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 <[e-mail]>:
"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

Documentation/kernel-parameters.txt

···
 			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
 			to determine OS memory pressure for page stealing by
 			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.

arch/Kconfig

···
 config HAVE_DMA_ATTRS
 	bool
 
+config HAVE_DMA_CONTIGUOUS
+	bool
+
 config USE_GENERIC_SMP_HELPERS
 	bool
 

arch/arm/Kconfig

···
 	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
···
 	  <http://www.arm.linux.org.uk/>.
 
 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

arch/arm/common/dmabounce.c

···
 	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;
 		}
···
 	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",
···
  * 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;
···
 
 	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
···
  * 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;
 
···
 
 	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);
···
 	buf = find_safe_buffer_dev(dev, addr, __func__);
 	if (!buf)
 		return 1;
+
+	off = addr - buf->safe_dma_addr;
 
 	BUG_ON(buf->direction != dir);
 
···
 	}
 	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);
···
 	buf = find_safe_buffer_dev(dev, addr, __func__);
 	if (!buf)
 		return 1;
+
+	off = addr - buf->safe_dma_addr;
 
 	BUG_ON(buf->direction != dir);
 
···
 	}
 	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)
···
 #endif
 
 	dev->archdata.dmabounce = device_info;
+	set_dma_ops(dev, &dmabounce_ops);
 
 	dev_info(dev, "dmabounce: registered device\n");
 
···
 	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
 
 	dev->archdata.dmabounce = NULL;
+	set_dma_ops(dev, NULL);
 
 	if (!device_info) {
 		dev_warn(dev,

arch/arm/include/asm/device.h

···
 #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
 };
 

arch/arm/include/asm/dma-contiguous.h

···
+#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

arch/arm/include/asm/dma-iommu.h

···
+#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

arch/arm/include/asm/dma-mapping.h

···
 
 #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
 
 /*
- * 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;
 }
 
 /*
···
 {
 }
 
+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);
+}
 
-#define dma_free_writecombine(dev,size,cpu_addr,handle) \
-	dma_free_coherent(dev,size,cpu_addr,handle)
+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);
+}
 
-int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
-		void *, dma_addr_t, size_t);
+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);
+}
+
+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
···
  */
 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.
···
  */
 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;
-	addr = __dma_map_page(dev, page, offset, size, dir);
-	debug_dma_map_page(dev, page, offset, size, dir, addr, true);
-
-	return addr;
-}
-
-/**
- * dma_map_page - map a portion of a page for streaming DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @page: page that buffer resides in
- * @offset: offset into page for start 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_page().
- */
-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_addr_t addr;
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	addr = __dma_map_page(dev, page, offset, size, dir);
-	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
-
-	return addr;
-}
-
-/**
- * dma_unmap_single - unmap a single buffer previously mapped
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @size: size of buffer (same as passed to dma_map_single)
- * @dir: DMA transfer direction (same as passed to dma_map_single)
- *
- * Unmap a single streaming mode DMA translation.  The handle and size
- * must match what was provided in the previous dma_map_single() call.
- * All other usages are undefined.
- *
- * After this call, reads by the CPU to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	debug_dma_unmap_page(dev, handle, size, dir, true);
-	__dma_unmap_page(dev, handle, size, dir);
-}
-
-/**
- * dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @size: size of buffer (same as passed to dma_map_page)
- * @dir: DMA transfer direction (same as passed to dma_map_page)
- *
- * Unmap a page streaming mode DMA translation.  The handle and size
- * must match what was provided in the previous dma_map_page() call.
- * All other usages are undefined.
- *
- * After this call, reads by the CPU to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-static inline void dma_unmap_page(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	debug_dma_unmap_page(dev, handle, size, dir, false);
-	__dma_unmap_page(dev, handle, size, dir);
-}
-
-/**
- * dma_sync_single_range_for_cpu
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @offset: offset of region to start sync
- * @size: size of region to sync
- * @dir: DMA transfer direction (same as passed to dma_map_single)
- *
- * Make physical memory consistent for a single streaming mode DMA
- * translation after a transfer.
- *
- * If you perform a dma_map_single() but wish to interrogate the
- * buffer using the cpu, yet do not wish to teardown the PCI dma
- * mapping, you must call this function before doing so.  At the
- * next point you give the PCI dma address back to the card, you
- * must first the perform a dma_sync_for_device, and then the
- * device again owns the buffer.
- */
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t handle, unsigned long offset, size_t size,
-		enum dma_data_direction dir)
-{
-	BUG_ON(!valid_dma_direction(dir));
-
-	debug_dma_sync_single_for_cpu(dev, handle + offset, size, dir);
-
-	if (!dmabounce_sync_for_cpu(dev, handle, offset, size, dir))
-		return;
-
-	__dma_single_dev_to_cpu(dma_to_virt(dev, handle) + offset, size, dir);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t handle, unsigned long offset, size_t size,
-		enum dma_data_direction dir)
-{
-	BUG_ON(!valid_dma_direction(dir));
-
-	debug_dma_sync_single_for_device(dev, handle + offset, size, dir);
-
-	if (!dmabounce_sync_for_device(dev, handle, offset, size, dir))
-		return;
-
-	__dma_single_cpu_to_dev(dma_to_virt(dev, handle) + offset, size, dir);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	dma_sync_single_range_for_cpu(dev, handle, 0, size, dir);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	dma_sync_single_range_for_device(dev, handle, 0, size, dir);
-}
 
