Merge tag 'dma-mapping-4.13' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping infrastructure from Christoph Hellwig:
 "This is the first pull request for the new dma-mapping subsystem

  In this new subsystem we'll try to properly maintain all the generic
  code related to dma-mapping, and will further consolidate arch code
  into common helpers.

  This pull request contains:

   - removal of the DMA_ERROR_CODE macro, replacing it with calls to
     ->mapping_error so that the dma_map_ops instances are more self
     contained and can be shared across architectures (me)

   - removal of the ->set_dma_mask method, which duplicates the
     ->dma_capable one in terms of functionality, but requires more
     duplicate code.

   - various updates for the coherent dma pool and related arm code
     (Vladimir)

   - various smaller cleanups (me)"

* tag 'dma-mapping-4.13' of git://git.infradead.org/users/hch/dma-mapping: (56 commits)
  ARM: dma-mapping: Remove traces of NOMMU code
  ARM: NOMMU: Set ARM_DMA_MEM_BUFFERABLE for M-class cpus
  ARM: NOMMU: Introduce dma operations for noMMU
  drivers: dma-mapping: allow dma_common_mmap() for NOMMU
  drivers: dma-coherent: Introduce default DMA pool
  drivers: dma-coherent: Account dma_pfn_offset when used with device tree
  dma: Take into account dma_pfn_offset
  dma-mapping: replace dmam_alloc_noncoherent with dmam_alloc_attrs
  dma-mapping: remove dmam_free_noncoherent
  crypto: qat - avoid an uninitialized variable warning
  au1100fb: remove a bogus dma_free_nonconsistent call
  MAINTAINERS: add entry for dma mapping helpers
  powerpc: merge __dma_set_mask into dma_set_mask
  dma-mapping: remove the set_dma_mask method
  powerpc/cell: use the dma_supported method for ops switching
  powerpc/cell: clean up fixed mapping dma_ops initialization
  tile: remove dma_supported and mapping_error methods
  xen-swiotlb: remove xen_swiotlb_set_dma_mask
  arm: implement ->dma_supported instead of ->set_dma_mask
  mips/loongson64: implement ->dma_supported instead of ->set_dma_mask
  ...

75 files changed, 778 insertions, 725 deletions

diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index 979228b..4ed3883 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -550,32 +550,11 @@ and to unmap it:
 	dma_unmap_single(dev, dma_handle, size, direction);
 
 You should call dma_mapping_error() as dma_map_single() could fail and return
-error. Not all DMA implementations support the dma_mapping_error() interface.
-However, it is a good practice to call dma_mapping_error() interface, which
-will invoke the generic mapping error check interface. Doing so will ensure
-that the mapping code will work correctly on all DMA implementations without
-any dependency on the specifics of the underlying implementation. Using the
-returned address without checking for errors could result in failures ranging
-from panics to silent data corruption. A couple of examples of incorrect ways
-to check for errors that make assumptions about the underlying DMA
-implementation are as follows and these are applicable to dma_map_page() as
-well.
-
-Incorrect example 1:
-	dma_addr_t dma_handle;
-
-	dma_handle = dma_map_single(dev, addr, size, direction);
-	if ((dma_handle & 0xffff != 0) || (dma_handle >= 0x1000000)) {
-		goto map_error;
-	}
-
-Incorrect example 2:
-	dma_addr_t dma_handle;
-
-	dma_handle = dma_map_single(dev, addr, size, direction);
-	if (dma_handle == DMA_ERROR_CODE) {
-		goto map_error;
-	}
+error.  Doing so will ensure that the mapping code will work correctly on all
+DMA implementations without any dependency on the specifics of the underlying
+implementation. Using the returned address without checking for errors could
+result in failures ranging from panics to silent data corruption.  The same
+applies to dma_map_page() as well.
 
 You should call dma_unmap_single() when the DMA activity is finished, e.g.,
 from the interrupt which told you that the DMA transfer is done.
diff --git a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
index 3da0ebd..16291f2 100644
--- a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
+++ b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
@@ -68,6 +68,9 @@ Linux implementation note:
 - If a "linux,cma-default" property is present, then Linux will use the
   region for the default pool of the contiguous memory allocator.
 
+- If a "linux,dma-default" property is present, then Linux will use the
+  region for the default pool of the consistent DMA allocator.
+
 Device node references to reserved memory
 -----------------------------------------
 Regions in the /reserved-memory node may be referenced by other device
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index 2d132fc..4231b45 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -240,10 +240,9 @@ CLOCK
 
 DMA
   dmam_alloc_coherent()
-  dmam_alloc_noncoherent()
+  dmam_alloc_attrs()
   dmam_declare_coherent_memory()
   dmam_free_coherent()
-  dmam_free_noncoherent()
   dmam_pool_create()
   dmam_pool_destroy()
 
diff --git a/MAINTAINERS b/MAINTAINERS
index c8f7952..e23b07d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2631,6 +2631,21 @@ S:	Maintained
 F:	net/bluetooth/
 F:	include/net/bluetooth/
 
+DMA MAPPING HELPERS
+M:	Christoph Hellwig <hch@lst.de>
+M:	Marek Szyprowski <m.szyprowski@samsung.com>
+R:	Robin Murphy <robin.murphy@arm.com>
+L:	linux-kernel@vger.kernel.org
+T:	git git://git.infradead.org/users/hch/dma-mapping.git
+W:	http://git.infradead.org/users/hch/dma-mapping.git
+S:	Supported
+F:	lib/dma-debug.c
+F:	lib/dma-noop.c
+F:	lib/dma-virt.c
+F:	drivers/base/dma-mapping.c
+F:	drivers/base/dma-coherent.c
+F:	include/linux/dma-mapping.h
+
 BONDING DRIVER
 M:	Jay Vosburgh <j.vosburgh@gmail.com>
 M:	Veaceslav Falico <vfalico@gmail.com>
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index abd59fa..0b731e8 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -22,6 +22,7 @@ config ARM
 	select CLONE_BACKWARDS
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select DMA_NOOP_OPS if !MMU
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
 	select GENERIC_ALLOCATOR
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index 9b1b7be..9a92de6 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -33,6 +33,7 @@
 #include <linux/scatterlist.h>
 
 #include <asm/cacheflush.h>
+#include <asm/dma-iommu.h>
 
 #undef STATS
 
@@ -256,7 +257,7 @@ static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
 	if (buf == NULL) {
 		dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
 		       __func__, ptr);
-		return DMA_ERROR_CODE;
+		return ARM_MAPPING_ERROR;
 	}
 
 	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
@@ -326,7 +327,7 @@ static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page,
 
 	ret = needs_bounce(dev, dma_addr, size);
 	if (ret < 0)
-		return DMA_ERROR_CODE;
+		return ARM_MAPPING_ERROR;
 
 	if (ret == 0) {
 		arm_dma_ops.sync_single_for_device(dev, dma_addr, size, dir);
@@ -335,7 +336,7 @@ static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page,
 
 	if (PageHighMem(page)) {
 		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
-		return DMA_ERROR_CODE;
+		return ARM_MAPPING_ERROR;
 	}
 
 	return map_single(dev, page_address(page) + offset, size, dir, attrs);
@@ -444,12 +445,17 @@ static void dmabounce_sync_for_device(struct device *dev,
 	arm_dma_ops.sync_single_for_device(dev, handle, size, dir);
 }
 
-static int dmabounce_set_mask(struct device *dev, u64 dma_mask)
+static int dmabounce_dma_supported(struct device *dev, u64 dma_mask)
 {
 	if (dev->archdata.dmabounce)
 		return 0;
 
-	return arm_dma_ops.set_dma_mask(dev, dma_mask);
+	return arm_dma_ops.dma_supported(dev, dma_mask);
+}
+
+static int dmabounce_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return arm_dma_ops.mapping_error(dev, dma_addr);
 }
 
 static const struct dma_map_ops dmabounce_ops = {
@@ -465,7 +471,8 @@ static const struct dma_map_ops dmabounce_ops = {
 	.unmap_sg		= arm_dma_unmap_sg,
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
-	.set_dma_mask		= dmabounce_set_mask,
+	.dma_supported		= dmabounce_dma_supported,
+	.mapping_error		= dmabounce_mapping_error,
 };
 
 static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 2ef282f..c090ec6 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -9,6 +9,8 @@
 #include <linux/kmemcheck.h>
 #include <linux/kref.h>
 
+#define ARM_MAPPING_ERROR		(~(dma_addr_t)0x0)
+
 struct dma_iommu_mapping {
 	/* iommu specific data */
 	struct iommu_domain	*domain;
@@ -33,5 +35,7 @@ int arm_iommu_attach_device(struct device *dev,
 					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/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 680d3f3..4e0285a 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -12,18 +12,14 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
 extern const struct dma_map_ops arm_dma_ops;
 extern const struct dma_map_ops arm_coherent_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return &arm_dma_ops;
+	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_noop_ops;
 }
 
-#define HAVE_ARCH_DMA_SUPPORTED 1
-extern int dma_supported(struct device *dev, u64 mask);
-
 #ifdef __arch_page_to_dma
 #error Please update to __arch_pfn_to_dma
 #endif
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index c6c4c9c..877a0e3 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1045,8 +1045,8 @@ config ARM_L1_CACHE_SHIFT
 	default 5
 
 config ARM_DMA_MEM_BUFFERABLE
-	bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K) && !CPU_V7
-	default y if CPU_V6 || CPU_V6K || CPU_V7
+	bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K || CPU_V7M) && !CPU_V7
+	default y if CPU_V6 || CPU_V6K || CPU_V7 || CPU_V7M
 	help
 	  Historically, the kernel has used strongly ordered mappings to
 	  provide DMA coherent memory.  With the advent of ARMv7, mapping
@@ -1061,6 +1061,10 @@ config ARM_DMA_MEM_BUFFERABLE
 	  and therefore turning this on may result in unpredictable driver
 	  behaviour.  Therefore, we offer this as an option.
 
+	  On some of the beefier ARMv7-M machines (with DMA and write
+	  buffers) you likely want this enabled, while those that
+	  didn't need it until now also won't need it in the future.
+
 	  You are recommended say 'Y' here and debug any affected drivers.
 
 config ARM_HEAVY_MB
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index b3dea80..950d19b 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -2,9 +2,8 @@
 # Makefile for the linux arm-specific parts of the memory manager.
 #
 
-obj-y				:= dma-mapping.o extable.o fault.o init.o \
-				   iomap.o
-
+obj-y				:= extable.o fault.o init.o iomap.o
+obj-y				+= dma-mapping$(MMUEXT).o
 obj-$(CONFIG_MMU)		+= fault-armv.o flush.o idmap.o ioremap.o \
 				   mmap.o pgd.o mmu.o pageattr.o
 
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
new file mode 100644
index 0000000..90ee354
--- /dev/null
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -0,0 +1,228 @@
+/*
+ *  Based on linux/arch/arm/mm/dma-mapping.c
+ *
+ *  Copyright (C) 2000-2004 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+
+#include <asm/cachetype.h>
+#include <asm/cacheflush.h>
+#include <asm/outercache.h>
+#include <asm/cp15.h>
+
+#include "dma.h"
+
+/*
+ *  dma_noop_ops is used if
+ *   - MMU/MPU is off
+ *   - cpu is v7m w/o cache support
+ *   - device is coherent
+ *  otherwise arm_nommu_dma_ops is used.
+ *
+ *  arm_nommu_dma_ops rely on consistent DMA memory (please, refer to
+ *  [1] on how to declare such memory).
+ *
+ *  [1] Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
+ */
+
+static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
+				 dma_addr_t *dma_handle, gfp_t gfp,
+				 unsigned long attrs)
+
+{
+	const struct dma_map_ops *ops = &dma_noop_ops;
+
+	/*
+	 * We are here because:
+	 * - no consistent DMA region has been defined, so we can't
+	 *   continue.
+	 * - there is no space left in consistent DMA region, so we
+	 *   only can fallback to generic allocator if we are
+	 *   advertised that consistency is not required.
+	 */
+
+	if (attrs & DMA_ATTR_NON_CONSISTENT)
+		return ops->alloc(dev, size, dma_handle, gfp, attrs);
+
+	WARN_ON_ONCE(1);
+	return NULL;
+}
+
+static void arm_nommu_dma_free(struct device *dev, size_t size,
+			       void *cpu_addr, dma_addr_t dma_addr,
+			       unsigned long attrs)
+{
+	const struct dma_map_ops *ops = &dma_noop_ops;
+
+	if (attrs & DMA_ATTR_NON_CONSISTENT)
+		ops->free(dev, size, cpu_addr, dma_addr, attrs);
+	else
+		WARN_ON_ONCE(1);
+
+	return;
+}
+
+static void __dma_page_cpu_to_dev(phys_addr_t paddr, size_t size,
+				  enum dma_data_direction dir)
+{
+	dmac_map_area(__va(paddr), size, dir);
+
+	if (dir == DMA_FROM_DEVICE)
+		outer_inv_range(paddr, paddr + size);
+	else
+		outer_clean_range(paddr, paddr + size);
+}
+
+static void __dma_page_dev_to_cpu(phys_addr_t paddr, size_t size,
+				  enum dma_data_direction dir)
+{
+	if (dir != DMA_TO_DEVICE) {
+		outer_inv_range(paddr, paddr + size);
+		dmac_unmap_area(__va(paddr), size, dir);
+	}
+}
+
+static dma_addr_t arm_nommu_dma_map_page(struct device *dev, struct page *page,
+					 unsigned long offset, size_t size,
+					 enum dma_data_direction dir,
+					 unsigned long attrs)
+{
+	dma_addr_t handle = page_to_phys(page) + offset;
+
+	__dma_page_cpu_to_dev(handle, size, dir);
+
+	return handle;
+}
+
+static void arm_nommu_dma_unmap_page(struct device *dev, dma_addr_t handle,
+				     size_t size, enum dma_data_direction dir,
+				     unsigned long attrs)
+{
+	__dma_page_dev_to_cpu(handle, size, dir);
+}
+
+
+static int arm_nommu_dma_map_sg(struct device *dev, struct scatterlist *sgl,
+				int nents, enum dma_data_direction dir,
+				unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i) {
+		sg_dma_address(sg) = sg_phys(sg);
+		sg_dma_len(sg) = sg->length;
+		__dma_page_cpu_to_dev(sg_dma_address(sg), sg_dma_len(sg), dir);
+	}
+
+	return nents;
+}
+
+static void arm_nommu_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
+				   int nents, enum dma_data_direction dir,
+				   unsigned long attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		__dma_page_dev_to_cpu(sg_dma_address(sg), sg_dma_len(sg), dir);
+}
+
+static void arm_nommu_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	__dma_page_cpu_to_dev(handle, size, dir);
+}
+
+static void arm_nommu_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	__dma_page_cpu_to_dev(handle, size, dir);
+}
+
+static void arm_nommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+					     int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		__dma_page_cpu_to_dev(sg_dma_address(sg), sg_dma_len(sg), dir);
+}
+
+static void arm_nommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+					  int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		__dma_page_dev_to_cpu(sg_dma_address(sg), sg_dma_len(sg), dir);
+}
+
+const struct dma_map_ops arm_nommu_dma_ops = {
+	.alloc			= arm_nommu_dma_alloc,
+	.free			= arm_nommu_dma_free,
+	.map_page		= arm_nommu_dma_map_page,
+	.unmap_page		= arm_nommu_dma_unmap_page,
+	.map_sg			= arm_nommu_dma_map_sg,
+	.unmap_sg		= arm_nommu_dma_unmap_sg,
+	.sync_single_for_device	= arm_nommu_dma_sync_single_for_device,
+	.sync_single_for_cpu	= arm_nommu_dma_sync_single_for_cpu,
+	.sync_sg_for_device	= arm_nommu_dma_sync_sg_for_device,
+	.sync_sg_for_cpu	= arm_nommu_dma_sync_sg_for_cpu,
+};
+EXPORT_SYMBOL(arm_nommu_dma_ops);
+
+static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent)
+{
+	return coherent ? &dma_noop_ops : &arm_nommu_dma_ops;
+}
+
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+			const struct iommu_ops *iommu, bool coherent)
+{
+	const struct dma_map_ops *dma_ops;
+
+	if (IS_ENABLED(CONFIG_CPU_V7M)) {
+		/*
+		 * Cache support for v7m is optional, so can be treated as
+		 * coherent if no cache has been detected. Note that it is not
+		 * enough to check if MPU is in use or not since in absense of
+		 * MPU system memory map is used.
+		 */
+		dev->archdata.dma_coherent = (cacheid) ? coherent : true;
+	} else {
+		/*
+		 * Assume coherent DMA in case MMU/MPU has not been set up.
+		 */
+		dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true;
+	}
+
+	dma_ops = arm_nommu_get_dma_map_ops(dev->archdata.dma_coherent);
+
+	set_dma_ops(dev, dma_ops);
+}
+
+void arch_teardown_dma_ops(struct device *dev)
+{
+}
+
+#define PREALLOC_DMA_DEBUG_ENTRIES	4096
+
+static int __init dma_debug_do_init(void)
+{
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+	return 0;
+}
+core_initcall(dma_debug_do_init);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index bd83c53..e7380ba 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -180,6 +180,11 @@ static void arm_dma_sync_single_for_device(struct device *dev,
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
+static int arm_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == ARM_MAPPING_ERROR;
+}
+
 const struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
@@ -193,6 +198,8 @@ const struct dma_map_ops arm_dma_ops = {
 	.sync_single_for_device	= arm_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
+	.mapping_error		= arm_dma_mapping_error,
+	.dma_supported		= arm_dma_supported,
 };
 EXPORT_SYMBOL(arm_dma_ops);
 
