notify about the new mapping */
-	if (domain_type_is_vm(domain)) {
-		/* VM typed domains can have more than one IOMMUs */
-		int iommu_id;
-
-		for_each_domain_iommu(iommu_id, domain) {
-			iommu = g_iommus[iommu_id];
-			__mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
-		}
-	} else {
-		/* General domains only have one IOMMU */
-		iommu = domain_get_iommu(domain);
+	for_each_domain_iommu(iommu_id, domain) {
+		iommu = g_iommus[iommu_id];
 		__mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
 	}
 
@@ -2435,8 +2358,18 @@ static struct dmar_domain *find_domain(struct device *dev)
 {
 	struct device_domain_info *info;
 
+	if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO)) {
+		struct iommu_domain *domain;
+
+		dev->archdata.iommu = NULL;
+		domain = iommu_get_domain_for_dev(dev);
+		if (domain)
+			intel_iommu_attach_device(domain, dev);
+	}
+
 	/* No lock here, assumes no domain exit in normal case */
 	info = dev->archdata.iommu;
+
 	if (likely(info))
 		return info->domain;
 	return NULL;
@@ -2580,6 +2513,31 @@ static int get_last_alias(struct pci_dev *pdev, u16 alias, void *opaque)
 	return 0;
 }
 
+static int domain_init(struct dmar_domain *domain, int guest_width)
+{
+	int adjust_width;
+
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
+	domain_reserve_special_ranges(domain);
+
+	/* calculate AGAW */
+	domain->gaw = guest_width;
+	adjust_width = guestwidth_to_adjustwidth(guest_width);
+	domain->agaw = width_to_agaw(adjust_width);
+
+	domain->iommu_coherency = 0;
+	domain->iommu_snooping = 0;
+	domain->iommu_superpage = 0;
+	domain->max_addr = 0;
+
+	/* always allocate the top pgd */
+	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
+	if (!domain->pgd)
+		return -ENOMEM;
+	domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
+	return 0;
+}
+
 static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw)
 {
 	struct device_domain_info *info;
@@ -2617,13 +2575,20 @@ static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw)
 	domain = alloc_domain(0);
 	if (!domain)
 		return NULL;
-	if (domain_init(domain, iommu, gaw)) {
+
+	if (domain_init(domain, gaw)) {
 		domain_exit(domain);
 		return NULL;
 	}
 
-out:
+	if (init_iova_flush_queue(&domain->iovad,
+				  iommu_flush_iova,
+				  iova_entry_free)) {
+		pr_warn("iova flush queue initialization failed\n");
+		intel_iommu_strict = 1;
+	}
 
+out:
 	return domain;
 }
 
@@ -2663,29 +2628,6 @@ static struct dmar_domain *set_domain_for_dev(struct device *dev,
 	return domain;
 }
 
-static struct dmar_domain *get_domain_for_dev(struct device *dev, int gaw)
-{
-	struct dmar_domain *domain, *tmp;
-
-	domain = find_domain(dev);
-	if (domain)
-		goto out;
-
-	domain = find_or_alloc_domain(dev, gaw);
-	if (!domain)
-		goto out;
-
-	tmp = set_domain_for_dev(dev, domain);
-	if (!tmp || domain != tmp) {
-		domain_exit(domain);
-		domain = tmp;
-	}
-
-out:
-
-	return domain;
-}
-
 static int iommu_domain_identity_map(struct dmar_domain *domain,
 				     unsigned long long start,
 				     unsigned long long end)
@@ -2750,75 +2692,21 @@ static int domain_prepare_identity_map(struct device *dev,
 	return iommu_domain_identity_map(domain, start, end);
 }
 
-static int iommu_prepare_identity_map(struct device *dev,
-				      unsigned long long start,
-				      unsigned long long end)
-{
-	struct dmar_domain *domain;
-	int ret;
-
-	domain = get_domain_for_dev(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
-	if (!domain)
-		return -ENOMEM;
-
-	ret = domain_prepare_identity_map(dev, domain, start, end);
-	if (ret)
-		domain_exit(domain);
-
-	return ret;
-}
-
-static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
-					 struct device *dev)
-{
-	if (dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
-		return 0;
-	return iommu_prepare_identity_map(dev, rmrr->base_address,
-					  rmrr->end_address);
-}
-
-#ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA
-static inline void iommu_prepare_isa(void)
-{
-	struct pci_dev *pdev;
-	int ret;
-
-	pdev = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL);
-	if (!pdev)
-		return;
-
-	pr_info("Prepare 0-16MiB unity mapping for LPC\n");
-	ret = iommu_prepare_identity_map(&pdev->dev, 0, 16*1024*1024 - 1);
-
-	if (ret)
-		pr_err("Failed to create 0-16MiB identity map - floppy might not work\n");
-
-	pci_dev_put(pdev);
-}
-#else
-static inline void iommu_prepare_isa(void)
-{
-	return;
-}
-#endif /* !CONFIG_INTEL_IOMMU_FLPY_WA */
-
-static int md_domain_init(struct dmar_domain *domain, int guest_width);
-
 static int __init si_domain_init(int hw)
 {
-	int nid, ret;
+	struct dmar_rmrr_unit *rmrr;
+	struct device *dev;
+	int i, nid, ret;
 
 	si_domain = alloc_domain(DOMAIN_FLAG_STATIC_IDENTITY);
 	if (!si_domain)
 		return -EFAULT;
 
-	if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+	if (domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
 		domain_exit(si_domain);
 		return -EFAULT;
 	}
 
-	pr_debug("Identity mapping domain allocated\n");
-
 	if (hw)
 		return 0;
 
@@ -2834,6 +2722,31 @@ static int __init si_domain_init(int hw)
 		}
 	}
 
+	/*
+	 * Normally we use DMA domains for devices which have RMRRs. But we
+	 * loose this requirement for graphic and usb devices. Identity map
+	 * the RMRRs for graphic and USB devices so that they could use the
+	 * si_domain.
+	 */
+	for_each_rmrr_units(rmrr) {
+		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
+					  i, dev) {
+			unsigned long long start = rmrr->base_address;
+			unsigned long long end = rmrr->end_address;
+
+			if (device_is_rmrr_locked(dev))
+				continue;
+
+			if (WARN_ON(end < start ||
+				    end >> agaw_to_width(si_domain->agaw)))
+				continue;
+
+			ret = iommu_domain_identity_map(si_domain, start, end);
+			if (ret)
+				return ret;
+		}
+	}
+
 	return 0;
 }
 
@@ -2841,9 +2754,6 @@ static int identity_mapping(struct device *dev)
 {
 	struct device_domain_info *info;
 
-	if (likely(!iommu_identity_mapping))
-		return 0;
-
 	info = dev->archdata.iommu;
 	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
 		return (info->domain == si_domain);
@@ -2882,7 +2792,8 @@ static bool device_has_rmrr(struct device *dev)
 		 */
 		for_each_active_dev_scope(rmrr->devices,
 					  rmrr->devices_cnt, i, tmp)
-			if (tmp == dev) {
+			if (tmp == dev ||
+			    is_downstream_to_pci_bridge(dev, tmp)) {
 				rcu_read_unlock();
 				return true;
 			}
@@ -2891,6 +2802,35 @@ static bool device_has_rmrr(struct device *dev)
 	return false;
 }
 
+/**
+ * device_rmrr_is_relaxable - Test whether the RMRR of this device
+ * is relaxable (ie. is allowed to be not enforced under some conditions)
+ * @dev: device handle
+ *
+ * We assume that PCI USB devices with RMRRs have them largely
+ * for historical reasons and that the RMRR space is not actively used post
+ * boot.  This exclusion may change if vendors begin to abuse it.
+ *
+ * The same exception is made for graphics devices, with the requirement that
+ * any use of the RMRR regions will be torn down before assigning the device
+ * to a guest.
+ *
+ * Return: true if the RMRR is relaxable, false otherwise
+ */
+static bool device_rmrr_is_relaxable(struct device *dev)
+{
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(dev))
+		return false;
+
+	pdev = to_pci_dev(dev);
+	if (IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev))
+		return true;
+	else
+		return false;
+}
+
 /*
  * There are a couple cases where we need to restrict the functionality of
  * devices associated with RMRRs.  The first is when evaluating a device for
@@ -2905,52 +2845,51 @@ static bool device_has_rmrr(struct device *dev)
  * We therefore prevent devices associated with an RMRR from participating in
  * the IOMMU API, which eliminates them from device assignment.
  *
- * In both cases we assume that PCI USB devices with RMRRs have them largely
- * for historical reasons and that the RMRR space is not actively used post
- * boot.  This exclusion may change if vendors begin to abuse it.
- *
- * The same exception is made for graphics devices, with the requirement that
- * any use of the RMRR regions will be torn down before assigning the device
- * to a guest.
+ * In both cases, devices which have relaxable RMRRs are not concerned by this
+ * restriction. See device_rmrr_is_relaxable comment.
  */
 static bool device_is_rmrr_locked(struct device *dev)
 {
 	if (!device_has_rmrr(dev))
 		return false;
 
-	if (dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-
-		if (IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev))
-			return false;
-	}
+	if (device_rmrr_is_relaxable(dev))
+		return false;
 
 	return true;
 }
 
-static int iommu_should_identity_map(struct device *dev, int startup)
+/*
+ * Return the required default domain type for a specific device.
+ *
+ * @dev: the device in query
+ * @startup: true if this is during early boot
+ *
+ * Returns:
+ *  - IOMMU_DOMAIN_DMA: device requires a dynamic mapping domain
+ *  - IOMMU_DOMAIN_IDENTITY: device requires an identical mapping domain
+ *  - 0: both identity and dynamic domains work for this device
+ */
+static int device_def_domain_type(struct device *dev)
 {
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(dev);
 
 		if (device_is_rmrr_locked(dev))
-			return 0;
+			return IOMMU_DOMAIN_DMA;
 
 		/*
 		 * Prevent any device marked as untrusted from getting
 		 * placed into the statically identity mapping domain.
 		 */
 		if (pdev->untrusted)
-			return 0;
+			return IOMMU_DOMAIN_DMA;
 
 		if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
-			return 1;
+			return IOMMU_DOMAIN_IDENTITY;
 
 		if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev))
-			return 1;
-
-		if (!(iommu_identity_mapping & IDENTMAP_ALL))
-			return 0;
+			return IOMMU_DOMAIN_IDENTITY;
 
 		/*
 		 * We want to start off with all devices in the 1:1 domain, and
@@ -2971,94 +2910,18 @@ static int iommu_should_identity_map(struct device *dev, int startup)
 		 */
 		if (!pci_is_pcie(pdev)) {
 			if (!pci_is_root_bus(pdev->bus))
-				return 0;
+				return IOMMU_DOMAIN_DMA;
 			if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI)
-				return 0;
+				return IOMMU_DOMAIN_DMA;
 		} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE)
-			return 0;
+			return IOMMU_DOMAIN_DMA;
 	} else {
 		if (device_has_rmrr(dev))
-			return 0;
+			return IOMMU_DOMAIN_DMA;
 	}
 
