diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index dc91de5..955b6ca 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -224,28 +224,26 @@ static int pci_dac_dma_supported(struct pci_dev *dev, u64 mask)
    until either pci_unmap_single or pci_dma_sync_single is performed.  */
 
 static dma_addr_t
-pci_map_single_1(struct pci_dev *pdev, void *cpu_addr, size_t size,
+pci_map_single_1(struct pci_dev *pdev, phys_addr_t paddr, size_t size,
 		 int dac_allowed)
 {
 	struct pci_controller *hose = pdev ? pdev->sysdata : pci_isa_hose;
 	dma_addr_t max_dma = pdev ? pdev->dma_mask : ISA_DMA_MASK;
+	unsigned long offset = offset_in_page(paddr);
 	struct pci_iommu_arena *arena;
 	long npages, dma_ofs, i;
-	unsigned long paddr;
 	dma_addr_t ret;
 	unsigned int align = 0;
 	struct device *dev = pdev ? &pdev->dev : NULL;
 
-	paddr = __pa(cpu_addr);
-
 #if !DEBUG_NODIRECT
 	/* First check to see if we can use the direct map window.  */
 	if (paddr + size + __direct_map_base - 1 <= max_dma
 	    && paddr + size <= __direct_map_size) {
 		ret = paddr + __direct_map_base;
 
-		DBGA2("pci_map_single: [%p,%zx] -> direct %llx from %ps\n",
-		      cpu_addr, size, ret, __builtin_return_address(0));
+		DBGA2("pci_map_single: [%pa,%zx] -> direct %llx from %ps\n",
+		      &paddr, size, ret, __builtin_return_address(0));
 
 		return ret;
 	}
@@ -255,8 +253,8 @@ pci_map_single_1(struct pci_dev *pdev, void *cpu_addr, size_t size,
 	if (dac_allowed) {
 		ret = paddr + alpha_mv.pci_dac_offset;
 
-		DBGA2("pci_map_single: [%p,%zx] -> DAC %llx from %ps\n",
-		      cpu_addr, size, ret, __builtin_return_address(0));
+		DBGA2("pci_map_single: [%pa,%zx] -> DAC %llx from %ps\n",
+		      &paddr, size, ret, __builtin_return_address(0));
 
 		return ret;
 	}
@@ -290,10 +288,10 @@ pci_map_single_1(struct pci_dev *pdev, void *cpu_addr, size_t size,
 		arena->ptes[i + dma_ofs] = mk_iommu_pte(paddr);
 
 	ret = arena->dma_base + dma_ofs * PAGE_SIZE;
-	ret += (unsigned long)cpu_addr & ~PAGE_MASK;
+	ret += offset;
 
-	DBGA2("pci_map_single: [%p,%zx] np %ld -> sg %llx from %ps\n",
-	      cpu_addr, size, npages, ret, __builtin_return_address(0));
+	DBGA2("pci_map_single: [%pa,%zx] np %ld -> sg %llx from %ps\n",
+	      &paddr, size, npages, ret, __builtin_return_address(0));
 
 	return ret;
 }
@@ -322,19 +320,18 @@ static struct pci_dev *alpha_gendev_to_pci(struct device *dev)
 	return NULL;
 }
 
-static dma_addr_t alpha_pci_map_page(struct device *dev, struct page *page,
-				     unsigned long offset, size_t size,
-				     enum dma_data_direction dir,
+static dma_addr_t alpha_pci_map_phys(struct device *dev, phys_addr_t phys,
+				     size_t size, enum dma_data_direction dir,
 				     unsigned long attrs)
 {
 	struct pci_dev *pdev = alpha_gendev_to_pci(dev);
 	int dac_allowed;
 
-	BUG_ON(dir == DMA_NONE);
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
 
-	dac_allowed = pdev ? pci_dac_dma_supported(pdev, pdev->dma_mask) : 0; 
-	return pci_map_single_1(pdev, (char *)page_address(page) + offset, 
-				size, dac_allowed);
+	dac_allowed = pdev ? pci_dac_dma_supported(pdev, pdev->dma_mask) : 0;
+	return pci_map_single_1(pdev, phys, size, dac_allowed);
 }
 
 /* Unmap a single streaming mode DMA translation.  The DMA_ADDR and
@@ -343,7 +340,7 @@ static dma_addr_t alpha_pci_map_page(struct device *dev, struct page *page,
    the cpu to the buffer are guaranteed to see whatever the device
    wrote there.  */
 
-static void alpha_pci_unmap_page(struct device *dev, dma_addr_t dma_addr,
+static void alpha_pci_unmap_phys(struct device *dev, dma_addr_t dma_addr,
 				 size_t size, enum dma_data_direction dir,
 				 unsigned long attrs)
 {
@@ -353,8 +350,6 @@ static void alpha_pci_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	struct pci_iommu_arena *arena;
 	long dma_ofs, npages;
 
-	BUG_ON(dir == DMA_NONE);
-
 	if (dma_addr >= __direct_map_base
 	    && dma_addr < __direct_map_base + __direct_map_size) {
 		/* Nothing to do.  */
@@ -429,7 +424,7 @@ try_again:
 	}
 	memset(cpu_addr, 0, size);
 
-	*dma_addrp = pci_map_single_1(pdev, cpu_addr, size, 0);
+	*dma_addrp = pci_map_single_1(pdev, virt_to_phys(cpu_addr), size, 0);
 	if (*dma_addrp == DMA_MAPPING_ERROR) {
 		free_pages((unsigned long)cpu_addr, order);
 		if (alpha_mv.mv_pci_tbi || (gfp & GFP_DMA))
@@ -643,9 +638,8 @@ static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg,
 	/* Fast path single entry scatterlists.  */
 	if (nents == 1) {
 		sg->dma_length = sg->length;
-		sg->dma_address
-		  = pci_map_single_1(pdev, SG_ENT_VIRT_ADDRESS(sg),
-				     sg->length, dac_allowed);
+		sg->dma_address = pci_map_single_1(pdev, sg_phys(sg),
+						   sg->length, dac_allowed);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
 			return -EIO;
 		return 1;
@@ -917,8 +911,8 @@ iommu_unbind(struct pci_iommu_arena *arena, long pg_start, long pg_count)
 const struct dma_map_ops alpha_pci_ops = {
 	.alloc			= alpha_pci_alloc_coherent,
 	.free			= alpha_pci_free_coherent,
-	.map_page		= alpha_pci_map_page,
-	.unmap_page		= alpha_pci_unmap_page,
+	.map_phys		= alpha_pci_map_phys,
+	.unmap_phys		= alpha_pci_unmap_phys,
 	.map_sg			= alpha_pci_map_sg,
 	.unmap_sg		= alpha_pci_unmap_sg,
 	.dma_supported		= alpha_pci_supported,
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 08641a9..a4c765d 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -624,16 +624,14 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 	kfree(buf);
 }
 
-static void dma_cache_maint_page(struct page *page, unsigned long offset,
-	size_t size, enum dma_data_direction dir,
+static void dma_cache_maint_page(phys_addr_t phys, size_t size,
+	enum dma_data_direction dir,
 	void (*op)(const void *, size_t, int))
 {
-	unsigned long pfn;
+	unsigned long offset = offset_in_page(phys);
+	unsigned long pfn = __phys_to_pfn(phys);
 	size_t left = size;
 
-	pfn = page_to_pfn(page) + offset / PAGE_SIZE;
-	offset %= PAGE_SIZE;
-
 	/*
 	 * A single sg entry may refer to multiple physically contiguous
 	 * pages.  But we still need to process highmem pages individually.
@@ -644,17 +642,18 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 		size_t len = left;
 		void *vaddr;
 
-		page = pfn_to_page(pfn);
-
-		if (PageHighMem(page)) {
+		phys = __pfn_to_phys(pfn);
+		if (PhysHighMem(phys)) {
 			if (len + offset > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
 
 			if (cache_is_vipt_nonaliasing()) {
-				vaddr = kmap_atomic(page);
+				vaddr = kmap_atomic_pfn(pfn);
 				op(vaddr + offset, len, dir);
 				kunmap_atomic(vaddr);
 			} else {
+				struct page *page = phys_to_page(phys);
+
 				vaddr = kmap_high_get(page);
 				if (vaddr) {
 					op(vaddr + offset, len, dir);
@@ -662,7 +661,8 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 				}
 			}
 		} else {
-			vaddr = page_address(page) + offset;
+			phys += offset;
+			vaddr = phys_to_virt(phys);
 			op(vaddr, len, dir);
 		}
 		offset = 0;
@@ -676,14 +676,11 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
  * Note: Drivers should NOT use this function directly.
  * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
  */
-static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
-	size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+			      enum dma_data_direction dir)
 {
-	phys_addr_t paddr;
+	dma_cache_maint_page(paddr, size, dir, dmac_map_area);
 
-	dma_cache_maint_page(page, off, size, dir, dmac_map_area);
-
-	paddr = page_to_phys(page) + off;
 	if (dir == DMA_FROM_DEVICE) {
 		outer_inv_range(paddr, paddr + size);
 	} else {
@@ -692,17 +689,15 @@ static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
 	/* FIXME: non-speculating: flush on bidirectional mappings? */
 }
 
-static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
-	size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+			   enum dma_data_direction dir)
 {
-	phys_addr_t paddr = page_to_phys(page) + off;
-
 	/* FIXME: non-speculating: not required */
 	/* in any case, don't bother invalidating if DMA to device */
 	if (dir != DMA_TO_DEVICE) {
 		outer_inv_range(paddr, paddr + size);
 
-		dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+		dma_cache_maint_page(paddr, size, dir, dmac_unmap_area);
 	}
 
 	/*
@@ -737,6 +732,9 @@ static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
 	if (attrs & DMA_ATTR_PRIVILEGED)
 		prot |= IOMMU_PRIV;
 
+	if (attrs & DMA_ATTR_MMIO)
+		prot |= IOMMU_MMIO;
+
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
 		return prot | IOMMU_READ | IOMMU_WRITE;
@@ -1205,7 +1203,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		unsigned int len = PAGE_ALIGN(s->offset + s->length);
 
 		if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
+			arch_sync_dma_for_device(sg_phys(s), s->length, dir);
 
 		prot = __dma_info_to_prot(dir, attrs);
 
@@ -1307,8 +1305,7 @@ static void arm_iommu_unmap_sg(struct device *dev,
 			__iommu_remove_mapping(dev, sg_dma_address(s),
 					       sg_dma_len(s));
 		if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			__dma_page_dev_to_cpu(sg_page(s), s->offset,
-					      s->length, dir);
+			arch_sync_dma_for_cpu(sg_phys(s), s->length, dir);
 	}
 }
 
@@ -1330,7 +1327,7 @@ static void arm_iommu_sync_sg_for_cpu(struct device *dev,
 		return;
 
 	for_each_sg(sg, s, nents, i)
-		__dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir);
+		arch_sync_dma_for_cpu(sg_phys(s), s->length, dir);
 
 }
 
@@ -1352,29 +1349,31 @@ static void arm_iommu_sync_sg_for_device(struct device *dev,
 		return;
 
 	for_each_sg(sg, s, nents, i)
-		__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
+		arch_sync_dma_for_device(sg_phys(s), s->length, dir);
 }
 