@@ -211,6 +218,8 @@ const struct dma_map_ops arm_coherent_dma_ops = {
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
 	.map_sg			= arm_dma_map_sg,
+	.mapping_error		= arm_dma_mapping_error,
+	.dma_supported		= arm_dma_supported,
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
 
@@ -344,8 +353,6 @@ static void __dma_free_buffer(struct page *page, size_t size)
 	}
 }
 
-#ifdef CONFIG_MMU
-
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
 				     const void *caller, bool want_vaddr,
@@ -647,22 +654,6 @@ static inline pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot)
 	return prot;
 }
 
-#define nommu() 0
-
-#else	/* !CONFIG_MMU */
-
-#define nommu() 1
-
-#define __get_dma_pgprot(attrs, prot)				__pgprot(0)
-#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv)	NULL
-#define __alloc_from_pool(size, ret_page)			NULL
-#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, coherent_flag, gfp)	NULL
-#define __free_from_pool(cpu_addr, size)			do { } while (0)
-#define __free_from_contiguous(dev, page, cpu_addr, size, wv)	do { } while (0)
-#define __dma_free_remap(cpu_addr, size)			do { } while (0)
-
-#endif	/* CONFIG_MMU */
-
 static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
 				   struct page **ret_page)
 {
@@ -799,13 +790,13 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	gfp &= ~(__GFP_COMP);
 	args.gfp = gfp;
 
-	*handle = DMA_ERROR_CODE;
+	*handle = ARM_MAPPING_ERROR;
 	allowblock = gfpflags_allow_blocking(gfp);
 	cma = allowblock ? dev_get_cma_area(dev) : false;
 
 	if (cma)
 		buf->allocator = &cma_allocator;
-	else if (nommu() || is_coherent)
+	else if (is_coherent)
 		buf->allocator = &simple_allocator;
 	else if (allowblock)
 		buf->allocator = &remap_allocator;
@@ -854,8 +845,7 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		 unsigned long attrs)
 {
-	int ret = -ENXIO;
-#ifdef CONFIG_MMU
+	int ret;
 	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long pfn = dma_to_pfn(dev, dma_addr);
@@ -870,10 +860,6 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 				      vma->vm_end - vma->vm_start,
 				      vma->vm_page_prot);
 	}
-#else
-	ret = vm_iomap_memory(vma, vma->vm_start,
-			      (vma->vm_end - vma->vm_start));
-#endif	/* CONFIG_MMU */
 
 	return ret;
 }
@@ -892,9 +878,7 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		 unsigned long attrs)
 {
-#ifdef CONFIG_MMU
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-#endif	/* CONFIG_MMU */
 	return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
 }
 
@@ -1177,11 +1161,10 @@ void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
  * during bus mastering, then you would pass 0x00ffffff as the mask
  * to this function.
  */
-int dma_supported(struct device *dev, u64 mask)
+int arm_dma_supported(struct device *dev, u64 mask)
 {
 	return __dma_supported(dev, mask, false);
 }
-EXPORT_SYMBOL(dma_supported);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
@@ -1254,7 +1237,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 	if (i == mapping->nr_bitmaps) {
 		if (extend_iommu_mapping(mapping)) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return DMA_ERROR_CODE;
+			return ARM_MAPPING_ERROR;
 		}
 
 		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
@@ -1262,7 +1245,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 
 		if (start > mapping->bits) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return DMA_ERROR_CODE;
+			return ARM_MAPPING_ERROR;
 		}
 
 		bitmap_set(mapping->bitmaps[i], start, count);
@@ -1445,7 +1428,7 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size,
 	int i;
 
 	dma_addr = __alloc_iova(mapping, size);
-	if (dma_addr == DMA_ERROR_CODE)
+	if (dma_addr == ARM_MAPPING_ERROR)
 		return dma_addr;
 
 	iova = dma_addr;
@@ -1472,7 +1455,7 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size,
 fail:
 	iommu_unmap(mapping->domain, dma_addr, iova-dma_addr);
 	__free_iova(mapping, dma_addr, size);
-	return DMA_ERROR_CODE;
+	return ARM_MAPPING_ERROR;
 }
 
 static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size)
@@ -1533,7 +1516,7 @@ static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, &page, size, attrs);
-	if (*handle == DMA_ERROR_CODE)
+	if (*handle == ARM_MAPPING_ERROR)
 		goto err_mapping;
 
 	return addr;
@@ -1561,7 +1544,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	struct page **pages;
 	void *addr = NULL;
 
-	*handle = DMA_ERROR_CODE;
+	*handle = ARM_MAPPING_ERROR;
 	size = PAGE_ALIGN(size);
 
 	if (coherent_flag  == COHERENT || !gfpflags_allow_blocking(gfp))
@@ -1582,7 +1565,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, pages, size, attrs);
-	if (*handle == DMA_ERROR_CODE)
+	if (*handle == ARM_MAPPING_ERROR)
 		goto err_buffer;
 
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
@@ -1732,10 +1715,10 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 	int prot;
 
 	size = PAGE_ALIGN(size);
-	*handle = DMA_ERROR_CODE;
+	*handle = ARM_MAPPING_ERROR;
 
 	iova_base = iova = __alloc_iova(mapping, size);
-	if (iova == DMA_ERROR_CODE)
+	if (iova == ARM_MAPPING_ERROR)
 		return -ENOMEM;
 
 	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
@@ -1775,7 +1758,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	for (i = 1; i < nents; i++) {
 		s = sg_next(s);
 
-		s->dma_address = DMA_ERROR_CODE;
+		s->dma_address = ARM_MAPPING_ERROR;
 		s->dma_length = 0;
 
 		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
@@ -1950,7 +1933,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	int ret, prot, len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == DMA_ERROR_CODE)
+	if (dma_addr == ARM_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs);
@@ -1962,7 +1945,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return DMA_ERROR_CODE;
+	return ARM_MAPPING_ERROR;
 }
 
 /**
@@ -2056,7 +2039,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev,
 	size_t len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == DMA_ERROR_CODE)
+	if (dma_addr == ARM_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
@@ -2068,7 +2051,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev,
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return DMA_ERROR_CODE;
+	return ARM_MAPPING_ERROR;
 }
 
 /**
@@ -2140,6 +2123,9 @@ const struct dma_map_ops iommu_ops = {
 
 	.map_resource		= arm_iommu_map_resource,
 	.unmap_resource		= arm_iommu_unmap_resource,
+
+	.mapping_error		= arm_dma_mapping_error,
+	.dma_supported		= arm_dma_supported,
 };
 
 const struct dma_map_ops iommu_coherent_ops = {
@@ -2156,6 +2142,9 @@ const struct dma_map_ops iommu_coherent_ops = {
 
 	.map_resource	= arm_iommu_map_resource,
 	.unmap_resource	= arm_iommu_unmap_resource,
+
+	.mapping_error		= arm_dma_mapping_error,
+	.dma_supported		= arm_dma_supported,
 };
 
 /**
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index f0325d9..785d2a5 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -185,23 +185,6 @@ EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
 const struct dma_map_ops *xen_dma_ops;
 EXPORT_SYMBOL(xen_dma_ops);
 
-static const struct dma_map_ops xen_swiotlb_dma_ops = {
-	.alloc = xen_swiotlb_alloc_coherent,
-	.free = xen_swiotlb_free_coherent,
-	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
-	.map_sg = xen_swiotlb_map_sg_attrs,
-	.unmap_sg = xen_swiotlb_unmap_sg_attrs,
-	.map_page = xen_swiotlb_map_page,
-	.unmap_page = xen_swiotlb_unmap_page,
-	.dma_supported = xen_swiotlb_dma_supported,
-	.set_dma_mask = xen_swiotlb_set_dma_mask,
-	.mmap = xen_swiotlb_dma_mmap,
-	.get_sgtable = xen_swiotlb_get_sgtable,
-};
-
 int __init xen_mm_init(void)
 {
 	struct gnttab_cache_flush cflush;
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index f72779a..0df756b 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -24,7 +24,6 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern const struct dma_map_ops dummy_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 3e340b6..e90cd1d 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -175,7 +175,6 @@ static void *__dma_alloc(struct device *dev, size_t size,
 no_map:
 	__dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
 no_mem:
-	*dma_handle = DMA_ERROR_CODE;
 	return NULL;
 }
 
@@ -478,7 +477,7 @@ static dma_addr_t __dummy_map_page(struct device *dev, struct page *page,
 				   enum dma_data_direction dir,
 				   unsigned long attrs)
 {
-	return DMA_ERROR_CODE;
+	return 0;
 }
 
 static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr,
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index 3c1bd64..89bdb82 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -41,6 +41,7 @@ config BLACKFIN
 	select MODULES_USE_ELF_RELA
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_NMI
+	select ARCH_NO_COHERENT_DMA_MMAP
 
 config GENERIC_CSUM
 	def_bool y
diff --git a/arch/c6x/include/asm/dma-mapping.h b/arch/c6x/include/asm/dma-mapping.h
index aca9f75..05daf10 100644
--- a/arch/c6x/include/asm/dma-mapping.h
+++ b/arch/c6x/include/asm/dma-mapping.h
@@ -12,11 +12,6 @@
 #ifndef _ASM_C6X_DMA_MAPPING_H
 #define _ASM_C6X_DMA_MAPPING_H
 
-/*
- * DMA errors are defined by all-bits-set in the DMA address.
- */
-#define DMA_ERROR_CODE ~0
-
 extern const struct dma_map_ops c6x_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/arch/hexagon/include/asm/dma-mapping.h b/arch/hexagon/include/asm/dma-mapping.h
index d3a87bd..463dbc1 100644
--- a/arch/hexagon/include/asm/dma-mapping.h
+++ b/arch/hexagon/include/asm/dma-mapping.h
@@ -29,8 +29,6 @@
 #include <asm/io.h>
 
 struct device;
-extern int bad_dma_address;
-#define DMA_ERROR_CODE bad_dma_address
 
 extern const struct dma_map_ops *dma_ops;
 
@@ -39,9 +37,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return dma_ops;
 }
 
-#define HAVE_ARCH_DMA_SUPPORTED 1
-extern int dma_supported(struct device *dev, u64 mask);
-extern int dma_is_consistent(struct device *dev, dma_addr_t dma_handle);
 extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 			   enum dma_data_direction direction);
 
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index e74b650..546792d 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -25,25 +25,16 @@
 #include <linux/module.h>
 #include <asm/page.h>
 
+#define HEXAGON_MAPPING_ERROR	0
+
 const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-int bad_dma_address;  /*  globals are automatically initialized to zero  */
-
 static inline void *dma_addr_to_virt(dma_addr_t dma_addr)
 {
 	return phys_to_virt((unsigned long) dma_addr);
 }
 
-int dma_supported(struct device *dev, u64 mask)
-{
-	if (mask == DMA_BIT_MASK(32))
-		return 1;
-	else
-		return 0;
-}
-EXPORT_SYMBOL(dma_supported);
-
 static struct gen_pool *coherent_pool;
 
 
@@ -181,7 +172,7 @@ static dma_addr_t hexagon_map_page(struct device *dev, struct page *page,
 	WARN_ON(size == 0);
 
 	if (!check_addr("map_single", dev, bus, size))
-		return bad_dma_address;
+		return HEXAGON_MAPPING_ERROR;
 
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		dma_sync(dma_addr_to_virt(bus), size, dir);
@@ -203,6 +194,11 @@ static void hexagon_sync_single_for_device(struct device *dev,
 	dma_sync(dma_addr_to_virt(dma_handle), size, dir);
 }
 