-	/*
-	 * At boot time, we don't yet know if devices will be 64-bit capable.
-	 * Assume that they will — if they turn out not to be, then we can
-	 * take them out of the 1:1 domain later.
-	 */
-	if (!startup) {
-		/*
-		 * If the device's dma_mask is less than the system's memory
-		 * size then this is not a candidate for identity mapping.
-		 */
-		u64 dma_mask = *dev->dma_mask;
-
-		if (dev->coherent_dma_mask &&
-		    dev->coherent_dma_mask < dma_mask)
-			dma_mask = dev->coherent_dma_mask;
-
-		return dma_mask >= dma_get_required_mask(dev);
-	}
-
-	return 1;
-}
-
-static int __init dev_prepare_static_identity_mapping(struct device *dev, int hw)
-{
-	int ret;
-
-	if (!iommu_should_identity_map(dev, 1))
-		return 0;
-
-	ret = domain_add_dev_info(si_domain, dev);
-	if (!ret)
-		dev_info(dev, "%s identity mapping\n",
-			 hw ? "Hardware" : "Software");
-	else if (ret == -ENODEV)
-		/* device not associated with an iommu */
-		ret = 0;
-
-	return ret;
-}
-
-
-static int __init iommu_prepare_static_identity_mapping(int hw)
-{
-	struct pci_dev *pdev = NULL;
-	struct dmar_drhd_unit *drhd;
-	/* To avoid a -Wunused-but-set-variable warning. */
-	struct intel_iommu *iommu __maybe_unused;
-	struct device *dev;
-	int i;
-	int ret = 0;
-
-	for_each_pci_dev(pdev) {
-		ret = dev_prepare_static_identity_mapping(&pdev->dev, hw);
-		if (ret)
-			return ret;
-	}
-
-	for_each_active_iommu(iommu, drhd)
-		for_each_active_dev_scope(drhd->devices, drhd->devices_cnt, i, dev) {
-			struct acpi_device_physical_node *pn;
-			struct acpi_device *adev;
-
-			if (dev->bus != &acpi_bus_type)
-				continue;
-
-			adev= to_acpi_device(dev);
-			mutex_lock(&adev->physical_node_lock);
-			list_for_each_entry(pn, &adev->physical_node_list, node) {
-				ret = dev_prepare_static_identity_mapping(pn->dev, hw);
-				if (ret)
-					break;
-			}
-			mutex_unlock(&adev->physical_node_lock);
-			if (ret)
-				return ret;
-		}
-
-	return 0;
+	return (iommu_identity_mapping & IDENTMAP_ALL) ?
+			IOMMU_DOMAIN_IDENTITY : 0;
 }
 
 static void intel_iommu_init_qi(struct intel_iommu *iommu)
@@ -3283,11 +3146,8 @@ out_unmap:
 static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;
-	struct dmar_rmrr_unit *rmrr;
-	bool copied_tables = false;
-	struct device *dev;
 	struct intel_iommu *iommu;
-	int i, ret;
+	int ret;
 
 	/*
 	 * for each drhd
@@ -3320,7 +3180,12 @@ static int __init init_dmars(void)
 		goto error;
 	}
 
-	for_each_active_iommu(iommu, drhd) {
+	for_each_iommu(iommu, drhd) {
+		if (drhd->ignored) {
+			iommu_disable_translation(iommu);
+			continue;
+		}
+
 		/*
 		 * Find the max pasid size of all IOMMU's in the system.
 		 * We need to ensure the system pasid table is no bigger
@@ -3380,7 +3245,6 @@ static int __init init_dmars(void)
 			} else {
 				pr_info("Copied translation tables from previous kernel for %s\n",
 					iommu->name);
-				copied_tables = true;
 			}
 		}
 
@@ -3416,62 +3280,9 @@ static int __init init_dmars(void)
 
 	check_tylersburg_isoch();
 
-	if (iommu_identity_mapping) {
-		ret = si_domain_init(hw_pass_through);
-		if (ret)
-			goto free_iommu;
-	}
-
-
-	/*
-	 * If we copied translations from a previous kernel in the kdump
-	 * case, we can not assign the devices to domains now, as that
-	 * would eliminate the old mappings. So skip this part and defer
-	 * the assignment to device driver initialization time.
-	 */
-	if (copied_tables)
-		goto domains_done;
-
-	/*
-	 * If pass through is not set or not enabled, setup context entries for
-	 * identity mappings for rmrr, gfx, and isa and may fall back to static
-	 * identity mapping if iommu_identity_mapping is set.
-	 */
-	if (iommu_identity_mapping) {
-		ret = iommu_prepare_static_identity_mapping(hw_pass_through);
-		if (ret) {
-			pr_crit("Failed to setup IOMMU pass-through\n");
-			goto free_iommu;
-		}
-	}
-	/*
-	 * For each rmrr
-	 *   for each dev attached to rmrr
-	 *   do
-	 *     locate drhd for dev, alloc domain for dev
-	 *     allocate free domain
-	 *     allocate page table entries for rmrr
-	 *     if context not allocated for bus
-	 *           allocate and init context
-	 *           set present in root table for this bus
-	 *     init context with domain, translation etc
-	 *    endfor
-	 * endfor
-	 */
-	pr_info("Setting RMRR:\n");
-	for_each_rmrr_units(rmrr) {
-		/* some BIOS lists non-exist devices in DMAR table. */
-		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
-					  i, dev) {
-			ret = iommu_prepare_rmrr_dev(rmrr, dev);
-			if (ret)
-				pr_err("Mapping reserved region failed\n");
-		}
-	}
-
-	iommu_prepare_isa();
-
-domains_done:
+	ret = si_domain_init(hw_pass_through);
+	if (ret)
+		goto free_iommu;
 
 	/*
 	 * for each drhd
@@ -3509,11 +3320,6 @@ domains_done:
 		ret = dmar_set_interrupt(iommu);
 		if (ret)
 			goto free_iommu;
-
-		if (!translation_pre_enabled(iommu))
-			iommu_enable_translation(iommu);
-
-		iommu_disable_protect_mem_regions(iommu);
 	}
 
 	return 0;
@@ -3563,16 +3369,17 @@ static unsigned long intel_alloc_iova(struct device *dev,
 	return iova_pfn;
 }
 
-struct dmar_domain *get_valid_domain_for_dev(struct device *dev)
+static struct dmar_domain *get_private_domain_for_dev(struct device *dev)
 {
 	struct dmar_domain *domain, *tmp;
 	struct dmar_rmrr_unit *rmrr;
 	struct device *i_dev;
 	int i, ret;
 
+	/* Device shouldn't be attached by any domains. */
 	domain = find_domain(dev);
 	if (domain)
-		goto out;
+		return NULL;
 
 	domain = find_or_alloc_domain(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
 	if (!domain)
@@ -3602,10 +3409,10 @@ struct dmar_domain *get_valid_domain_for_dev(struct device *dev)
 	}
 
 out:
-
 	if (!domain)
 		dev_err(dev, "Allocating domain failed\n");
-
+	else
+		domain->domain.type = IOMMU_DOMAIN_DMA;
 
 	return domain;
 }
@@ -3613,17 +3420,19 @@ out:
 /* Check if the dev needs to go through non-identity map and unmap process.*/
 static bool iommu_need_mapping(struct device *dev)
 {
-	int found;
+	int ret;
 
 	if (iommu_dummy(dev))
 		return false;
 
-	if (!iommu_identity_mapping)
-		return true;
+	ret = identity_mapping(dev);
+	if (ret) {
+		u64 dma_mask = *dev->dma_mask;
 
-	found = identity_mapping(dev);
-	if (found) {
-		if (iommu_should_identity_map(dev, 0))
+		if (dev->coherent_dma_mask && dev->coherent_dma_mask < dma_mask)
+			dma_mask = dev->coherent_dma_mask;
+
+		if (dma_mask >= dma_get_required_mask(dev))
 			return false;
 
 		/*
@@ -3631,17 +3440,20 @@ static bool iommu_need_mapping(struct device *dev)
 		 * non-identity mapping.
 		 */
 		dmar_remove_one_dev_info(dev);
-		dev_info(dev, "32bit DMA uses non-identity mapping\n");
-	} else {
-		/*
-		 * In case of a detached 64 bit DMA device from vm, the device
-		 * is put into si_domain for identity mapping.
-		 */
-		if (iommu_should_identity_map(dev, 0) &&
-		    !domain_add_dev_info(si_domain, dev)) {
-			dev_info(dev, "64bit DMA uses identity mapping\n");
-			return false;
+		ret = iommu_request_dma_domain_for_dev(dev);
+		if (ret) {
+			struct iommu_domain *domain;
+			struct dmar_domain *dmar_domain;
+
+			domain = iommu_get_domain_for_dev(dev);
+			if (domain) {
+				dmar_domain = to_dmar_domain(domain);
+				dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
+			}
+			get_private_domain_for_dev(dev);
 		}
+
+		dev_info(dev, "32bit DMA uses non-identity mapping\n");
 	}
 
 	return true;
@@ -3660,7 +3472,7 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
 
 	BUG_ON(dir == DMA_NONE);
 
-	domain = get_valid_domain_for_dev(dev);
+	domain = find_domain(dev);
 	if (!domain)
 		return DMA_MAPPING_ERROR;
 
@@ -3875,7 +3687,7 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 	if (!iommu_need_mapping(dev))
 		return dma_direct_map_sg(dev, sglist, nelems, dir, attrs);
 
-	domain = get_valid_domain_for_dev(dev);
+	domain = find_domain(dev);
 	if (!domain)
 		return 0;
 
@@ -4194,13 +4006,10 @@ static void __init init_iommu_pm_ops(void)
 static inline void init_iommu_pm_ops(void) {}
 #endif	/* CONFIG_PM */
 
-
 int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
-	int prot = DMA_PTE_READ|DMA_PTE_WRITE;
 	struct dmar_rmrr_unit *rmrru;
-	size_t length;
 
 	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
 	if (!rmrru)
@@ -4211,23 +4020,15 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 	rmrru->base_address = rmrr->base_address;
 	rmrru->end_address = rmrr->end_address;
 
-	length = rmrr->end_address - rmrr->base_address + 1;
-	rmrru->resv = iommu_alloc_resv_region(rmrr->base_address, length, prot,
-					      IOMMU_RESV_DIRECT);
-	if (!rmrru->resv)
-		goto free_rmrru;
-
 	rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1),
 				((void *)rmrr) + rmrr->header.length,
 				&rmrru->devices_cnt);
 	if (rmrru->devices_cnt && rmrru->devices == NULL)
-		goto free_all;
+		goto free_rmrru;
 
 	list_add(&rmrru->list, &dmar_rmrr_units);
 
 	return 0;
-free_all:
-	kfree(rmrru->resv);
 free_rmrru:
 	kfree(rmrru);
 out:
@@ -4445,7 +4246,6 @@ static void intel_iommu_free_dmars(void)
 	list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) {
 		list_del(&rmrru->list);
 		dmar_free_dev_scope(&rmrru->devices, &rmrru->devices_cnt);
-		kfree(rmrru->resv);
 		kfree(rmrru);
 	}
 
@@ -4550,42 +4350,6 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 	return 0;
 }
 
-/*
- * Here we only respond to action of unbound device from driver.
- *
- * Added device is not attached to its DMAR domain here yet. That will happen
- * when mapping the device to iova.
- */
-static int device_notifier(struct notifier_block *nb,
-				  unsigned long action, void *data)
-{
-	struct device *dev = data;
-	struct dmar_domain *domain;
-
-	if (iommu_dummy(dev))
-		return 0;
-
-	if (action == BUS_NOTIFY_REMOVED_DEVICE) {
-		domain = find_domain(dev);
-		if (!domain)
-			return 0;
-
-		dmar_remove_one_dev_info(dev);
-		if (!domain_type_is_vm_or_si(domain) &&
-		    list_empty(&domain->devices))
-			domain_exit(domain);
-	} else if (action == BUS_NOTIFY_ADD_DEVICE) {
-		if (iommu_should_identity_map(dev, 1))
-			domain_add_dev_info(si_domain, dev);
-	}
-
-	return 0;
-}
-
-static struct notifier_block device_nb = {
-	.notifier_call = device_notifier,
-};
-
 static int intel_iommu_memory_notifier(struct notifier_block *nb,
 				       unsigned long val, void *v)
 {
@@ -4812,6 +4576,49 @@ static int __init platform_optin_force_iommu(void)
 	return 1;
 }
 
+static int __init probe_acpi_namespace_devices(void)
+{
+	struct dmar_drhd_unit *drhd;
+	/* To avoid a -Wunused-but-set-variable warning. */
+	struct intel_iommu *iommu __maybe_unused;
+	struct device *dev;
+	int i, ret = 0;
+
+	for_each_active_iommu(iommu, drhd) {
+		for_each_active_dev_scope(drhd->devices,
+					  drhd->devices_cnt, i, dev) {
+			struct acpi_device_physical_node *pn;
+			struct iommu_group *group;
+			struct acpi_device *adev;
+
+			if (dev->bus != &acpi_bus_type)
+				continue;
+
+			adev = to_acpi_device(dev);
+			mutex_lock(&adev->physical_node_lock);
+			list_for_each_entry(pn,
+					    &adev->physical_node_list, node) {
+				group = iommu_group_get(pn->dev);
+				if (group) {
+					iommu_group_put(group);
+					continue;
+				}
+
+				pn->dev->bus->iommu_ops = &intel_iommu_ops;
+				ret = iommu_probe_device(pn->dev);
+				if (ret)
+					break;
+			}
+			mutex_unlock(&adev->physical_node_lock);
+
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
 int __init intel_iommu_init(void)
 {
 	int ret = -ENODEV;
@@ -4901,7 +4708,6 @@ int __init intel_iommu_init(void)
 		goto out_free_reserved_range;
 	}
 	up_write(&dmar_global_lock);
-	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
 