 /**
- * arm_iommu_map_page
+ * arm_iommu_map_phys
  * @dev: valid struct device pointer
- * @page: page that buffer resides in
- * @offset: offset into page for start of buffer
+ * @phys: physical address that buffer resides in
  * @size: size of buffer to map
  * @dir: DMA transfer direction
+ * @attrs: DMA mapping attributes
  *
  * IOMMU aware version of arm_dma_map_page()
  */
-static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir,
-	     unsigned long attrs)
+static dma_addr_t arm_iommu_map_phys(struct device *dev, phys_addr_t phys,
+	     size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
+	int len = PAGE_ALIGN(size + offset_in_page(phys));
+	phys_addr_t addr = phys & PAGE_MASK;
 	dma_addr_t dma_addr;
-	int ret, prot, len = PAGE_ALIGN(size + offset);
+	int ret, prot;
 
-	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_page_cpu_to_dev(page, offset, size, dir);
+	if (!dev->dma_coherent &&
+	    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
+		arch_sync_dma_for_device(phys, size, dir);
 
 	dma_addr = __alloc_iova(mapping, len);
 	if (dma_addr == DMA_MAPPING_ERROR)
@@ -1382,12 +1381,11 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
 
 	prot = __dma_info_to_prot(dir, attrs);
 
-	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len,
-			prot, GFP_KERNEL);
+	ret = iommu_map(mapping->domain, dma_addr, addr, len, prot, GFP_KERNEL);
 	if (ret < 0)
 		goto fail;
 
-	return dma_addr + offset;
+	return dma_addr + offset_in_page(phys);
 fail:
 	__free_iova(mapping, dma_addr, len);
 	return DMA_MAPPING_ERROR;
@@ -1399,82 +1397,27 @@ fail:
  * @handle: DMA address of buffer
  * @size: size of buffer (same as passed to dma_map_page)
  * @dir: DMA transfer direction (same as passed to dma_map_page)
+ * @attrs: DMA mapping attributes
  *
- * IOMMU aware version of arm_dma_unmap_page()
+ * IOMMU aware version of arm_dma_unmap_phys()
  */
-static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
+static void arm_iommu_unmap_phys(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page;
 	int offset = handle & ~PAGE_MASK;
 	int len = PAGE_ALIGN(size + offset);
 
 	if (!iova)
 		return;
 
-	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
-		page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
-		__dma_page_dev_to_cpu(page, offset, size, dir);
-	}
-
-	iommu_unmap(mapping->domain, iova, len);
-	__free_iova(mapping, iova, len);
-}
-
-/**
- * arm_iommu_map_resource - map a device resource for DMA
- * @dev: valid struct device pointer
- * @phys_addr: physical address of resource
- * @size: size of resource to map
- * @dir: DMA transfer direction
- */
-static dma_addr_t arm_iommu_map_resource(struct device *dev,
-		phys_addr_t phys_addr, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
-	dma_addr_t dma_addr;
-	int ret, prot;
-	phys_addr_t addr = phys_addr & PAGE_MASK;
-	unsigned int offset = phys_addr & ~PAGE_MASK;
-	size_t len = PAGE_ALIGN(size + offset);
-
-	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == DMA_MAPPING_ERROR)
-		return dma_addr;
-
-	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
-
-	ret = iommu_map(mapping->domain, dma_addr, addr, len, prot, GFP_KERNEL);
-	if (ret < 0)
-		goto fail;
-
-	return dma_addr + offset;
-fail:
-	__free_iova(mapping, dma_addr, len);
-	return DMA_MAPPING_ERROR;
-}
+	if (!dev->dma_coherent &&
+	    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO))) {
+		phys_addr_t phys = iommu_iova_to_phys(mapping->domain, iova);
 
-/**
- * arm_iommu_unmap_resource - unmap a device DMA resource
- * @dev: valid struct device pointer
- * @dma_handle: DMA address to resource
- * @size: size of resource to map
- * @dir: DMA transfer direction
- */
-static void arm_iommu_unmap_resource(struct device *dev, dma_addr_t dma_handle,
-		size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
-	dma_addr_t iova = dma_handle & PAGE_MASK;
-	unsigned int offset = dma_handle & ~PAGE_MASK;
-	size_t len = PAGE_ALIGN(size + offset);
-
-	if (!iova)
-		return;
+		arch_sync_dma_for_cpu(phys + offset, size, dir);
+	}
 
 	iommu_unmap(mapping->domain, iova, len);
 	__free_iova(mapping, iova, len);
@@ -1485,14 +1428,14 @@ static void arm_iommu_sync_single_for_cpu(struct device *dev,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page;
 	unsigned int offset = handle & ~PAGE_MASK;
+	phys_addr_t phys;
 
 	if (dev->dma_coherent || !iova)
 		return;
 
-	page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
-	__dma_page_dev_to_cpu(page, offset, size, dir);
+	phys = iommu_iova_to_phys(mapping->domain, iova);
+	arch_sync_dma_for_cpu(phys + offset, size, dir);
 }
 
 static void arm_iommu_sync_single_for_device(struct device *dev,
@@ -1500,14 +1443,14 @@ static void arm_iommu_sync_single_for_device(struct device *dev,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page;
 	unsigned int offset = handle & ~PAGE_MASK;
+	phys_addr_t phys;
 
 	if (dev->dma_coherent || !iova)
 		return;
 
-	page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
-	__dma_page_cpu_to_dev(page, offset, size, dir);
+	phys = iommu_iova_to_phys(mapping->domain, iova);
+	arch_sync_dma_for_device(phys + offset, size, dir);
 }
 
 static const struct dma_map_ops iommu_ops = {
@@ -1516,8 +1459,8 @@ static const struct dma_map_ops iommu_ops = {
 	.mmap		= arm_iommu_mmap_attrs,
 	.get_sgtable	= arm_iommu_get_sgtable,
 
-	.map_page		= arm_iommu_map_page,
-	.unmap_page		= arm_iommu_unmap_page,
+	.map_phys		= arm_iommu_map_phys,
+	.unmap_phys		= arm_iommu_unmap_phys,
 	.sync_single_for_cpu	= arm_iommu_sync_single_for_cpu,
 	.sync_single_for_device	= arm_iommu_sync_single_for_device,
 
@@ -1525,9 +1468,6 @@ static const struct dma_map_ops iommu_ops = {
 	.unmap_sg		= arm_iommu_unmap_sg,
 	.sync_sg_for_cpu	= arm_iommu_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_iommu_sync_sg_for_device,
-
-	.map_resource		= arm_iommu_map_resource,
-	.unmap_resource		= arm_iommu_unmap_resource,
 };
 
 /**
@@ -1794,20 +1734,6 @@ void arch_teardown_dma_ops(struct device *dev)
 	set_dma_ops(dev, NULL);
 }
 
-void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-	__dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
-			      size, dir);
-}
-
-void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-	__dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
-			      size, dir);
-}
-
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs)
 {
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index c97b089..eb9fb2f 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -521,18 +521,24 @@ static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
 	__free_pages(virt_to_page(vaddr), get_order(size));
 }
 
-static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
+static dma_addr_t jazz_dma_map_phys(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	phys_addr_t phys = page_to_phys(page) + offset;
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		/*
+		 * This check is included because older versions of the code lacked
+		 * MMIO path support, and my ability to test this path is limited.
+		 * However, from a software technical standpoint, there is no restriction,
+		 * as the following code operates solely on physical addresses.
+		 */
+		return DMA_MAPPING_ERROR;
 
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		arch_sync_dma_for_device(phys, size, dir);
 	return vdma_alloc(phys, size);
 }
 
-static void jazz_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
+static void jazz_dma_unmap_phys(struct device *dev, dma_addr_t dma_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
@@ -607,8 +613,8 @@ static void jazz_dma_sync_sg_for_cpu(struct device *dev,
 const struct dma_map_ops jazz_dma_ops = {
 	.alloc			= jazz_dma_alloc,
 	.free			= jazz_dma_free,
-	.map_page		= jazz_dma_map_page,
-	.unmap_page		= jazz_dma_unmap_page,
+	.map_phys		= jazz_dma_map_phys,
+	.unmap_phys		= jazz_dma_unmap_phys,
 	.map_sg			= jazz_dma_map_sg,
 	.unmap_sg		= jazz_dma_unmap_sg,
 	.sync_single_for_cpu	= jazz_dma_sync_single_for_cpu,
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index b410021..eafdd63 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -274,12 +274,12 @@ extern void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 				  unsigned long mask, gfp_t flag, int node);
 extern void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 				void *vaddr, dma_addr_t dma_handle);
-extern dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
-				 struct page *page, unsigned long offset,
-				 size_t size, unsigned long mask,
+extern dma_addr_t iommu_map_phys(struct device *dev, struct iommu_table *tbl,
+				 phys_addr_t phys, size_t size,
+				 unsigned long mask,
 				 enum dma_data_direction direction,
 				 unsigned long attrs);
-extern void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
+extern void iommu_unmap_phys(struct iommu_table *tbl, dma_addr_t dma_handle,
 			     size_t size, enum dma_data_direction direction,
 			     unsigned long attrs);
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 0359ab7..aa3689d 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -93,28 +93,26 @@ static void dma_iommu_free_coherent(struct device *dev, size_t size,
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
- * comprises a page address and offset into that page. The dma_addr_t
- * returned will point to the same byte within the page as was passed in.
+ * is a physical address to that page. The dma_addr_t returned will point
+ * to the same byte within the page as was passed in.
  */
-static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
-				     unsigned long offset, size_t size,
+static dma_addr_t dma_iommu_map_phys(struct device *dev, phys_addr_t phys,
+				     size_t size,
 				     enum dma_data_direction direction,
 				     unsigned long attrs)
 {
-	return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
-			      size, dma_get_mask(dev), direction, attrs);
+	return iommu_map_phys(dev, get_iommu_table_base(dev), phys, size,
+			      dma_get_mask(dev), direction, attrs);
 }
 
-
-static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
+static void dma_iommu_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 				 size_t size, enum dma_data_direction direction,
 				 unsigned long attrs)
 {
-	iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
+	iommu_unmap_phys(get_iommu_table_base(dev), dma_handle, size, direction,
 			 attrs);
 }
 
-
 static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 			    int nelems, enum dma_data_direction direction,
 			    unsigned long attrs)
@@ -211,8 +209,8 @@ const struct dma_map_ops dma_iommu_ops = {
 	.map_sg			= dma_iommu_map_sg,
 	.unmap_sg		= dma_iommu_unmap_sg,
 	.dma_supported		= dma_iommu_dma_supported,
-	.map_page		= dma_iommu_map_page,
-	.unmap_page		= dma_iommu_unmap_page,
+	.map_phys		= dma_iommu_map_phys,
+	.unmap_phys		= dma_iommu_unmap_phys,
 	.get_required_mask	= dma_iommu_get_required_mask,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index b7dcf07..0ce7131 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -848,12 +848,12 @@ EXPORT_SYMBOL_GPL(iommu_tce_table_put);
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
- * comprises a page address and offset into that page. The dma_addr_t
- * returned will point to the same byte within the page as was passed in.
+ * is physical address into that page. The dma_addr_t returned will point
+ * to the same byte within the page as was passed in.
  */
-dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
-			  struct page *page, unsigned long offset, size_t size,
-			  unsigned long mask, enum dma_data_direction direction,
+dma_addr_t iommu_map_phys(struct device *dev, struct iommu_table *tbl,
+			  phys_addr_t phys, size_t size, unsigned long mask,
+			  enum dma_data_direction direction,
 			  unsigned long attrs)
 {
 	dma_addr_t dma_handle = DMA_MAPPING_ERROR;
@@ -863,7 +863,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 
 	BUG_ON(direction == DMA_NONE);
 