+static int hexagon_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == HEXAGON_MAPPING_ERROR;
+}
+
 const struct dma_map_ops hexagon_dma_ops = {
 	.alloc		= hexagon_dma_alloc_coherent,
 	.free		= hexagon_free_coherent,
@@ -210,6 +206,7 @@ const struct dma_map_ops hexagon_dma_ops = {
 	.map_page	= hexagon_map_page,
 	.sync_single_for_cpu = hexagon_sync_single_for_cpu,
 	.sync_single_for_device = hexagon_sync_single_for_device,
+	.mapping_error	= hexagon_mapping_error,
 	.is_phys	= 1,
 };
 
diff --git a/arch/hexagon/kernel/hexagon_ksyms.c b/arch/hexagon/kernel/hexagon_ksyms.c
index 00bcad9..aa248f5 100644
--- a/arch/hexagon/kernel/hexagon_ksyms.c
+++ b/arch/hexagon/kernel/hexagon_ksyms.c
@@ -40,7 +40,6 @@ EXPORT_SYMBOL(memset);
 /* Additional variables */
 EXPORT_SYMBOL(__phys_offset);
 EXPORT_SYMBOL(_dflt_cache_att);
-EXPORT_SYMBOL(bad_dma_address);
 
 #define DECLARE_EXPORT(name)     \
 	extern void name(void); EXPORT_SYMBOL(name)
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 73ec3c6..3ce5ab4 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -12,8 +12,6 @@
 
 #define ARCH_HAS_DMA_GET_REQUIRED_MASK
 
-#define DMA_ERROR_CODE 0
-
 extern const struct dma_map_ops *dma_ops;
 extern struct ia64_machine_vector ia64_mv;
 extern void set_iommu_machvec(void);
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 9547446..87cde1e 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -19,6 +19,7 @@ config M32R
 	select HAVE_DEBUG_STACKOVERFLOW
 	select CPU_NO_EFFICIENT_FFS
 	select DMA_NOOP_OPS
+	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 
 config SBUS
 	bool
diff --git a/arch/m32r/include/asm/dma-mapping.h b/arch/m32r/include/asm/dma-mapping.h
index c01d9f5..aff3ae8 100644
--- a/arch/m32r/include/asm/dma-mapping.h
+++ b/arch/m32r/include/asm/dma-mapping.h
@@ -8,8 +8,6 @@
 #include <linux/dma-debug.h>
 #include <linux/io.h>
 
-#define DMA_ERROR_CODE (~(dma_addr_t)0x0)
-
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
 	return &dma_noop_ops;
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index d140206..5abb548 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -2,6 +2,7 @@ config M68K
 	bool
 	default y
 	select ARCH_MIGHT_HAVE_PC_PARPORT if ISA
+	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 	select HAVE_IDE
 	select HAVE_AOUT if MMU
 	select HAVE_DEBUG_BUGVERBOSE
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 8e47121..4ed8ebf 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -2,6 +2,7 @@ config MICROBLAZE
 	def_bool y
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select TIMER_OF
diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h
index 3fad5e7..e15cd2f 100644
--- a/arch/microblaze/include/asm/dma-mapping.h
+++ b/arch/microblaze/include/asm/dma-mapping.h
@@ -28,8 +28,6 @@
 #include <asm/io.h>
 #include <asm/cacheflush.h>
 
-#define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
-
 #define __dma_alloc_coherent(dev, gfp, size, handle)	NULL
 #define __dma_free_coherent(size, addr)		((void)0)
 
diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
index 178ca17..34486c1 100644
--- a/arch/mips/loongson64/common/dma-swiotlb.c
+++ b/arch/mips/loongson64/common/dma-swiotlb.c
@@ -75,19 +75,11 @@ static void loongson_dma_sync_sg_for_device(struct device *dev,
 	mb();
 }
 
-static int loongson_dma_set_mask(struct device *dev, u64 mask)
+static int loongson_dma_supported(struct device *dev, u64 mask)
 {
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	if (mask > DMA_BIT_MASK(loongson_sysconf.dma_mask_bits)) {
-		*dev->dma_mask = DMA_BIT_MASK(loongson_sysconf.dma_mask_bits);
-		return -EIO;
-	}
-
-	*dev->dma_mask = mask;
-
-	return 0;
+	if (mask > DMA_BIT_MASK(loongson_sysconf.dma_mask_bits))
+		return 0;
+	return swiotlb_dma_supported(dev, mask);
 }
 
 dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
@@ -126,8 +118,7 @@ static const struct dma_map_ops loongson_dma_map_ops = {
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
 	.sync_sg_for_device = loongson_dma_sync_sg_for_device,
 	.mapping_error = swiotlb_dma_mapping_error,
-	.dma_supported = swiotlb_dma_supported,
-	.set_dma_mask = loongson_dma_set_mask
+	.dma_supported = loongson_dma_supported,
 };
 
 void __init plat_swiotlb_setup(void)
diff --git a/arch/openrisc/include/asm/dma-mapping.h b/arch/openrisc/include/asm/dma-mapping.h
index 0c0075f..f41bd3c 100644
--- a/arch/openrisc/include/asm/dma-mapping.h
+++ b/arch/openrisc/include/asm/dma-mapping.h
@@ -26,8 +26,6 @@
 #include <linux/kmemcheck.h>
 #include <linux/dma-mapping.h>
 
-#define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
-
 extern const struct dma_map_ops or1k_dma_map_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
@@ -35,11 +33,4 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return &or1k_dma_map_ops;
 }
 
-#define HAVE_ARCH_DMA_SUPPORTED 1
-static inline int dma_supported(struct device *dev, u64 dma_mask)
-{
-	/* Support 32 bit DMA mask exclusively */
-	return dma_mask == DMA_BIT_MASK(32);
-}
-
 #endif	/* __ASM_OPENRISC_DMA_MAPPING_H */
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 181a095..eaece3d 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -17,10 +17,6 @@
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 
-#ifdef CONFIG_PPC64
-#define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
-#endif
-
 /* Some dma direct funcs must be visible for use in other dma_ops */
 extern void *__dma_direct_alloc_coherent(struct device *dev, size_t size,
 					 dma_addr_t *dma_handle, gfp_t flag,
@@ -116,7 +112,6 @@ static inline void set_dma_offset(struct device *dev, dma_addr_t off)
 #define HAVE_ARCH_DMA_SET_MASK 1
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
 
-extern int __dma_set_mask(struct device *dev, u64 dma_mask);
 extern u64 __dma_get_required_mask(struct device *dev);
 
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 8a8ce22..20febe0 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -139,6 +139,8 @@ struct scatterlist;
 
 #ifdef CONFIG_PPC64
 
+#define IOMMU_MAPPING_ERROR		(~(dma_addr_t)0x0)
+
 static inline void set_iommu_table_base(struct device *dev,
 					struct iommu_table *base)
 {
@@ -238,6 +240,8 @@ static inline int __init tce_iommu_bus_notifier_init(void)
 }
 #endif /* !CONFIG_IOMMU_API */
 
+int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr);
+
 #else
 
 static inline void *get_iommu_table_base(struct device *dev)
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index fb7cbaa..8f7abf9 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -105,6 +105,11 @@ static u64 dma_iommu_get_required_mask(struct device *dev)
 	return mask;
 }
 
+int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == IOMMU_MAPPING_ERROR;
+}
+
 struct dma_map_ops dma_iommu_ops = {
 	.alloc			= dma_iommu_alloc_coherent,
 	.free			= dma_iommu_free_coherent,
@@ -115,5 +120,6 @@ struct dma_map_ops dma_iommu_ops = {
 	.map_page		= dma_iommu_map_page,
 	.unmap_page		= dma_iommu_unmap_page,
 	.get_required_mask	= dma_iommu_get_required_mask,
+	.mapping_error		= dma_iommu_mapping_error,
 };
 EXPORT_SYMBOL(dma_iommu_ops);
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 41c7495..4194bbb 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -314,18 +314,6 @@ EXPORT_SYMBOL(dma_set_coherent_mask);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
 
-int __dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	const struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL))
-		return dma_ops->set_dma_mask(dev, dma_mask);
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
-
 int dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	if (ppc_md.dma_set_mask)
@@ -338,7 +326,10 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 			return phb->controller_ops.dma_set_mask(pdev, dma_mask);
 	}
 
-	return __dma_set_mask(dev, dma_mask);
+	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
+		return -EIO;
+	*dev->dma_mask = dma_mask;
+	return 0;
 }
 EXPORT_SYMBOL(dma_set_mask);
 
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index f2b724c..233ca3f 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -198,11 +198,11 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	if (unlikely(npages == 0)) {
 		if (printk_ratelimit())
 			WARN_ON(1);
-		return DMA_ERROR_CODE;
+		return IOMMU_MAPPING_ERROR;
 	}
 
 	if (should_fail_iommu(dev))
-		return DMA_ERROR_CODE;
+		return IOMMU_MAPPING_ERROR;
 
 	/*
 	 * We don't need to disable preemption here because any CPU can
@@ -278,7 +278,7 @@ again:
 		} else {
 			/* Give up */
 			spin_unlock_irqrestore(&(pool->lock), flags);
-			return DMA_ERROR_CODE;
+			return IOMMU_MAPPING_ERROR;
 		}
 	}
 
@@ -310,13 +310,13 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 			      unsigned long attrs)
 {
 	unsigned long entry;
-	dma_addr_t ret = DMA_ERROR_CODE;
+	dma_addr_t ret = IOMMU_MAPPING_ERROR;
 	int build_fail;
 
 	entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order);
 
-	if (unlikely(entry == DMA_ERROR_CODE))
-		return DMA_ERROR_CODE;
+	if (unlikely(entry == IOMMU_MAPPING_ERROR))
+		return IOMMU_MAPPING_ERROR;
 
 	entry += tbl->it_offset;	/* Offset into real TCE table */
 	ret = entry << tbl->it_page_shift;	/* Set the return dma address */
@@ -328,12 +328,12 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 
 	/* tbl->it_ops->set() only returns non-zero for transient errors.
 	 * Clean up the table bitmap in this case and return
-	 * DMA_ERROR_CODE. For all other errors the functionality is
+	 * IOMMU_MAPPING_ERROR. For all other errors the functionality is
 	 * not altered.
 	 */
 	if (unlikely(build_fail)) {
 		__iommu_free(tbl, ret, npages);
-		return DMA_ERROR_CODE;
+		return IOMMU_MAPPING_ERROR;
 	}
 
 	/* Flush/invalidate TLB caches if necessary */
@@ -478,7 +478,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
 		/* Handle failure */
-		if (unlikely(entry == DMA_ERROR_CODE)) {
+		if (unlikely(entry == IOMMU_MAPPING_ERROR)) {
 			if (!(attrs & DMA_ATTR_NO_WARN) &&
 			    printk_ratelimit())
 				dev_info(dev, "iommu_alloc failed, tbl %p "
@@ -545,7 +545,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 	 */
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = DMA_ERROR_CODE;
+		outs->dma_address = IOMMU_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
@@ -563,7 +563,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
 						 IOMMU_PAGE_SIZE(tbl));
 			__iommu_free(tbl, vaddr, npages);
-			s->dma_address = DMA_ERROR_CODE;
+			s->dma_address = IOMMU_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
@@ -777,7 +777,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 			  unsigned long mask, enum dma_data_direction direction,
 			  unsigned long attrs)
 {
-	dma_addr_t dma_handle = DMA_ERROR_CODE;
+	dma_addr_t dma_handle = IOMMU_MAPPING_ERROR;
 	void *vaddr;
 	unsigned long uaddr;
 	unsigned int npages, align;
@@ -797,7 +797,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
 					 mask >> tbl->it_page_shift, align,
 					 attrs);
-		if (dma_handle == DMA_ERROR_CODE) {
+		if (dma_handle == IOMMU_MAPPING_ERROR) {
 			if (!(attrs & DMA_ATTR_NO_WARN) &&
 			    printk_ratelimit())  {
 				dev_info(dev, "iommu_alloc failed, tbl %p "
@@ -869,7 +869,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
 			      mask >> tbl->it_page_shift, io_order, 0);
-	if (mapping == DMA_ERROR_CODE) {
+	if (mapping == IOMMU_MAPPING_ERROR) {
 		free_pages((unsigned long)ret, order);
 		return NULL;
 	}
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 71b995bb..29d4f96 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -644,32 +644,22 @@ static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg,
 				   direction, attrs);
 }
 
-static int dma_fixed_dma_supported(struct device *dev, u64 mask)
-{
-	return mask == DMA_BIT_MASK(64);
-}
-
-static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask);
+static int dma_suported_and_switch(struct device *dev, u64 dma_mask);
 
 static const struct dma_map_ops dma_iommu_fixed_ops = {
 	.alloc          = dma_fixed_alloc_coherent,
 	.free           = dma_fixed_free_coherent,
 	.map_sg         = dma_fixed_map_sg,
 	.unmap_sg       = dma_fixed_unmap_sg,
-	.dma_supported  = dma_fixed_dma_supported,
-	.set_dma_mask   = dma_set_mask_and_switch,
+	.dma_supported  = dma_suported_and_switch,
 	.map_page       = dma_fixed_map_page,
 	.unmap_page     = dma_fixed_unmap_page,
+	.mapping_error	= dma_iommu_mapping_error,
 };
 
-static void cell_dma_dev_setup_fixed(struct device *dev);
-
 static void cell_dma_dev_setup(struct device *dev)
 {
-	/* Order is important here, these are not mutually exclusive */
-	if (get_dma_ops(dev) == &dma_iommu_fixed_ops)
-		cell_dma_dev_setup_fixed(dev);
-	else if (get_pci_dma_ops() == &dma_iommu_ops)
+	if (get_pci_dma_ops() == &dma_iommu_ops)
 		set_iommu_table_base(dev, cell_get_iommu_table(dev));
 	else if (get_pci_dma_ops() == &dma_direct_ops)
 		set_dma_offset(dev, cell_dma_direct_offset);
@@ -956,38 +946,29 @@ out:
 	return dev_addr;
 }
 
-static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask)
+static int dma_suported_and_switch(struct device *dev, u64 dma_mask)
 {
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
 	if (dma_mask == DMA_BIT_MASK(64) &&
-		cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR)
-	{
+	    cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR) {
+		u64 addr = cell_iommu_get_fixed_address(dev) +
+			dma_iommu_fixed_base;
 		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
+		dev_dbg(dev, "iommu: fixed addr = %llx\n", addr);
 		set_dma_ops(dev, &dma_iommu_fixed_ops);
-	} else {
+		set_dma_offset(dev, addr);
+		return 1;
+	}
+
+	if (dma_iommu_dma_supported(dev, dma_mask)) {
 		dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
 		set_dma_ops(dev, get_pci_dma_ops());
+		cell_dma_dev_setup(dev);
+		return 1;
 	}
 
-	cell_dma_dev_setup(dev);
-
-	*dev->dma_mask = dma_mask;
-
 	return 0;
 }
 
-static void cell_dma_dev_setup_fixed(struct device *dev)
-{
-	u64 addr;
-
-	addr = cell_iommu_get_fixed_address(dev) + dma_iommu_fixed_base;
-	set_dma_offset(dev, addr);
-
-	dev_dbg(dev, "iommu: fixed addr = %llx\n", addr);
-}
-
 static void insert_16M_pte(unsigned long addr, unsigned long *ptab,
 			   unsigned long base_pte)
 {
@@ -1139,7 +1120,7 @@ static int __init cell_iommu_fixed_mapping_init(void)
 		cell_iommu_setup_window(iommu, np, dbase, dsize, 0);
 	}
 
