Merge branch 'for-linus' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping

Pull CMA and ARM DMA-mapping updates from Marek Szyprowski:
 "These patches contain two major updates for DMA mapping subsystem
  (mainly for ARM architecture).  First one is Contiguous Memory
  Allocator (CMA) which makes it possible for device drivers to allocate
  big contiguous chunks of memory after the system has booted.

  The main difference from the similar frameworks is the fact that CMA
  allows to transparently reuse the memory region reserved for the big
  chunk allocation as a system memory, so no memory is wasted when no
  big chunk is allocated.  Once the alloc request is issued, the
  framework migrates system pages to create space for the required big
  chunk of physically contiguous memory.

  For more information one can refer to nice LWN articles:

   - 'A reworked contiguous memory allocator':
		http://lwn.net/Articles/447405/

   - 'CMA and ARM':
		http://lwn.net/Articles/450286/

   - 'A deep dive into CMA':
		http://lwn.net/Articles/486301/

   - and the following thread with the patches and links to all previous
     versions:
		https://lkml.org/lkml/2012/4/3/204

  The main client for this new framework is ARM DMA-mapping subsystem.

  The second part provides a complete redesign in ARM DMA-mapping
  subsystem.  The core implementation has been changed to use common
  struct dma_map_ops based infrastructure with the recent updates for
  new dma attributes merged in v3.4-rc2.  This allows to use more than
  one implementation of dma-mapping calls and change/select them on the
  struct device basis.  The first client of this new infractructure is
  dmabounce implementation which has been completely cut out of the
  core, common code.

  The last patch of this redesign update introduces a new, experimental
  implementation of dma-mapping calls on top of generic IOMMU framework.
  This lets ARM sub-platform to transparently use IOMMU for DMA-mapping
  calls if one provides required IOMMU hardware.

  For more information please refer to the following thread:
		http://www.spinics.net/lists/arm-kernel/msg175729.html

  The last patch merges changes from both updates and provides a
  resolution for the conflicts which cannot be avoided when patches have
  been applied on the same files (mainly arch/arm/mm/dma-mapping.c)."

Acked by Andrew Morton <akpm@linux-foundation.org>:
 "Yup, this one please.  It's had much work, plenty of review and I
  think even Russell is happy with it."

* 'for-linus' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping: (28 commits)
  ARM: dma-mapping: use PMD size for section unmap
  cma: fix migration mode
  ARM: integrate CMA with DMA-mapping subsystem
  X86: integrate CMA with DMA-mapping subsystem
  drivers: add Contiguous Memory Allocator
  mm: trigger page reclaim in alloc_contig_range() to stabilise watermarks
  mm: extract reclaim code from __alloc_pages_direct_reclaim()
  mm: Serialize access to min_free_kbytes
  mm: page_isolation: MIGRATE_CMA isolation functions added
  mm: mmzone: MIGRATE_CMA migration type added
  mm: page_alloc: change fallbacks array handling
  mm: page_alloc: introduce alloc_contig_range()
  mm: compaction: export some of the functions
  mm: compaction: introduce isolate_freepages_range()
  mm: compaction: introduce map_pages()
  mm: compaction: introduce isolate_migratepages_range()
  mm: page_alloc: remove trailing whitespace
  ARM: dma-mapping: add support for IOMMU mapper
  ARM: dma-mapping: use alloc, mmap, free from dma_ops
  ARM: dma-mapping: remove redundant code and do the cleanup
  ...

Conflicts:
	arch/x86/include/asm/dma-mapping.h

41 files changed, 2898 insertions, 780 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b69cfdc1211..f1959b7d13d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -508,6 +508,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Also note the kernel might malfunction if you disable
 			some critical bits.
 