-	vaddr = page_address(page) + offset;
+	vaddr = phys_to_virt(phys);
 	uaddr = (unsigned long)vaddr;
 
 	if (tbl) {
@@ -890,7 +890,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 	return dma_handle;
 }
 
-void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
+void iommu_unmap_phys(struct iommu_table *tbl, dma_addr_t dma_handle,
 		      size_t size, enum dma_data_direction direction,
 		      unsigned long attrs)
 {
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index afbaabf..f4f3477 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -551,18 +551,20 @@ static void ps3_free_coherent(struct device *_dev, size_t size, void *vaddr,
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
- * comprises a page address and offset into that page. The dma_addr_t
- * returned will point to the same byte within the page as was passed in.
+ * is physical address to that hat page. The dma_addr_t returned will point
+ * to the same byte within the page as was passed in.
  */
 
-static dma_addr_t ps3_sb_map_page(struct device *_dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction,
-	unsigned long attrs)
+static dma_addr_t ps3_sb_map_phys(struct device *_dev, phys_addr_t phys,
+	size_t size, enum dma_data_direction direction, unsigned long attrs)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 	int result;
 	dma_addr_t bus_addr;
-	void *ptr = page_address(page) + offset;
+	void *ptr = phys_to_virt(phys);
+
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
 
 	result = ps3_dma_map(dev->d_region, (unsigned long)ptr, size,
 			     &bus_addr,
@@ -577,8 +579,8 @@ static dma_addr_t ps3_sb_map_page(struct device *_dev, struct page *page,
 	return bus_addr;
 }
 
-static dma_addr_t ps3_ioc0_map_page(struct device *_dev, struct page *page,
-				    unsigned long offset, size_t size,
+static dma_addr_t ps3_ioc0_map_phys(struct device *_dev, phys_addr_t phys,
+				    size_t size,
 				    enum dma_data_direction direction,
 				    unsigned long attrs)
 {
@@ -586,7 +588,10 @@ static dma_addr_t ps3_ioc0_map_page(struct device *_dev, struct page *page,
 	int result;
 	dma_addr_t bus_addr;
 	u64 iopte_flag;
-	void *ptr = page_address(page) + offset;
+	void *ptr = phys_to_virt(phys);
+
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
 
 	iopte_flag = CBE_IOPTE_M;
 	switch (direction) {
@@ -613,7 +618,7 @@ static dma_addr_t ps3_ioc0_map_page(struct device *_dev, struct page *page,
 	return bus_addr;
 }
 
-static void ps3_unmap_page(struct device *_dev, dma_addr_t dma_addr,
+static void ps3_unmap_phys(struct device *_dev, dma_addr_t dma_addr,
 	size_t size, enum dma_data_direction direction, unsigned long attrs)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
@@ -690,8 +695,8 @@ static const struct dma_map_ops ps3_sb_dma_ops = {
 	.map_sg = ps3_sb_map_sg,
 	.unmap_sg = ps3_sb_unmap_sg,
 	.dma_supported = ps3_dma_supported,
-	.map_page = ps3_sb_map_page,
-	.unmap_page = ps3_unmap_page,
+	.map_phys = ps3_sb_map_phys,
+	.unmap_phys = ps3_unmap_phys,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
 	.alloc_pages_op = dma_common_alloc_pages,
@@ -704,8 +709,8 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = {
 	.map_sg = ps3_ioc0_map_sg,
 	.unmap_sg = ps3_ioc0_unmap_sg,
 	.dma_supported = ps3_dma_supported,
-	.map_page = ps3_ioc0_map_page,
-	.unmap_page = ps3_unmap_page,
+	.map_phys = ps3_ioc0_map_phys,
+	.unmap_phys = ps3_unmap_phys,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
 	.alloc_pages_op = dma_common_alloc_pages,
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index 3436b0a..cad2deb 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -86,17 +86,18 @@ static void ibmebus_free_coherent(struct device *dev,
 	kfree(vaddr);
 }
 
-static dma_addr_t ibmebus_map_page(struct device *dev,
-				   struct page *page,
-				   unsigned long offset,
+static dma_addr_t ibmebus_map_phys(struct device *dev, phys_addr_t phys,
 				   size_t size,
 				   enum dma_data_direction direction,
 				   unsigned long attrs)
 {
-	return (dma_addr_t)(page_address(page) + offset);
+	if (attrs & DMA_ATTR_MMIO)
+		return DMA_MAPPING_ERROR;
+
+	return (dma_addr_t)(phys_to_virt(phys));
 }
 
-static void ibmebus_unmap_page(struct device *dev,
+static void ibmebus_unmap_phys(struct device *dev,
 			       dma_addr_t dma_addr,
 			       size_t size,
 			       enum dma_data_direction direction,
@@ -146,8 +147,8 @@ static const struct dma_map_ops ibmebus_dma_ops = {
 	.unmap_sg           = ibmebus_unmap_sg,
 	.dma_supported      = ibmebus_dma_supported,
 	.get_required_mask  = ibmebus_dma_get_required_mask,
-	.map_page           = ibmebus_map_page,
-	.unmap_page         = ibmebus_unmap_page,
+	.map_phys           = ibmebus_map_phys,
+	.unmap_phys         = ibmebus_unmap_phys,
 };
 
 static int ibmebus_match_path(struct device *dev, const void *data)
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index ac1d2d2..18cffac 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -512,18 +512,21 @@ static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
 	vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 }
 
-static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
-                                         unsigned long offset, size_t size,
-                                         enum dma_data_direction direction,
-                                         unsigned long attrs)
+static dma_addr_t vio_dma_iommu_map_phys(struct device *dev, phys_addr_t phys,
+					 size_t size,
+					 enum dma_data_direction direction,
+					 unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 	dma_addr_t ret = DMA_MAPPING_ERROR;
 
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return ret;
+
 	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))))
 		goto out_fail;
-	ret = iommu_map_page(dev, tbl, page, offset, size, dma_get_mask(dev),
+	ret = iommu_map_phys(dev, tbl, phys, size, dma_get_mask(dev),
 			direction, attrs);
 	if (unlikely(ret == DMA_MAPPING_ERROR))
 		goto out_deallocate;
@@ -536,7 +539,7 @@ out_fail:
 	return DMA_MAPPING_ERROR;
 }
 
-static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
+static void vio_dma_iommu_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 				     size_t size,
 				     enum dma_data_direction direction,
 				     unsigned long attrs)
@@ -544,7 +547,7 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
-	iommu_unmap_page(tbl, dma_handle, size, direction, attrs);
+	iommu_unmap_phys(tbl, dma_handle, size, direction, attrs);
 	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
 }
 
@@ -605,8 +608,8 @@ static const struct dma_map_ops vio_dma_mapping_ops = {
 	.free              = vio_dma_iommu_free_coherent,
 	.map_sg            = vio_dma_iommu_map_sg,
 	.unmap_sg          = vio_dma_iommu_unmap_sg,
-	.map_page          = vio_dma_iommu_map_page,
-	.unmap_page        = vio_dma_iommu_unmap_page,
+	.map_phys          = vio_dma_iommu_map_phys,
+	.unmap_phys        = vio_dma_iommu_unmap_phys,
 	.dma_supported     = dma_iommu_dma_supported,
 	.get_required_mask = dma_iommu_get_required_mask,
 	.mmap		   = dma_common_mmap,
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index da03636..46ef88b 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -260,26 +260,35 @@ static void dma_4u_free_coherent(struct device *dev, size_t size,
 		free_pages((unsigned long)cpu, order);
 }
 
-static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page,
-				  unsigned long offset, size_t sz,
-				  enum dma_data_direction direction,
+static dma_addr_t dma_4u_map_phys(struct device *dev, phys_addr_t phys,
+				  size_t sz, enum dma_data_direction direction,
 				  unsigned long attrs)
 {
 	struct iommu *iommu;
 	struct strbuf *strbuf;
 	iopte_t *base;
 	unsigned long flags, npages, oaddr;
-	unsigned long i, base_paddr, ctx;
+	unsigned long i, ctx;
 	u32 bus_addr, ret;
 	unsigned long iopte_protection;
 
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		/*
+		 * This check is included because older versions of the code
+		 * lacked MMIO path support, and my ability to test this path
+		 * is limited. However, from a software technical standpoint,
+		 * there is no restriction, as the following code operates
+		 * solely on physical addresses.
+		 */
+		goto bad_no_ctx;
+
 	iommu = dev->archdata.iommu;
 	strbuf = dev->archdata.stc;
 
 	if (unlikely(direction == DMA_NONE))
 		goto bad_no_ctx;
 
-	oaddr = (unsigned long)(page_address(page) + offset);
+	oaddr = (unsigned long)(phys_to_virt(phys));
 	npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 
@@ -296,7 +305,6 @@ static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page,
 	bus_addr = (iommu->tbl.table_map_base +
 		    ((base - iommu->page_table) << IO_PAGE_SHIFT));
 	ret = bus_addr | (oaddr & ~IO_PAGE_MASK);
-	base_paddr = __pa(oaddr & IO_PAGE_MASK);
 	if (strbuf->strbuf_enabled)
 		iopte_protection = IOPTE_STREAMING(ctx);
 	else
@@ -304,8 +312,8 @@ static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page,
 	if (direction != DMA_TO_DEVICE)
 		iopte_protection |= IOPTE_WRITE;
 
-	for (i = 0; i < npages; i++, base++, base_paddr += IO_PAGE_SIZE)
-		iopte_val(*base) = iopte_protection | base_paddr;
+	for (i = 0; i < npages; i++, base++, phys += IO_PAGE_SIZE)
+		iopte_val(*base) = iopte_protection | phys;
 
 	return ret;
 
@@ -383,7 +391,7 @@ do_flush_sync:
 		       vaddr, ctx, npages);
 }
 
-static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
+static void dma_4u_unmap_phys(struct device *dev, dma_addr_t bus_addr,
 			      size_t sz, enum dma_data_direction direction,
 			      unsigned long attrs)
 {
@@ -753,8 +761,8 @@ static int dma_4u_supported(struct device *dev, u64 device_mask)
 static const struct dma_map_ops sun4u_dma_ops = {
 	.alloc			= dma_4u_alloc_coherent,
 	.free			= dma_4u_free_coherent,
-	.map_page		= dma_4u_map_page,
-	.unmap_page		= dma_4u_unmap_page,
+	.map_phys		= dma_4u_map_phys,
+	.unmap_phys		= dma_4u_unmap_phys,
 	.map_sg			= dma_4u_map_sg,
 	.unmap_sg		= dma_4u_unmap_sg,
 	.sync_single_for_cpu	= dma_4u_sync_single_for_cpu,
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index b720b21..791f0a7 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -352,9 +352,8 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
 		free_pages((unsigned long)cpu, order);
 }
 
