diff --git a/arch/Kconfig b/arch/Kconfig
index 516f2b0..786a85d 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -248,11 +248,18 @@
 	bool
 
 #
-# Select if arch has an uncached kernel segment and provides the
-# uncached_kernel_address / cached_kernel_address symbols to use it
+# Select if the architecture provides the arch_dma_set_uncached symbol to
+# either provide an uncached segement alias for a DMA allocation, or
+# to remap the page tables in place.
 #
-config ARCH_HAS_UNCACHED_SEGMENT
-	select ARCH_HAS_DMA_PREP_COHERENT
+config ARCH_HAS_DMA_SET_UNCACHED
+	bool
+
+#
+# Select if the architectures provides the arch_dma_clear_uncached symbol
+# to undo an in-place page table remap for uncached access.
+#
+config ARCH_HAS_DMA_CLEAR_UNCACHED
 	bool
 
 # Select if arch init_task must go in the __init_task_data section
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 772f48e..86405cc 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -33,7 +33,5 @@
 					struct dma_iommu_mapping *mapping);
 void arm_iommu_detach_device(struct device *dev);
 
-int arm_dma_supported(struct device *dev, u64 mask);
-
 #endif /* __KERNEL__ */
 #endif
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 9414d72f..8a89491 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -179,6 +179,23 @@
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly.  For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask
+ * to this function.
+ */
+static int arm_dma_supported(struct device *dev, u64 mask)
+{
+	unsigned long max_dma_pfn = min(max_pfn - 1, arm_dma_pfn_limit);
+
+	/*
+	 * Translate the device's DMA mask to a PFN limit.  This
+	 * PFN number includes the page which we can DMA to.
+	 */
+	return dma_to_pfn(dev, mask) >= max_dma_pfn;
+}
+
 const struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
@@ -219,49 +236,6 @@
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
 
-static int __dma_supported(struct device *dev, u64 mask, bool warn)
-{
-	unsigned long max_dma_pfn = min(max_pfn - 1, arm_dma_pfn_limit);
-
-	/*
-	 * Translate the device's DMA mask to a PFN limit.  This
-	 * PFN number includes the page which we can DMA to.
-	 */
-	if (dma_to_pfn(dev, mask) < max_dma_pfn) {
-		if (warn)
-			dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n",
-				 mask,
-				 dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1,
-				 max_dma_pfn + 1);
-		return 0;
-	}
-
-	return 1;
-}
-
-static u64 get_coherent_dma_mask(struct device *dev)
-{
-	u64 mask = (u64)DMA_BIT_MASK(32);
-
-	if (dev) {
-		mask = dev->coherent_dma_mask;
-
-		/*
-		 * Sanity check the DMA mask - it must be non-zero, and
-		 * must be able to be satisfied by a DMA allocation.
-		 */
-		if (mask == 0) {
-			dev_warn(dev, "coherent DMA mask is unset\n");
-			return 0;
-		}
-
-		if (!__dma_supported(dev, mask, true))
-			return 0;
-	}
-
-	return mask;
-}
-
 static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag)
 {
 	/*
@@ -688,7 +662,7 @@
 			 gfp_t gfp, pgprot_t prot, bool is_coherent,
 			 unsigned long attrs, const void *caller)
 {
-	u64 mask = get_coherent_dma_mask(dev);
+	u64 mask = min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 	struct page *page = NULL;
 	void *addr;
 	bool allowblock, cma;
@@ -712,9 +686,6 @@
 	}
 #endif
 
-	if (!mask)
-		return NULL;
-
 	buf = kzalloc(sizeof(*buf),
 		      gfp & ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM));
 	if (!buf)
@@ -1087,17 +1058,6 @@
 					    dir);
 }
 
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask
- * to this function.
- */
-int arm_dma_supported(struct device *dev, u64 mask)
-{
-	return __dma_supported(dev, mask, false);
-}
-
 static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
 {
 	/*
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 242f58e..15baa68 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -8,7 +8,7 @@
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select ARCH_HAS_UNCACHED_SEGMENT if !MMU
+	select ARCH_HAS_DMA_SET_UNCACHED if !MMU
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_TABLE_SORT
diff --git a/arch/microblaze/mm/consistent.c b/arch/microblaze/mm/consistent.c
index 8c5f0c3..e09b66e 100644
--- a/arch/microblaze/mm/consistent.c
+++ b/arch/microblaze/mm/consistent.c
@@ -40,7 +40,7 @@
 #define UNCACHED_SHADOW_MASK 0
 #endif /* CONFIG_XILINX_UNCACHED_SHADOW */
 
-void *uncached_kernel_address(void *ptr)
+void *arch_dma_set_uncached(void *ptr, size_t size)
 {
 	unsigned long addr = (unsigned long)ptr;
 