+	cma=nn[MG]	[ARM,KNL]
+			Sets the size of kernel global memory area for contiguous
+			memory allocations. For more information, see
+			include/linux/dma-contiguous.h
+
 	cmo_free_hint=	[PPC] Format: { yes | no }
 			Specify whether pages are marked as being inactive
 			when they are freed.  This is used in CMO environments
@@ -515,6 +520,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			a hypervisor.
 			Default: yes
 
+	coherent_pool=nn[KMG]	[ARM,KNL]
+			Sets the size of memory pool for coherent, atomic dma
+			allocations if Contiguous Memory Allocator (CMA) is used.
+
 	code_bytes	[X86] How many bytes of object code to print
 			in an oops report.
 			Range: 0 - 8192
diff --git a/arch/Kconfig b/arch/Kconfig
index e9a910876cd..8c3d957fa8e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -159,6 +159,9 @@ config HAVE_ARCH_TRACEHOOK
 config HAVE_DMA_ATTRS
 	bool
 
+config HAVE_DMA_CONTIGUOUS
+	bool
+
 config USE_GENERIC_SMP_HELPERS
 	bool
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5458aa9db06..3ca1ba981ef 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -5,6 +5,9 @@ config ARM
 	select HAVE_AOUT
 	select HAVE_DMA_API_DEBUG
 	select HAVE_IDE if PCI || ISA || PCMCIA
+	select HAVE_DMA_ATTRS
+	select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
+	select CMA if (CPU_V6 || CPU_V6K || CPU_V7)
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
@@ -54,6 +57,14 @@ config ARM
 config ARM_HAS_SG_CHAIN
 	bool
 
+config NEED_SG_DMA_LENGTH
+	bool
+
+config ARM_DMA_USE_IOMMU
+	select NEED_SG_DMA_LENGTH
+	select ARM_HAS_SG_CHAIN
+	bool
+
 config HAVE_PWM
 	bool
 
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index 595ecd290eb..9d7eb530f95 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -173,7 +173,8 @@ find_safe_buffer(struct dmabounce_device_info *device_info, dma_addr_t safe_dma_
 	read_lock_irqsave(&device_info->lock, flags);
 
 	list_for_each_entry(b, &device_info->safe_buffers, node)
-		if (b->safe_dma_addr == safe_dma_addr) {
+		if (b->safe_dma_addr <= safe_dma_addr &&
+		    b->safe_dma_addr + b->size > safe_dma_addr) {
 			rb = b;
 			break;
 		}
@@ -254,7 +255,7 @@ 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 ~0;
+		return DMA_ERROR_CODE;
 	}
 
 	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
@@ -307,8 +308,9 @@ static inline void unmap_single(struct device *dev, struct safe_buffer *buf,
  * substitute the safe buffer for the unsafe one.
  * (basically move the buffer from an unsafe area to a safe one)
  */
-dma_addr_t __dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir)
+static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
 {
 	dma_addr_t dma_addr;
 	int ret;
@@ -320,21 +322,20 @@ dma_addr_t __dma_map_page(struct device *dev, struct page *page,
 
 	ret = needs_bounce(dev, dma_addr, size);
 	if (ret < 0)
-		return ~0;
+		return DMA_ERROR_CODE;
 
 	if (ret == 0) {
-		__dma_page_cpu_to_dev(page, offset, size, dir);
+		arm_dma_ops.sync_single_for_device(dev, dma_addr, size, dir);
 		return dma_addr;
 	}
 
 	if (PageHighMem(page)) {
 		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
-		return ~0;
+		return DMA_ERROR_CODE;
 	}
 
 	return map_single(dev, page_address(page) + offset, size, dir);
 }
-EXPORT_SYMBOL(__dma_map_page);
 
 /*
  * see if a mapped address was really a "safe" buffer and if so, copy
@@ -342,8 +343,8 @@ EXPORT_SYMBOL(__dma_map_page);
  * the safe buffer.  (basically return things back to the way they
  * should be)
  */
-void __dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
-		enum dma_data_direction dir)
+static void dmabounce_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
+		enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	struct safe_buffer *buf;
 