-static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
-				  unsigned long offset, size_t sz,
-				  enum dma_data_direction direction,
+static dma_addr_t dma_4v_map_phys(struct device *dev, phys_addr_t phys,
+				  size_t sz, enum dma_data_direction direction,
 				  unsigned long attrs)
 {
 	struct iommu *iommu;
@@ -362,18 +361,27 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 	struct iommu_map_table *tbl;
 	u64 mask;
 	unsigned long flags, npages, oaddr;
-	unsigned long i, base_paddr;
-	unsigned long prot;
+	unsigned long i, prot;
 	dma_addr_t bus_addr, ret;
 	long entry;
 
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		/*
+		 * This check is included because older versions of the code
+		 * lacked MMIO path support, and my ability to test this path
+		 * is limited. However, from a software technical standpoint,
+		 * there is no restriction, as the following code operates
+		 * solely on physical addresses.
+		 */
+		goto bad;
+
 	iommu = dev->archdata.iommu;
 	atu = iommu->atu;
 
 	if (unlikely(direction == DMA_NONE))
 		goto bad;
 
-	oaddr = (unsigned long)(page_address(page) + offset);
+	oaddr = (unsigned long)(phys_to_virt(phys));
 	npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 
@@ -391,7 +399,6 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 
 	bus_addr = (tbl->table_map_base + (entry << IO_PAGE_SHIFT));
 	ret = bus_addr | (oaddr & ~IO_PAGE_MASK);
-	base_paddr = __pa(oaddr & IO_PAGE_MASK);
 	prot = HV_PCI_MAP_ATTR_READ;
 	if (direction != DMA_TO_DEVICE)
 		prot |= HV_PCI_MAP_ATTR_WRITE;
@@ -403,8 +410,8 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 
 	iommu_batch_start(dev, prot, entry);
 
-	for (i = 0; i < npages; i++, base_paddr += IO_PAGE_SIZE) {
-		long err = iommu_batch_add(base_paddr, mask);
+	for (i = 0; i < npages; i++, phys += IO_PAGE_SIZE) {
+		long err = iommu_batch_add(phys, mask);
 		if (unlikely(err < 0L))
 			goto iommu_map_fail;
 	}
@@ -426,7 +433,7 @@ iommu_map_fail:
 	return DMA_MAPPING_ERROR;
 }
 
-static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
+static void dma_4v_unmap_phys(struct device *dev, dma_addr_t bus_addr,
 			      size_t sz, enum dma_data_direction direction,
 			      unsigned long attrs)
 {
@@ -686,8 +693,8 @@ static int dma_4v_supported(struct device *dev, u64 device_mask)
 static const struct dma_map_ops sun4v_dma_ops = {
 	.alloc				= dma_4v_alloc_coherent,
 	.free				= dma_4v_free_coherent,
-	.map_page			= dma_4v_map_page,
-	.unmap_page			= dma_4v_unmap_page,
+	.map_phys			= dma_4v_map_phys,
+	.unmap_phys			= dma_4v_unmap_phys,
 	.map_sg				= dma_4v_map_sg,
 	.unmap_sg			= dma_4v_unmap_sg,
 	.dma_supported			= dma_4v_supported,
diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index d8376f6..d409cb4 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -94,13 +94,14 @@ static int __init iounit_init(void)
 subsys_initcall(iounit_init);
 
 /* One has to hold iounit->lock to call this */
-static unsigned long iounit_get_area(struct iounit_struct *iounit, unsigned long vaddr, int size)
+static dma_addr_t iounit_get_area(struct iounit_struct *iounit,
+				  phys_addr_t phys, int size)
 {
 	int i, j, k, npages;
 	unsigned long rotor, scan, limit;
 	iopte_t iopte;
 
-        npages = ((vaddr & ~PAGE_MASK) + size + (PAGE_SIZE-1)) >> PAGE_SHIFT;
+	npages = (offset_in_page(phys) + size + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 
 	/* A tiny bit of magic ingredience :) */
 	switch (npages) {
@@ -109,7 +110,7 @@ static unsigned long iounit_get_area(struct iounit_struct *iounit, unsigned long
 	default: i = 0x0213; break;
 	}
 	
-	IOD(("iounit_get_area(%08lx,%d[%d])=", vaddr, size, npages));
+	IOD(("%s(%pa,%d[%d])=", __func__, &phys, size, npages));
 	
 next:	j = (i & 15);
 	rotor = iounit->rotor[j - 1];
@@ -124,7 +125,8 @@ nexti:	scan = find_next_zero_bit(iounit->bmap, limit, scan);
 		}
 		i >>= 4;
 		if (!(i & 15))
-			panic("iounit_get_area: Couldn't find free iopte slots for (%08lx,%d)\n", vaddr, size);
+			panic("iounit_get_area: Couldn't find free iopte slots for (%pa,%d)\n",
+			      &phys, size);
 		goto next;
 	}
 	for (k = 1, scan++; k < npages; k++)
@@ -132,30 +134,29 @@ nexti:	scan = find_next_zero_bit(iounit->bmap, limit, scan);
 			goto nexti;
 	iounit->rotor[j - 1] = (scan < limit) ? scan : iounit->limit[j - 1];
 	scan -= npages;
-	iopte = MKIOPTE(__pa(vaddr & PAGE_MASK));
-	vaddr = IOUNIT_DMA_BASE + (scan << PAGE_SHIFT) + (vaddr & ~PAGE_MASK);
+	iopte = MKIOPTE(phys & PAGE_MASK);
+	phys = IOUNIT_DMA_BASE + (scan << PAGE_SHIFT) + offset_in_page(phys);
 	for (k = 0; k < npages; k++, iopte = __iopte(iopte_val(iopte) + 0x100), scan++) {
 		set_bit(scan, iounit->bmap);
 		sbus_writel(iopte_val(iopte), &iounit->page_table[scan]);
 	}
-	IOD(("%08lx\n", vaddr));
-	return vaddr;
+	IOD(("%pa\n", &phys));
+	return phys;
 }
 
-static dma_addr_t iounit_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t len, enum dma_data_direction dir,
-		unsigned long attrs)
+static dma_addr_t iounit_map_phys(struct device *dev, phys_addr_t phys,
+		size_t len, enum dma_data_direction dir, unsigned long attrs)
 {
-	void *vaddr = page_address(page) + offset;
 	struct iounit_struct *iounit = dev->archdata.iommu;
-	unsigned long ret, flags;
+	unsigned long flags;
+	dma_addr_t ret;
 	
 	/* XXX So what is maxphys for us and how do drivers know it? */
 	if (!len || len > 256 * 1024)
 		return DMA_MAPPING_ERROR;
 
 	spin_lock_irqsave(&iounit->lock, flags);
-	ret = iounit_get_area(iounit, (unsigned long)vaddr, len);
+	ret = iounit_get_area(iounit, phys, len);
 	spin_unlock_irqrestore(&iounit->lock, flags);
 	return ret;
 }
@@ -171,14 +172,15 @@ static int iounit_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 	/* FIXME: Cache some resolved pages - often several sg entries are to the same page */
 	spin_lock_irqsave(&iounit->lock, flags);
 	for_each_sg(sgl, sg, nents, i) {
-		sg->dma_address = iounit_get_area(iounit, (unsigned long) sg_virt(sg), sg->length);
+		sg->dma_address =
+			iounit_get_area(iounit, sg_phys(sg), sg->length);
 		sg->dma_length = sg->length;
 	}
 	spin_unlock_irqrestore(&iounit->lock, flags);
 	return nents;
 }
 
-static void iounit_unmap_page(struct device *dev, dma_addr_t vaddr, size_t len,
+static void iounit_unmap_phys(struct device *dev, dma_addr_t vaddr, size_t len,
 		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
@@ -279,8 +281,8 @@ static const struct dma_map_ops iounit_dma_ops = {
 	.alloc			= iounit_alloc,
 	.free			= iounit_free,
 #endif
-	.map_page		= iounit_map_page,
-	.unmap_page		= iounit_unmap_page,
+	.map_phys		= iounit_map_phys,
+	.unmap_phys		= iounit_unmap_phys,
 	.map_sg			= iounit_map_sg,
 	.unmap_sg		= iounit_unmap_sg,
 };
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 5a5080d..f48adf6 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -181,18 +181,20 @@ static void iommu_flush_iotlb(iopte_t *iopte, unsigned int niopte)
 	}
 }
 
-static dma_addr_t __sbus_iommu_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t len, bool per_page_flush)
+static dma_addr_t __sbus_iommu_map_phys(struct device *dev, phys_addr_t paddr,
+		size_t len, bool per_page_flush, unsigned long attrs)
 {
 	struct iommu_struct *iommu = dev->archdata.iommu;
-	phys_addr_t paddr = page_to_phys(page) + offset;
-	unsigned long off = paddr & ~PAGE_MASK;
+	unsigned long off = offset_in_page(paddr);
 	unsigned long npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	unsigned long pfn = __phys_to_pfn(paddr);
 	unsigned int busa, busa0;
 	iopte_t *iopte, *iopte0;
 	int ioptex, i;
 
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
+
 	/* XXX So what is maxphys for us and how do drivers know it? */
 	if (!len || len > 256 * 1024)
 		return DMA_MAPPING_ERROR;
@@ -202,10 +204,10 @@ static dma_addr_t __sbus_iommu_map_page(struct device *dev, struct page *page,
 	 * XXX Is this a good assumption?
 	 * XXX What if someone else unmaps it here and races us?
 	 */
-	if (per_page_flush && !PageHighMem(page)) {
+	if (per_page_flush && !PhysHighMem(paddr)) {
 		unsigned long vaddr, p;
 
-		vaddr = (unsigned long)page_address(page) + offset;
+		vaddr = (unsigned long)phys_to_virt(paddr);
 		for (p = vaddr & PAGE_MASK; p < vaddr + len; p += PAGE_SIZE)
 			flush_page_for_dma(p);
 	}
@@ -231,19 +233,19 @@ static dma_addr_t __sbus_iommu_map_page(struct device *dev, struct page *page,
 	return busa0 + off;
 }
 
-static dma_addr_t sbus_iommu_map_page_gflush(struct device *dev,
-		struct page *page, unsigned long offset, size_t len,
-		enum dma_data_direction dir, unsigned long attrs)
+static dma_addr_t sbus_iommu_map_phys_gflush(struct device *dev,
+		phys_addr_t phys, size_t len, enum dma_data_direction dir,
+		unsigned long attrs)
 {
 	flush_page_for_dma(0);
-	return __sbus_iommu_map_page(dev, page, offset, len, false);
+	return __sbus_iommu_map_phys(dev, phys, len, false, attrs);
 }
 