@@ -49,11 +49,4 @@
 		pr_warn("ERROR: Your cache coherent area is CACHED!!!\n");
 	return (void *)addr;
 }
-
-void *cached_kernel_address(void *ptr)
-{
-	unsigned long addr = (unsigned long)ptr;
-
-	return (void *)(addr & ~UNCACHED_SHADOW_MASK);
-}
 #endif /* CONFIG_MMU */
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index f8f3dbd..690718b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1192,8 +1192,9 @@
 	# significant advantages.
 	#
 	select ARCH_HAS_DMA_WRITE_COMBINE
+	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select ARCH_HAS_UNCACHED_SEGMENT
+	select ARCH_HAS_DMA_SET_UNCACHED
 	select DMA_NONCOHERENT_MMAP
 	select DMA_NONCOHERENT_CACHE_SYNC
 	select NEED_DMA_MAP_STATE
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index dc42ffc..fcea92d 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -49,16 +49,11 @@
 	dma_cache_wback_inv((unsigned long)page_address(page), size);
 }
 
-void *uncached_kernel_address(void *addr)
+void *arch_dma_set_uncached(void *addr, size_t size)
 {
 	return (void *)(__pa(addr) + UNCAC_BASE);
 }
 
-void *cached_kernel_address(void *addr)
-{
-	return __va(addr) - UNCAC_BASE;
-}
-
 static inline void dma_sync_virt(void *addr, size_t size,
 		enum dma_data_direction dir)
 {
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 44b5da3..2fc4ed2 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -2,9 +2,10 @@
 config NIOS2
 	def_bool y
 	select ARCH_32BIT_OFF_T
+	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select ARCH_HAS_UNCACHED_SEGMENT
+	select ARCH_HAS_DMA_SET_UNCACHED
 	select ARCH_NO_SWAP
 	select TIMER_OF
 	select GENERIC_ATOMIC64
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index 0ed711e..fd887d5 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -67,7 +67,7 @@
 	flush_dcache_range(start, start + size);
 }
 
-void *uncached_kernel_address(void *ptr)
+void *arch_dma_set_uncached(void *ptr, size_t size)
 {
 	unsigned long addr = (unsigned long)ptr;
 
@@ -75,13 +75,3 @@
 
 	return (void *)ptr;
 }
-
-void *cached_kernel_address(void *ptr)
-{
-	unsigned long addr = (unsigned long)ptr;
-
-	addr &= ~CONFIG_NIOS2_IO_REGION_BASE;
-	addr |= CONFIG_NIOS2_KERNEL_REGION_BASE;
-
-	return (void *)ptr;
-}
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 1928e061..7e94fe3 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -7,6 +7,8 @@
 config OPENRISC
 	def_bool y
 	select ARCH_32BIT_OFF_T
+	select ARCH_HAS_DMA_SET_UNCACHED
+	select ARCH_HAS_DMA_CLEAR_UNCACHED
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select OF
 	select OF_EARLY_FLATTREE
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index adec711..c152a68 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -11,8 +11,6 @@
  * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
  *
  * DMA mapping callbacks...
- * As alloc_coherent is the only DMA callback being used currently, that's
- * the only thing implemented properly.  The rest need looking into...
  */
 
 #include <linux/dma-noncoherent.h>
@@ -67,62 +65,29 @@
 	.pte_entry		= page_clear_nocache,
 };
 
-/*
- * Alloc "coherent" memory, which for OpenRISC means simply uncached.
- *
- * This function effectively just calls __get_free_pages, sets the
- * cache-inhibit bit on those pages, and makes sure that the pages are
- * flushed out of the cache before they are used.
- *
- * If the NON_CONSISTENT attribute is set, then this function just
- * returns "normal", cachable memory.
- *
- * There are additional flags WEAK_ORDERING and WRITE_COMBINE to take
- * into consideration here, too.  All current known implementations of
- * the OR1K support only strongly ordered memory accesses, so that flag
- * is being ignored for now; uncached but write-combined memory is a
- * missing feature of the OR1K.
- */
-void *
-arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp, unsigned long attrs)
+void *arch_dma_set_uncached(void *cpu_addr, size_t size)
 {
-	unsigned long va;
-	void *page;
-
-	page = alloc_pages_exact(size, gfp | __GFP_ZERO);
-	if (!page)
-		return NULL;
-
-	/* This gives us the real physical address of the first page. */
-	*dma_handle = __pa(page);
-
-	va = (unsigned long)page;
+	unsigned long va = (unsigned long)cpu_addr;
+	int error;
 
 	/*
 	 * We need to iterate through the pages, clearing the dcache for
 	 * them and setting the cache-inhibit bit.
 	 */
-	if (walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops,
-			NULL)) {
-		free_pages_exact(page, size);
-		return NULL;
-	}
-
-	return (void *)va;
+	error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops,
+			NULL);
+	if (error)
+		return ERR_PTR(error);
+	return cpu_addr;
 }
 
-void
-arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
+void arch_dma_clear_uncached(void *cpu_addr, size_t size)
 {
-	unsigned long va = (unsigned long)vaddr;
+	unsigned long va = (unsigned long)cpu_addr;
 