 #if defined(CONFIG_X86) && defined(CONFIG_SWIOTLB)
 	swiotlb = 0;
@@ -4919,11 +4725,25 @@ int __init intel_iommu_init(void)
 	}
 
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
-	bus_register_notifier(&pci_bus_type, &device_nb);
 	if (si_domain && !hw_pass_through)
 		register_memory_notifier(&intel_iommu_memory_nb);
 	cpuhp_setup_state(CPUHP_IOMMU_INTEL_DEAD, "iommu/intel:dead", NULL,
 			  intel_iommu_cpu_dead);
+
+	down_read(&dmar_global_lock);
+	if (probe_acpi_namespace_devices())
+		pr_warn("ACPI name space devices didn't probe correctly\n");
+	up_read(&dmar_global_lock);
+
+	/* Finally, we enable the DMA remapping hardware. */
+	for_each_iommu(iommu, drhd) {
+		if (!drhd->ignored && !translation_pre_enabled(iommu))
+			iommu_enable_translation(iommu);
+
+		iommu_disable_protect_mem_regions(iommu);
+	}
+	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
+
 	intel_iommu_enabled = 1;
 	intel_iommu_debugfs_init();
 
@@ -4962,6 +4782,7 @@ static void domain_context_clear(struct intel_iommu *iommu, struct device *dev)
 
 static void __dmar_remove_one_dev_info(struct device_domain_info *info)
 {
+	struct dmar_domain *domain;
 	struct intel_iommu *iommu;
 	unsigned long flags;
 
@@ -4971,6 +4792,7 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info)
 		return;
 
 	iommu = info->iommu;
+	domain = info->domain;
 
 	if (info->dev) {
 		if (dev_is_pci(info->dev) && sm_supported(iommu))
@@ -4985,9 +4807,14 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info)
 	unlink_domain_info(info);
 
 	spin_lock_irqsave(&iommu->lock, flags);
-	domain_detach_iommu(info->domain, iommu);
+	domain_detach_iommu(domain, iommu);
 	spin_unlock_irqrestore(&iommu->lock, flags);
 
+	/* free the private domain */
+	if (domain->flags & DOMAIN_FLAG_LOSE_CHILDREN &&
+	    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY))
+		domain_exit(info->domain);
+
 	free_devinfo_mem(info);
 }
 
@@ -5002,62 +4829,55 @@ static void dmar_remove_one_dev_info(struct device *dev)
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
-static int md_domain_init(struct dmar_domain *domain, int guest_width)
-{
-	int adjust_width;
-
-	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
-	domain_reserve_special_ranges(domain);
-
-	/* calculate AGAW */
-	domain->gaw = guest_width;
-	adjust_width = guestwidth_to_adjustwidth(guest_width);
-	domain->agaw = width_to_agaw(adjust_width);
-
-	domain->iommu_coherency = 0;
-	domain->iommu_snooping = 0;
-	domain->iommu_superpage = 0;
-	domain->max_addr = 0;
-
-	/* always allocate the top pgd */
-	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
-	if (!domain->pgd)
-		return -ENOMEM;
-	domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
-	return 0;
-}
-
 static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 {
 	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED)
-		return NULL;
+	switch (type) {
+	case IOMMU_DOMAIN_DMA:
+	/* fallthrough */
+	case IOMMU_DOMAIN_UNMANAGED:
+		dmar_domain = alloc_domain(0);
+		if (!dmar_domain) {
+			pr_err("Can't allocate dmar_domain\n");
+			return NULL;
+		}
+		if (domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+			pr_err("Domain initialization failed\n");
+			domain_exit(dmar_domain);
+			return NULL;
+		}
 
-	dmar_domain = alloc_domain(DOMAIN_FLAG_VIRTUAL_MACHINE);
-	if (!dmar_domain) {
-		pr_err("Can't allocate dmar_domain\n");
-		return NULL;
-	}
-	if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
-		pr_err("Domain initialization failed\n");
-		domain_exit(dmar_domain);
+		if (type == IOMMU_DOMAIN_DMA &&
+		    init_iova_flush_queue(&dmar_domain->iovad,
+					  iommu_flush_iova, iova_entry_free)) {
+			pr_warn("iova flush queue initialization failed\n");
+			intel_iommu_strict = 1;
+		}
+
+		domain_update_iommu_cap(dmar_domain);
+
+		domain = &dmar_domain->domain;
+		domain->geometry.aperture_start = 0;
+		domain->geometry.aperture_end   =
+				__DOMAIN_MAX_ADDR(dmar_domain->gaw);
+		domain->geometry.force_aperture = true;
+
+		return domain;
+	case IOMMU_DOMAIN_IDENTITY:
+		return &si_domain->domain;
+	default:
 		return NULL;
 	}
-	domain_update_iommu_cap(dmar_domain);
-
-	domain = &dmar_domain->domain;
-	domain->geometry.aperture_start = 0;
-	domain->geometry.aperture_end   = __DOMAIN_MAX_ADDR(dmar_domain->gaw);
-	domain->geometry.force_aperture = true;
 
-	return domain;
+	return NULL;
 }
 
 static void intel_iommu_domain_free(struct iommu_domain *domain)
 {
-	domain_exit(to_dmar_domain(domain));
+	if (domain != &si_domain->domain)
+		domain_exit(to_dmar_domain(domain));
 }
 
 /*
@@ -5233,7 +5053,8 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 {
 	int ret;
 
-	if (device_is_rmrr_locked(dev)) {
+	if (domain->type == IOMMU_DOMAIN_UNMANAGED &&
+	    device_is_rmrr_locked(dev)) {
 		dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement.  Contact your platform vendor.\n");
 		return -EPERM;
 	}
@@ -5246,15 +5067,8 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 		struct dmar_domain *old_domain;
 
 		old_domain = find_domain(dev);
-		if (old_domain) {
-			rcu_read_lock();
+		if (old_domain)
 			dmar_remove_one_dev_info(dev);
-			rcu_read_unlock();
-
-			if (!domain_type_is_vm_or_si(old_domain) &&
-			    list_empty(&old_domain->devices))
-				domain_exit(old_domain);
-		}
 	}
 
 	ret = prepare_domain_attach_device(domain, dev);
@@ -5300,6 +5114,9 @@ static int intel_iommu_map(struct iommu_domain *domain,
 	int prot = 0;
 	int ret;
 
+	if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN)
+		return -EINVAL;
+
 	if (iommu_prot & IOMMU_READ)
 		prot |= DMA_PTE_READ;
 	if (iommu_prot & IOMMU_WRITE)
@@ -5341,6 +5158,8 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 	/* Cope with horrid API which requires us to unmap more than the
 	   size argument if it happens to be a large-page mapping. */
 	BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level));
+	if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN)
+		return 0;
 
 	if (size < VTD_PAGE_SIZE << level_to_offset_bits(level))
 		size = VTD_PAGE_SIZE << level_to_offset_bits(level);
@@ -5372,6 +5191,9 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	int level = 0;
 	u64 phys = 0;
 
+	if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN)
+		return 0;
+
 	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level);
 	if (pte)
 		phys = dma_pte_addr(pte);
@@ -5427,9 +5249,12 @@ static bool intel_iommu_capable(enum iommu_cap cap)
 
 static int intel_iommu_add_device(struct device *dev)
 {
+	struct dmar_domain *dmar_domain;
+	struct iommu_domain *domain;
 	struct intel_iommu *iommu;
 	struct iommu_group *group;
 	u8 bus, devfn;
+	int ret;
 
 	iommu = device_to_iommu(dev, &bus, &devfn);
 	if (!iommu)
@@ -5437,12 +5262,45 @@ static int intel_iommu_add_device(struct device *dev)
 
 	iommu_device_link(&iommu->iommu, dev);
 
+	if (translation_pre_enabled(iommu))
+		dev->archdata.iommu = DEFER_DEVICE_DOMAIN_INFO;
+
 	group = iommu_group_get_for_dev(dev);
 
 	if (IS_ERR(group))
 		return PTR_ERR(group);
 
 	iommu_group_put(group);
+
+	domain = iommu_get_domain_for_dev(dev);
+	dmar_domain = to_dmar_domain(domain);
+	if (domain->type == IOMMU_DOMAIN_DMA) {
+		if (device_def_domain_type(dev) == IOMMU_DOMAIN_IDENTITY) {
+			ret = iommu_request_dm_for_dev(dev);
+			if (ret) {
+				dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
+				domain_add_dev_info(si_domain, dev);
+				dev_info(dev,
+					 "Device uses a private identity domain.\n");
+			}
+		}
+	} else {
+		if (device_def_domain_type(dev) == IOMMU_DOMAIN_DMA) {
+			ret = iommu_request_dma_domain_for_dev(dev);
+			if (ret) {
+				dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
+				if (!get_private_domain_for_dev(dev)) {
+					dev_warn(dev,
+						 "Failed to get a private domain.\n");
+					return -ENOMEM;
+				}
+
+				dev_info(dev,
+					 "Device uses a private dma domain.\n");
+			}
+		}
+	}
+
 	return 0;
 }
 
@@ -5463,22 +5321,51 @@ static void intel_iommu_remove_device(struct device *dev)
 static void intel_iommu_get_resv_regions(struct device *device,
 					 struct list_head *head)
 {
+	int prot = DMA_PTE_READ | DMA_PTE_WRITE;
 	struct iommu_resv_region *reg;
 	struct dmar_rmrr_unit *rmrr;
 	struct device *i_dev;
 	int i;
 
-	rcu_read_lock();
+	down_read(&dmar_global_lock);
 	for_each_rmrr_units(rmrr) {
 		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
 					  i, i_dev) {
-			if (i_dev != device)
+			struct iommu_resv_region *resv;
+			enum iommu_resv_type type;
+			size_t length;
+
+			if (i_dev != device &&
+			    !is_downstream_to_pci_bridge(device, i_dev))
 				continue;
 
-			list_add_tail(&rmrr->resv->list, head);
+			length = rmrr->end_address - rmrr->base_address + 1;
+
+			type = device_rmrr_is_relaxable(device) ?
+				IOMMU_RESV_DIRECT_RELAXABLE : IOMMU_RESV_DIRECT;
+
+			resv = iommu_alloc_resv_region(rmrr->base_address,
+						       length, prot, type);
+			if (!resv)
+				break;
+
+			list_add_tail(&resv->list, head);
 		}
 	}
-	rcu_read_unlock();
+	up_read(&dmar_global_lock);
+
+#ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA
+	if (dev_is_pci(device)) {
+		struct pci_dev *pdev = to_pci_dev(device);
+
+		if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) {
+			reg = iommu_alloc_resv_region(0, 1UL << 24, 0,
+						      IOMMU_RESV_DIRECT);
+			if (reg)
+				list_add_tail(&reg->list, head);
+		}
+	}
+#endif /* CONFIG_INTEL_IOMMU_FLOPPY_WA */
 
 	reg = iommu_alloc_resv_region(IOAPIC_RANGE_START,
 				      IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1,
@@ -5493,10 +5380,8 @@ static void intel_iommu_put_resv_regions(struct device *dev,
 {
 	struct iommu_resv_region *entry, *next;
 
-	list_for_each_entry_safe(entry, next, head, list) {
-		if (entry->type == IOMMU_RESV_MSI)
-			kfree(entry);
-	}
+	list_for_each_entry_safe(entry, next, head, list)
+		kfree(entry);
 }
 
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev)
@@ -5508,7 +5393,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev)
 	u64 ctx_lo;
 	int ret;
 
-	domain = get_valid_domain_for_dev(dev);
+	domain = find_domain(dev);
 	if (!domain)
 		return -EINVAL;
 
@@ -5550,6 +5435,19 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev)
 	return ret;
 }
 
+static void intel_iommu_apply_resv_region(struct device *dev,
+					  struct iommu_domain *domain,
+					  struct iommu_resv_region *region)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long start, end;
+
+	start = IOVA_PFN(region->start);
+	end   = IOVA_PFN(region->start + region->length - 1);
+
+	WARN_ON_ONCE(!reserve_iova(&dmar_domain->iovad, start, end));
+}
+
 #ifdef CONFIG_INTEL_IOMMU_SVM
 struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
 {
@@ -5699,6 +5597,12 @@ intel_iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev)
 			dmar_domain->default_pasid : -EINVAL;
 }
 