-static dma_addr_t sbus_iommu_map_page_pflush(struct device *dev,
-		struct page *page, unsigned long offset, size_t len,
-		enum dma_data_direction dir, unsigned long attrs)
+static dma_addr_t sbus_iommu_map_phys_pflush(struct device *dev,
+		phys_addr_t phys, size_t len, enum dma_data_direction dir,
+		unsigned long attrs)
 {
-	return __sbus_iommu_map_page(dev, page, offset, len, true);
+	return __sbus_iommu_map_phys(dev, phys, len, true, attrs);
 }
 
 static int __sbus_iommu_map_sg(struct device *dev, struct scatterlist *sgl,
@@ -254,8 +256,8 @@ static int __sbus_iommu_map_sg(struct device *dev, struct scatterlist *sgl,
 	int j;
 
 	for_each_sg(sgl, sg, nents, j) {
-		sg->dma_address =__sbus_iommu_map_page(dev, sg_page(sg),
-				sg->offset, sg->length, per_page_flush);
+		sg->dma_address = __sbus_iommu_map_phys(dev, sg_phys(sg),
+				sg->length, per_page_flush, attrs);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
 			return -EIO;
 		sg->dma_length = sg->length;
@@ -277,7 +279,7 @@ static int sbus_iommu_map_sg_pflush(struct device *dev, struct scatterlist *sgl,
 	return __sbus_iommu_map_sg(dev, sgl, nents, dir, attrs, true);
 }
 
-static void sbus_iommu_unmap_page(struct device *dev, dma_addr_t dma_addr,
+static void sbus_iommu_unmap_phys(struct device *dev, dma_addr_t dma_addr,
 		size_t len, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iommu_struct *iommu = dev->archdata.iommu;
@@ -303,7 +305,7 @@ static void sbus_iommu_unmap_sg(struct device *dev, struct scatterlist *sgl,
 	int i;
 
 	for_each_sg(sgl, sg, nents, i) {
-		sbus_iommu_unmap_page(dev, sg->dma_address, sg->length, dir,
+		sbus_iommu_unmap_phys(dev, sg->dma_address, sg->length, dir,
 				attrs);
 		sg->dma_address = 0x21212121;
 	}
@@ -426,8 +428,8 @@ static const struct dma_map_ops sbus_iommu_dma_gflush_ops = {
 	.alloc			= sbus_iommu_alloc,
 	.free			= sbus_iommu_free,
 #endif
-	.map_page		= sbus_iommu_map_page_gflush,
-	.unmap_page		= sbus_iommu_unmap_page,
+	.map_phys		= sbus_iommu_map_phys_gflush,
+	.unmap_phys		= sbus_iommu_unmap_phys,
 	.map_sg			= sbus_iommu_map_sg_gflush,
 	.unmap_sg		= sbus_iommu_unmap_sg,
 };
@@ -437,8 +439,8 @@ static const struct dma_map_ops sbus_iommu_dma_pflush_ops = {
 	.alloc			= sbus_iommu_alloc,
 	.free			= sbus_iommu_free,
 #endif
-	.map_page		= sbus_iommu_map_page_pflush,
-	.unmap_page		= sbus_iommu_unmap_page,
+	.map_phys		= sbus_iommu_map_phys_pflush,
+	.unmap_phys		= sbus_iommu_unmap_phys,
 	.map_sg			= sbus_iommu_map_sg_pflush,
 	.unmap_sg		= sbus_iommu_unmap_sg,
 };
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index e6e68a3..e8000a5 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -222,13 +222,14 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 }
 
 /* Map a single area into the IOMMU */
-static dma_addr_t gart_map_page(struct device *dev, struct page *page,
-				unsigned long offset, size_t size,
-				enum dma_data_direction dir,
+static dma_addr_t gart_map_phys(struct device *dev, phys_addr_t paddr,
+				size_t size, enum dma_data_direction dir,
 				unsigned long attrs)
 {
 	unsigned long bus;
-	phys_addr_t paddr = page_to_phys(page) + offset;
+
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
 
 	if (!need_iommu(dev, paddr, size))
 		return paddr;
@@ -242,7 +243,7 @@ static dma_addr_t gart_map_page(struct device *dev, struct page *page,
 /*
  * Free a DMA mapping.
  */
-static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr,
+static void gart_unmap_phys(struct device *dev, dma_addr_t dma_addr,
 			    size_t size, enum dma_data_direction dir,
 			    unsigned long attrs)
 {
@@ -282,7 +283,7 @@ static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 	for_each_sg(sg, s, nents, i) {
 		if (!s->dma_length || !s->length)
 			break;
-		gart_unmap_page(dev, s->dma_address, s->dma_length, dir, 0);
+		gart_unmap_phys(dev, s->dma_address, s->dma_length, dir, 0);
 	}
 }
 
@@ -487,7 +488,7 @@ static void
 gart_free_coherent(struct device *dev, size_t size, void *vaddr,
 		   dma_addr_t dma_addr, unsigned long attrs)
 {
-	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
+	gart_unmap_phys(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
 	dma_direct_free(dev, size, vaddr, dma_addr, attrs);
 }
 
@@ -672,8 +673,8 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
 static const struct dma_map_ops gart_dma_ops = {
 	.map_sg				= gart_map_sg,
 	.unmap_sg			= gart_unmap_sg,
-	.map_page			= gart_map_page,
-	.unmap_page			= gart_unmap_page,
+	.map_phys			= gart_map_phys,
+	.unmap_phys			= gart_unmap_phys,
 	.alloc				= gart_alloc_coherent,
 	.free				= gart_free_coherent,
 	.mmap				= dma_common_mmap,
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index feef537..4e70717 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -517,10 +517,10 @@ static u32 hint_lookup[] = {
  * ccio_io_pdir_entry - Initialize an I/O Pdir.
  * @pdir_ptr: A pointer into I/O Pdir.
  * @sid: The Space Identifier.
- * @vba: The virtual address.
+ * @pba: The physical address.
  * @hints: The DMA Hint.
  *
- * Given a virtual address (vba, arg2) and space id, (sid, arg1),
+ * Given a physical address (pba, arg2) and space id, (sid, arg1),
  * load the I/O PDIR entry pointed to by pdir_ptr (arg0). Each IO Pdir
  * entry consists of 8 bytes as shown below (MSB == bit 0):
  *
@@ -543,7 +543,7 @@ static u32 hint_lookup[] = {
  * index are bits 12:19 of the value returned by LCI.
  */ 
 static void
-ccio_io_pdir_entry(__le64 *pdir_ptr, space_t sid, unsigned long vba,
+ccio_io_pdir_entry(__le64 *pdir_ptr, space_t sid, phys_addr_t pba,
 		   unsigned long hints)
 {
 	register unsigned long pa;
@@ -557,7 +557,7 @@ ccio_io_pdir_entry(__le64 *pdir_ptr, space_t sid, unsigned long vba,
 	** "hints" parm includes the VALID bit!
 	** "dep" clobbers the physical address offset bits as well.
 	*/
-	pa = lpa(vba);
+	pa = pba;
 	asm volatile("depw  %1,31,12,%0" : "+r" (pa) : "r" (hints));
 	((u32 *)pdir_ptr)[1] = (u32) pa;
 
@@ -582,7 +582,7 @@ ccio_io_pdir_entry(__le64 *pdir_ptr, space_t sid, unsigned long vba,
 	** Grab virtual index [0:11]
 	** Deposit virt_idx bits into I/O PDIR word
 	*/
-	asm volatile ("lci %%r0(%1), %0" : "=r" (ci) : "r" (vba));
+	asm volatile ("lci %%r0(%1), %0" : "=r" (ci) : "r" (phys_to_virt(pba)));
 	asm volatile ("extru %1,19,12,%0" : "+r" (ci) : "r" (ci));
 	asm volatile ("depw  %1,15,12,%0" : "+r" (pa) : "r" (ci));
 
@@ -704,14 +704,14 @@ ccio_dma_supported(struct device *dev, u64 mask)
 /**
  * ccio_map_single - Map an address range into the IOMMU.
  * @dev: The PCI device.
- * @addr: The start address of the DMA region.
+ * @addr: The physical address of the DMA region.
  * @size: The length of the DMA region.
  * @direction: The direction of the DMA transaction (to/from device).
  *
  * This function implements the pci_map_single function.
  */
 static dma_addr_t 
-ccio_map_single(struct device *dev, void *addr, size_t size,
+ccio_map_single(struct device *dev, phys_addr_t addr, size_t size,
 		enum dma_data_direction direction)
 {
 	int idx;
@@ -730,7 +730,7 @@ ccio_map_single(struct device *dev, void *addr, size_t size,
 	BUG_ON(size <= 0);
 
 	/* save offset bits */
-	offset = ((unsigned long) addr) & ~IOVP_MASK;
+	offset = offset_in_page(addr);
 
 	/* round up to nearest IOVP_SIZE */
 	size = ALIGN(size + offset, IOVP_SIZE);
@@ -746,15 +746,15 @@ ccio_map_single(struct device *dev, void *addr, size_t size,
 
 	pdir_start = &(ioc->pdir_base[idx]);
 
-	DBG_RUN("%s() %px -> %#lx size: %zu\n",
-		__func__, addr, (long)(iovp | offset), size);
+	DBG_RUN("%s() %pa -> %#lx size: %zu\n",
+		__func__, &addr, (long)(iovp | offset), size);
 
 	/* If not cacheline aligned, force SAFE_DMA on the whole mess */
-	if((size % L1_CACHE_BYTES) || ((unsigned long)addr % L1_CACHE_BYTES))
+	if ((size % L1_CACHE_BYTES) || (addr % L1_CACHE_BYTES))
 		hint |= HINT_SAFE_DMA;
 
 	while(size > 0) {
-		ccio_io_pdir_entry(pdir_start, KERNEL_SPACE, (unsigned long)addr, hint);
+		ccio_io_pdir_entry(pdir_start, KERNEL_SPACE, addr, hint);
 
 		DBG_RUN(" pdir %p %08x%08x\n",
 			pdir_start,
@@ -773,17 +773,18 @@ ccio_map_single(struct device *dev, void *addr, size_t size,
 
 
 static dma_addr_t
-ccio_map_page(struct device *dev, struct page *page, unsigned long offset,
-		size_t size, enum dma_data_direction direction,
-		unsigned long attrs)
+ccio_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+	      enum dma_data_direction direction, unsigned long attrs)
 {
-	return ccio_map_single(dev, page_address(page) + offset, size,
-			direction);
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
+
+	return ccio_map_single(dev, phys, size, direction);
 }
 