@@ -352,19 +353,18 @@ void __dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 
 	buf = find_safe_buffer_dev(dev, dma_addr, __func__);
 	if (!buf) {
-		__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, dma_addr)),
-			dma_addr & ~PAGE_MASK, size, dir);
+		arm_dma_ops.sync_single_for_cpu(dev, dma_addr, size, dir);
 		return;
 	}
 
 	unmap_single(dev, buf, size, dir);
 }
-EXPORT_SYMBOL(__dma_unmap_page);
 
-int dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr,
-		unsigned long off, size_t sz, enum dma_data_direction dir)
+static int __dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr,
+		size_t sz, enum dma_data_direction dir)
 {
 	struct safe_buffer *buf;
+	unsigned long off;
 
 	dev_dbg(dev, "%s(dma=%#x,off=%#lx,sz=%zx,dir=%x)\n",
 		__func__, addr, off, sz, dir);
@@ -373,6 +373,8 @@ int dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr,
 	if (!buf)
 		return 1;
 
+	off = addr - buf->safe_dma_addr;
+
 	BUG_ON(buf->direction != dir);
 
 	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
@@ -388,12 +390,21 @@ int dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr,
 	}
 	return 0;
 }
-EXPORT_SYMBOL(dmabounce_sync_for_cpu);
 
-int dmabounce_sync_for_device(struct device *dev, dma_addr_t addr,
-		unsigned long off, size_t sz, enum dma_data_direction dir)
+static void dmabounce_sync_for_cpu(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (!__dmabounce_sync_for_cpu(dev, handle, size, dir))
+		return;
+
+	arm_dma_ops.sync_single_for_cpu(dev, handle, size, dir);
+}
+
+static int __dmabounce_sync_for_device(struct device *dev, dma_addr_t addr,
+		size_t sz, enum dma_data_direction dir)
 {
 	struct safe_buffer *buf;
+	unsigned long off;
 
 	dev_dbg(dev, "%s(dma=%#x,off=%#lx,sz=%zx,dir=%x)\n",
 		__func__, addr, off, sz, dir);
@@ -402,6 +413,8 @@ int dmabounce_sync_for_device(struct device *dev, dma_addr_t addr,
 	if (!buf)
 		return 1;
 
+	off = addr - buf->safe_dma_addr;
+
 	BUG_ON(buf->direction != dir);
 
 	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
@@ -417,7 +430,38 @@ int dmabounce_sync_for_device(struct device *dev, dma_addr_t addr,
 	}
 	return 0;
 }
-EXPORT_SYMBOL(dmabounce_sync_for_device);
+
+static void dmabounce_sync_for_device(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (!__dmabounce_sync_for_device(dev, handle, size, dir))
+		return;
+
+	arm_dma_ops.sync_single_for_device(dev, handle, size, dir);
+}
+
+static int dmabounce_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (dev->archdata.dmabounce)
+		return 0;
+
+	return arm_dma_ops.set_dma_mask(dev, dma_mask);
+}
+
+static struct dma_map_ops dmabounce_ops = {
+	.alloc			= arm_dma_alloc,
+	.free			= arm_dma_free,
+	.mmap			= arm_dma_mmap,
+	.map_page		= dmabounce_map_page,
+	.unmap_page		= dmabounce_unmap_page,
+	.sync_single_for_cpu	= dmabounce_sync_for_cpu,
+	.sync_single_for_device	= dmabounce_sync_for_device,
+	.map_sg			= arm_dma_map_sg,
+	.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,
+};
 
 static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
 		const char *name, unsigned long size)
@@ -479,6 +523,7 @@ int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
 #endif
 
 	dev->archdata.dmabounce = device_info;
+	set_dma_ops(dev, &dmabounce_ops);
 
 	dev_info(dev, "dmabounce: registered device\n");
 