+static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain,
+					   struct device *dev)
+{
+	return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
+}
+
 const struct iommu_ops intel_iommu_ops = {
 	.capable		= intel_iommu_capable,
 	.domain_alloc		= intel_iommu_domain_alloc,
@@ -5715,11 +5619,13 @@ const struct iommu_ops intel_iommu_ops = {
 	.remove_device		= intel_iommu_remove_device,
 	.get_resv_regions	= intel_iommu_get_resv_regions,
 	.put_resv_regions	= intel_iommu_put_resv_regions,
+	.apply_resv_region	= intel_iommu_apply_resv_region,
 	.device_group		= pci_device_group,
 	.dev_has_feat		= intel_iommu_dev_has_feat,
 	.dev_feat_enabled	= intel_iommu_dev_feat_enabled,
 	.dev_enable_feat	= intel_iommu_dev_enable_feat,
 	.dev_disable_feat	= intel_iommu_dev_disable_feat,
+	.is_attach_deferred	= intel_iommu_is_attach_deferred,
 	.pgsize_bitmap		= INTEL_IOMMU_PGSIZES,
 };
 
diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index fe51d8af457f..040a445be300 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -169,23 +169,6 @@ attach_out:
 	return 0;
 }
 
-/* Get PRESENT bit of a PASID directory entry. */
-static inline bool
-pasid_pde_is_present(struct pasid_dir_entry *pde)
-{
-	return READ_ONCE(pde->val) & PASID_PTE_PRESENT;
-}
-
-/* Get PASID table from a PASID directory entry. */
-static inline struct pasid_entry *
-get_pasid_table_from_pde(struct pasid_dir_entry *pde)
-{
-	if (!pasid_pde_is_present(pde))
-		return NULL;
-
-	return phys_to_virt(READ_ONCE(pde->val) & PDE_PFN_MASK);
-}
-
 void intel_pasid_free_table(struct device *dev)
 {
 	struct device_domain_info *info;
diff --git a/drivers/iommu/intel-pasid.h b/drivers/iommu/intel-pasid.h
index 23537b3f34e3..fc8cd8f17de1 100644
--- a/drivers/iommu/intel-pasid.h
+++ b/drivers/iommu/intel-pasid.h
@@ -18,6 +18,10 @@
 #define PDE_PFN_MASK			PAGE_MASK
 #define PASID_PDE_SHIFT			6
 #define MAX_NR_PASID_BITS		20
+#define PASID_TBL_ENTRIES		BIT(PASID_PDE_SHIFT)
+
+#define is_pasid_enabled(entry)		(((entry)->lo >> 3) & 0x1)
+#define get_pasid_dir_size(entry)	(1 << ((((entry)->lo >> 9) & 0x7) + 7))
 
 /*
  * Domain ID reserved for pasid entries programmed for first-level
@@ -49,6 +53,28 @@ struct pasid_table {
 	struct list_head	dev;		/* device list */
 };
 
+/* Get PRESENT bit of a PASID directory entry. */
+static inline bool pasid_pde_is_present(struct pasid_dir_entry *pde)
+{
+	return READ_ONCE(pde->val) & PASID_PTE_PRESENT;
+}
+
+/* Get PASID table from a PASID directory entry. */
+static inline struct pasid_entry *
+get_pasid_table_from_pde(struct pasid_dir_entry *pde)
+{
+	if (!pasid_pde_is_present(pde))
+		return NULL;
+
+	return phys_to_virt(READ_ONCE(pde->val) & PDE_PFN_MASK);
+}
+
+/* Get PRESENT bit of a PASID table entry. */
+static inline bool pasid_pte_is_present(struct pasid_entry *pte)
+{
+	return READ_ONCE(pte->val[0]) & PASID_PTE_PRESENT;
+}
+
 extern u32 intel_pasid_max_id;
 int intel_pasid_alloc_id(void *ptr, int start, int end, gfp_t gfp);
 void intel_pasid_free_id(int pasid);
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index eceaa7e968ae..780de0caafe8 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -366,6 +366,21 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		}
 
 		list_add_tail(&svm->list, &global_svm_list);
+	} else {
+		/*
+		 * Binding a new device with existing PASID, need to setup
+		 * the PASID entry.
+		 */
+		spin_lock(&iommu->lock);
+		ret = intel_pasid_setup_first_level(iommu, dev,
+						mm ? mm->pgd : init_mm.pgd,
+						svm->pasid, FLPT_DEFAULT_DID,
+						mm ? 0 : PASID_FLAG_SUPERVISOR_MODE);
+		spin_unlock(&iommu->lock);
+		if (ret) {
+			kfree(sdev);
+			goto out;
+		}
 	}
 	list_add_rcu(&sdev->list, &svm->devs);
 
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 4160aa9f3f80..4786ca061e31 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -101,7 +101,7 @@ static void init_ir_status(struct intel_iommu *iommu)
 		iommu->flags |= VTD_FLAG_IRQ_REMAP_PRE_ENABLED;
 }
 
-static int alloc_irte(struct intel_iommu *iommu, int irq,
+static int alloc_irte(struct intel_iommu *iommu,
 		      struct irq_2_iommu *irq_iommu, u16 count)
 {
 	struct ir_table *table = iommu->ir_table;
@@ -1374,7 +1374,7 @@ static int intel_irq_remapping_alloc(struct irq_domain *domain,
 		goto out_free_parent;
 
 	down_read(&dmar_global_lock);
-	index = alloc_irte(iommu, virq, &data->irq_2_iommu, nr_irqs);
+	index = alloc_irte(iommu, &data->irq_2_iommu, nr_irqs);
 	up_read(&dmar_global_lock);
 	if (index < 0) {
 		pr_warn("Failed to allocate IRTE\n");
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index aa7a3fa6dd09..0fc8dfab2abf 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -204,7 +204,7 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 		dev_err(dev, "Page table does not fit in PTE: %pa", &phys);
 		goto out_free;
 	}
-	if (table && !(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) {
+	if (table && !cfg->coherent_walk) {
 		dma = dma_map_single(dev, table, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
 			goto out_free;
@@ -238,7 +238,7 @@ static void __arm_v7s_free_table(void *table, int lvl,
 	struct device *dev = cfg->iommu_dev;
 	size_t size = ARM_V7S_TABLE_SIZE(lvl);
 
-	if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA))
+	if (!cfg->coherent_walk)
 		dma_unmap_single(dev, __arm_v7s_dma_addr(table), size,
 				 DMA_TO_DEVICE);
 	if (lvl == 1)
@@ -250,7 +250,7 @@ static void __arm_v7s_free_table(void *table, int lvl,
 static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries,
 			       struct io_pgtable_cfg *cfg)
 {
-	if (cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)
+	if (cfg->coherent_walk)
 		return;
 
 	dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep),
@@ -716,7 +716,6 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 			    IO_PGTABLE_QUIRK_NO_PERMS |
 			    IO_PGTABLE_QUIRK_TLBI_ON_MAP |
 			    IO_PGTABLE_QUIRK_ARM_MTK_4GB |
-			    IO_PGTABLE_QUIRK_NO_DMA |
 			    IO_PGTABLE_QUIRK_NON_STRICT))
 		return NULL;
 
@@ -779,8 +778,11 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	/* TTBRs */
 	cfg->arm_v7s_cfg.ttbr[0] = virt_to_phys(data->pgd) |
 				   ARM_V7S_TTBR_S | ARM_V7S_TTBR_NOS |
-				   ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
-				   ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA);
+				   (cfg->coherent_walk ?
+				   (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
+				    ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
+				   (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
+				    ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
 	cfg->arm_v7s_cfg.ttbr[1] = 0;
 	return &data->iop;
 
@@ -835,7 +837,8 @@ static int __init arm_v7s_do_selftests(void)
 		.tlb = &dummy_tlb_ops,
 		.oas = 32,
 		.ias = 32,
-		.quirks = IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_DMA,
+		.coherent_walk = true,
+		.quirks = IO_PGTABLE_QUIRK_ARM_NS,
 		.pgsize_bitmap = SZ_4K | SZ_64K | SZ_1M | SZ_16M,
 	};
 	unsigned int iova, size, iova_start;
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 4b6b2f3150a9..161a7d56264d 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -156,10 +156,12 @@
 #define ARM_LPAE_MAIR_ATTR_MASK		0xff
 #define ARM_LPAE_MAIR_ATTR_DEVICE	0x04
 #define ARM_LPAE_MAIR_ATTR_NC		0x44
+#define ARM_LPAE_MAIR_ATTR_INC_OWBRWA	0xf4
 #define ARM_LPAE_MAIR_ATTR_WBRWA	0xff
 #define ARM_LPAE_MAIR_ATTR_IDX_NC	0
 #define ARM_LPAE_MAIR_ATTR_IDX_CACHE	1
 #define ARM_LPAE_MAIR_ATTR_IDX_DEV	2
+#define ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE	3
 
 #define ARM_MALI_LPAE_TTBR_ADRMODE_TABLE (3u << 0)
 #define ARM_MALI_LPAE_TTBR_READ_INNER	BIT(2)
@@ -239,7 +241,7 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 		return NULL;
 
 	pages = page_address(p);
-	if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) {
+	if (!cfg->coherent_walk) {
 		dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
 			goto out_free;
@@ -265,7 +267,7 @@ out_free:
 static void __arm_lpae_free_pages(void *pages, size_t size,
 				  struct io_pgtable_cfg *cfg)
 {
-	if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA))
+	if (!cfg->coherent_walk)
 		dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages),
 				 size, DMA_TO_DEVICE);
 	free_pages((unsigned long)pages, get_order(size));
@@ -283,7 +285,7 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
 {
 	*ptep = pte;
 
-	if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA))
+	if (!cfg->coherent_walk)
 		__arm_lpae_sync_pte(ptep, cfg);
 }
 
@@ -361,8 +363,7 @@ static arm_lpae_iopte arm_lpae_install_table(arm_lpae_iopte *table,
 
 	old = cmpxchg64_relaxed(ptep, curr, new);
 
-	if ((cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA) ||
-	    (old & ARM_LPAE_PTE_SW_SYNC))
+	if (cfg->coherent_walk || (old & ARM_LPAE_PTE_SW_SYNC))
 		return old;
 
 	/* Even if it's not ours, there's no point waiting; just kick it */
@@ -403,8 +404,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 		pte = arm_lpae_install_table(cptep, ptep, 0, cfg);
 		if (pte)
 			__arm_lpae_free_pages(cptep, tblsz, cfg);
-	} else if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA) &&
-		   !(pte & ARM_LPAE_PTE_SW_SYNC)) {
+	} else if (!cfg->coherent_walk && !(pte & ARM_LPAE_PTE_SW_SYNC)) {
 		__arm_lpae_sync_pte(ptep, cfg);
 	}
 
@@ -459,6 +459,9 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 		else if (prot & IOMMU_CACHE)
 			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
+		else if (prot & IOMMU_QCOM_SYS_CACHE)
+			pte |= (ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE
+				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	}
 
 	if (prot & IOMMU_NOEXEC)
@@ -783,7 +786,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	u64 reg;
 	struct arm_lpae_io_pgtable *data;
 
-	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_DMA |
+	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NON_STRICT))
 		return NULL;
 
@@ -792,9 +795,15 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 		return NULL;
 
 	/* TCR */
-	reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
-	      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
-	      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+	if (cfg->coherent_walk) {
+		reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
+		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
+		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+	} else {
+		reg = (ARM_LPAE_TCR_SH_OS << ARM_LPAE_TCR_SH0_SHIFT) |
+		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_IRGN0_SHIFT) |
+		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_ORGN0_SHIFT);
+	}
 
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
@@ -846,7 +855,9 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	      (ARM_LPAE_MAIR_ATTR_WBRWA
 	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) |
 	      (ARM_LPAE_MAIR_ATTR_DEVICE
-	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
+	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV)) |
+	      (ARM_LPAE_MAIR_ATTR_INC_OWBRWA
+	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE));
 
 	cfg->arm_lpae_s1_cfg.mair[0] = reg;
 	cfg->arm_lpae_s1_cfg.mair[1] = 0;
@@ -876,8 +887,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	struct arm_lpae_io_pgtable *data;
 