-	dma_iommu_ops.set_dma_mask = dma_set_mask_and_switch;
+	dma_iommu_ops.dma_supported = dma_suported_and_switch;
 	set_pci_dma_ops(&dma_iommu_ops);
 
 	return 0;
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 117beb9..8a47f16 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -519,7 +519,7 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct iommu_table *tbl;
-	dma_addr_t ret = DMA_ERROR_CODE;
+	dma_addr_t ret = IOMMU_MAPPING_ERROR;
 
 	tbl = get_iommu_table_base(dev);
 	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) {
@@ -625,6 +625,7 @@ static const struct dma_map_ops vio_dma_mapping_ops = {
 	.unmap_page        = vio_dma_iommu_unmap_page,
 	.dma_supported     = vio_dma_iommu_dma_supported,
 	.get_required_mask = vio_dma_get_required_mask,
+	.mapping_error	   = dma_iommu_mapping_error,
 };
 
 /**
diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
index 3108b8d..512ad0e 100644
--- a/arch/s390/include/asm/dma-mapping.h
+++ b/arch/s390/include/asm/dma-mapping.h
@@ -8,8 +8,6 @@
 #include <linux/dma-debug.h>
 #include <linux/io.h>
 
-#define DMA_ERROR_CODE		(~(dma_addr_t) 0x0)
-
 extern const struct dma_map_ops s390_pci_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 8eb1cc3..0d300ee 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -14,6 +14,8 @@
 #include <linux/pci.h>
 #include <asm/pci_dma.h>
 
+#define S390_MAPPING_ERROR		(~(dma_addr_t) 0x0)
+
 static struct kmem_cache *dma_region_table_cache;
 static struct kmem_cache *dma_page_table_cache;
 static int s390_iommu_strict;
@@ -281,7 +283,7 @@ static dma_addr_t dma_alloc_address(struct device *dev, int size)
 
 out_error:
 	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
-	return DMA_ERROR_CODE;
+	return S390_MAPPING_ERROR;
 }
 
 static void dma_free_address(struct device *dev, dma_addr_t dma_addr, int size)
@@ -329,7 +331,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
 	/* This rounds up number of pages based on size and offset */
 	nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
 	dma_addr = dma_alloc_address(dev, nr_pages);
-	if (dma_addr == DMA_ERROR_CODE) {
+	if (dma_addr == S390_MAPPING_ERROR) {
 		ret = -ENOSPC;
 		goto out_err;
 	}
@@ -352,7 +354,7 @@ out_free:
 out_err:
 	zpci_err("map error:\n");
 	zpci_err_dma(ret, pa);
-	return DMA_ERROR_CODE;
+	return S390_MAPPING_ERROR;
 }
 
 static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
@@ -429,7 +431,7 @@ static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	int ret;
 
 	dma_addr_base = dma_alloc_address(dev, nr_pages);
-	if (dma_addr_base == DMA_ERROR_CODE)
+	if (dma_addr_base == S390_MAPPING_ERROR)
 		return -ENOMEM;
 
 	dma_addr = dma_addr_base;
@@ -476,7 +478,7 @@ static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	for (i = 1; i < nr_elements; i++) {
 		s = sg_next(s);
 
-		s->dma_address = DMA_ERROR_CODE;
+		s->dma_address = S390_MAPPING_ERROR;
 		s->dma_length = 0;
 
 		if (s->offset || (size & ~PAGE_MASK) ||
@@ -525,6 +527,11 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 		s->dma_length = 0;
 	}
 }
+	
+static int s390_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == S390_MAPPING_ERROR;
+}
 
 int zpci_dma_init_device(struct zpci_dev *zdev)
 {
@@ -659,6 +666,7 @@ const struct dma_map_ops s390_pci_dma_ops = {
 	.unmap_sg	= s390_dma_unmap_sg,
 	.map_page	= s390_dma_map_pages,
 	.unmap_page	= s390_dma_unmap_pages,
+	.mapping_error	= s390_mapping_error,
 	/* if we support direct DMA this must be conditional */
 	.is_phys	= 0,
 	/* dma_supported is unconditionally true without a callback */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index ee08695..640a859 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -2,6 +2,7 @@ config SUPERH
 	def_bool y
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 	select HAVE_PATA_PLATFORM
 	select CLKDEV_LOOKUP
 	select HAVE_IDE if HAS_IOPORT_MAP
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
index d99008af..9b06be0 100644
--- a/arch/sh/include/asm/dma-mapping.h
+++ b/arch/sh/include/asm/dma-mapping.h
@@ -9,8 +9,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return dma_ops;
 }
 
-#define DMA_ERROR_CODE 0
-
 void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		    enum dma_data_direction dir);
 
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 69cc627..60bf163 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -5,11 +5,6 @@
 #include <linux/mm.h>
 #include <linux/dma-debug.h>
 
-#define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
-
-#define HAVE_ARCH_DMA_SUPPORTED 1
-int dma_supported(struct device *dev, u64 mask);
-
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 				  enum dma_data_direction dir)
 {
@@ -19,7 +14,6 @@ static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 }
 
 extern const struct dma_map_ops *dma_ops;
-extern const struct dma_map_ops *leon_dma_ops;
 extern const struct dma_map_ops pci32_dma_ops;
 
 extern struct bus_type pci_bus_type;
@@ -28,7 +22,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
 #ifdef CONFIG_SPARC_LEON
 	if (sparc_cpu_model == sparc_leon)
-		return leon_dma_ops;
+		return &pci32_dma_ops;
 #endif
 #if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
 	if (bus == &pci_bus_type)
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index c63ba99..fcbcc031 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -314,7 +314,7 @@ bad:
 bad_no_ctx:
 	if (printk_ratelimit())
 		WARN_ON(1);
-	return DMA_ERROR_CODE;
+	return SPARC_MAPPING_ERROR;
 }
 
 static void strbuf_flush(struct strbuf *strbuf, struct iommu *iommu,
@@ -547,7 +547,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = DMA_ERROR_CODE;
+		outs->dma_address = SPARC_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
@@ -573,7 +573,7 @@ iommu_map_failed:
 			iommu_tbl_range_free(&iommu->tbl, vaddr, npages,
 					     IOMMU_ERROR_CODE);
 
-			s->dma_address = DMA_ERROR_CODE;
+			s->dma_address = SPARC_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
@@ -741,6 +741,26 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
+static int dma_4u_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == SPARC_MAPPING_ERROR;
+}
+
+static int dma_4u_supported(struct device *dev, u64 device_mask)
+{
+	struct iommu *iommu = dev->archdata.iommu;
+
+	if (device_mask > DMA_BIT_MASK(32))
+		return 0;
+	if ((device_mask & iommu->dma_addr_mask) == iommu->dma_addr_mask)
+		return 1;
+#ifdef CONFIG_PCI
+	if (dev_is_pci(dev))
+		return pci64_dma_supported(to_pci_dev(dev), device_mask);
+#endif
+	return 0;
+}
+
 static const struct dma_map_ops sun4u_dma_ops = {
 	.alloc			= dma_4u_alloc_coherent,
 	.free			= dma_4u_free_coherent,
@@ -750,31 +770,9 @@ static const struct dma_map_ops sun4u_dma_ops = {
 	.unmap_sg		= dma_4u_unmap_sg,
 	.sync_single_for_cpu	= dma_4u_sync_single_for_cpu,
 	.sync_sg_for_cpu	= dma_4u_sync_sg_for_cpu,
+	.dma_supported		= dma_4u_supported,
+	.mapping_error		= dma_4u_mapping_error,
 };
 
 const struct dma_map_ops *dma_ops = &sun4u_dma_ops;
 EXPORT_SYMBOL(dma_ops);
-
-int dma_supported(struct device *dev, u64 device_mask)
-{
-	struct iommu *iommu = dev->archdata.iommu;
-	u64 dma_addr_mask = iommu->dma_addr_mask;
-
-	if (device_mask > DMA_BIT_MASK(32)) {
-		if (iommu->atu)
-			dma_addr_mask = iommu->atu->dma_addr_mask;
-		else
-			return 0;
-	}
-
-	if ((device_mask & dma_addr_mask) == dma_addr_mask)
-		return 1;
-
-#ifdef CONFIG_PCI
-	if (dev_is_pci(dev))
-		return pci64_dma_supported(to_pci_dev(dev), device_mask);
-#endif
-
-	return 0;
-}
-EXPORT_SYMBOL(dma_supported);
diff --git a/arch/sparc/kernel/iommu_common.h b/arch/sparc/kernel/iommu_common.h
index 8284933..5ea5c19 100644
--- a/arch/sparc/kernel/iommu_common.h
+++ b/arch/sparc/kernel/iommu_common.h
@@ -47,4 +47,6 @@ static inline int is_span_boundary(unsigned long entry,
 	return iommu_is_span_boundary(entry, nr, shift, boundary_size);
 }
 
+#define SPARC_MAPPING_ERROR	(~(dma_addr_t)0x0)
+
 #endif /* _IOMMU_COMMON_H */
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index cf20033..12894f2 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -401,6 +401,11 @@ static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	BUG();
 }
 
+static int sbus_dma_supported(struct device *dev, u64 mask)
+{
+	return 0;
+}
+
 static const struct dma_map_ops sbus_dma_ops = {
 	.alloc			= sbus_alloc_coherent,
 	.free			= sbus_free_coherent,
@@ -410,6 +415,7 @@ static const struct dma_map_ops sbus_dma_ops = {
 	.unmap_sg		= sbus_unmap_sg,
 	.sync_sg_for_cpu	= sbus_sync_sg_for_cpu,
 	.sync_sg_for_device	= sbus_sync_sg_for_device,
+	.dma_supported		= sbus_dma_supported,
 };
 
 static int __init sparc_register_ioport(void)
@@ -637,6 +643,7 @@ static void pci32_sync_sg_for_device(struct device *device, struct scatterlist *
 	}
 }
 
+/* note: leon re-uses pci32_dma_ops */
 const struct dma_map_ops pci32_dma_ops = {
 	.alloc			= pci32_alloc_coherent,
 	.free			= pci32_free_coherent,
@@ -651,29 +658,9 @@ const struct dma_map_ops pci32_dma_ops = {
 };
 EXPORT_SYMBOL(pci32_dma_ops);
 
-/* leon re-uses pci32_dma_ops */
-const struct dma_map_ops *leon_dma_ops = &pci32_dma_ops;
-EXPORT_SYMBOL(leon_dma_ops);
-
 const struct dma_map_ops *dma_ops = &sbus_dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-
-/*
- * Return whether the given PCI device DMA address mask can be
- * supported properly.  For example, if your device can only drive the
- * low 24-bits during PCI bus mastering, then you would pass
- * 0x00ffffff as the mask to this function.
- */
-int dma_supported(struct device *dev, u64 mask)
-{
-	if (dev_is_pci(dev))
-		return 1;
-
-	return 0;
-}
-EXPORT_SYMBOL(dma_supported);
-
 #ifdef CONFIG_PROC_FS
 
 static int sparc_io_proc_show(struct seq_file *m, void *v)
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 68bec7c..24f21c7 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -24,6 +24,7 @@
 
 #include "pci_impl.h"
 #include "iommu_common.h"
+#include "kernel.h"
 
 #include "pci_sun4v.h"
 
@@ -412,12 +413,12 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 bad:
 	if (printk_ratelimit())
 		WARN_ON(1);
-	return DMA_ERROR_CODE;
+	return SPARC_MAPPING_ERROR;
 
 iommu_map_fail:
 	local_irq_restore(flags);
 	iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE);
-	return DMA_ERROR_CODE;
+	return SPARC_MAPPING_ERROR;
 }
 
 static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
@@ -590,7 +591,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = DMA_ERROR_CODE;
+		outs->dma_address = SPARC_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
@@ -607,7 +608,7 @@ iommu_map_failed:
 			iommu_tbl_range_free(tbl, vaddr, npages,
 					     IOMMU_ERROR_CODE);
 			/* XXX demap? XXX */
-			s->dma_address = DMA_ERROR_CODE;
+			s->dma_address = SPARC_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
@@ -669,6 +670,26 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	local_irq_restore(flags);
 }
 
+static int dma_4v_supported(struct device *dev, u64 device_mask)
+{
+	struct iommu *iommu = dev->archdata.iommu;
+	u64 dma_addr_mask;
+
+	if (device_mask > DMA_BIT_MASK(32) && iommu->atu)
+		dma_addr_mask = iommu->atu->dma_addr_mask;
+	else
+		dma_addr_mask = iommu->dma_addr_mask;
+
+	if ((device_mask & dma_addr_mask) == dma_addr_mask)
+		return 1;
+	return pci64_dma_supported(to_pci_dev(dev), device_mask);
+}
+
+static int dma_4v_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == SPARC_MAPPING_ERROR;
+}
+
 static const struct dma_map_ops sun4v_dma_ops = {
 	.alloc				= dma_4v_alloc_coherent,
 	.free				= dma_4v_free_coherent,
@@ -676,6 +697,8 @@ static const struct dma_map_ops sun4v_dma_ops = {
 	.unmap_page			= dma_4v_unmap_page,
 	.map_sg				= dma_4v_map_sg,
 	.unmap_sg			= dma_4v_unmap_sg,
+	.dma_supported			= dma_4v_supported,
+	.mapping_error			= dma_4v_mapping_error,
 };
 
 static void pci_sun4v_scan_bus(struct pci_pbm_info *pbm, struct device *parent)
diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c
index 569bb6d..f2abedc 100644
--- a/arch/tile/kernel/pci-dma.c
+++ b/arch/tile/kernel/pci-dma.c
@@ -317,18 +317,6 @@ static void tile_dma_sync_sg_for_device(struct device *dev,
 	}
 }
 
-static inline int
-tile_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-static inline int
-tile_dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
 static const struct dma_map_ops tile_default_dma_map_ops = {
 	.alloc = tile_dma_alloc_coherent,
 	.free = tile_dma_free_coherent,
@@ -340,8 +328,6 @@ static const struct dma_map_ops tile_default_dma_map_ops = {
 	.sync_single_for_device = tile_dma_sync_single_for_device,
 	.sync_sg_for_cpu = tile_dma_sync_sg_for_cpu,
 	.sync_sg_for_device = tile_dma_sync_sg_for_device,
-	.mapping_error = tile_dma_mapping_error,
-	.dma_supported = tile_dma_supported
 };
 
 const struct dma_map_ops *tile_dma_map_ops = &tile_default_dma_map_ops;
@@ -504,18 +490,6 @@ static void tile_pci_dma_sync_sg_for_device(struct device *dev,
 	}
 }
 