 
 /**
- * ccio_unmap_page - Unmap an address range from the IOMMU.
+ * ccio_unmap_phys - Unmap an address range from the IOMMU.
  * @dev: The PCI device.
  * @iova: The start address of the DMA region.
  * @size: The length of the DMA region.
@@ -791,7 +792,7 @@ ccio_map_page(struct device *dev, struct page *page, unsigned long offset,
  * @attrs: attributes
  */
 static void 
-ccio_unmap_page(struct device *dev, dma_addr_t iova, size_t size,
+ccio_unmap_phys(struct device *dev, dma_addr_t iova, size_t size,
 		enum dma_data_direction direction, unsigned long attrs)
 {
 	struct ioc *ioc;
@@ -853,7 +854,8 @@ ccio_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag,
 
 	if (ret) {
 		memset(ret, 0, size);
-		*dma_handle = ccio_map_single(dev, ret, size, DMA_BIDIRECTIONAL);
+		*dma_handle = ccio_map_single(dev, virt_to_phys(ret), size,
+					      DMA_BIDIRECTIONAL);
 	}
 
 	return ret;
@@ -873,7 +875,7 @@ static void
 ccio_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
-	ccio_unmap_page(dev, dma_handle, size, 0, 0);
+	ccio_unmap_phys(dev, dma_handle, size, 0, 0);
 	free_pages((unsigned long)cpu_addr, get_order(size));
 }
 
@@ -920,7 +922,7 @@ ccio_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	/* Fast path single entry scatterlists. */
 	if (nents == 1) {
 		sg_dma_address(sglist) = ccio_map_single(dev,
-				sg_virt(sglist), sglist->length,
+				sg_phys(sglist), sglist->length,
 				direction);
 		sg_dma_len(sglist) = sglist->length;
 		return 1;
@@ -1004,7 +1006,7 @@ ccio_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents,
 #ifdef CCIO_COLLECT_STATS
 		ioc->usg_pages += sg_dma_len(sglist) >> PAGE_SHIFT;
 #endif
-		ccio_unmap_page(dev, sg_dma_address(sglist),
+		ccio_unmap_phys(dev, sg_dma_address(sglist),
 				  sg_dma_len(sglist), direction, 0);
 		++sglist;
 		nents--;
@@ -1017,8 +1019,8 @@ static const struct dma_map_ops ccio_ops = {
 	.dma_supported =	ccio_dma_supported,
 	.alloc =		ccio_alloc,
 	.free =			ccio_free,
-	.map_page =		ccio_map_page,
-	.unmap_page =		ccio_unmap_page,
+	.map_phys =		ccio_map_phys,
+	.unmap_phys =		ccio_unmap_phys,
 	.map_sg =		ccio_map_sg,
 	.unmap_sg =		ccio_unmap_sg,
 	.get_sgtable =		dma_common_get_sgtable,
@@ -1072,7 +1074,7 @@ static int ccio_proc_info(struct seq_file *m, void *p)
 			   ioc->msingle_calls, ioc->msingle_pages,
 			   (int)((ioc->msingle_pages * 1000)/ioc->msingle_calls));
 
-		/* KLUGE - unmap_sg calls unmap_page for each mapped page */
+		/* KLUGE - unmap_sg calls unmap_phys for each mapped page */
 		min = ioc->usingle_calls - ioc->usg_calls;
 		max = ioc->usingle_pages - ioc->usg_pages;
 		seq_printf(m, "pci_unmap_single: %8ld calls  %8ld pages (avg %d/1000)\n",
diff --git a/drivers/parisc/iommu-helpers.h b/drivers/parisc/iommu-helpers.h
index c43f1a2..0691884 100644
--- a/drivers/parisc/iommu-helpers.h
+++ b/drivers/parisc/iommu-helpers.h
@@ -14,7 +14,7 @@
 static inline unsigned int
 iommu_fill_pdir(struct ioc *ioc, struct scatterlist *startsg, int nents, 
 		unsigned long hint,
-		void (*iommu_io_pdir_entry)(__le64 *, space_t, unsigned long,
+		void (*iommu_io_pdir_entry)(__le64 *, space_t, phys_addr_t,
 					    unsigned long))
 {
 	struct scatterlist *dma_sg = startsg;	/* pointer to current DMA */
@@ -28,7 +28,7 @@ iommu_fill_pdir(struct ioc *ioc, struct scatterlist *startsg, int nents,
 	 dma_sg--;
 
 	while (nents-- > 0) {
-		unsigned long vaddr;
+		phys_addr_t paddr;
 		long size;
 
 		DBG_RUN_SG(" %d : %08lx %p/%05x\n", nents,
@@ -67,7 +67,7 @@ iommu_fill_pdir(struct ioc *ioc, struct scatterlist *startsg, int nents,
 		
 		BUG_ON(pdirp == NULL);
 		
-		vaddr = (unsigned long)sg_virt(startsg);
+		paddr = sg_phys(startsg);
 		sg_dma_len(dma_sg) += startsg->length;
 		size = startsg->length + dma_offset;
 		dma_offset = 0;
@@ -76,8 +76,8 @@ iommu_fill_pdir(struct ioc *ioc, struct scatterlist *startsg, int nents,
 #endif
 		do {
 			iommu_io_pdir_entry(pdirp, KERNEL_SPACE, 
-					    vaddr, hint);
-			vaddr += IOVP_SIZE;
+					    paddr, hint);
+			paddr += IOVP_SIZE;
 			size -= IOVP_SIZE;
 			pdirp++;
 		} while(unlikely(size > 0));
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index fc3863c..a6eb6bf 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -532,7 +532,7 @@ typedef unsigned long space_t;
  * sba_io_pdir_entry - fill in one IO PDIR entry
  * @pdir_ptr:  pointer to IO PDIR entry
  * @sid: process Space ID - currently only support KERNEL_SPACE
- * @vba: Virtual CPU address of buffer to map
+ * @pba: Physical address of buffer to map
  * @hint: DMA hint set to use for this mapping
  *
  * SBA Mapping Routine
@@ -569,20 +569,17 @@ typedef unsigned long space_t;
  */
 
 static void
-sba_io_pdir_entry(__le64 *pdir_ptr, space_t sid, unsigned long vba,
+sba_io_pdir_entry(__le64 *pdir_ptr, space_t sid, phys_addr_t pba,
 		  unsigned long hint)
 {
-	u64 pa; /* physical address */
 	register unsigned ci; /* coherent index */
 
-	pa = lpa(vba);
-	pa &= IOVP_MASK;
+	asm("lci 0(%1), %0" : "=r" (ci) : "r" (phys_to_virt(pba)));
+	pba &= IOVP_MASK;
+	pba |= (ci >> PAGE_SHIFT) & 0xff;  /* move CI (8 bits) into lowest byte */
 
-	asm("lci 0(%1), %0" : "=r" (ci) : "r" (vba));
-	pa |= (ci >> PAGE_SHIFT) & 0xff;  /* move CI (8 bits) into lowest byte */
-
-	pa |= SBA_PDIR_VALID_BIT;	/* set "valid" bit */
-	*pdir_ptr = cpu_to_le64(pa);	/* swap and store into I/O Pdir */
+	pba |= SBA_PDIR_VALID_BIT;	/* set "valid" bit */
+	*pdir_ptr = cpu_to_le64(pba);	/* swap and store into I/O Pdir */
 
 	/*
 	 * If the PDC_MODEL capabilities has Non-coherent IO-PDIR bit set
@@ -707,7 +704,7 @@ static int sba_dma_supported( struct device *dev, u64 mask)
  * See Documentation/core-api/dma-api-howto.rst
  */
 static dma_addr_t
-sba_map_single(struct device *dev, void *addr, size_t size,
+sba_map_single(struct device *dev, phys_addr_t addr, size_t size,
 	       enum dma_data_direction direction)
 {
 	struct ioc *ioc;
@@ -722,7 +719,7 @@ sba_map_single(struct device *dev, void *addr, size_t size,
 		return DMA_MAPPING_ERROR;
 
 	/* save offset bits */
-	offset = ((dma_addr_t) (long) addr) & ~IOVP_MASK;
+	offset = offset_in_page(addr);
 
 	/* round up to nearest IOVP_SIZE */
 	size = (size + offset + ~IOVP_MASK) & IOVP_MASK;
@@ -739,13 +736,13 @@ sba_map_single(struct device *dev, void *addr, size_t size,
 	pide = sba_alloc_range(ioc, dev, size);
 	iovp = (dma_addr_t) pide << IOVP_SHIFT;
 
-	DBG_RUN("%s() 0x%p -> 0x%lx\n",
-		__func__, addr, (long) iovp | offset);
+	DBG_RUN("%s() 0x%pa -> 0x%lx\n",
+		__func__, &addr, (long) iovp | offset);
 
 	pdir_start = &(ioc->pdir_base[pide]);
 
 	while (size > 0) {
-		sba_io_pdir_entry(pdir_start, KERNEL_SPACE, (unsigned long) addr, 0);
+		sba_io_pdir_entry(pdir_start, KERNEL_SPACE, addr, 0);
 
 		DBG_RUN("	pdir 0x%p %02x%02x%02x%02x%02x%02x%02x%02x\n",
 			pdir_start,
@@ -778,17 +775,18 @@ sba_map_single(struct device *dev, void *addr, size_t size,
 
 
 static dma_addr_t
-sba_map_page(struct device *dev, struct page *page, unsigned long offset,
-		size_t size, enum dma_data_direction direction,
-		unsigned long attrs)
+sba_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction direction, unsigned long attrs)
 {
-	return sba_map_single(dev, page_address(page) + offset, size,
-			direction);
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
+
+	return sba_map_single(dev, phys, size, direction);
 }
 
 
 /**
- * sba_unmap_page - unmap one IOVA and free resources
+ * sba_unmap_phys - unmap one IOVA and free resources
  * @dev: instance of PCI owned by the driver that's asking.
  * @iova:  IOVA of driver buffer previously mapped.
  * @size:  number of bytes mapped in driver buffer.
@@ -798,7 +796,7 @@ sba_map_page(struct device *dev, struct page *page, unsigned long offset,
  * See Documentation/core-api/dma-api-howto.rst
  */
 static void
-sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size,
+sba_unmap_phys(struct device *dev, dma_addr_t iova, size_t size,
 		enum dma_data_direction direction, unsigned long attrs)
 {
 	struct ioc *ioc;
@@ -893,7 +891,7 @@ static void *sba_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle
 
 	if (ret) {
 		memset(ret, 0, size);
-		*dma_handle = sba_map_single(hwdev, ret, size, 0);
+		*dma_handle = sba_map_single(hwdev, virt_to_phys(ret), size, 0);
 	}
 
 	return ret;
@@ -914,7 +912,7 @@ static void
 sba_free(struct device *hwdev, size_t size, void *vaddr,
 		    dma_addr_t dma_handle, unsigned long attrs)
 {
-	sba_unmap_page(hwdev, dma_handle, size, 0, 0);
+	sba_unmap_phys(hwdev, dma_handle, size, 0, 0);
 	free_pages((unsigned long) vaddr, get_order(size));
 }
 