 	/* The NS quirk doesn't apply at stage 2 */
-	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_NO_DMA |
-			    IO_PGTABLE_QUIRK_NON_STRICT))
+	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_NON_STRICT))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
@@ -1212,7 +1222,7 @@ static int __init arm_lpae_do_selftests(void)
 	struct io_pgtable_cfg cfg = {
 		.tlb = &dummy_tlb_ops,
 		.oas = 48,
-		.quirks = IO_PGTABLE_QUIRK_NO_DMA,
+		.coherent_walk = true,
 	};
 
 	for (i = 0; i < ARRAY_SIZE(pgsize); ++i) {
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 9f0a2844371c..0c674d80c37f 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -61,10 +61,11 @@ struct iommu_group_attribute {
 };
 
 static const char * const iommu_group_resv_type_string[] = {
-	[IOMMU_RESV_DIRECT]	= "direct",
-	[IOMMU_RESV_RESERVED]	= "reserved",
-	[IOMMU_RESV_MSI]	= "msi",
-	[IOMMU_RESV_SW_MSI]	= "msi",
+	[IOMMU_RESV_DIRECT]			= "direct",
+	[IOMMU_RESV_DIRECT_RELAXABLE]		= "direct-relaxable",
+	[IOMMU_RESV_RESERVED]			= "reserved",
+	[IOMMU_RESV_MSI]			= "msi",
+	[IOMMU_RESV_SW_MSI]			= "msi",
 };
 
 #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
@@ -95,15 +96,43 @@ void iommu_device_unregister(struct iommu_device *iommu)
 	spin_unlock(&iommu_device_lock);
 }
 
+static struct iommu_param *iommu_get_dev_param(struct device *dev)
+{
+	struct iommu_param *param = dev->iommu_param;
+
+	if (param)
+		return param;
+
+	param = kzalloc(sizeof(*param), GFP_KERNEL);
+	if (!param)
+		return NULL;
+
+	mutex_init(&param->lock);
+	dev->iommu_param = param;
+	return param;
+}
+
+static void iommu_free_dev_param(struct device *dev)
+{
+	kfree(dev->iommu_param);
+	dev->iommu_param = NULL;
+}
+
 int iommu_probe_device(struct device *dev)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
-	int ret = -EINVAL;
+	int ret;
 
 	WARN_ON(dev->iommu_group);
+	if (!ops)
+		return -EINVAL;
 
-	if (ops)
-		ret = ops->add_device(dev);
+	if (!iommu_get_dev_param(dev))
+		return -ENOMEM;
+
+	ret = ops->add_device(dev);
+	if (ret)
+		iommu_free_dev_param(dev);
 
 	return ret;
 }
@@ -114,6 +143,8 @@ void iommu_release_device(struct device *dev)
 
 	if (dev->iommu_group)
 		ops->remove_device(dev);
+
+	iommu_free_dev_param(dev);
 }
 
 static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
@@ -225,18 +256,21 @@ static int iommu_insert_resv_region(struct iommu_resv_region *new,
 			pos = pos->next;
 		} else if ((start >= a) && (end <= b)) {
 			if (new->type == type)
-				goto done;
+				return 0;
 			else
 				pos = pos->next;
 		} else {
 			if (new->type == type) {
 				phys_addr_t new_start = min(a, start);
 				phys_addr_t new_end = max(b, end);
+				int ret;
 
 				list_del(&entry->list);
 				entry->start = new_start;
 				entry->length = new_end - new_start + 1;
-				iommu_insert_resv_region(entry, regions);
+				ret = iommu_insert_resv_region(entry, regions);
+				kfree(entry);
+				return ret;
 			} else {
 				pos = pos->next;
 			}
@@ -249,7 +283,6 @@ insert:
 		return -ENOMEM;
 
 	list_add_tail(&region->list, pos);
-done:
 	return 0;
 }
 
@@ -561,7 +594,8 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 		start = ALIGN(entry->start, pg_size);
 		end   = ALIGN(entry->start + entry->length, pg_size);
 
-		if (entry->type != IOMMU_RESV_DIRECT)
+		if (entry->type != IOMMU_RESV_DIRECT &&
+		    entry->type != IOMMU_RESV_DIRECT_RELAXABLE)
 			continue;
 
 		for (addr = start; addr < end; addr += pg_size) {
@@ -843,6 +877,206 @@ int iommu_group_unregister_notifier(struct iommu_group *group,
 EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier);
 
 /**
+ * iommu_register_device_fault_handler() - Register a device fault handler
+ * @dev: the device
+ * @handler: the fault handler
+ * @data: private data passed as argument to the handler
+ *
+ * When an IOMMU fault event is received, this handler gets called with the
+ * fault event and data as argument. The handler should return 0 on success. If
+ * the fault is recoverable (IOMMU_FAULT_PAGE_REQ), the consumer should also
+ * complete the fault by calling iommu_page_response() with one of the following
+ * response code:
+ * - IOMMU_PAGE_RESP_SUCCESS: retry the translation
+ * - IOMMU_PAGE_RESP_INVALID: terminate the fault
+ * - IOMMU_PAGE_RESP_FAILURE: terminate the fault and stop reporting
+ *   page faults if possible.
+ *
+ * Return 0 if the fault handler was installed successfully, or an error.
+ */
+int iommu_register_device_fault_handler(struct device *dev,
+					iommu_dev_fault_handler_t handler,
+					void *data)
+{
+	struct iommu_param *param = dev->iommu_param;
+	int ret = 0;
+
+	if (!param)
+		return -EINVAL;
+
+	mutex_lock(&param->lock);
+	/* Only allow one fault handler registered for each device */
+	if (param->fault_param) {
+		ret = -EBUSY;
+		goto done_unlock;
+	}
+
+	get_device(dev);
+	param->fault_param = kzalloc(sizeof(*param->fault_param), GFP_KERNEL);
+	if (!param->fault_param) {
+		put_device(dev);
+		ret = -ENOMEM;
+		goto done_unlock;
+	}
+	param->fault_param->handler = handler;
+	param->fault_param->data = data;
+	mutex_init(&param->fault_param->lock);
+	INIT_LIST_HEAD(&param->fault_param->faults);
+
+done_unlock:
+	mutex_unlock(&param->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_register_device_fault_handler);
+
+/**
+ * iommu_unregister_device_fault_handler() - Unregister the device fault handler
+ * @dev: the device
+ *
+ * Remove the device fault handler installed with
+ * iommu_register_device_fault_handler().
+ *
+ * Return 0 on success, or an error.
+ */
+int iommu_unregister_device_fault_handler(struct device *dev)
+{
+	struct iommu_param *param = dev->iommu_param;
+	int ret = 0;
+
+	if (!param)
+		return -EINVAL;
+
+	mutex_lock(&param->lock);
+
+	if (!param->fault_param)
+		goto unlock;
+
+	/* we cannot unregister handler if there are pending faults */
+	if (!list_empty(&param->fault_param->faults)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	kfree(param->fault_param);
+	param->fault_param = NULL;
+	put_device(dev);
+unlock:
+	mutex_unlock(&param->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_unregister_device_fault_handler);
+
+/**
+ * iommu_report_device_fault() - Report fault event to device driver
+ * @dev: the device
+ * @evt: fault event data
+ *
+ * Called by IOMMU drivers when a fault is detected, typically in a threaded IRQ
+ * handler. When this function fails and the fault is recoverable, it is the
+ * caller's responsibility to complete the fault.
+ *
+ * Return 0 on success, or an error.
+ */
+int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt)
+{
+	struct iommu_param *param = dev->iommu_param;
+	struct iommu_fault_event *evt_pending = NULL;
+	struct iommu_fault_param *fparam;
+	int ret = 0;
+
+	if (!param || !evt)
+		return -EINVAL;
+
+	/* we only report device fault if there is a handler registered */
+	mutex_lock(&param->lock);
+	fparam = param->fault_param;
+	if (!fparam || !fparam->handler) {
+		ret = -EINVAL;
+		goto done_unlock;
+	}
+
+	if (evt->fault.type == IOMMU_FAULT_PAGE_REQ &&
+	    (evt->fault.prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) {
+		evt_pending = kmemdup(evt, sizeof(struct iommu_fault_event),
+				      GFP_KERNEL);
+		if (!evt_pending) {
+			ret = -ENOMEM;
+			goto done_unlock;
+		}
+		mutex_lock(&fparam->lock);
+		list_add_tail(&evt_pending->list, &fparam->faults);
+		mutex_unlock(&fparam->lock);
+	}
+
+	ret = fparam->handler(&evt->fault, fparam->data);
+	if (ret && evt_pending) {
+		mutex_lock(&fparam->lock);
+		list_del(&evt_pending->list);
+		mutex_unlock(&fparam->lock);
+		kfree(evt_pending);
+	}
+done_unlock:
+	mutex_unlock(&param->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_report_device_fault);
+
+int iommu_page_response(struct device *dev,
+			struct iommu_page_response *msg)
+{
+	bool pasid_valid;
+	int ret = -EINVAL;
+	struct iommu_fault_event *evt;
+	struct iommu_fault_page_request *prm;
+	struct iommu_param *param = dev->iommu_param;
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+
+	if (!domain || !domain->ops->page_response)
+		return -ENODEV;
+
+	if (!param || !param->fault_param)
+		return -EINVAL;
+
+	if (msg->version != IOMMU_PAGE_RESP_VERSION_1 ||
+	    msg->flags & ~IOMMU_PAGE_RESP_PASID_VALID)
+		return -EINVAL;
+
+	/* Only send response if there is a fault report pending */
+	mutex_lock(&param->fault_param->lock);
+	if (list_empty(&param->fault_param->faults)) {
+		dev_warn_ratelimited(dev, "no pending PRQ, drop response\n");
+		goto done_unlock;
+	}
+	/*
+	 * Check if we have a matching page request pending to respond,
+	 * otherwise return -EINVAL
+	 */
+	list_for_each_entry(evt, &param->fault_param->faults, list) {
+		prm = &evt->fault.prm;
+		pasid_valid = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+
+		if ((pasid_valid && prm->pasid != msg->pasid) ||
+		    prm->grpid != msg->grpid)
+			continue;
+
+		/* Sanitize the reply */
+		msg->flags = pasid_valid ? IOMMU_PAGE_RESP_PASID_VALID : 0;
+
+		ret = domain->ops->page_response(dev, evt, msg);
+		list_del(&evt->list);
+		kfree(evt);
+		break;
+	}
+
+done_unlock:
+	mutex_unlock(&param->fault_param->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_page_response);
+
+/**
  * iommu_group_id - Return ID for a group
  * @group: the group to ID
  *
@@ -1895,24 +2129,23 @@ struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
 	return region;
 }
 
-/* Request that a device is direct mapped by the IOMMU */
-int iommu_request_dm_for_dev(struct device *dev)
+static int
+request_default_domain_for_dev(struct device *dev, unsigned long type)
 {
-	struct iommu_domain *dm_domain;
+	struct iommu_domain *domain;
 	struct iommu_group *group;
 	int ret;
 
 	/* Device must already be in a group before calling this function */
-	group = iommu_group_get_for_dev(dev);
-	if (IS_ERR(group))
-		return PTR_ERR(group);
+	group = iommu_group_get(dev);
+	if (!group)
+		return -EINVAL;
 
 	mutex_lock(&group->mutex);
 
 	/* Check if the default domain is already direct mapped */
 	ret = 0;
-	if (group->default_domain &&
-	    group->default_domain->type == IOMMU_DOMAIN_IDENTITY)
+	if (group->default_domain && group->default_domain->type == type)
 		goto out;
 
 	/* Don't change mappings of existing devices */
@@ -1922,23 +2155,26 @@ int iommu_request_dm_for_dev(struct device *dev)
 
 	/* Allocate a direct mapped domain */
 	ret = -ENOMEM;
-	dm_domain = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_IDENTITY);
-	if (!dm_domain)
+	domain = __iommu_domain_alloc(dev->bus, type);
+	if (!domain)
 		goto out;
 
 	/* Attach the device to the domain */
-	ret = __iommu_attach_group(dm_domain, group);
+	ret = __iommu_attach_group(domain, group);
 	if (ret) {
-		iommu_domain_free(dm_domain);
+		iommu_domain_free(domain);
 		goto out;
 	}
 
+	iommu_group_create_direct_mappings(group, dev);
+
 	/* Make the direct mapped domain the default for this group */
 	if (group->default_domain)
 		iommu_domain_free(group->default_domain);
-	group->default_domain = dm_domain;
+	group->default_domain = domain;
 