@@ -497,6 +542,7 @@ void dmabounce_unregister_dev(struct device *dev)
 	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
 
 	dev->archdata.dmabounce = NULL;
+	set_dma_ops(dev, NULL);
 
 	if (!device_info) {
 		dev_warn(dev,
diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
index 7aa368003b0..b69c0d3285f 100644
--- a/arch/arm/include/asm/device.h
+++ b/arch/arm/include/asm/device.h
@@ -7,12 +7,16 @@
 #define ASMARM_DEVICE_H
 
 struct dev_archdata {
+	struct dma_map_ops	*dma_ops;
 #ifdef CONFIG_DMABOUNCE
 	struct dmabounce_device_info *dmabounce;
 #endif
 #ifdef CONFIG_IOMMU_API
 	void *iommu; /* private IOMMU data */
 #endif
+#ifdef CONFIG_ARM_DMA_USE_IOMMU
+	struct dma_iommu_mapping	*mapping;
+#endif
 };
 
 struct omap_device;
diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
new file mode 100644
index 00000000000..3ed37b4d93d
--- /dev/null
+++ b/arch/arm/include/asm/dma-contiguous.h
@@ -0,0 +1,15 @@
+#ifndef ASMARM_DMA_CONTIGUOUS_H
+#define ASMARM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_CMA
+
+#include <linux/types.h>
+#include <asm-generic/dma-contiguous.h>
+
+void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
+
+#endif
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
new file mode 100644
index 00000000000..799b09409fa
--- /dev/null
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -0,0 +1,34 @@
+#ifndef ASMARM_DMA_IOMMU_H
+#define ASMARM_DMA_IOMMU_H
+
+#ifdef __KERNEL__
+
+#include <linux/mm_types.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
+#include <linux/kmemcheck.h>
+
+struct dma_iommu_mapping {
+	/* iommu specific data */
+	struct iommu_domain	*domain;
+
+	void			*bitmap;
+	size_t			bits;
+	unsigned int		order;
+	dma_addr_t		base;
+
+	spinlock_t		lock;
+	struct kref		kref;
+};
+
+struct dma_iommu_mapping *
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size,
+			 int order);
+
+void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping);
+
+int arm_iommu_attach_device(struct device *dev,
+					struct dma_iommu_mapping *mapping);
+
+#endif /* __KERNEL__ */
+#endif
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index cb3b7c981c4..bbef15d0489 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -5,11 +5,35 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
+#include <linux/dma-attrs.h>
 #include <linux/dma-debug.h>
 
 #include <asm-generic/dma-coherent.h>
 #include <asm/memory.h>
 
+#define DMA_ERROR_CODE	(~0)
+extern struct dma_map_ops arm_dma_ops;
+
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (dev && dev->archdata.dma_ops)
+		return dev->archdata.dma_ops;
+	return &arm_dma_ops;
+}
+
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+	BUG_ON(!dev);
+	dev->archdata.dma_ops = ops;
+}
+
+#include <asm-generic/dma-mapping-common.h>
+
+static inline int dma_set_mask(struct device *dev, u64 mask)
+{
+	return get_dma_ops(dev)->set_dma_mask(dev, mask);
+}
+
 #ifdef __arch_page_to_dma
 #error Please update to __arch_pfn_to_dma
 #endif
@@ -62,68 +86,11 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 #endif
 