 	/* walk_page_range shouldn't be able to fail here */
 	WARN_ON(walk_page_range(&init_mm, va, va + size,
 			&clear_nocache_walk_ops, NULL));
-
-	free_pages_exact(vaddr, size);
 }
 
 void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 32ee759..de22942 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -6,7 +6,7 @@
 	select ARCH_HAS_DMA_PREP_COHERENT if MMU
 	select ARCH_HAS_SYNC_DMA_FOR_CPU if MMU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if MMU
-	select ARCH_HAS_UNCACHED_SEGMENT if MMU
+	select ARCH_HAS_DMA_SET_UNCACHED if MMU
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_FRAME_POINTERS
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 72b6222..17c4384 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -88,18 +88,12 @@
 
 /*
  * Memory caching is platform-dependent in noMMU xtensa configurations.
- * The following two functions should be implemented in platform code
- * in order to enable coherent DMA memory operations when CONFIG_MMU is not
- * enabled.
+ * This function should be implemented in platform code in order to enable
+ * coherent DMA memory operations when CONFIG_MMU is not enabled.
  */
 #ifdef CONFIG_MMU
-void *uncached_kernel_address(void *p)
+void *arch_dma_set_uncached(void *p, size_t size)
 {
 	return p + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR;
 }
-
-void *cached_kernel_address(void *p)
-{
-	return p + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
-}
 #endif /* CONFIG_MMU */
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index ca9b577..b59f1b6 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -108,7 +108,7 @@
 }
 #endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
 
-void *uncached_kernel_address(void *addr);
-void *cached_kernel_address(void *addr);
+void *arch_dma_set_uncached(void *addr, size_t size);
+void arch_dma_clear_uncached(void *addr, size_t size);
 
 #endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 551b0eb..2a0c498 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -134,7 +134,7 @@
 
 	spin_lock_irqsave(&mem->spinlock, flags);
 
-	if (unlikely(size > (mem->size << PAGE_SHIFT)))
+	if (unlikely(size > ((dma_addr_t)mem->size << PAGE_SHIFT)))
 		goto err;
 
 	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
@@ -144,8 +144,9 @@
 	/*
 	 * Memory was found in the coherent area.
 	 */
-	*dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT);
-	ret = mem->virt_base + (pageno << PAGE_SHIFT);
+	*dma_handle = dma_get_device_base(dev, mem) +
+			((dma_addr_t)pageno << PAGE_SHIFT);
+	ret = mem->virt_base + ((dma_addr_t)pageno << PAGE_SHIFT);
 	spin_unlock_irqrestore(&mem->spinlock, flags);
 	memset(ret, 0, size);
 	return ret;
@@ -194,7 +195,7 @@
 				       int order, void *vaddr)
 {
 	if (mem && vaddr >= mem->virt_base && vaddr <
-		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		   (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) {
 		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
 		unsigned long flags;
 
@@ -238,10 +239,10 @@
 		struct vm_area_struct *vma, void *vaddr, size_t size, int *ret)
 {
 	if (mem && vaddr >= mem->virt_base && vaddr + size <=
-		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		   (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) {
 		unsigned long off = vma->vm_pgoff;
 		int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
-		int user_count = vma_pages(vma);
+		unsigned long user_count = vma_pages(vma);
 		int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
 		*ret = -ENXIO;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index ac7956c..a856005 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -157,11 +157,8 @@
 		ret = dma_common_contiguous_remap(page, PAGE_ALIGN(size),
 				dma_pgprot(dev, PAGE_KERNEL, attrs),
 				__builtin_return_address(0));
-		if (!ret) {
-			dma_free_contiguous(dev, page, size);
-			return ret;
-		}
-
+		if (!ret)
+			goto out_free_pages;
 		memset(ret, 0, size);
 		goto done;
 	}
@@ -174,8 +171,7 @@
 		 * so log an error and fail.
 		 */
 		dev_info(dev, "Rejecting highmem page from CMA.\n");
-		dma_free_contiguous(dev, page, size);
-		return NULL;
+		goto out_free_pages;
 	}
 
 	ret = page_address(page);
@@ -184,10 +180,12 @@
 
 	memset(ret, 0, size);
 
-	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    dma_alloc_need_uncached(dev, attrs)) {
 		arch_dma_prep_coherent(page, size);
-		ret = uncached_kernel_address(ret);
+		ret = arch_dma_set_uncached(ret, size);
+		if (IS_ERR(ret))
+			goto out_free_pages;
 	}
 done:
 	if (force_dma_unencrypted(dev))
@@ -195,6 +193,9 @@
 	else
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 	return ret;
+out_free_pages:
+	dma_free_contiguous(dev, page, size);
+	return NULL;
 }
 
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
@@ -218,6 +219,8 @@
 
 	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr))
 		vunmap(cpu_addr);
+	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
+		arch_dma_clear_uncached(cpu_addr, size);
 
 	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
 }
@@ -225,7 +228,7 @@
 void *dma_direct_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    dma_alloc_need_uncached(dev, attrs))
 		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
@@ -235,7 +238,7 @@
 void dma_direct_free(struct device *dev, size_t size,
 		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
 {
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    dma_alloc_need_uncached(dev, attrs))
 		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);