-	dev_info(dev, "Using iommu direct mapping\n");
+	dev_info(dev, "Using iommu %s mapping\n",
+		 type == IOMMU_DOMAIN_DMA ? "dma" : "direct");
 
 	ret = 0;
 out:
@@ -1948,6 +2184,18 @@ out:
 	return ret;
 }
 
+/* Request that a device is direct mapped by the IOMMU */
+int iommu_request_dm_for_dev(struct device *dev)
+{
+	return request_default_domain_for_dev(dev, IOMMU_DOMAIN_IDENTITY);
+}
+
+/* Request that a device can't be direct mapped by the IOMMU */
+int iommu_request_dma_domain_for_dev(struct device *dev)
+{
+	return request_default_domain_for_dev(dev, IOMMU_DOMAIN_DMA);
+}
+
 const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
 {
 	const struct iommu_ops *ops = NULL;
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 9a380c10655e..ad0098c0c87c 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -36,12 +36,16 @@
 #define arm_iommu_detach_device(...)	do {} while (0)
 #endif
 
-#define IPMMU_CTX_MAX 8
+#define IPMMU_CTX_MAX		8U
+#define IPMMU_CTX_INVALID	-1
+
+#define IPMMU_UTLB_MAX		48U
 
 struct ipmmu_features {
 	bool use_ns_alias_offset;
 	bool has_cache_leaf_nodes;
 	unsigned int number_of_contexts;
+	unsigned int num_utlbs;
 	bool setup_imbuscr;
 	bool twobit_imttbcr_sl0;
 	bool reserved_context;
@@ -53,11 +57,11 @@ struct ipmmu_vmsa_device {
 	struct iommu_device iommu;
 	struct ipmmu_vmsa_device *root;
 	const struct ipmmu_features *features;
-	unsigned int num_utlbs;
 	unsigned int num_ctx;
 	spinlock_t lock;			/* Protects ctx and domains[] */
 	DECLARE_BITMAP(ctx, IPMMU_CTX_MAX);
 	struct ipmmu_vmsa_domain *domains[IPMMU_CTX_MAX];
+	s8 utlb_ctx[IPMMU_UTLB_MAX];
 
 	struct iommu_group *group;
 	struct dma_iommu_mapping *mapping;
@@ -186,7 +190,8 @@ static struct ipmmu_vmsa_device *to_ipmmu(struct device *dev)
 #define IMMAIR_ATTR_IDX_WBRWA		1
 #define IMMAIR_ATTR_IDX_DEV		2
 
-#define IMEAR				0x0030
+#define IMELAR				0x0030	/* IMEAR on R-Car Gen2 */
+#define IMEUAR				0x0034	/* R-Car Gen3 only */
 
 #define IMPCTR				0x0200
 #define IMPSTR				0x0208
@@ -334,6 +339,7 @@ static void ipmmu_utlb_enable(struct ipmmu_vmsa_domain *domain,
 	ipmmu_write(mmu, IMUCTR(utlb),
 		    IMUCTR_TTSEL_MMU(domain->context_id) | IMUCTR_FLUSH |
 		    IMUCTR_MMUEN);
+	mmu->utlb_ctx[utlb] = domain->context_id;
 }
 
 /*
@@ -345,6 +351,7 @@ static void ipmmu_utlb_disable(struct ipmmu_vmsa_domain *domain,
 	struct ipmmu_vmsa_device *mmu = domain->mmu;
 
 	ipmmu_write(mmu, IMUCTR(utlb), 0);
+	mmu->utlb_ctx[utlb] = IPMMU_CTX_INVALID;
 }
 
 static void ipmmu_tlb_flush_all(void *cookie)
@@ -403,52 +410,10 @@ static void ipmmu_domain_free_context(struct ipmmu_vmsa_device *mmu,
 	spin_unlock_irqrestore(&mmu->lock, flags);
 }
 
-static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
+static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain)
 {
 	u64 ttbr;
 	u32 tmp;
-	int ret;
-
-	/*
-	 * Allocate the page table operations.
-	 *
-	 * VMSA states in section B3.6.3 "Control of Secure or Non-secure memory
-	 * access, Long-descriptor format" that the NStable bit being set in a
-	 * table descriptor will result in the NStable and NS bits of all child
-	 * entries being ignored and considered as being set. The IPMMU seems
-	 * not to comply with this, as it generates a secure access page fault
-	 * if any of the NStable and NS bits isn't set when running in
-	 * non-secure mode.
-	 */
-	domain->cfg.quirks = IO_PGTABLE_QUIRK_ARM_NS;
-	domain->cfg.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K;
-	domain->cfg.ias = 32;
-	domain->cfg.oas = 40;
-	domain->cfg.tlb = &ipmmu_gather_ops;
-	domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32);
-	domain->io_domain.geometry.force_aperture = true;
-	/*
-	 * TODO: Add support for coherent walk through CCI with DVM and remove
-	 * cache handling. For now, delegate it to the io-pgtable code.
-	 */
-	domain->cfg.iommu_dev = domain->mmu->root->dev;
-
-	/*
-	 * Find an unused context.
-	 */
-	ret = ipmmu_domain_allocate_context(domain->mmu->root, domain);
-	if (ret < 0)
-		return ret;
-
-	domain->context_id = ret;
-
-	domain->iop = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &domain->cfg,
-					   domain);
-	if (!domain->iop) {
-		ipmmu_domain_free_context(domain->mmu->root,
-					  domain->context_id);
-		return -EINVAL;
-	}
 
 	/* TTBR0 */
 	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr[0];
@@ -494,7 +459,55 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
 	 */
 	ipmmu_ctx_write_all(domain, IMCTR,
 			    IMCTR_INTEN | IMCTR_FLUSH | IMCTR_MMUEN);
+}
+
+static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
+{
+	int ret;
+
+	/*
+	 * Allocate the page table operations.
+	 *
+	 * VMSA states in section B3.6.3 "Control of Secure or Non-secure memory
+	 * access, Long-descriptor format" that the NStable bit being set in a
+	 * table descriptor will result in the NStable and NS bits of all child
+	 * entries being ignored and considered as being set. The IPMMU seems
+	 * not to comply with this, as it generates a secure access page fault
+	 * if any of the NStable and NS bits isn't set when running in
+	 * non-secure mode.
+	 */
+	domain->cfg.quirks = IO_PGTABLE_QUIRK_ARM_NS;
+	domain->cfg.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K;
+	domain->cfg.ias = 32;
+	domain->cfg.oas = 40;
+	domain->cfg.tlb = &ipmmu_gather_ops;
+	domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32);
+	domain->io_domain.geometry.force_aperture = true;
+	/*
+	 * TODO: Add support for coherent walk through CCI with DVM and remove
+	 * cache handling. For now, delegate it to the io-pgtable code.
+	 */
+	domain->cfg.coherent_walk = false;
+	domain->cfg.iommu_dev = domain->mmu->root->dev;
+
+	/*
+	 * Find an unused context.
+	 */
+	ret = ipmmu_domain_allocate_context(domain->mmu->root, domain);
+	if (ret < 0)
+		return ret;
+
+	domain->context_id = ret;
+
+	domain->iop = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &domain->cfg,
+					   domain);
+	if (!domain->iop) {
+		ipmmu_domain_free_context(domain->mmu->root,
+					  domain->context_id);
+		return -EINVAL;
+	}
 
+	ipmmu_domain_setup_context(domain);
 	return 0;
 }
 
@@ -522,14 +535,16 @@ static irqreturn_t ipmmu_domain_irq(struct ipmmu_vmsa_domain *domain)
 {
 	const u32 err_mask = IMSTR_MHIT | IMSTR_ABORT | IMSTR_PF | IMSTR_TF;
 	struct ipmmu_vmsa_device *mmu = domain->mmu;
+	unsigned long iova;
 	u32 status;
-	u32 iova;
 
 	status = ipmmu_ctx_read_root(domain, IMSTR);
 	if (!(status & err_mask))
 		return IRQ_NONE;
 
-	iova = ipmmu_ctx_read_root(domain, IMEAR);
+	iova = ipmmu_ctx_read_root(domain, IMELAR);
+	if (IS_ENABLED(CONFIG_64BIT))
+		iova |= (u64)ipmmu_ctx_read_root(domain, IMEUAR) << 32;
 
 	/*
 	 * Clear the error status flags. Unlike traditional interrupt flag
@@ -541,10 +556,10 @@ static irqreturn_t ipmmu_domain_irq(struct ipmmu_vmsa_domain *domain)
 
 	/* Log fatal errors. */
 	if (status & IMSTR_MHIT)
-		dev_err_ratelimited(mmu->dev, "Multiple TLB hits @0x%08x\n",
+		dev_err_ratelimited(mmu->dev, "Multiple TLB hits @0x%lx\n",
 				    iova);
 	if (status & IMSTR_ABORT)
-		dev_err_ratelimited(mmu->dev, "Page Table Walk Abort @0x%08x\n",
+		dev_err_ratelimited(mmu->dev, "Page Table Walk Abort @0x%lx\n",
 				    iova);
 
 	if (!(status & (IMSTR_PF | IMSTR_TF)))
@@ -560,7 +575,7 @@ static irqreturn_t ipmmu_domain_irq(struct ipmmu_vmsa_domain *domain)
 		return IRQ_HANDLED;
 
 	dev_err_ratelimited(mmu->dev,
-			    "Unhandled fault: status 0x%08x iova 0x%08x\n",
+			    "Unhandled fault: status 0x%08x iova 0x%lx\n",
 			    status, iova);
 
 	return IRQ_HANDLED;
@@ -885,27 +900,37 @@ error:
 
 static int ipmmu_add_device(struct device *dev)
 {
+	struct ipmmu_vmsa_device *mmu = to_ipmmu(dev);
 	struct iommu_group *group;
+	int ret;
 
 	/*
 	 * Only let through devices that have been verified in xlate()
 	 */
-	if (!to_ipmmu(dev))
+	if (!mmu)
 		return -ENODEV;
 
-	if (IS_ENABLED(CONFIG_ARM) && !IS_ENABLED(CONFIG_IOMMU_DMA))
-		return ipmmu_init_arm_mapping(dev);
+	if (IS_ENABLED(CONFIG_ARM) && !IS_ENABLED(CONFIG_IOMMU_DMA)) {
+		ret = ipmmu_init_arm_mapping(dev);
+		if (ret)
+			return ret;
+	} else {
+		group = iommu_group_get_for_dev(dev);
+		if (IS_ERR(group))
+			return PTR_ERR(group);
 
-	group = iommu_group_get_for_dev(dev);
-	if (IS_ERR(group))
-		return PTR_ERR(group);
+		iommu_group_put(group);
+	}
 
-	iommu_group_put(group);
+	iommu_device_link(&mmu->iommu, dev);
 	return 0;
 }
 
 static void ipmmu_remove_device(struct device *dev)
 {
+	struct ipmmu_vmsa_device *mmu = to_ipmmu(dev);
+
+	iommu_device_unlink(&mmu->iommu, dev);
 	arm_iommu_detach_device(dev);
 	iommu_group_remove_device(dev);
 }
@@ -959,6 +984,7 @@ static const struct ipmmu_features ipmmu_features_default = {
 	.use_ns_alias_offset = true,
 	.has_cache_leaf_nodes = false,
 	.number_of_contexts = 1, /* software only tested with one context */
+	.num_utlbs = 32,
 	.setup_imbuscr = true,
 	.twobit_imttbcr_sl0 = false,
 	.reserved_context = false,
@@ -968,6 +994,7 @@ static const struct ipmmu_features ipmmu_features_rcar_gen3 = {
 	.use_ns_alias_offset = false,
 	.has_cache_leaf_nodes = true,
 	.number_of_contexts = 8,
+	.num_utlbs = 48,
 	.setup_imbuscr = false,
 	.twobit_imttbcr_sl0 = true,
 	.reserved_context = true,
@@ -1020,10 +1047,10 @@ static int ipmmu_probe(struct platform_device *pdev)
 	}
 
 	mmu->dev = &pdev->dev;
-	mmu->num_utlbs = 48;
 	spin_lock_init(&mmu->lock);
 	bitmap_zero(mmu->ctx, IPMMU_CTX_MAX);
 	mmu->features = of_device_get_match_data(&pdev->dev);
+	memset(mmu->utlb_ctx, IPMMU_CTX_INVALID, mmu->features->num_utlbs);
 	dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
 