@@ -962,7 +960,7 @@ sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 
 	/* Fast path single entry scatterlists. */
 	if (nents == 1) {
-		sg_dma_address(sglist) = sba_map_single(dev, sg_virt(sglist),
+		sg_dma_address(sglist) = sba_map_single(dev, sg_phys(sglist),
 						sglist->length, direction);
 		sg_dma_len(sglist)     = sglist->length;
 		return 1;
@@ -1061,7 +1059,7 @@ sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents,
 
 	while (nents && sg_dma_len(sglist)) {
 
-		sba_unmap_page(dev, sg_dma_address(sglist), sg_dma_len(sglist),
+		sba_unmap_phys(dev, sg_dma_address(sglist), sg_dma_len(sglist),
 				direction, 0);
 #ifdef SBA_COLLECT_STATS
 		ioc->usg_pages += ((sg_dma_address(sglist) & ~IOVP_MASK) + sg_dma_len(sglist) + IOVP_SIZE - 1) >> PAGE_SHIFT;
@@ -1085,8 +1083,8 @@ static const struct dma_map_ops sba_ops = {
 	.dma_supported =	sba_dma_supported,
 	.alloc =		sba_alloc,
 	.free =			sba_free,
-	.map_page =		sba_map_page,
-	.unmap_page =		sba_unmap_page,
+	.map_phys =		sba_map_phys,
+	.unmap_phys =		sba_unmap_phys,
 	.map_sg =		sba_map_sg,
 	.unmap_sg =		sba_unmap_sg,
 	.get_sgtable =		dma_common_get_sgtable,
diff --git a/drivers/xen/grant-dma-ops.c b/drivers/xen/grant-dma-ops.c
index 29257d2..14077d2 100644
--- a/drivers/xen/grant-dma-ops.c
+++ b/drivers/xen/grant-dma-ops.c
@@ -163,18 +163,22 @@ static void xen_grant_dma_free_pages(struct device *dev, size_t size,
 	xen_grant_dma_free(dev, size, page_to_virt(vaddr), dma_handle, 0);
 }
 
-static dma_addr_t xen_grant_dma_map_page(struct device *dev, struct page *page,
-					 unsigned long offset, size_t size,
+static dma_addr_t xen_grant_dma_map_phys(struct device *dev, phys_addr_t phys,
+					 size_t size,
 					 enum dma_data_direction dir,
 					 unsigned long attrs)
 {
 	struct xen_grant_dma_data *data;
+	unsigned long offset = offset_in_page(phys);
 	unsigned long dma_offset = xen_offset_in_page(offset),
 			pfn_offset = XEN_PFN_DOWN(offset);
 	unsigned int i, n_pages = XEN_PFN_UP(dma_offset + size);
 	grant_ref_t grant;
 	dma_addr_t dma_handle;
 
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
+
 	if (WARN_ON(dir == DMA_NONE))
 		return DMA_MAPPING_ERROR;
 
@@ -190,7 +194,7 @@ static dma_addr_t xen_grant_dma_map_page(struct device *dev, struct page *page,
 
 	for (i = 0; i < n_pages; i++) {
 		gnttab_grant_foreign_access_ref(grant + i, data->backend_domid,
-				pfn_to_gfn(page_to_xen_pfn(page) + i + pfn_offset),
+				pfn_to_gfn(page_to_xen_pfn(phys_to_page(phys)) + i + pfn_offset),
 				dir == DMA_TO_DEVICE);
 	}
 
@@ -199,7 +203,7 @@ static dma_addr_t xen_grant_dma_map_page(struct device *dev, struct page *page,
 	return dma_handle;
 }
 
-static void xen_grant_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+static void xen_grant_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 				     size_t size, enum dma_data_direction dir,
 				     unsigned long attrs)
 {
@@ -242,7 +246,7 @@ static void xen_grant_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 		return;
 
 	for_each_sg(sg, s, nents, i)
-		xen_grant_dma_unmap_page(dev, s->dma_address, sg_dma_len(s), dir,
+		xen_grant_dma_unmap_phys(dev, s->dma_address, sg_dma_len(s), dir,
 				attrs);
 }
 
@@ -257,7 +261,7 @@ static int xen_grant_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		return -EINVAL;
 
 	for_each_sg(sg, s, nents, i) {
-		s->dma_address = xen_grant_dma_map_page(dev, sg_page(s), s->offset,
+		s->dma_address = xen_grant_dma_map_phys(dev, sg_phys(s),
 				s->length, dir, attrs);
 		if (s->dma_address == DMA_MAPPING_ERROR)
 			goto out;
@@ -286,8 +290,8 @@ static const struct dma_map_ops xen_grant_dma_ops = {
 	.free_pages = xen_grant_dma_free_pages,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
-	.map_page = xen_grant_dma_map_page,
-	.unmap_page = xen_grant_dma_unmap_page,
+	.map_phys = xen_grant_dma_map_phys,
+	.unmap_phys = xen_grant_dma_unmap_phys,
 	.map_sg = xen_grant_dma_map_sg,
 	.unmap_sg = xen_grant_dma_unmap_sg,
 	.dma_supported = xen_grant_dma_supported,
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index dd7747a..ccf2502 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -200,17 +200,32 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr,
  * physical address to use is returned.
  *
  * Once the device is given the dma address, the device owns this memory until
- * either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed.
+ * either xen_swiotlb_unmap_phys or xen_swiotlb_dma_sync_single is performed.
  */
-static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
-				unsigned long offset, size_t size,
-				enum dma_data_direction dir,
+static dma_addr_t xen_swiotlb_map_phys(struct device *dev, phys_addr_t phys,
+				size_t size, enum dma_data_direction dir,
 				unsigned long attrs)
 {
-	phys_addr_t map, phys = page_to_phys(page) + offset;
-	dma_addr_t dev_addr = xen_phys_to_dma(dev, phys);
+	dma_addr_t dev_addr;
+	phys_addr_t map;
 
 	BUG_ON(dir == DMA_NONE);
+
+	if (attrs & DMA_ATTR_MMIO) {
+		if (unlikely(!dma_capable(dev, phys, size, false))) {
+			dev_err_once(
+				dev,
+				"DMA addr %pa+%zu overflow (mask %llx, bus limit %llx).\n",
+				&phys, size, *dev->dma_mask,
+				dev->bus_dma_limit);
+			WARN_ON_ONCE(1);
+			return DMA_MAPPING_ERROR;
+		}
+		return phys;
+	}
+
+	dev_addr = xen_phys_to_dma(dev, phys);
+
 	/*
 	 * If the address happens to be in the device's DMA window,
 	 * we can safely return the device addr and not worry about bounce
@@ -257,13 +272,13 @@ done:
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
- * match what was provided for in a previous xen_swiotlb_map_page call.  All
+ * match what was provided for in a previous xen_swiotlb_map_phys call.  All
  * other usages are undefined.
  *
  * After this call, reads by the cpu to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
-static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+static void xen_swiotlb_unmap_phys(struct device *hwdev, dma_addr_t dev_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	phys_addr_t paddr = xen_dma_to_phys(hwdev, dev_addr);
@@ -325,7 +340,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
 
 /*
  * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_page() above.
+ * concerning calls here are the same as for swiotlb_unmap_phys() above.
  */
 static void
 xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
@@ -337,7 +352,7 @@ xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i)
-		xen_swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg),
+		xen_swiotlb_unmap_phys(hwdev, sg->dma_address, sg_dma_len(sg),
 				dir, attrs);
 
 }
@@ -352,8 +367,8 @@ xen_swiotlb_map_sg(struct device *dev, struct scatterlist *sgl, int nelems,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i) {
-		sg->dma_address = xen_swiotlb_map_page(dev, sg_page(sg),
-				sg->offset, sg->length, dir, attrs);
+		sg->dma_address = xen_swiotlb_map_phys(dev, sg_phys(sg),
+				sg->length, dir, attrs);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
 			goto out_unmap;
 		sg_dma_len(sg) = sg->length;
@@ -392,25 +407,6 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
 	}
 }
 
-static dma_addr_t xen_swiotlb_direct_map_resource(struct device *dev,
-						  phys_addr_t paddr,
-						  size_t size,
-						  enum dma_data_direction dir,
-						  unsigned long attrs)
-{
-	dma_addr_t dma_addr = paddr;
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
-		dev_err_once(dev,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		WARN_ON_ONCE(1);
-		return DMA_MAPPING_ERROR;
-	}
-
-	return dma_addr;
-}
-
 /*
  * Return whether the given device DMA address mask can be supported
  * properly.  For example, if your device can only drive the low 24-bits
@@ -437,13 +433,12 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
 	.map_sg = xen_swiotlb_map_sg,
 	.unmap_sg = xen_swiotlb_unmap_sg,
-	.map_page = xen_swiotlb_map_page,
-	.unmap_page = xen_swiotlb_unmap_page,
+	.map_phys = xen_swiotlb_map_phys,
+	.unmap_phys = xen_swiotlb_unmap_phys,
 	.dma_supported = xen_swiotlb_dma_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
 	.alloc_pages_op = dma_common_alloc_pages,
 	.free_pages = dma_common_free_pages,
 	.max_mapping_size = swiotlb_max_mapping_size,
-	.map_resource = xen_swiotlb_direct_map_resource,
 };
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 10882d0..4809204 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -31,10 +31,10 @@ struct dma_map_ops {
 			void *cpu_addr, dma_addr_t dma_addr, size_t size,
 			unsigned long attrs);
 
-	dma_addr_t (*map_page)(struct device *dev, struct page *page,
-			unsigned long offset, size_t size,
-			enum dma_data_direction dir, unsigned long attrs);
-	void (*unmap_page)(struct device *dev, dma_addr_t dma_handle,
+	dma_addr_t (*map_phys)(struct device *dev, phys_addr_t phys,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	void (*unmap_phys)(struct device *dev, dma_addr_t dma_handle,
 			size_t size, enum dma_data_direction dir,
 			unsigned long attrs);
 	/*
@@ -46,12 +46,6 @@ struct dma_map_ops {
 			enum dma_data_direction dir, unsigned long attrs);
 	void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nents,
 			enum dma_data_direction dir, unsigned long attrs);
-	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
-			size_t size, enum dma_data_direction dir,
-			unsigned long attrs);
-	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
-			size_t size, enum dma_data_direction dir,
-			unsigned long attrs);
 	void (*sync_single_for_cpu)(struct device *dev, dma_addr_t dma_handle,
 			size_t size, enum dma_data_direction dir);
 	void (*sync_single_for_device)(struct device *dev,
diff --git a/include/linux/map_benchmark.h b/include/uapi/linux/map_benchmark.h
similarity index 80%
rename from include/linux/map_benchmark.h
rename to include/uapi/linux/map_benchmark.h
index 48e2ff9..c2d9108 100644
--- a/include/linux/map_benchmark.h
+++ b/include/uapi/linux/map_benchmark.h
@@ -1,10 +1,12 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
 /*
- * Copyright (C) 2022 HiSilicon Limited.
+ * Copyright (C) 2022-2025 HiSilicon Limited.
  */
 
-#ifndef _KERNEL_DMA_BENCHMARK_H
-#define _KERNEL_DMA_BENCHMARK_H
+#ifndef _UAPI_DMA_BENCHMARK_H
+#define _UAPI_DMA_BENCHMARK_H
+
+#include <linux/types.h>
 
 #define DMA_MAP_BENCHMARK       _IOWR('d', 1, struct map_benchmark)
 #define DMA_MAP_MAX_THREADS     1024
@@ -29,4 +31,5 @@ struct map_benchmark {
 	__u32 granule;  /* how many PAGE_SIZE will do map/unmap once a time */
 	__u8 expansion[76]; /* For future use */
 };
-#endif /* _KERNEL_DMA_BENCHMARK_H */
+
+#endif /* _UAPI_DMA_BENCHMARK_H */
diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c
index 92de80e..16a5173 100644
--- a/kernel/dma/dummy.c
+++ b/kernel/dma/dummy.c
@@ -11,17 +11,16 @@ static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma,
 	return -ENXIO;
 }
 