-static inline int
-tile_pci_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-static inline int
-tile_pci_dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
 static const struct dma_map_ops tile_pci_default_dma_map_ops = {
 	.alloc = tile_pci_dma_alloc_coherent,
 	.free = tile_pci_dma_free_coherent,
@@ -527,8 +501,6 @@ static const struct dma_map_ops tile_pci_default_dma_map_ops = {
 	.sync_single_for_device = tile_pci_dma_sync_single_for_device,
 	.sync_sg_for_cpu = tile_pci_dma_sync_sg_for_cpu,
 	.sync_sg_for_device = tile_pci_dma_sync_sg_for_device,
-	.mapping_error = tile_pci_dma_mapping_error,
-	.dma_supported = tile_pci_dma_supported
 };
 
 const struct dma_map_ops *gx_pci_dma_map_ops = &tile_pci_default_dma_map_ops;
@@ -578,8 +550,6 @@ static const struct dma_map_ops pci_hybrid_dma_ops = {
 	.sync_single_for_device = tile_pci_dma_sync_single_for_device,
 	.sync_sg_for_cpu = tile_pci_dma_sync_sg_for_cpu,
 	.sync_sg_for_device = tile_pci_dma_sync_sg_for_device,
-	.mapping_error = tile_pci_dma_mapping_error,
-	.dma_supported = tile_pci_dma_supported
 };
 
 const struct dma_map_ops *gx_legacy_pci_dma_map_ops = &pci_swiotlb_dma_ops;
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 08a0838..398c798 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -19,8 +19,6 @@
 # define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
 #endif
 
-#define DMA_ERROR_CODE	0
-
 extern int iommu_merge;
 extern struct device x86_dma_fallback_dev;
 extern int panic_on_overflow;
@@ -35,9 +33,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp);
 #define arch_dma_alloc_attrs arch_dma_alloc_attrs
 
-#define HAVE_ARCH_DMA_SUPPORTED 1
-extern int dma_supported(struct device *hwdev, u64 mask);
-
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_addr, gfp_t flag,
 					unsigned long attrs);
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 7938698..fca144a 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -6,6 +6,8 @@ extern int force_iommu, no_iommu;
 extern int iommu_detected;
 extern int iommu_pass_through;
 
+int x86_dma_supported(struct device *dev, u64 mask);
+
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 815dd63..cc0e8bc 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -704,6 +704,7 @@ static const struct dma_map_ops gart_dma_ops = {
 	.alloc				= gart_alloc_coherent,
 	.free				= gart_free_coherent,
 	.mapping_error			= gart_mapping_error,
+	.dma_supported			= x86_dma_supported,
 };
 
 static void gart_iommu_shutdown(void)
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index fda7867..5286a4a 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -50,6 +50,8 @@
 #include <asm/x86_init.h>
 #include <asm/iommu_table.h>
 
+#define CALGARY_MAPPING_ERROR	0
+
 #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
 int use_calgary __read_mostly = 1;
 #else
@@ -252,7 +254,7 @@ static unsigned long iommu_range_alloc(struct device *dev,
 			if (panic_on_overflow)
 				panic("Calgary: fix the allocator.\n");
 			else
-				return DMA_ERROR_CODE;
+				return CALGARY_MAPPING_ERROR;
 		}
 	}
 
@@ -272,10 +274,10 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 
 	entry = iommu_range_alloc(dev, tbl, npages);
 
-	if (unlikely(entry == DMA_ERROR_CODE)) {
+	if (unlikely(entry == CALGARY_MAPPING_ERROR)) {
 		pr_warn("failed to allocate %u pages in iommu %p\n",
 			npages, tbl);
-		return DMA_ERROR_CODE;
+		return CALGARY_MAPPING_ERROR;
 	}
 
 	/* set the return dma address */
@@ -295,7 +297,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	unsigned long flags;
 
 	/* were we called with bad_dma_address? */
-	badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE);
+	badend = CALGARY_MAPPING_ERROR + (EMERGENCY_PAGES * PAGE_SIZE);
 	if (unlikely(dma_addr < badend)) {
 		WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
 		       "address 0x%Lx\n", dma_addr);
@@ -380,7 +382,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 		npages = iommu_num_pages(vaddr, s->length, PAGE_SIZE);
 
 		entry = iommu_range_alloc(dev, tbl, npages);
-		if (entry == DMA_ERROR_CODE) {
+		if (entry == CALGARY_MAPPING_ERROR) {
 			/* makes sure unmap knows to stop */
 			s->dma_length = 0;
 			goto error;
@@ -398,7 +400,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 error:
 	calgary_unmap_sg(dev, sg, nelems, dir, 0);
 	for_each_sg(sg, s, nelems, i) {
-		sg->dma_address = DMA_ERROR_CODE;
+		sg->dma_address = CALGARY_MAPPING_ERROR;
 		sg->dma_length = 0;
 	}
 	return 0;
@@ -453,7 +455,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
 
 	/* set up tces to cover the allocated range */
 	mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
-	if (mapping == DMA_ERROR_CODE)
+	if (mapping == CALGARY_MAPPING_ERROR)
 		goto free;
 	*dma_handle = mapping;
 	return ret;
@@ -478,6 +480,11 @@ static void calgary_free_coherent(struct device *dev, size_t size,
 	free_pages((unsigned long)vaddr, get_order(size));
 }
 
+static int calgary_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == CALGARY_MAPPING_ERROR;
+}
+
 static const struct dma_map_ops calgary_dma_ops = {
 	.alloc = calgary_alloc_coherent,
 	.free = calgary_free_coherent,
@@ -485,6 +492,8 @@ static const struct dma_map_ops calgary_dma_ops = {
 	.unmap_sg = calgary_unmap_sg,
 	.map_page = calgary_map_page,
 	.unmap_page = calgary_unmap_page,
+	.mapping_error = calgary_mapping_error,
+	.dma_supported = x86_dma_supported,
 };
 
 static inline void __iomem * busno_to_bbar(unsigned char num)
@@ -732,7 +741,7 @@ static void __init calgary_reserve_regions(struct pci_dev *dev)
 	struct iommu_table *tbl = pci_iommu(dev->bus);
 
 	/* reserve EMERGENCY_PAGES from bad_dma_address and up */
-	iommu_range_reserve(tbl, DMA_ERROR_CODE, EMERGENCY_PAGES);
+	iommu_range_reserve(tbl, CALGARY_MAPPING_ERROR, EMERGENCY_PAGES);
 
 	/* avoid the BIOS/VGA first 640KB-1MB region */
 	/* for CalIOC2 - avoid the entire first MB */
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 3a216ec..5e16d3f 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -213,10 +213,8 @@ static __init int iommu_setup(char *p)
 }
 early_param("iommu", iommu_setup);
 
-int dma_supported(struct device *dev, u64 mask)
+int x86_dma_supported(struct device *dev, u64 mask)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
 #ifdef CONFIG_PCI
 	if (mask > 0xffffffff && forbid_dac > 0) {
 		dev_info(dev, "PCI: Disallowing DAC for device\n");
@@ -224,9 +222,6 @@ int dma_supported(struct device *dev, u64 mask)
 	}
 #endif
 
-	if (ops->dma_supported)
-		return ops->dma_supported(dev, mask);
-
 	/* Copied from i386. Doesn't make much sense, because it will
 	   only work for pci_alloc_coherent.
 	   The caller just has to use GFP_DMA in this case. */
@@ -252,7 +247,6 @@ int dma_supported(struct device *dev, u64 mask)
 
 	return 1;
 }
-EXPORT_SYMBOL(dma_supported);
 
 static int __init pci_iommu_init(void)
 {
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index a88952e..a6d4040 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -11,6 +11,8 @@
 #include <asm/iommu.h>
 #include <asm/dma.h>
 
+#define NOMMU_MAPPING_ERROR		0
+
 static int
 check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
 {
@@ -33,7 +35,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
 	dma_addr_t bus = page_to_phys(page) + offset;
 	WARN_ON(size == 0);
 	if (!check_addr("map_single", dev, bus, size))
-		return DMA_ERROR_CODE;
+		return NOMMU_MAPPING_ERROR;
 	flush_write_buffers();
 	return bus;
 }
@@ -88,6 +90,11 @@ static void nommu_sync_sg_for_device(struct device *dev,
 	flush_write_buffers();
 }
 
+static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == NOMMU_MAPPING_ERROR;
+}
+
 const struct dma_map_ops nommu_dma_ops = {
 	.alloc			= dma_generic_alloc_coherent,
 	.free			= dma_generic_free_coherent,
@@ -96,4 +103,6 @@ const struct dma_map_ops nommu_dma_ops = {
 	.sync_single_for_device = nommu_sync_single_for_device,
 	.sync_sg_for_device	= nommu_sync_sg_for_device,
 	.is_phys		= 1,
+	.mapping_error		= nommu_mapping_error,
+	.dma_supported		= x86_dma_supported,
 };
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index ec008e8..53d6002 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -26,6 +26,7 @@
 #include <linux/pci_ids.h>
 #include <linux/export.h>
 #include <linux/list.h>
+#include <asm/iommu.h>
 
 #define STA2X11_SWIOTLB_SIZE (4*1024*1024)
 extern int swiotlb_late_init_with_default_size(size_t default_size);
@@ -191,7 +192,7 @@ static const struct dma_map_ops sta2x11_dma_ops = {
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
 	.sync_sg_for_device = swiotlb_sync_sg_for_device,
 	.mapping_error = swiotlb_dma_mapping_error,
-	.dma_supported = NULL, /* FIXME: we should use this instead! */
+	.dma_supported = x86_dma_supported,
 };
 
 /* At setup time, we use our own ops if the device is a ConneXt one */
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 42b08f8..37c6056 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -18,20 +18,6 @@
 
 int xen_swiotlb __read_mostly;
 
-static const struct dma_map_ops xen_swiotlb_dma_ops = {
-	.alloc = xen_swiotlb_alloc_coherent,
-	.free = xen_swiotlb_free_coherent,
-	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
-	.map_sg = xen_swiotlb_map_sg_attrs,
-	.unmap_sg = xen_swiotlb_unmap_sg_attrs,
-	.map_page = xen_swiotlb_map_page,
-	.unmap_page = xen_swiotlb_unmap_page,
-	.dma_supported = xen_swiotlb_dma_supported,
-};
-
 /*
  * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary
  *
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index f4126cf..7ad6d77 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -3,6 +3,7 @@ config ZONE_DMA
 
 config XTENSA
 	def_bool y
+	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index c6140fa..269738d 100644
--- a/arch/xtensa/include/asm/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
@@ -16,8 +16,6 @@
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
 
-#define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
-
 extern const struct dma_map_ops xtensa_dma_map_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c
index 640a7e6..2ae24c2 100644
--- a/drivers/base/dma-coherent.c
+++ b/drivers/base/dma-coherent.c
@@ -16,8 +16,27 @@ struct dma_coherent_mem {
 	int		flags;
 	unsigned long	*bitmap;
 	spinlock_t	spinlock;
+	bool		use_dev_dma_pfn_offset;
 };
 
+static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init;
+
+static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev)
+{
+	if (dev && dev->dma_mem)
+		return dev->dma_mem;
+	return dma_coherent_default_memory;
+}
+
+static inline dma_addr_t dma_get_device_base(struct device *dev,
+					     struct dma_coherent_mem * mem)
+{
+	if (mem->use_dev_dma_pfn_offset)
+		return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
+	else
+		return mem->device_base;
+}
+
 static bool dma_init_coherent_memory(
 	phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags,
 	struct dma_coherent_mem **mem)
@@ -83,6 +102,9 @@ static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
 static int dma_assign_coherent_memory(struct device *dev,
 				      struct dma_coherent_mem *mem)
 {
+	if (!dev)
+		return -ENODEV;
+
 	if (dev->dma_mem)
 		return -EBUSY;
 
@@ -133,7 +155,7 @@ void *dma_mark_declared_memory_occupied(struct device *dev,
 		return ERR_PTR(-EINVAL);
 
 	spin_lock_irqsave(&mem->spinlock, flags);
-	pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+	pos = PFN_DOWN(device_addr - dma_get_device_base(dev, mem));
 	err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
 	spin_unlock_irqrestore(&mem->spinlock, flags);
 
@@ -161,15 +183,12 @@ EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
 int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 				       dma_addr_t *dma_handle, void **ret)
 {
-	struct dma_coherent_mem *mem;
+	struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
 	int order = get_order(size);
 	unsigned long flags;
 	int pageno;
 	int dma_memory_map;
 
-	if (!dev)
-		return 0;
-	mem = dev->dma_mem;
 	if (!mem)
 		return 0;
 
@@ -186,7 +205,7 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 	/*
 	 * Memory was found in the per-device area.
 	 */
-	*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+	*dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT);
 	*ret = mem->virt_base + (pageno << PAGE_SHIFT);
 	dma_memory_map = (mem->flags & DMA_MEMORY_MAP);
 	spin_unlock_irqrestore(&mem->spinlock, flags);
@@ -223,7 +242,7 @@ EXPORT_SYMBOL(dma_alloc_from_coherent);
  */
 int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
 {
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+	struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
 
 	if (mem && vaddr >= mem->virt_base && vaddr <
 		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
@@ -257,7 +276,7 @@ EXPORT_SYMBOL(dma_release_from_coherent);
 int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
 			   void *vaddr, size_t size, int *ret)
 {
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+	struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
 
 	if (mem && vaddr >= mem->virt_base && vaddr + size <=
 		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
@@ -287,6 +306,8 @@ EXPORT_SYMBOL(dma_mmap_from_coherent);
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
 