 	/* Map I/O memory and request IRQ. */
@@ -1047,8 +1074,7 @@ static int ipmmu_probe(struct platform_device *pdev)
 	if (mmu->features->use_ns_alias_offset)
 		mmu->base += IM_NS_ALIAS_OFFSET;
 
-	mmu->num_ctx = min_t(unsigned int, IPMMU_CTX_MAX,
-			     mmu->features->number_of_contexts);
+	mmu->num_ctx = min(IPMMU_CTX_MAX, mmu->features->number_of_contexts);
 
 	irq = platform_get_irq(pdev, 0);
 
@@ -1140,10 +1166,48 @@ static int ipmmu_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int ipmmu_resume_noirq(struct device *dev)
+{
+	struct ipmmu_vmsa_device *mmu = dev_get_drvdata(dev);
+	unsigned int i;
+
+	/* Reset root MMU and restore contexts */
+	if (ipmmu_is_root(mmu)) {
+		ipmmu_device_reset(mmu);
+
+		for (i = 0; i < mmu->num_ctx; i++) {
+			if (!mmu->domains[i])
+				continue;
+
+			ipmmu_domain_setup_context(mmu->domains[i]);
+		}
+	}
+
+	/* Re-enable active micro-TLBs */
+	for (i = 0; i < mmu->features->num_utlbs; i++) {
+		if (mmu->utlb_ctx[i] == IPMMU_CTX_INVALID)
+			continue;
+
+		ipmmu_utlb_enable(mmu->root->domains[mmu->utlb_ctx[i]], i);
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops ipmmu_pm  = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(NULL, ipmmu_resume_noirq)
+};
+#define DEV_PM_OPS	&ipmmu_pm
+#else
+#define DEV_PM_OPS	NULL
+#endif /* CONFIG_PM_SLEEP */
+
 static struct platform_driver ipmmu_driver = {
 	.driver = {
 		.name = "ipmmu-vmsa",
 		.of_match_table = of_match_ptr(ipmmu_of_ids),
+		.pm = DEV_PM_OPS,
 	},
 	.probe = ipmmu_probe,
 	.remove	= ipmmu_remove,
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
index ff31bddba60a..8e19bfa94121 100644
--- a/drivers/iommu/omap-iommu-debug.c
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -236,17 +236,6 @@ DEBUG_FOPS_RO(regs);
 DEFINE_SHOW_ATTRIBUTE(tlb);
 DEFINE_SHOW_ATTRIBUTE(pagetable);
 
-#define __DEBUG_ADD_FILE(attr, mode)					\
-	{								\
-		struct dentry *dent;					\
-		dent = debugfs_create_file(#attr, mode, obj->debug_dir,	\
-					   obj, &attr##_fops);	        \
-		if (!dent)						\
-			goto err;					\
-	}
-
-#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 0400)
-
 void omap_iommu_debugfs_add(struct omap_iommu *obj)
 {
 	struct dentry *d;
@@ -254,23 +243,13 @@ void omap_iommu_debugfs_add(struct omap_iommu *obj)
 	if (!iommu_debug_root)
 		return;
 
-	obj->debug_dir = debugfs_create_dir(obj->name, iommu_debug_root);
-	if (!obj->debug_dir)
-		return;
+	d = debugfs_create_dir(obj->name, iommu_debug_root);
+	obj->debug_dir = d;
 
-	d = debugfs_create_u32("nr_tlb_entries", 0400, obj->debug_dir,
-			       &obj->nr_tlb_entries);
-	if (!d)
-		return;
-
-	DEBUG_ADD_FILE_RO(regs);
-	DEBUG_ADD_FILE_RO(tlb);
-	DEBUG_ADD_FILE_RO(pagetable);
-
-	return;
-
-err:
-	debugfs_remove_recursive(obj->debug_dir);
+	debugfs_create_u32("nr_tlb_entries", 0400, d, &obj->nr_tlb_entries);
+	debugfs_create_file("regs", 0400, d, obj, &regs_fops);
+	debugfs_create_file("tlb", 0400, d, obj, &tlb_fops);
+	debugfs_create_file("pagetable", 0400, d, obj, &pagetable_fops);
 }
 
 void omap_iommu_debugfs_remove(struct omap_iommu *obj)
@@ -284,8 +263,6 @@ void omap_iommu_debugfs_remove(struct omap_iommu *obj)
 void __init omap_iommu_debugfs_init(void)
 {
 	iommu_debug_root = debugfs_create_dir("omap_iommu", NULL);
-	if (!iommu_debug_root)
-		pr_err("can't create debugfs dir\n");
 }
 
 void __exit omap_iommu_debugfs_exit(void)
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index 62f9c61338a5..dfb961d8c21b 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -35,8 +35,7 @@
 
 static const struct iommu_ops omap_iommu_ops;
 
-#define to_iommu(dev)							\
-	((struct omap_iommu *)platform_get_drvdata(to_platform_device(dev)))
+#define to_iommu(dev)	((struct omap_iommu *)dev_get_drvdata(dev))
 
 /* bitmap of the page sizes currently supported */
 #define OMAP_IOMMU_PGSIZES	(SZ_4K | SZ_64K | SZ_1M | SZ_16M)
diff --git a/include/linux/device.h b/include/linux/device.h
index 4a295e324ac5..b6ff25d9fff4 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -42,6 +42,7 @@ struct iommu_ops;
 struct iommu_group;
 struct iommu_fwspec;
 struct dev_pin_info;
+struct iommu_param;
 
 struct bus_attribute {
 	struct attribute	attr;
@@ -961,6 +962,7 @@ struct dev_links_info {
  * 		device (i.e. the bus driver that discovered the device).
  * @iommu_group: IOMMU group the device belongs to.
  * @iommu_fwspec: IOMMU-specific properties supplied by firmware.
+ * @iommu_param: Per device generic IOMMU runtime data
  *
  * @offline_disabled: If set, the device is permanently online.
  * @offline:	Set after successful invocation of bus type's .offline().
@@ -1054,6 +1056,7 @@ struct device {
 	void	(*release)(struct device *dev);
 	struct iommu_group	*iommu_group;
 	struct iommu_fwspec	*iommu_fwspec;
+	struct iommu_param	*iommu_param;
 
 	bool			offline_disabled:1;
 	bool			offline:1;
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index 37258c8b2063..2112f21f73d8 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -5,59 +5,21 @@
 #ifndef __DMA_IOMMU_H
 #define __DMA_IOMMU_H
 
-#ifdef __KERNEL__
+#include <linux/errno.h>
 #include <linux/types.h>
-#include <asm/errno.h>
 
 #ifdef CONFIG_IOMMU_DMA
 #include <linux/dma-mapping.h>
 #include <linux/iommu.h>
 #include <linux/msi.h>
 
-int iommu_dma_init(void);
-
 /* Domain management interface for IOMMU drivers */
 int iommu_get_dma_cookie(struct iommu_domain *domain);
 int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base);
 void iommu_put_dma_cookie(struct iommu_domain *domain);
 
 /* Setup call for arch DMA mapping code */
-int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
-		u64 size, struct device *dev);
-
-/* General helpers for DMA-API <-> IOMMU-API interaction */
-int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
-		     unsigned long attrs);
-
-/*
- * These implement the bulk of the relevant DMA mapping callbacks, but require
- * the arch code to take care of attributes and cache maintenance
- */
-struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
-		unsigned long attrs, int prot, dma_addr_t *handle,
-		void (*flush_page)(struct device *, const void *, phys_addr_t));
-void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
-		dma_addr_t *handle);
-
-int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma);
-
-dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, int prot);
-int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, int prot);
-
-/*
- * Arch code with no special attribute handling may use these
- * directly as DMA mapping callbacks for simplicity
- */
-void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size,
-		enum dma_data_direction dir, unsigned long attrs);
-void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir, unsigned long attrs);
-dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
-void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
+void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size);
 
 /* The DMA API isn't _quite_ the whole story, though... */
 /*
@@ -75,16 +37,16 @@ void iommu_dma_compose_msi_msg(struct msi_desc *desc,
 
 void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list);
 
-#else
+#else /* CONFIG_IOMMU_DMA */
 
 struct iommu_domain;
 struct msi_desc;
 struct msi_msg;
 struct device;
 
-static inline int iommu_dma_init(void)
+static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base,
+		u64 size)
 {
-	return 0;
 }
 
 static inline int iommu_get_dma_cookie(struct iommu_domain *domain)
@@ -117,5 +79,4 @@ static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_he
 }
 
 #endif	/* CONFIG_IOMMU_DMA */
-#endif	/* __KERNEL__ */
 #endif	/* __DMA_IOMMU_H */
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 6a8dd4af0147..f2ae8a006ff8 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -435,6 +435,12 @@ enum {
 #define VTD_FLAG_TRANS_PRE_ENABLED	(1 << 0)
 #define VTD_FLAG_IRQ_REMAP_PRE_ENABLED	(1 << 1)
 
+extern int intel_iommu_sm;
+
+#define sm_supported(iommu)	(intel_iommu_sm && ecap_smts((iommu)->ecap))
+#define pasid_supported(iommu)	(sm_supported(iommu) &&			\
+				 ecap_pasid((iommu)->ecap))
+
 struct pasid_entry;
 struct pasid_state_entry;
 struct page_req_dsc;
@@ -642,7 +648,6 @@ extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
 
 extern int dmar_ir_support(void);
 
-struct dmar_domain *get_valid_domain_for_dev(struct device *dev);
 void *alloc_pgtable_page(int node);
 void free_pgtable_page(void *vaddr);
 struct intel_iommu *domain_get_iommu(struct dmar_domain *domain);
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index 54ffcc6a322e..94f047a8a845 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -49,7 +49,7 @@ struct svm_dev_ops {
 
 /**
  * intel_svm_bind_mm() - Bind the current process to a PASID
- * @dev:	Device to be granted acccess
+ * @dev:	Device to be granted access
  * @pasid:	Address for allocated PASID
  * @flags:	Flags. Later for requesting supervisor mode, etc.
  * @ops:	Callbacks to device driver
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 76969a564831..b5a450a3bb47 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -44,6 +44,8 @@ struct iommu_gather_ops {
  *                 tables.
  * @ias:           Input address (iova) size, in bits.
  * @oas:           Output address (paddr) size, in bits.
+ * @coherent_walk  A flag to indicate whether or not page table walks made
+ *                 by the IOMMU are coherent with the CPU caches.
  * @tlb:           TLB management callbacks for this set of tables.
  * @iommu_dev:     The device representing the DMA configuration for the
  *                 page table walker.
@@ -68,11 +70,6 @@ struct io_pgtable_cfg {
 	 *	when the SoC is in "4GB mode" and they can only access the high
 	 *	remap of DRAM (0x1_00000000 to 0x1_ffffffff).
 	 *
-	 * IO_PGTABLE_QUIRK_NO_DMA: Guarantees that the tables will only ever
-	 *	be accessed by a fully cache-coherent IOMMU or CPU (e.g. for a
-	 *	software-emulated IOMMU), such that pagetable updates need not
-	 *	be treated as explicit DMA data.
-	 *
 	 * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
 	 *	on unmap, for DMA domains using the flush queue mechanism for
 	 *	delayed invalidation.
@@ -81,12 +78,12 @@ struct io_pgtable_cfg {
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
 	#define IO_PGTABLE_QUIRK_TLBI_ON_MAP	BIT(2)
 	#define IO_PGTABLE_QUIRK_ARM_MTK_4GB	BIT(3)
-	#define IO_PGTABLE_QUIRK_NO_DMA		BIT(4)
-	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(5)
+	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
 	unsigned int			oas;
+	bool				coherent_walk;
 	const struct iommu_gather_ops	*tlb;
 	struct device			*iommu_dev;
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e552c3b63f6f..fdc355ccc570 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/of.h>
+#include <uapi/linux/iommu.h>
 
 #define IOMMU_READ	(1 << 0)
 #define IOMMU_WRITE	(1 << 1)
@@ -29,6 +30,12 @@
  * if the IOMMU page table format is equivalent.
  */
 #define IOMMU_PRIV	(1 << 5)
+/*
+ * Non-coherent masters on few Qualcomm SoCs can use this page protection flag
+ * to set correct cacheability attributes to use an outer level of cache -
+ * last level cache, aka system cache.
+ */
+#define IOMMU_QCOM_SYS_CACHE	(1 << 6)
 
 struct iommu_ops;
 struct iommu_group;
@@ -37,6 +44,7 @@ struct device;
 struct iommu_domain;
 struct notifier_block;
 struct iommu_sva;
+struct iommu_fault_event;
 