 /*
- * The DMA API is built upon the notion of "buffer ownership".  A buffer
- * is either exclusively owned by the CPU (and therefore may be accessed
- * by it) or exclusively owned by the DMA device.  These helper functions
- * represent the transitions between these two ownership states.
- *
- * Note, however, that on later ARMs, this notion does not work due to
- * speculative prefetches.  We model our approach on the assumption that
- * the CPU does do speculative prefetches, which means we clean caches
- * before transfers and delay cache invalidation until transfer completion.
- *
- * Private support functions: these are not part of the API and are
- * liable to change.  Drivers must not use these.
- */
-static inline void __dma_single_cpu_to_dev(const void *kaddr, size_t size,
-	enum dma_data_direction dir)
-{
-	extern void ___dma_single_cpu_to_dev(const void *, size_t,
-		enum dma_data_direction);
-
-	if (!arch_is_coherent())
-		___dma_single_cpu_to_dev(kaddr, size, dir);
-}
-
-static inline void __dma_single_dev_to_cpu(const void *kaddr, size_t size,
-	enum dma_data_direction dir)
-{
-	extern void ___dma_single_dev_to_cpu(const void *, size_t,
-		enum dma_data_direction);
-
-	if (!arch_is_coherent())
-		___dma_single_dev_to_cpu(kaddr, size, dir);
-}
-
-static inline void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
-	size_t size, enum dma_data_direction dir)
-{
-	extern void ___dma_page_cpu_to_dev(struct page *, unsigned long,
-		size_t, enum dma_data_direction);
-
-	if (!arch_is_coherent())
-		___dma_page_cpu_to_dev(page, off, size, dir);
-}
-
-static inline void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
-	size_t size, enum dma_data_direction dir)
-{
-	extern void ___dma_page_dev_to_cpu(struct page *, unsigned long,
-		size_t, enum dma_data_direction);
-
-	if (!arch_is_coherent())
-		___dma_page_dev_to_cpu(page, off, size, dir);
-}
-
-extern int dma_supported(struct device *, u64);
-extern int dma_set_mask(struct device *, u64);
-
-/*
  * DMA errors are defined by all-bits-set in the DMA address.
  */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-	return dma_addr == ~0;
+	return dma_addr == DMA_ERROR_CODE;
 }
 
 /*
@@ -141,69 +108,118 @@ static inline void dma_free_noncoherent(struct device *dev, size_t size,
 {
 }
 
+extern int dma_supported(struct device *dev, u64 mask);
+
 /**
- * dma_alloc_coherent - allocate consistent memory for DMA
+ * arm_dma_alloc - allocate consistent memory for DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @size: required memory size
  * @handle: bus-specific DMA address
+ * @attrs: optinal attributes that specific mapping properties
  *
- * Allocate some uncached, unbuffered memory for a device for
- * performing DMA.  This function allocates pages, and will
- * return the CPU-viewed address, and sets @handle to be the
- * device-viewed address.
+ * Allocate some memory for a device for performing DMA.  This function
+ * allocates pages, and will return the CPU-viewed address, and sets @handle
+ * to be the device-viewed address.
  */
-extern void *dma_alloc_coherent(struct device *, size_t, dma_addr_t *, gfp_t);
+extern void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+			   gfp_t gfp, struct dma_attrs *attrs);
+
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag,
+				       struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *cpu_addr;
+	BUG_ON(!ops);
+
+	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+	return cpu_addr;
+}
 
 /**
- * dma_free_coherent - free memory allocated by dma_alloc_coherent
+ * arm_dma_free - free memory allocated by arm_dma_alloc
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @size: size of memory originally requested in dma_alloc_coherent
  * @cpu_addr: CPU-view address returned from dma_alloc_coherent
  * @handle: device-view address returned from dma_alloc_coherent
+ * @attrs: optinal attributes that specific mapping properties
  *
  * Free (and unmap) a DMA buffer previously allocated by
- * dma_alloc_coherent().
+ * arm_dma_alloc().
  *
  * References to memory and mappings associated with cpu_addr/handle
  * during and after this call executing are illegal.
  */
-extern void dma_free_coherent(struct device *, size_t, void *, dma_addr_t);
+extern void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
+			 dma_addr_t handle, struct dma_attrs *attrs);
+
+#define dma_free_coherent(d, s, c, h) dma_free_attrs(d, s, c, h, NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle,
+				     struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	ops->free(dev, size, cpu_addr, dma_handle, attrs);
+}
 
 /**
- * dma_mmap_coherent - map a coherent DMA allocation into user space
+ * arm_dma_mmap - map a coherent DMA allocation into user space
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @vma: vm_area_struct describing requested user mapping
  * @cpu_addr: kernel CPU-view address returned from dma_alloc_coherent
  * @handle: device-view address returned from dma_alloc_coherent
  * @size: size of memory originally requested in dma_alloc_coherent
+ * @attrs: optinal attributes that specific mapping properties
  *
  * Map a coherent DMA buffer previously allocated by dma_alloc_coherent
  * into user space.  The coherent DMA buffer must not be freed by the
  * driver until the user space mapping has been released.
  */
-int dma_mmap_coherent(struct device *, struct vm_area_struct *,
-		void *, dma_addr_t, size_t);
+extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+			void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			struct dma_attrs *attrs);
 