+static struct reserved_mem *dma_reserved_default_memory __initdata;
+
 static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
 	struct dma_coherent_mem *mem = rmem->priv;
@@ -299,6 +320,7 @@ static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 			&rmem->base, (unsigned long)rmem->size / SZ_1M);
 		return -ENODEV;
 	}
+	mem->use_dev_dma_pfn_offset = true;
 	rmem->priv = mem;
 	dma_assign_coherent_memory(dev, mem);
 	return 0;
@@ -307,7 +329,8 @@ static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 static void rmem_dma_device_release(struct reserved_mem *rmem,
 				    struct device *dev)
 {
-	dev->dma_mem = NULL;
+	if (dev)
+		dev->dma_mem = NULL;
 }
 
 static const struct reserved_mem_ops rmem_dma_ops = {
@@ -327,6 +350,12 @@ static int __init rmem_dma_setup(struct reserved_mem *rmem)
 		pr_err("Reserved memory: regions without no-map are not yet supported\n");
 		return -EINVAL;
 	}
+
+	if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) {
+		WARN(dma_reserved_default_memory,
+		     "Reserved memory: region for default DMA coherent area is redefined\n");
+		dma_reserved_default_memory = rmem;
+	}
 #endif
 
 	rmem->ops = &rmem_dma_ops;
@@ -334,5 +363,32 @@ static int __init rmem_dma_setup(struct reserved_mem *rmem)
 		&rmem->base, (unsigned long)rmem->size / SZ_1M);
 	return 0;
 }
+
+static int __init dma_init_reserved_memory(void)
+{
+	const struct reserved_mem_ops *ops;
+	int ret;
+
+	if (!dma_reserved_default_memory)
+		return -ENOMEM;
+
+	ops = dma_reserved_default_memory->ops;
+
+	/*
+	 * We rely on rmem_dma_device_init() does not propagate error of
+	 * dma_assign_coherent_memory() for "NULL" device.
+	 */
+	ret = ops->device_init(dma_reserved_default_memory, NULL);
+
+	if (!ret) {
+		dma_coherent_default_memory = dma_reserved_default_memory->priv;
+		pr_info("DMA: default coherent area is set\n");
+	}
+
+	return ret;
+}
+
+core_initcall(dma_init_reserved_memory);
+
 RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
 #endif
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index 9dbef4d..5096755 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -22,20 +22,15 @@ struct dma_devres {
 	size_t		size;
 	void		*vaddr;
 	dma_addr_t	dma_handle;
+	unsigned long	attrs;
 };
 
-static void dmam_coherent_release(struct device *dev, void *res)
+static void dmam_release(struct device *dev, void *res)
 {
 	struct dma_devres *this = res;
 
-	dma_free_coherent(dev, this->size, this->vaddr, this->dma_handle);
-}
-
-static void dmam_noncoherent_release(struct device *dev, void *res)
-{
-	struct dma_devres *this = res;
-
-	dma_free_noncoherent(dev, this->size, this->vaddr, this->dma_handle);
+	dma_free_attrs(dev, this->size, this->vaddr, this->dma_handle,
+			this->attrs);
 }
 
 static int dmam_match(struct device *dev, void *res, void *match_data)
@@ -69,7 +64,7 @@ void *dmam_alloc_coherent(struct device *dev, size_t size,
 	struct dma_devres *dr;
 	void *vaddr;
 
-	dr = devres_alloc(dmam_coherent_release, sizeof(*dr), gfp);
+	dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
 	if (!dr)
 		return NULL;
 
@@ -104,35 +99,35 @@ void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
 	struct dma_devres match_data = { size, vaddr, dma_handle };
 
 	dma_free_coherent(dev, size, vaddr, dma_handle);
-	WARN_ON(devres_destroy(dev, dmam_coherent_release, dmam_match,
-			       &match_data));
+	WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data));
 }
 EXPORT_SYMBOL(dmam_free_coherent);
 
 /**
- * dmam_alloc_non_coherent - Managed dma_alloc_noncoherent()
+ * dmam_alloc_attrs - Managed dma_alloc_attrs()
  * @dev: Device to allocate non_coherent memory for
  * @size: Size of allocation
  * @dma_handle: Out argument for allocated DMA handle
  * @gfp: Allocation flags
+ * @attrs: Flags in the DMA_ATTR_* namespace.
  *
- * Managed dma_alloc_noncoherent().  Memory allocated using this
- * function will be automatically released on driver detach.
+ * Managed dma_alloc_attrs().  Memory allocated using this function will be
+ * automatically released on driver detach.
  *
  * RETURNS:
  * Pointer to allocated memory on success, NULL on failure.
  */
-void *dmam_alloc_noncoherent(struct device *dev, size_t size,
-			     dma_addr_t *dma_handle, gfp_t gfp)
+void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	struct dma_devres *dr;
 	void *vaddr;
 
-	dr = devres_alloc(dmam_noncoherent_release, sizeof(*dr), gfp);
+	dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
 	if (!dr)
 		return NULL;
 
-	vaddr = dma_alloc_noncoherent(dev, size, dma_handle, gfp);
+	vaddr = dma_alloc_attrs(dev, size, dma_handle, gfp, attrs);
 	if (!vaddr) {
 		devres_free(dr);
 		return NULL;
@@ -141,32 +136,13 @@ void *dmam_alloc_noncoherent(struct device *dev, size_t size,
 	dr->vaddr = vaddr;
 	dr->dma_handle = *dma_handle;
 	dr->size = size;
+	dr->attrs = attrs;
 
 	devres_add(dev, dr);
 
 	return vaddr;
 }
-EXPORT_SYMBOL(dmam_alloc_noncoherent);
-
-/**
- * dmam_free_coherent - Managed dma_free_noncoherent()
- * @dev: Device to free noncoherent memory for
- * @size: Size of allocation
- * @vaddr: Virtual address of the memory to free
- * @dma_handle: DMA handle of the memory to free
- *
- * Managed dma_free_noncoherent().
- */
-void dmam_free_noncoherent(struct device *dev, size_t size, void *vaddr,
-			   dma_addr_t dma_handle)
-{
-	struct dma_devres match_data = { size, vaddr, dma_handle };
-
-	dma_free_noncoherent(dev, size, vaddr, dma_handle);
-	WARN_ON(!devres_destroy(dev, dmam_noncoherent_release, dmam_match,
-				&match_data));
-}
-EXPORT_SYMBOL(dmam_free_noncoherent);
+EXPORT_SYMBOL(dmam_alloc_attrs);
 
 #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
 
@@ -251,7 +227,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size)
 {
 	int ret = -ENXIO;
-#if defined(CONFIG_MMU) && !defined(CONFIG_ARCH_NO_COHERENT_DMA_MMAP)
+#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
 	unsigned long user_count = vma_pages(vma);
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
@@ -268,7 +244,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 				      user_count << PAGE_SHIFT,
 				      vma->vm_page_prot);
 	}
-#endif	/* CONFIG_MMU && !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
+#endif	/* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
 
 	return ret;
 }
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 5b5efcc..baffae8 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -686,7 +686,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 
 	blp = dma_map_single(dev, bufl, sz, DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, blp)))
-		goto err;
+		goto err_in;
 
 	for_each_sg(sgl, sg, n, i) {
 		int y = sg_nctr;
@@ -699,7 +699,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 						      DMA_BIDIRECTIONAL);
 		bufl->bufers[y].len = sg->length;
 		if (unlikely(dma_mapping_error(dev, bufl->bufers[y].addr)))
-			goto err;
+			goto err_in;
 		sg_nctr++;
 	}
 	bufl->num_bufs = sg_nctr;
@@ -717,10 +717,10 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 		buflout = kzalloc_node(sz_out, GFP_ATOMIC,
 				       dev_to_node(&GET_DEV(inst->accel_dev)));
 		if (unlikely(!buflout))
-			goto err;
+			goto err_in;
 		bloutp = dma_map_single(dev, buflout, sz_out, DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(dev, bloutp)))
-			goto err;
+			goto err_out;
 		bufers = buflout->bufers;
 		for_each_sg(sglout, sg, n, i) {
 			int y = sg_nctr;
@@ -732,7 +732,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 							sg->length,
 							DMA_BIDIRECTIONAL);
 			if (unlikely(dma_mapping_error(dev, bufers[y].addr)))
-				goto err;
+				goto err_out;
 			bufers[y].len = sg->length;
 			sg_nctr++;
 		}
@@ -747,9 +747,20 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 		qat_req->buf.sz_out = 0;
 	}
 	return 0;
-err:
-	dev_err(dev, "Failed to map buf for dma\n");
-	sg_nctr = 0;
+
+err_out:
+	n = sg_nents(sglout);
+	for (i = 0; i < n; i++)
+		if (!dma_mapping_error(dev, buflout->bufers[i].addr))
+			dma_unmap_single(dev, buflout->bufers[i].addr,
+					 buflout->bufers[i].len,
+					 DMA_BIDIRECTIONAL);
+	if (!dma_mapping_error(dev, bloutp))
+		dma_unmap_single(dev, bloutp, sz_out, DMA_TO_DEVICE);
+	kfree(buflout);
+
+err_in:
+	n = sg_nents(sgl);
 	for (i = 0; i < n; i++)
 		if (!dma_mapping_error(dev, bufl->bufers[i].addr))
 			dma_unmap_single(dev, bufl->bufers[i].addr,
@@ -759,17 +770,8 @@ err:
 	if (!dma_mapping_error(dev, blp))
 		dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE);
 	kfree(bufl);
-	if (sgl != sglout && buflout) {
-		n = sg_nents(sglout);
-		for (i = 0; i < n; i++)
-			if (!dma_mapping_error(dev, buflout->bufers[i].addr))
-				dma_unmap_single(dev, buflout->bufers[i].addr,
-						 buflout->bufers[i].len,
-						 DMA_BIDIRECTIONAL);
-		if (!dma_mapping_error(dev, bloutp))
-			dma_unmap_single(dev, bloutp, sz_out, DMA_TO_DEVICE);
-		kfree(buflout);
-	}
+
+	dev_err(dev, "Failed to map buf for dma\n");
 	return -ENOMEM;
 }
 
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 6ad4384..ed8ed11 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -839,8 +839,6 @@ static int ioat_xor_val_self_test(struct ioatdma_device *ioat_dma)
 		goto free_resources;
 	}
 
-	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
-		dma_srcs[i] = DMA_ERROR_CODE;
 	for (i = 0; i < IOAT_NUM_SRC_TEST; i++) {
 		dma_srcs[i] = dma_map_page(dev, xor_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
@@ -910,8 +908,6 @@ static int ioat_xor_val_self_test(struct ioatdma_device *ioat_dma)
 
 	xor_val_result = 1;
 
-	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
-		dma_srcs[i] = DMA_ERROR_CODE;
 	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) {
 		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
@@ -965,8 +961,6 @@ static int ioat_xor_val_self_test(struct ioatdma_device *ioat_dma)
 	op = IOAT_OP_XOR_VAL;
 
 	xor_val_result = 0;
-	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
-		dma_srcs[i] = DMA_ERROR_CODE;
 	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) {
 		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
@@ -1017,18 +1011,14 @@ static int ioat_xor_val_self_test(struct ioatdma_device *ioat_dma)
 	goto free_resources;
 dma_unmap:
 	if (op == IOAT_OP_XOR) {
-		if (dest_dma != DMA_ERROR_CODE)
-			dma_unmap_page(dev, dest_dma, PAGE_SIZE,
-				       DMA_FROM_DEVICE);
-		for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
-			if (dma_srcs[i] != DMA_ERROR_CODE)
-				dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
-					       DMA_TO_DEVICE);
+		while (--i >= 0)
+			dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
+				       DMA_TO_DEVICE);
+		dma_unmap_page(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
 	} else if (op == IOAT_OP_XOR_VAL) {
-		for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
-			if (dma_srcs[i] != DMA_ERROR_CODE)
-				dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
-					       DMA_TO_DEVICE);
+		while (--i >= 0)
+			dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
+				       DMA_TO_DEVICE);
 	}
 free_resources:
 	dma->device_free_chan_resources(dma_chan);
diff --git a/drivers/firmware/tegra/ivc.c b/drivers/firmware/tegra/ivc.c
index 29ecfd8..a01461d 100644
--- a/drivers/firmware/tegra/ivc.c
+++ b/drivers/firmware/tegra/ivc.c
@@ -646,12 +646,12 @@ int tegra_ivc_init(struct tegra_ivc *ivc, struct device *peer, void *rx,
 	if (peer) {
 		ivc->rx.phys = dma_map_single(peer, rx, queue_size,
 					      DMA_BIDIRECTIONAL);
-		if (ivc->rx.phys == DMA_ERROR_CODE)
+		if (dma_mapping_error(peer, ivc->rx.phys))
 			return -ENOMEM;
 
 		ivc->tx.phys = dma_map_single(peer, tx, queue_size,
 					      DMA_BIDIRECTIONAL);
-		if (ivc->tx.phys == DMA_ERROR_CODE) {
+		if (dma_mapping_error(peer, ivc->tx.phys)) {
 			dma_unmap_single(peer, ivc->rx.phys, queue_size,
 					 DMA_BIDIRECTIONAL);
 			return -ENOMEM;
diff --git a/drivers/gpu/drm/armada/armada_fb.c b/drivers/gpu/drm/armada/armada_fb.c
index 2a7eb68..92e6b08 100644
--- a/drivers/gpu/drm/armada/armada_fb.c
+++ b/drivers/gpu/drm/armada/armada_fb.c
@@ -133,7 +133,7 @@ static struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
 	}
 
 	/* Framebuffer objects must have a valid device address for scanout */
-	if (obj->dev_addr == DMA_ERROR_CODE) {
+	if (!obj->mapped) {
 		ret = -EINVAL;
 		goto err_unref;
 	}
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index d6c2a5d..a76ca21 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -175,6 +175,7 @@ armada_gem_linear_back(struct drm_device *dev, struct armada_gem_object *obj)
 
 		obj->phys_addr = obj->linear->start;
 		obj->dev_addr = obj->linear->start;
+		obj->mapped = true;
 	}
 
 	DRM_DEBUG_DRIVER("obj %p phys %#llx dev %#llx\n", obj,
@@ -205,7 +206,6 @@ armada_gem_alloc_private_object(struct drm_device *dev, size_t size)
 		return NULL;
 
 	drm_gem_private_object_init(dev, &obj->obj, size);
-	obj->dev_addr = DMA_ERROR_CODE;
 
 	DRM_DEBUG_DRIVER("alloc private obj %p size %zu\n", obj, size);
 
@@ -229,8 +229,6 @@ static struct armada_gem_object *armada_gem_alloc_object(struct drm_device *dev,
 		return NULL;
 	}
 
-	obj->dev_addr = DMA_ERROR_CODE;
-
 	mapping = obj->obj.filp->f_mapping;
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER | __GFP_RECLAIMABLE);
 
@@ -610,5 +608,6 @@ int armada_gem_map_import(struct armada_gem_object *dobj)
 		return -EINVAL;
 	}
 	dobj->dev_addr = sg_dma_address(dobj->sgt->sgl);
+	dobj->mapped = true;
 	return 0;
 }
diff --git a/drivers/gpu/drm/armada/armada_gem.h b/drivers/gpu/drm/armada/armada_gem.h
index b88d2b9..6e524e0 100644
--- a/drivers/gpu/drm/armada/armada_gem.h
+++ b/drivers/gpu/drm/armada/armada_gem.h
@@ -16,6 +16,7 @@ struct armada_gem_object {
 	void			*addr;
 	phys_addr_t		phys_addr;
 	resource_size_t		dev_addr;
+	bool			mapped;
 	struct drm_mm_node	*linear;	/* for linear backed */
 	struct page		*page;		/* for page backed */
 	struct sg_table		*sgt;		/* for imported */
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index c77a5ac..d48fd7c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -181,8 +181,8 @@ dma_addr_t exynos_drm_fb_dma_addr(struct drm_framebuffer *fb, int index)
 {
 	struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
 