 /* iommu fault flags */
 #define IOMMU_FAULT_READ	0x0
@@ -46,6 +54,7 @@ typedef int (*iommu_fault_handler_t)(struct iommu_domain *,
 			struct device *, unsigned long, int, void *);
 typedef int (*iommu_mm_exit_handler_t)(struct device *dev, struct iommu_sva *,
 				       void *);
+typedef int (*iommu_dev_fault_handler_t)(struct iommu_fault *, void *);
 
 struct iommu_domain_geometry {
 	dma_addr_t aperture_start; /* First address that can be mapped    */
@@ -123,6 +132,12 @@ enum iommu_attr {
 enum iommu_resv_type {
 	/* Memory regions which must be mapped 1:1 at all times */
 	IOMMU_RESV_DIRECT,
+	/*
+	 * Memory regions which are advertised to be 1:1 but are
+	 * commonly considered relaxable in some conditions,
+	 * for instance in device assignment use case (USB, Graphics)
+	 */
+	IOMMU_RESV_DIRECT_RELAXABLE,
 	/* Arbitrary "never map this or give it to a device" address ranges */
 	IOMMU_RESV_RESERVED,
 	/* Hardware MSI region (untranslated) */
@@ -212,6 +227,7 @@ struct iommu_sva_ops {
  * @sva_bind: Bind process address space to device
  * @sva_unbind: Unbind process address space from device
  * @sva_get_pasid: Get PASID associated to a SVA handle
+ * @page_response: handle page request response
  * @pgsize_bitmap: bitmap of all possible supported page sizes
  */
 struct iommu_ops {
@@ -272,6 +288,10 @@ struct iommu_ops {
 	void (*sva_unbind)(struct iommu_sva *handle);
 	int (*sva_get_pasid)(struct iommu_sva *handle);
 
+	int (*page_response)(struct device *dev,
+			     struct iommu_fault_event *evt,
+			     struct iommu_page_response *msg);
+
 	unsigned long pgsize_bitmap;
 };
 
@@ -289,6 +309,48 @@ struct iommu_device {
 	struct device *dev;
 };
 
+/**
+ * struct iommu_fault_event - Generic fault event
+ *
+ * Can represent recoverable faults such as a page requests or
+ * unrecoverable faults such as DMA or IRQ remapping faults.
+ *
+ * @fault: fault descriptor
+ * @list: pending fault event list, used for tracking responses
+ */
+struct iommu_fault_event {
+	struct iommu_fault fault;
+	struct list_head list;
+};
+
+/**
+ * struct iommu_fault_param - per-device IOMMU fault data
+ * @handler: Callback function to handle IOMMU faults at device level
+ * @data: handler private data
+ * @faults: holds the pending faults which needs response
+ * @lock: protect pending faults list
+ */
+struct iommu_fault_param {
+	iommu_dev_fault_handler_t handler;
+	void *data;
+	struct list_head faults;
+	struct mutex lock;
+};
+
+/**
+ * struct iommu_param - collection of per-device IOMMU data
+ *
+ * @fault_param: IOMMU detected device fault reporting data
+ *
+ * TODO: migrate other per device data pointers under iommu_dev_data, e.g.
+ *	struct iommu_group	*iommu_group;
+ *	struct iommu_fwspec	*iommu_fwspec;
+ */
+struct iommu_param {
+	struct mutex lock;
+	struct iommu_fault_param *fault_param;
+};
+
 int  iommu_device_register(struct iommu_device *iommu);
 void iommu_device_unregister(struct iommu_device *iommu);
 int  iommu_device_sysfs_add(struct iommu_device *iommu,
@@ -350,6 +412,7 @@ extern void iommu_set_fault_handler(struct iommu_domain *domain,
 extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
 extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
 extern int iommu_request_dm_for_dev(struct device *dev);
+extern int iommu_request_dma_domain_for_dev(struct device *dev);
 extern struct iommu_resv_region *
 iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot,
 			enum iommu_resv_type type);
@@ -378,6 +441,17 @@ extern int iommu_group_register_notifier(struct iommu_group *group,
 					 struct notifier_block *nb);
 extern int iommu_group_unregister_notifier(struct iommu_group *group,
 					   struct notifier_block *nb);
+extern int iommu_register_device_fault_handler(struct device *dev,
+					iommu_dev_fault_handler_t handler,
+					void *data);
+
+extern int iommu_unregister_device_fault_handler(struct device *dev);
+
+extern int iommu_report_device_fault(struct device *dev,
+				     struct iommu_fault_event *evt);
+extern int iommu_page_response(struct device *dev,
+			       struct iommu_page_response *msg);
+
 extern int iommu_group_id(struct iommu_group *group);
 extern struct iommu_group *iommu_group_get_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *);
@@ -492,6 +566,7 @@ struct iommu_ops {};
 struct iommu_group {};
 struct iommu_fwspec {};
 struct iommu_device {};
+struct iommu_fault_param {};
 
 static inline bool iommu_present(struct bus_type *bus)
 {
@@ -614,6 +689,11 @@ static inline int iommu_request_dm_for_dev(struct device *dev)
 	return -ENODEV;
 }
 
+static inline int iommu_request_dma_domain_for_dev(struct device *dev)
+{
+	return -ENODEV;
+}
+
 static inline int iommu_attach_group(struct iommu_domain *domain,
 				     struct iommu_group *group)
 {
@@ -685,6 +765,31 @@ static inline int iommu_group_unregister_notifier(struct iommu_group *group,
 	return 0;
 }
 
+static inline
+int iommu_register_device_fault_handler(struct device *dev,
+					iommu_dev_fault_handler_t handler,
+					void *data)
+{
+	return -ENODEV;
+}
+
+static inline int iommu_unregister_device_fault_handler(struct device *dev)
+{
+	return 0;
+}
+
+static inline
+int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt)
+{
+	return -ENODEV;
+}
+
+static inline int iommu_page_response(struct device *dev,
+				      struct iommu_page_response *msg)
+{
+	return -ENODEV;
+}
+
 static inline int iommu_group_id(struct iommu_group *group)
 {
 	return -ENODEV;
diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
new file mode 100644
index 000000000000..fc00c5d4741b
--- /dev/null
+++ b/include/uapi/linux/iommu.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * IOMMU user API definitions
+ */
+
+#ifndef _UAPI_IOMMU_H
+#define _UAPI_IOMMU_H
+
+#include <linux/types.h>
+
+#define IOMMU_FAULT_PERM_READ	(1 << 0) /* read */
+#define IOMMU_FAULT_PERM_WRITE	(1 << 1) /* write */
+#define IOMMU_FAULT_PERM_EXEC	(1 << 2) /* exec */
+#define IOMMU_FAULT_PERM_PRIV	(1 << 3) /* privileged */
+
+/* Generic fault types, can be expanded IRQ remapping fault */
+enum iommu_fault_type {
+	IOMMU_FAULT_DMA_UNRECOV = 1,	/* unrecoverable fault */
+	IOMMU_FAULT_PAGE_REQ,		/* page request fault */
+};
+
+enum iommu_fault_reason {
+	IOMMU_FAULT_REASON_UNKNOWN = 0,
+
+	/* Could not access the PASID table (fetch caused external abort) */
+	IOMMU_FAULT_REASON_PASID_FETCH,
+
+	/* PASID entry is invalid or has configuration errors */
+	IOMMU_FAULT_REASON_BAD_PASID_ENTRY,
+
+	/*
+	 * PASID is out of range (e.g. exceeds the maximum PASID
+	 * supported by the IOMMU) or disabled.
+	 */
+	IOMMU_FAULT_REASON_PASID_INVALID,
+
+	/*
+	 * An external abort occurred fetching (or updating) a translation
+	 * table descriptor
+	 */
+	IOMMU_FAULT_REASON_WALK_EABT,
+
+	/*
+	 * Could not access the page table entry (Bad address),
+	 * actual translation fault
+	 */
+	IOMMU_FAULT_REASON_PTE_FETCH,
+
+	/* Protection flag check failed */
+	IOMMU_FAULT_REASON_PERMISSION,
+
+	/* access flag check failed */
+	IOMMU_FAULT_REASON_ACCESS,
+
+	/* Output address of a translation stage caused Address Size fault */
+	IOMMU_FAULT_REASON_OOR_ADDRESS,
+};
+
+/**
+ * struct iommu_fault_unrecoverable - Unrecoverable fault data
+ * @reason: reason of the fault, from &enum iommu_fault_reason
+ * @flags: parameters of this fault (IOMMU_FAULT_UNRECOV_* values)
+ * @pasid: Process Address Space ID
+ * @perm: requested permission access using by the incoming transaction
+ *        (IOMMU_FAULT_PERM_* values)
+ * @addr: offending page address
+ * @fetch_addr: address that caused a fetch abort, if any
+ */
+struct iommu_fault_unrecoverable {
+	__u32	reason;
+#define IOMMU_FAULT_UNRECOV_PASID_VALID		(1 << 0)
+#define IOMMU_FAULT_UNRECOV_ADDR_VALID		(1 << 1)
+#define IOMMU_FAULT_UNRECOV_FETCH_ADDR_VALID	(1 << 2)
+	__u32	flags;
+	__u32	pasid;
+	__u32	perm;
+	__u64	addr;
+	__u64	fetch_addr;
+};
+
+/**
+ * struct iommu_fault_page_request - Page Request data
+ * @flags: encodes whether the corresponding fields are valid and whether this
+ *         is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values)
+ * @pasid: Process Address Space ID
+ * @grpid: Page Request Group Index
+ * @perm: requested page permissions (IOMMU_FAULT_PERM_* values)
+ * @addr: page address
+ * @private_data: device-specific private information
+ */
+struct iommu_fault_page_request {
+#define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID	(1 << 0)
+#define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE	(1 << 1)
+#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA	(1 << 2)
+	__u32	flags;
+	__u32	pasid;
+	__u32	grpid;
+	__u32	perm;
+	__u64	addr;
+	__u64	private_data[2];
+};
+
+/**
+ * struct iommu_fault - Generic fault data
+ * @type: fault type from &enum iommu_fault_type
+ * @padding: reserved for future use (should be zero)
+ * @event: fault event, when @type is %IOMMU_FAULT_DMA_UNRECOV
+ * @prm: Page Request message, when @type is %IOMMU_FAULT_PAGE_REQ
+ * @padding2: sets the fault size to allow for future extensions
+ */
+struct iommu_fault {
+	__u32	type;
+	__u32	padding;
+	union {
+		struct iommu_fault_unrecoverable event;
+		struct iommu_fault_page_request prm;
+		__u8 padding2[56];
+	};
+};
+
+/**
+ * enum iommu_page_response_code - Return status of fault handlers
+ * @IOMMU_PAGE_RESP_SUCCESS: Fault has been handled and the page tables
+ *	populated, retry the access. This is "Success" in PCI PRI.
+ * @IOMMU_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from
+ *	this device if possible. This is "Response Failure" in PCI PRI.
+ * @IOMMU_PAGE_RESP_INVALID: Could not handle this fault, don't retry the
+ *	access. This is "Invalid Request" in PCI PRI.
+ */
+enum iommu_page_response_code {
+	IOMMU_PAGE_RESP_SUCCESS = 0,
+	IOMMU_PAGE_RESP_INVALID,
+	IOMMU_PAGE_RESP_FAILURE,
+};
+
+/**
+ * struct iommu_page_response - Generic page response information
+ * @version: API version of this structure
+ * @flags: encodes whether the corresponding fields are valid
+ *         (IOMMU_FAULT_PAGE_RESPONSE_* values)
+ * @pasid: Process Address Space ID
+ * @grpid: Page Request Group Index
+ * @code: response code from &enum iommu_page_response_code
+ */
+struct iommu_page_response {
+#define IOMMU_PAGE_RESP_VERSION_1	1
+	__u32	version;
+#define IOMMU_PAGE_RESP_PASID_VALID	(1 << 0)
+	__u32	flags;
+	__u32	pasid;
+	__u32	grpid;
+	__u32	code;
+};
+
+#endif /* _UAPI_IOMMU_H */