-static dma_addr_t dma_dummy_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
+static dma_addr_t dma_dummy_map_phys(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	return DMA_MAPPING_ERROR;
 }
-static void dma_dummy_unmap_page(struct device *dev, dma_addr_t dma_handle,
+static void dma_dummy_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	/*
-	 * Dummy ops doesn't support map_page, so unmap_page should never be
+	 * Dummy ops doesn't support map_phys, so unmap_page should never be
 	 * called.
 	 */
 	WARN_ON_ONCE(true);
@@ -51,8 +50,8 @@ static int dma_dummy_supported(struct device *hwdev, u64 mask)
 
 const struct dma_map_ops dma_dummy_ops = {
 	.mmap                   = dma_dummy_mmap,
-	.map_page               = dma_dummy_map_page,
-	.unmap_page             = dma_dummy_unmap_page,
+	.map_phys               = dma_dummy_map_phys,
+	.unmap_phys             = dma_dummy_unmap_phys,
 	.map_sg                 = dma_dummy_map_sg,
 	.unmap_sg               = dma_dummy_unmap_sg,
 	.dma_supported          = dma_dummy_supported,
diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index cc19a3e..794041a 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -11,13 +11,13 @@
 #include <linux/dma-mapping.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
-#include <linux/map_benchmark.h>
 #include <linux/math64.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/timekeeping.h>
+#include <uapi/linux/map_benchmark.h>
 
 struct map_benchmark_data {
 	struct map_benchmark bparam;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index fe7472f..37163eb 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -157,7 +157,7 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	bool is_mmio = attrs & DMA_ATTR_MMIO;
-	dma_addr_t addr;
+	dma_addr_t addr = DMA_MAPPING_ERROR;
 
 	BUG_ON(!valid_dma_direction(dir));
 
@@ -169,21 +169,8 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 		addr = dma_direct_map_phys(dev, phys, size, dir, attrs);
 	else if (use_dma_iommu(dev))
 		addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
-	else if (is_mmio) {
-		if (!ops->map_resource)
-			return DMA_MAPPING_ERROR;
-
-		addr = ops->map_resource(dev, phys, size, dir, attrs);
-	} else {
-		struct page *page = phys_to_page(phys);
-		size_t offset = offset_in_page(phys);
-
-		/*
-		 * The dma_ops API contract for ops->map_page() requires
-		 * kmappable memory, while ops->map_resource() does not.
-		 */
-		addr = ops->map_page(dev, page, offset, size, dir, attrs);
-	}
+	else if (ops->map_phys)
+		addr = ops->map_phys(dev, phys, size, dir, attrs);
 
 	if (!is_mmio)
 		kmsan_handle_dma(phys, size, dir);
@@ -223,11 +210,8 @@ void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
 		dma_direct_unmap_phys(dev, addr, size, dir, attrs);
 	else if (use_dma_iommu(dev))
 		iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
-	else if (is_mmio) {
-		if (ops->unmap_resource)
-			ops->unmap_resource(dev, addr, size, dir, attrs);
-	} else
-		ops->unmap_page(dev, addr, size, dir, attrs);
+	else if (ops->unmap_phys)
+		ops->unmap_phys(dev, addr, size, dir, attrs);
 	trace_dma_unmap_phys(dev, addr, size, dir, attrs);
 	debug_dma_unmap_phys(dev, addr, size, dir);
 }
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 6f9d604..20caf9c 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -64,6 +64,7 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	struct page *page;
+	phys_addr_t phys;
 
 	page = dma_alloc_contiguous(dev, size, gfp);
 	if (!page)
@@ -71,11 +72,12 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
+	phys = page_to_phys(page);
 	if (use_dma_iommu(dev))
-		*dma_handle = iommu_dma_map_phys(dev, page_to_phys(page), size,
-						 dir, DMA_ATTR_SKIP_CPU_SYNC);
+		*dma_handle = iommu_dma_map_phys(dev, phys, size, dir,
+						 DMA_ATTR_SKIP_CPU_SYNC);
 	else
-		*dma_handle = ops->map_page(dev, page, 0, size, dir,
+		*dma_handle = ops->map_phys(dev, phys, size, dir,
 					    DMA_ATTR_SKIP_CPU_SYNC);
 	if (*dma_handle == DMA_MAPPING_ERROR) {
 		dma_free_contiguous(dev, page, size);
@@ -94,8 +96,8 @@ void dma_common_free_pages(struct device *dev, size_t size, struct page *page,
 	if (use_dma_iommu(dev))
 		iommu_dma_unmap_phys(dev, dma_handle, size, dir,
 				     DMA_ATTR_SKIP_CPU_SYNC);
-	else if (ops->unmap_page)
-		ops->unmap_page(dev, dma_handle, size, dir,
+	else if (ops->unmap_phys)
+		ops->unmap_phys(dev, dma_handle, size, dir,
 				DMA_ATTR_SKIP_CPU_SYNC);
 	dma_free_contiguous(dev, page, size);
 }
diff --git a/tools/Makefile b/tools/Makefile
index c31cbbd..cb40961 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -14,6 +14,7 @@ help:
 	@echo '  counter                - counter tools'
 	@echo '  cpupower               - a tool for all things x86 CPU power'
 	@echo '  debugging              - tools for debugging'
+	@echo '  dma                    - tools for DMA mapping'
 	@echo '  firewire               - the userspace part of nosy, an IEEE-1394 traffic sniffer'
 	@echo '  firmware               - Firmware tools'
 	@echo '  freefall               - laptop accelerometer program for disk protection'
@@ -69,7 +70,7 @@ acpi: FORCE
 cpupower: FORCE
 	$(call descend,power/$@)
 
-counter firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi firmware debugging tracing: FORCE
+counter dma firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi firmware debugging tracing: FORCE
 	$(call descend,$@)
 
 bpf/%: FORCE
@@ -122,7 +123,7 @@ kvm_stat: FORCE
 ynl: FORCE
 	$(call descend,net/ynl)
 
-all: acpi counter cpupower gpio hv firewire \
+all: acpi counter cpupower dma gpio hv firewire \
 		perf selftests bootconfig spi turbostat usb \
 		virtio mm bpf x86_energy_perf_policy \
 		tmon freefall iio objtool kvm_stat wmi \
@@ -134,7 +135,7 @@ acpi_install:
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install debugging_install tracing_install:
+counter_install dma_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install debugging_install tracing_install:
 	$(call descend,$(@:_install=),install)
 
 selftests_install:
@@ -164,7 +165,7 @@ kvm_stat_install:
 ynl_install:
 	$(call descend,net/$(@:_install=),install)
 
-install: acpi_install counter_install cpupower_install gpio_install \
+install: acpi_install counter_install cpupower_install dma_install gpio_install \
 		hv_install firewire_install iio_install \
 		perf_install selftests_install turbostat_install usb_install \
 		virtio_install mm_install bpf_install x86_energy_perf_policy_install \
@@ -178,7 +179,7 @@ acpi_clean:
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-counter_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean mm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean firmware_clean debugging_clean tracing_clean:
+counter_clean dma_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean mm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean firmware_clean debugging_clean tracing_clean:
 	$(call descend,$(@:_clean=),clean)
 
 libapi_clean:
@@ -224,7 +225,7 @@ build_clean:
 ynl_clean:
 	$(call descend,net/$(@:_clean=),clean)
 
-clean: acpi_clean counter_clean cpupower_clean hv_clean firewire_clean \
+clean: acpi_clean counter_clean cpupower_clean dma_clean hv_clean firewire_clean \
 		perf_clean selftests_clean turbostat_clean bootconfig_clean spi_clean usb_clean virtio_clean \
 		mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean \
diff --git a/tools/dma/.gitignore b/tools/dma/.gitignore
new file mode 100644
index 0000000..94b68cf
--- /dev/null
+++ b/tools/dma/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+dma_map_benchmark
+include/linux/map_benchmark.h
diff --git a/tools/dma/Makefile b/tools/dma/Makefile
new file mode 100644
index 0000000..e4abf37
--- /dev/null
+++ b/tools/dma/Makefile
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: GPL-2.0
+include ../scripts/Makefile.include
+
+bindir ?= /usr/bin
+
+# This will work when dma is built in tools env. where srctree
+# isn't set and when invoked from selftests build, where srctree
+# is set to ".". building_out_of_srctree is undefined for in srctree
+# builds
+ifndef building_out_of_srctree
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+# Do not use make's built-in rules
+# (this improves performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -r
+
+override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+
+ALL_TARGETS := dma_map_benchmark
+ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
+
+all: $(ALL_PROGRAMS)
+
+export srctree OUTPUT CC LD CFLAGS
+include $(srctree)/tools/build/Makefile.include
+
+#
+# We need the following to be outside of kernel tree
+#
+$(OUTPUT)include/linux/map_benchmark.h: ../../include/uapi/linux/map_benchmark.h
+	mkdir -p $(OUTPUT)include/linux 2>&1 || true
+	ln -sf $(CURDIR)/../../include/uapi/linux/map_benchmark.h $@
+
+prepare: $(OUTPUT)include/linux/map_benchmark.h
+
+FORCE:
+
+DMA_MAP_BENCHMARK = dma_map_benchmark
+$(DMA_MAP_BENCHMARK): prepare FORCE
+	$(CC) $(CFLAGS) $(DMA_MAP_BENCHMARK).c -o $(DMA_MAP_BENCHMARK)
+
+clean:
+	rm -f $(ALL_PROGRAMS)
+	rm -rf $(OUTPUT)include
+	find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete
+
+install: $(ALL_PROGRAMS)
+	install -d -m 755 $(DESTDIR)$(bindir);		\
+	for program in $(ALL_PROGRAMS); do		\
+		install $$program $(DESTDIR)$(bindir);	\
+	done
+
+.PHONY: all install clean prepare FORCE
diff --git a/tools/testing/selftests/dma/config b/tools/dma/config
similarity index 100%
rename from tools/testing/selftests/dma/config
rename to tools/dma/config
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/dma/dma_map_benchmark.c
similarity index 99%
rename from tools/testing/selftests/dma/dma_map_benchmark.c
rename to tools/dma/dma_map_benchmark.c
index b925756..dd0ed52 100644
--- a/tools/testing/selftests/dma/dma_map_benchmark.c
+++ b/tools/dma/dma_map_benchmark.c
@@ -10,7 +10,6 @@
 #include <unistd.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
-#include <linux/types.h>
 #include <linux/map_benchmark.h>
 
 #define NSEC_PER_MSEC	1000000L
diff --git a/tools/testing/selftests/dma/Makefile b/tools/testing/selftests/dma/Makefile
deleted file mode 100644
index cd8c5ec..0000000
--- a/tools/testing/selftests/dma/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -I../../../../usr/include/
-CFLAGS += -I../../../../include/
-
-TEST_GEN_PROGS := dma_map_benchmark
-
-include ../lib.mk