-	if (index >= MAX_FB_BUFFER)
-		return DMA_ERROR_CODE;
+	if (WARN_ON_ONCE(index >= MAX_FB_BUFFER))
+		return 0;
 
 	return exynos_fb->dma_addr[index];
 }
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 5c9759e..f16d0f2 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -54,6 +54,8 @@
 #include "amd_iommu_types.h"
 #include "irq_remapping.h"
 
+#define AMD_IOMMU_MAPPING_ERROR	0
+
 #define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
 
 #define LOOP_TIMEOUT	100000
@@ -2394,7 +2396,7 @@ static dma_addr_t __map_single(struct device *dev,
 	paddr &= PAGE_MASK;
 
 	address = dma_ops_alloc_iova(dev, dma_dom, pages, dma_mask);
-	if (address == DMA_ERROR_CODE)
+	if (address == AMD_IOMMU_MAPPING_ERROR)
 		goto out;
 
 	prot = dir2prot(direction);
@@ -2431,7 +2433,7 @@ out_unmap:
 
 	dma_ops_free_iova(dma_dom, address, pages);
 
-	return DMA_ERROR_CODE;
+	return AMD_IOMMU_MAPPING_ERROR;
 }
 
 /*
@@ -2483,7 +2485,7 @@ static dma_addr_t map_page(struct device *dev, struct page *page,
 	if (PTR_ERR(domain) == -EINVAL)
 		return (dma_addr_t)paddr;
 	else if (IS_ERR(domain))
-		return DMA_ERROR_CODE;
+		return AMD_IOMMU_MAPPING_ERROR;
 
 	dma_mask = *dev->dma_mask;
 	dma_dom = to_dma_ops_domain(domain);
@@ -2560,7 +2562,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 	npages = sg_num_pages(dev, sglist, nelems);
 
 	address = dma_ops_alloc_iova(dev, dma_dom, npages, dma_mask);
-	if (address == DMA_ERROR_CODE)
+	if (address == AMD_IOMMU_MAPPING_ERROR)
 		goto out_err;
 
 	prot = dir2prot(direction);
@@ -2683,7 +2685,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
 	*dma_addr = __map_single(dev, dma_dom, page_to_phys(page),
 				 size, DMA_BIDIRECTIONAL, dma_mask);
 
-	if (*dma_addr == DMA_ERROR_CODE)
+	if (*dma_addr == AMD_IOMMU_MAPPING_ERROR)
 		goto out_free;
 
 	return page_address(page);
@@ -2729,9 +2731,16 @@ free_mem:
  */
 static int amd_iommu_dma_supported(struct device *dev, u64 mask)
 {
+	if (!x86_dma_supported(dev, mask))
+		return 0;
 	return check_device(dev);
 }
 
+static int amd_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == AMD_IOMMU_MAPPING_ERROR;
+}
+
 static const struct dma_map_ops amd_iommu_dma_ops = {
 	.alloc		= alloc_coherent,
 	.free		= free_coherent,
@@ -2740,6 +2749,7 @@ static const struct dma_map_ops amd_iommu_dma_ops = {
 	.map_sg		= map_sg,
 	.unmap_sg	= unmap_sg,
 	.dma_supported	= amd_iommu_dma_supported,
+	.mapping_error	= amd_iommu_mapping_error,
 };
 
 static int init_reserved_iova_ranges(void)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 62618e7..9403336 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -31,6 +31,8 @@
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
 
+#define IOMMU_MAPPING_ERROR	0
+
 struct iommu_dma_msi_page {
 	struct list_head	list;
 	dma_addr_t		iova;
@@ -500,7 +502,7 @@ void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
 {
 	__iommu_dma_unmap(iommu_get_domain_for_dev(dev), *handle, size);
 	__iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
-	*handle = DMA_ERROR_CODE;
+	*handle = IOMMU_MAPPING_ERROR;
 }
 
 /**
@@ -533,7 +535,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
 	dma_addr_t iova;
 	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 
-	*handle = DMA_ERROR_CODE;
+	*handle = IOMMU_MAPPING_ERROR;
 
 	min_size = alloc_sizes & -alloc_sizes;
 	if (min_size < PAGE_SIZE) {
@@ -627,11 +629,11 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 
 	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
 	if (!iova)
-		return DMA_ERROR_CODE;
+		return IOMMU_MAPPING_ERROR;
 
 	if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
 		iommu_dma_free_iova(cookie, iova, size);
-		return DMA_ERROR_CODE;
+		return IOMMU_MAPPING_ERROR;
 	}
 	return iova + iova_off;
 }
@@ -671,7 +673,7 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 
 		s->offset += s_iova_off;
 		s->length = s_length;
-		sg_dma_address(s) = DMA_ERROR_CODE;
+		sg_dma_address(s) = IOMMU_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 
 		/*
@@ -714,11 +716,11 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
 	int i;
 
 	for_each_sg(sg, s, nents, i) {
-		if (sg_dma_address(s) != DMA_ERROR_CODE)
+		if (sg_dma_address(s) != IOMMU_MAPPING_ERROR)
 			s->offset += sg_dma_address(s);
 		if (sg_dma_len(s))
 			s->length = sg_dma_len(s);
-		sg_dma_address(s) = DMA_ERROR_CODE;
+		sg_dma_address(s) = IOMMU_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 	}
 }
@@ -836,7 +838,7 @@ void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 
 int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-	return dma_addr == DMA_ERROR_CODE;
+	return dma_addr == IOMMU_MAPPING_ERROR;
 }
 
 static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 8500ded..1e95475 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3981,6 +3981,9 @@ struct dma_map_ops intel_dma_ops = {
 	.map_page = intel_map_page,
 	.unmap_page = intel_unmap_page,
 	.mapping_error = intel_mapping_error,
+#ifdef CONFIG_X86
+	.dma_supported = x86_dma_supported,
+#endif
 };
 
 static inline int iommu_domain_cache_init(void)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 3e0a695..d17c2b0 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -469,56 +469,6 @@ static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter)
 	}
 }
 
-static void ibmveth_cleanup(struct ibmveth_adapter *adapter)
-{
-	int i;
-	struct device *dev = &adapter->vdev->dev;
-
-	if (adapter->buffer_list_addr != NULL) {
-		if (!dma_mapping_error(dev, adapter->buffer_list_dma)) {
-			dma_unmap_single(dev, adapter->buffer_list_dma, 4096,
-					DMA_BIDIRECTIONAL);
-			adapter->buffer_list_dma = DMA_ERROR_CODE;
-		}
-		free_page((unsigned long)adapter->buffer_list_addr);
-		adapter->buffer_list_addr = NULL;
-	}
-
-	if (adapter->filter_list_addr != NULL) {
-		if (!dma_mapping_error(dev, adapter->filter_list_dma)) {
-			dma_unmap_single(dev, adapter->filter_list_dma, 4096,
-					DMA_BIDIRECTIONAL);
-			adapter->filter_list_dma = DMA_ERROR_CODE;
-		}
-		free_page((unsigned long)adapter->filter_list_addr);
-		adapter->filter_list_addr = NULL;
-	}
-
-	if (adapter->rx_queue.queue_addr != NULL) {
-		dma_free_coherent(dev, adapter->rx_queue.queue_len,
-				  adapter->rx_queue.queue_addr,
-				  adapter->rx_queue.queue_dma);
-		adapter->rx_queue.queue_addr = NULL;
-	}
-
-	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
-		if (adapter->rx_buff_pool[i].active)
-			ibmveth_free_buffer_pool(adapter,
-						 &adapter->rx_buff_pool[i]);
-
-	if (adapter->bounce_buffer != NULL) {
-		if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
-			dma_unmap_single(&adapter->vdev->dev,
-					adapter->bounce_buffer_dma,
-					adapter->netdev->mtu + IBMVETH_BUFF_OH,
-					DMA_BIDIRECTIONAL);
-			adapter->bounce_buffer_dma = DMA_ERROR_CODE;
-		}
-		kfree(adapter->bounce_buffer);
-		adapter->bounce_buffer = NULL;
-	}
-}
-
 static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
         union ibmveth_buf_desc rxq_desc, u64 mac_address)
 {
@@ -575,14 +525,17 @@ static int ibmveth_open(struct net_device *netdev)
 	for(i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
 		rxq_entries += adapter->rx_buff_pool[i].size;
 
+	rc = -ENOMEM;
 	adapter->buffer_list_addr = (void*) get_zeroed_page(GFP_KERNEL);
-	adapter->filter_list_addr = (void*) get_zeroed_page(GFP_KERNEL);
+	if (!adapter->buffer_list_addr) {
+		netdev_err(netdev, "unable to allocate list pages\n");
+		goto out;
+	}
 
-	if (!adapter->buffer_list_addr || !adapter->filter_list_addr) {
-		netdev_err(netdev, "unable to allocate filter or buffer list "
-			   "pages\n");
-		rc = -ENOMEM;
-		goto err_out;
+	adapter->filter_list_addr = (void*) get_zeroed_page(GFP_KERNEL);
+	if (!adapter->filter_list_addr) {
+		netdev_err(netdev, "unable to allocate filter pages\n");
+		goto out_free_buffer_list;
 	}
 
 	dev = &adapter->vdev->dev;
@@ -592,22 +545,21 @@ static int ibmveth_open(struct net_device *netdev)
 	adapter->rx_queue.queue_addr =
 		dma_alloc_coherent(dev, adapter->rx_queue.queue_len,
 				   &adapter->rx_queue.queue_dma, GFP_KERNEL);
-	if (!adapter->rx_queue.queue_addr) {
-		rc = -ENOMEM;
-		goto err_out;
-	}
+	if (!adapter->rx_queue.queue_addr)
+		goto out_free_filter_list;
 
 	adapter->buffer_list_dma = dma_map_single(dev,
 			adapter->buffer_list_addr, 4096, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, adapter->buffer_list_dma)) {
+		netdev_err(netdev, "unable to map buffer list pages\n");
+		goto out_free_queue_mem;
+	}
+
 	adapter->filter_list_dma = dma_map_single(dev,
 			adapter->filter_list_addr, 4096, DMA_BIDIRECTIONAL);
-
-	if ((dma_mapping_error(dev, adapter->buffer_list_dma)) ||
-	    (dma_mapping_error(dev, adapter->filter_list_dma))) {
-		netdev_err(netdev, "unable to map filter or buffer list "
-			   "pages\n");
-		rc = -ENOMEM;
-		goto err_out;
+	if (dma_mapping_error(dev, adapter->filter_list_dma)) {
+		netdev_err(netdev, "unable to map filter list pages\n");
+		goto out_unmap_buffer_list;
 	}
 
 	adapter->rx_queue.index = 0;
@@ -638,7 +590,7 @@ static int ibmveth_open(struct net_device *netdev)
 				     rxq_desc.desc,
 				     mac_address);
 		rc = -ENONET;
-		goto err_out;
+		goto out_unmap_filter_list;
 	}
 
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
@@ -648,7 +600,7 @@ static int ibmveth_open(struct net_device *netdev)
 			netdev_err(netdev, "unable to alloc pool\n");
 			adapter->rx_buff_pool[i].active = 0;
 			rc = -ENOMEM;
-			goto err_out;
+			goto out_free_buffer_pools;
 		}
 	}
 
@@ -662,22 +614,21 @@ static int ibmveth_open(struct net_device *netdev)
 			lpar_rc = h_free_logical_lan(adapter->vdev->unit_address);
 		} while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));
 
-		goto err_out;
+		goto out_free_buffer_pools;
 	}
 
+	rc = -ENOMEM;
 	adapter->bounce_buffer =
 	    kmalloc(netdev->mtu + IBMVETH_BUFF_OH, GFP_KERNEL);
-	if (!adapter->bounce_buffer) {
-		rc = -ENOMEM;
-		goto err_out_free_irq;
-	}
+	if (!adapter->bounce_buffer)
+		goto out_free_irq;
+
 	adapter->bounce_buffer_dma =
 	    dma_map_single(&adapter->vdev->dev, adapter->bounce_buffer,
 			   netdev->mtu + IBMVETH_BUFF_OH, DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
 		netdev_err(netdev, "unable to map bounce buffer\n");
-		rc = -ENOMEM;
-		goto err_out_free_irq;
+		goto out_free_bounce_buffer;
 	}
 
 	netdev_dbg(netdev, "initial replenish cycle\n");
@@ -689,10 +640,31 @@ static int ibmveth_open(struct net_device *netdev)
 
 	return 0;
 
-err_out_free_irq:
+out_free_bounce_buffer:
+	kfree(adapter->bounce_buffer);
+out_free_irq:
 	free_irq(netdev->irq, netdev);
-err_out:
-	ibmveth_cleanup(adapter);
+out_free_buffer_pools:
+	while (--i >= 0) {
+		if (adapter->rx_buff_pool[i].active)
+			ibmveth_free_buffer_pool(adapter,
+						 &adapter->rx_buff_pool[i]);
+	}
+out_unmap_filter_list:
+	dma_unmap_single(dev, adapter->filter_list_dma, 4096,
+			 DMA_BIDIRECTIONAL);
+out_unmap_buffer_list:
+	dma_unmap_single(dev, adapter->buffer_list_dma, 4096,
+			 DMA_BIDIRECTIONAL);
+out_free_queue_mem:
+	dma_free_coherent(dev, adapter->rx_queue.queue_len,
+			  adapter->rx_queue.queue_addr,
+			  adapter->rx_queue.queue_dma);
+out_free_filter_list:
+	free_page((unsigned long)adapter->filter_list_addr);
+out_free_buffer_list:
+	free_page((unsigned long)adapter->buffer_list_addr);
+out:
 	napi_disable(&adapter->napi);
 	return rc;
 }
@@ -700,7 +672,9 @@ err_out:
 static int ibmveth_close(struct net_device *netdev)
 {
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->vdev->dev;
 	long lpar_rc;
+	int i;
 
 	netdev_dbg(netdev, "close starting\n");
 
@@ -724,7 +698,27 @@ static int ibmveth_close(struct net_device *netdev)
 
 	ibmveth_update_rx_no_buffer(adapter);
 
-	ibmveth_cleanup(adapter);
+	dma_unmap_single(dev, adapter->buffer_list_dma, 4096,
+			 DMA_BIDIRECTIONAL);
+	free_page((unsigned long)adapter->buffer_list_addr);
+
+	dma_unmap_single(dev, adapter->filter_list_dma, 4096,
+			 DMA_BIDIRECTIONAL);
+	free_page((unsigned long)adapter->filter_list_addr);
+
+	dma_free_coherent(dev, adapter->rx_queue.queue_len,
+			  adapter->rx_queue.queue_addr,
+			  adapter->rx_queue.queue_dma);
+
+	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
+		if (adapter->rx_buff_pool[i].active)
+			ibmveth_free_buffer_pool(adapter,
+						 &adapter->rx_buff_pool[i]);
+
+	dma_unmap_single(&adapter->vdev->dev, adapter->bounce_buffer_dma,
+			 adapter->netdev->mtu + IBMVETH_BUFF_OH,
+			 DMA_BIDIRECTIONAL);
+	kfree(adapter->bounce_buffer);
 
 	netdev_dbg(netdev, "close complete\n");
 