+#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL)
 
-/**
- * dma_alloc_writecombine - allocate writecombining memory for DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: required memory size
- * @handle: bus-specific DMA address
- *
- * Allocate some uncached, buffered memory for a device for
- * performing DMA.  This function allocates pages, and will
- * return the CPU-viewed address, and sets @handle to be the
- * device-viewed address.
- */
-extern void *dma_alloc_writecombine(struct device *, size_t, dma_addr_t *,
-		gfp_t);
+static inline int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size, struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+	return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+
+static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_alloc_attrs(dev, size, dma_handle, flag, &attrs);
+}
 
-#define dma_free_writecombine(dev,size,cpu_addr,handle) \
-	dma_free_coherent(dev,size,cpu_addr,handle)
+static inline void dma_free_writecombine(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs);
+}
 
-int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
-		void *, dma_addr_t, size_t);
+static inline int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
+		      void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
+}
 
 /*
  * This can be called during boot to increase the size of the consistent
@@ -212,8 +228,6 @@ int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
  */
 extern void __init init_consistent_dma_size(unsigned long size);
 
-
-#ifdef CONFIG_DMABOUNCE
 /*
  * For SA-1111, IXP425, and ADI systems  the dma-mapping functions are "magic"
  * and utilize bounce buffers as needed to work around limited DMA windows.
@@ -253,222 +267,19 @@ extern int dmabounce_register_dev(struct device *, unsigned long,
  */
 extern void dmabounce_unregister_dev(struct device *);
 
-/*
- * The DMA API, implemented by dmabounce.c.  See below for descriptions.
- */
-extern dma_addr_t __dma_map_page(struct device *, struct page *,
-		unsigned long, size_t, enum dma_data_direction);
-extern void __dma_unmap_page(struct device *, dma_addr_t, size_t,
-		enum dma_data_direction);
-
-/*
- * Private functions
- */
-int dmabounce_sync_for_cpu(struct device *, dma_addr_t, unsigned long,
-		size_t, enum dma_data_direction);
-int dmabounce_sync_for_device(struct device *, dma_addr_t, unsigned long,
-		size_t, enum dma_data_direction);
-#else
-static inline int dmabounce_sync_for_cpu(struct device *d, dma_addr_t addr,
-	unsigned long offset, size_t size, enum dma_data_direction dir)
-{
-	return 1;
-}
 
-static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
-	unsigned long offset, size_t size, enum dma_data_direction dir)
-{
-	return 1;
-}
-
-
-static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir)
-{
-	__dma_page_cpu_to_dev(page, offset, size, dir);
-	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
-}
-
-static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),
-		handle & ~PAGE_MASK, size, dir);
-}
-#endif /* CONFIG_DMABOUNCE */
-
-/**
- * dma_map_single - map a single buffer for streaming DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @cpu_addr: CPU direct mapped address of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Ensure that any data held in the cache is appropriately discarded
- * or written back.
- *
- * The device owns this memory once this call has completed.  The CPU
- * can regain ownership by calling dma_unmap_single() or
- * dma_sync_single_for_cpu().
- */
-static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-		size_t size, enum dma_data_direction dir)
-{
-	unsigned long offset;
-	struct page *page;
-	dma_addr_t addr;
-
-	BUG_ON(!virt_addr_valid(cpu_addr));
-	BUG_ON(!virt_addr_valid(cpu_addr + size - 1));
-	BUG_ON(!valid_dma_direction(dir));
-
-	page = virt_to_page(cpu_addr);
-	offset = (unsigned long)cpu_addr & ~PAGE_MASK;