@@ -1719,11 +1713,6 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 
 	netdev_dbg(netdev, "adapter @ 0x%p\n", adapter);
-
-	adapter->buffer_list_dma = DMA_ERROR_CODE;
-	adapter->filter_list_dma = DMA_ERROR_CODE;
-	adapter->rx_queue.queue_dma = DMA_ERROR_CODE;
-
 	netdev_dbg(netdev, "registering netdev...\n");
 
 	ibmveth_set_features(netdev, netdev->features);
diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c
index 35df2c1..8de42f6 100644
--- a/drivers/video/fbdev/au1100fb.c
+++ b/drivers/video/fbdev/au1100fb.c
@@ -532,10 +532,6 @@ failed:
 		clk_disable_unprepare(fbdev->lcdclk);
 		clk_put(fbdev->lcdclk);
 	}
-	if (fbdev->fb_mem) {
-		dma_free_noncoherent(&dev->dev, fbdev->fb_len, fbdev->fb_mem,
-				     fbdev->fb_phys);
-	}
 	if (fbdev->info.cmap.len != 0) {
 		fb_dealloc_cmap(&fbdev->info.cmap);
 	}
diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c
index 6c2b2ca..5f04b40 100644
--- a/drivers/video/fbdev/au1200fb.c
+++ b/drivers/video/fbdev/au1200fb.c
@@ -1694,9 +1694,10 @@ static int au1200fb_drv_probe(struct platform_device *dev)
 		/* Allocate the framebuffer to the maximum screen size */
 		fbdev->fb_len = (win->w[plane].xres * win->w[plane].yres * bpp) / 8;
 
-		fbdev->fb_mem = dmam_alloc_noncoherent(&dev->dev,
+		fbdev->fb_mem = dmam_alloc_attrs(&dev->dev,
 				PAGE_ALIGN(fbdev->fb_len),
-				&fbdev->fb_phys, GFP_KERNEL);
+				&fbdev->fb_phys, GFP_KERNEL,
+				DMA_ATTR_NON_CONSISTENT);
 		if (!fbdev->fb_mem) {
 			print_err("fail to allocate frambuffer (size: %dK))",
 				  fbdev->fb_len / 1024);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 8dab0d3..82fc54f 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -67,6 +67,8 @@ static unsigned long dma_alloc_coherent_mask(struct device *dev,
 }
 #endif
 
+#define XEN_SWIOTLB_ERROR_CODE	(~(dma_addr_t)0x0)
+
 static char *xen_io_tlb_start, *xen_io_tlb_end;
 static unsigned long xen_io_tlb_nslabs;
 /*
@@ -295,7 +297,8 @@ error:
 		free_pages((unsigned long)xen_io_tlb_start, order);
 	return rc;
 }
-void *
+
+static void *
 xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flags,
 			   unsigned long attrs)
@@ -346,9 +349,8 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	memset(ret, 0, size);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);
 
-void
+static void
 xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 			  dma_addr_t dev_addr, unsigned long attrs)
 {
@@ -369,8 +371,6 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 
 	xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
-
 
 /*
  * Map a single buffer of the indicated size for DMA in streaming mode.  The
@@ -379,7 +379,7 @@ EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
  * 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.
  */
-dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
+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,
 				unsigned long attrs)
@@ -412,7 +412,7 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir,
 				     attrs);
 	if (map == SWIOTLB_MAP_ERROR)
-		return DMA_ERROR_CODE;
+		return XEN_SWIOTLB_ERROR_CODE;
 
 	dev_addr = xen_phys_to_bus(map);
 	xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
@@ -427,9 +427,8 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	attrs |= DMA_ATTR_SKIP_CPU_SYNC;
 	swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
 
-	return DMA_ERROR_CODE;
+	return XEN_SWIOTLB_ERROR_CODE;
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
@@ -467,13 +466,12 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 	dma_mark_clean(phys_to_virt(paddr), size);
 }
 
-void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
 			    size_t size, enum dma_data_direction dir,
 			    unsigned long attrs)
 {
 	xen_unmap_single(hwdev, dev_addr, size, dir, attrs);
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page);
 
 /*
  * Make physical memory consistent for a single streaming mode DMA translation
@@ -516,7 +514,6 @@ xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
 {
 	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_cpu);
 
 void
 xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
@@ -524,7 +521,25 @@ xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
 {
 	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_device);
+
+/*
+ * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
+ */
+static void
+xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			   int nelems, enum dma_data_direction dir,
+			   unsigned long attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for_each_sg(sgl, sg, nelems, i)
+		xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs);
+
+}
 
 /*
  * Map a set of buffers described by scatterlist in streaming mode for DMA.
@@ -542,7 +557,7 @@ EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_device);
  * Device ownership issues as mentioned above for xen_swiotlb_map_page are the
  * same here.
  */
-int
+static int
 xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 			 int nelems, enum dma_data_direction dir,
 			 unsigned long attrs)
@@ -599,27 +614,6 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 	}
 	return nelems;
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg_attrs);
-
-/*
- * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_page() above.
- */
-void
-xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
-			   int nelems, enum dma_data_direction dir,
-			   unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	BUG_ON(dir == DMA_NONE);
-
-	for_each_sg(sgl, sg, nelems, i)
-		xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs);
-
-}
-EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);
 
 /*
  * Make physical memory consistent for a set of streaming mode DMA translations
@@ -641,21 +635,19 @@ xen_swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
 					sg_dma_len(sg), dir, target);
 }
 
-void
+static void
 xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
 			    int nelems, enum dma_data_direction dir)
 {
 	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_cpu);
 
-void
+static void
 xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
 			       int nelems, enum dma_data_direction dir)
 {
 	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_device);
 
 /*
  * Return whether the given device DMA address mask can be supported
@@ -663,31 +655,18 @@ EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_device);
  * during bus mastering, then you would pass 0x00ffffff as the mask to
  * this function.
  */
-int
+static int
 xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
 	return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_dma_supported);
-
-int
-xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
-{
-	if (!dev->dma_mask || !xen_swiotlb_dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
 
 /*
  * Create userspace mapping for the DMA-coherent memory.
  * This function should be called with the pages from the current domain only,
  * passing pages mapped from other domains would lead to memory corruption.
  */
-int
+static int
 xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		     unsigned long attrs)
@@ -699,13 +678,12 @@ xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 #endif
 	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mmap);
 
 /*
  * This function should be called with the pages from the current domain only,
  * passing pages mapped from other domains would lead to memory corruption.
  */
-int
+static int
 xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
 			void *cpu_addr, dma_addr_t handle, size_t size,
 			unsigned long attrs)
@@ -727,4 +705,25 @@ xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
 #endif
 	return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size);
 }
-EXPORT_SYMBOL_GPL(xen_swiotlb_get_sgtable);
+
+static int xen_swiotlb_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == XEN_SWIOTLB_ERROR_CODE;
+}
+
+const struct dma_map_ops xen_swiotlb_dma_ops = {
+	.alloc = xen_swiotlb_alloc_coherent,
+	.free = xen_swiotlb_free_coherent,
+	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
+	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
+	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
+	.map_sg = xen_swiotlb_map_sg_attrs,
+	.unmap_sg = xen_swiotlb_unmap_sg_attrs,
+	.map_page = xen_swiotlb_map_page,
+	.unmap_page = xen_swiotlb_unmap_page,
+	.dma_supported = xen_swiotlb_dma_supported,
+	.mmap = xen_swiotlb_dma_mmap,
+	.get_sgtable = xen_swiotlb_get_sgtable,
+	.mapping_error	= xen_swiotlb_mapping_error,
+};
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 4f3eece..843ab86 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -127,7 +127,6 @@ struct dma_map_ops {
 				   enum dma_data_direction dir);
 	int (*mapping_error)(struct device *dev, dma_addr_t dma_addr);
 	int (*dma_supported)(struct device *dev, u64 mask);
-	int (*set_dma_mask)(struct device *dev, u64 mask);
 #ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
 	u64 (*get_required_mask)(struct device *dev);
 #endif
@@ -546,15 +545,9 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 
 	if (get_dma_ops(dev)->mapping_error)
 		return get_dma_ops(dev)->mapping_error(dev, dma_addr);
-
-#ifdef DMA_ERROR_CODE
-	return dma_addr == DMA_ERROR_CODE;
-#else
 	return 0;
-#endif
 }
 
-#ifndef HAVE_ARCH_DMA_SUPPORTED
 static inline int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -565,16 +558,10 @@ static inline int dma_supported(struct device *dev, u64 mask)
 		return 1;
 	return ops->dma_supported(dev, mask);
 }
-#endif
 
 #ifndef HAVE_ARCH_DMA_SET_MASK
 static inline int dma_set_mask(struct device *dev, u64 mask)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (ops->set_dma_mask)
-		return ops->set_dma_mask(dev, mask);
-
 	if (!dev->dma_mask || !dma_supported(dev, mask))
 		return -EIO;
 	*dev->dma_mask = mask;
@@ -747,10 +734,9 @@ extern void *dmam_alloc_coherent(struct device *dev, size_t size,
 				 dma_addr_t *dma_handle, gfp_t gfp);
 extern void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
 			       dma_addr_t dma_handle);
-extern void *dmam_alloc_noncoherent(struct device *dev, size_t size,
-				    dma_addr_t *dma_handle, gfp_t gfp);
-extern void dmam_free_noncoherent(struct device *dev, size_t size, void *vaddr,
-				  dma_addr_t dma_handle);
+extern void *dmam_alloc_attrs(struct device *dev, size_t size,
+			      dma_addr_t *dma_handle, gfp_t gfp,
+			      unsigned long attrs);
 #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
 extern int dmam_declare_coherent_memory(struct device *dev,
 					phys_addr_t phys_addr,
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index 1f6d78f..ed2de36 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -1,69 +1,9 @@
 #ifndef __LINUX_SWIOTLB_XEN_H
 #define __LINUX_SWIOTLB_XEN_H
 
-#include <linux/dma-direction.h>
-#include <linux/scatterlist.h>
 #include <linux/swiotlb.h>
 
 extern int xen_swiotlb_init(int verbose, bool early);
+extern const struct dma_map_ops xen_swiotlb_dma_ops;
 
-extern void
-*xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-			    dma_addr_t *dma_handle, gfp_t flags,
-			    unsigned long attrs);
-
-extern void
-xen_swiotlb_free_coherent(struct device *hwdev, size_t size,
-			  void *vaddr, dma_addr_t dma_handle,
-			  unsigned long attrs);
-
-extern dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
-				       unsigned long offset, size_t size,
-				       enum dma_data_direction dir,
-				       unsigned long attrs);
-
-extern void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
-				   size_t size, enum dma_data_direction dir,
-				   unsigned long attrs);
-extern int
-xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
-			 int nelems, enum dma_data_direction dir,
-			 unsigned long attrs);
-
-extern void
-xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
-			   int nelems, enum dma_data_direction dir,
-			   unsigned long attrs);
-
-extern void
-xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-				size_t size, enum dma_data_direction dir);
-
-extern void
-xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-			    int nelems, enum dma_data_direction dir);
-
-extern void
-xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
-				   size_t size, enum dma_data_direction dir);
-
-extern void
-xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-			       int nelems, enum dma_data_direction dir);
-
-extern int
-xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
-
-extern int
-xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
-
-extern int
-xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		     unsigned long attrs);
-
-extern int
-xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
-			void *cpu_addr, dma_addr_t handle, size_t size,
-			unsigned long attrs);
 #endif /* __LINUX_SWIOTLB_XEN_H */
diff --git a/lib/dma-noop.c b/lib/dma-noop.c
index de26c8b..acc4190 100644
--- a/lib/dma-noop.c
+++ b/lib/dma-noop.c
@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/scatterlist.h>
+#include <linux/pfn.h>
 
 static void *dma_noop_alloc(struct device *dev, size_t size,
 			    dma_addr_t *dma_handle, gfp_t gfp,
@@ -16,7 +17,8 @@ static void *dma_noop_alloc(struct device *dev, size_t size,
 
 	ret = (void *)__get_free_pages(gfp, get_order(size));
 	if (ret)
-		*dma_handle = virt_to_phys(ret);
+		*dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset);
+
 	return ret;
 }
 
@@ -32,7 +34,7 @@ static dma_addr_t dma_noop_map_page(struct device *dev, struct page *page,
 				      enum dma_data_direction dir,
 				      unsigned long attrs)
 {
-	return page_to_phys(page) + offset;
+	return page_to_phys(page) + offset - PFN_PHYS(dev->dma_pfn_offset);
 }
 
 static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
@@ -43,34 +45,23 @@ static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nent
 	struct scatterlist *sg;
 
 	for_each_sg(sgl, sg, nents, i) {
+		dma_addr_t offset = PFN_PHYS(dev->dma_pfn_offset);
 		void *va;
 
 		BUG_ON(!sg_page(sg));
 		va = sg_virt(sg);
-		sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va);
+		sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va) - offset;
 		sg_dma_len(sg) = sg->length;
 	}
 
 	return nents;
 }
 
-static int dma_noop_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-static int dma_noop_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
 const struct dma_map_ops dma_noop_ops = {
 	.alloc			= dma_noop_alloc,
 	.free			= dma_noop_free,
 	.map_page		= dma_noop_map_page,
 	.map_sg			= dma_noop_map_sg,
-	.mapping_error		= dma_noop_mapping_error,
-	.dma_supported		= dma_noop_supported,
 };
 
 EXPORT_SYMBOL(dma_noop_ops);
diff --git a/lib/dma-virt.c b/lib/dma-virt.c
index dcd4df1..5c4f113 100644
--- a/lib/dma-virt.c
+++ b/lib/dma-virt.c
@@ -51,22 +51,10 @@ static int dma_virt_map_sg(struct device *dev, struct scatterlist *sgl,
 	return nents;
 }
 
-static int dma_virt_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return false;
-}
-
-static int dma_virt_supported(struct device *dev, u64 mask)
-{
-	return true;
-}
-
 const struct dma_map_ops dma_virt_ops = {
 	.alloc			= dma_virt_alloc,
 	.free			= dma_virt_free,
 	.map_page		= dma_virt_map_page,
 	.map_sg			= dma_virt_map_sg,
-	.mapping_error		= dma_virt_mapping_error,
-	.dma_supported		= dma_virt_supported,
 };
 EXPORT_SYMBOL(dma_virt_ops);