 /*
  * The scatter list versions of the above methods.
  */
-extern int dma_map_sg(struct device *, struct scatterlist *, int,
+extern int arm_dma_map_sg(struct device *, struct scatterlist *, int,
+		enum dma_data_direction, struct dma_attrs *attrs);
+extern void arm_dma_unmap_sg(struct device *, struct scatterlist *, int,
+		enum dma_data_direction, struct dma_attrs *attrs);
+extern void arm_dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
 		enum dma_data_direction);
-extern void dma_unmap_sg(struct device *, struct scatterlist *, int,
+extern void arm_dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
 		enum dma_data_direction);
-extern void dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
-		enum dma_data_direction);
-extern void dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
-		enum dma_data_direction);
-
 
 #endif /* __KERNEL__ */
 #endif

arch/arm/include/asm/mach/map.h

···
 #define MT_MEMORY_DTCM		12
 #define MT_MEMORY_ITCM		13
 #define MT_MEMORY_SO		14
+#define MT_MEMORY_DMA_READY	15
 
 #ifdef CONFIG_MMU
 extern void iotable_init(struct map_desc *, int);

arch/arm/kernel/setup.c

···
 extern void paging_init(struct machine_desc *desc);
 extern void sanity_check_meminfo(void);
 extern void reboot_setup(char *str);
+extern void setup_dma_zone(struct machine_desc *desc);
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
···
 	machine_desc = mdesc;
 	machine_name = mdesc->name;
 
-#ifdef CONFIG_ZONE_DMA
-	if (mdesc->dma_zone_size) {
-		extern unsigned long arm_dma_zone_size;
-		arm_dma_zone_size = mdesc->dma_zone_size;
-	}
-#endif
+	setup_dma_zone(mdesc);
+
 	if (mdesc->restart_mode)
 		reboot_setup(&mdesc->restart_mode);
 

arch/arm/mm/dma-mapping.c

···
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 #include <linux/slab.h>
+#include <linux/iommu.h>
+#include <linux/vmalloc.h>
 
 #include <asm/memory.h>
 #include <asm/highmem.h>
···
 #include <asm/tlbflush.h>
 #include <asm/sizes.h>
 #include <asm/mach/arch.h>
+#include <asm/dma-iommu.h>
+#include <asm/mach/map.h>
+#include <asm/system_info.h>
+#include <asm/dma-contiguous.h>
 
 #include "mm.h"
+
+/*
+ * 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.
+ *
+ */
+static void __dma_page_cpu_to_dev(struct page *, unsigned long,
+		size_t, enum dma_data_direction);
+static void __dma_page_dev_to_cpu(struct page *, unsigned long,
+		size_t, enum dma_data_direction);
+
+/**
+ * arm_dma_map_page - map a portion of a page for streaming DMA
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @page: page that buffer resides in
+ * @offset: offset into page for start 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_page().
+ */
+static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir,
+	     struct dma_attrs *attrs)
+{
+	if (!arch_is_coherent())
+		__dma_page_cpu_to_dev(page, offset, size, dir);
+	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
+}
+
+/**
+ * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @handle: DMA address of buffer
+ * @size: size of buffer (same as passed to dma_map_page)
+ * @dir: DMA transfer direction (same as passed to dma_map_page)
+ *
+ * Unmap a page streaming mode DMA translation.  The handle and size
+ * must match what was provided in the previous dma_map_page() call.
+ * All other usages are undefined.
+ *
+ * After this call, reads by the CPU to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ */
+static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	if (!arch_is_coherent())
+		__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),
+				      handle & ~PAGE_MASK, size, dir);
+}
+
+static void arm_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned int offset = handle & (PAGE_SIZE - 1);
+	struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
+	if (!arch_is_coherent())
+		__dma_page_dev_to_cpu(page, offset, size, dir);
+}
+
+static void arm_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned int offset = handle & (PAGE_SIZE - 1);
+	struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
+	if (!arch_is_coherent())
+		__dma_page_cpu_to_dev(page, offset, size, dir);
+}
+
+static int arm_dma_set_mask(struct device *dev, u64 dma_mask);
+
+struct dma_map_ops arm_dma_ops = {
+	.alloc			= arm_dma_alloc,
+	.free			= arm_dma_free,
+	.mmap			= arm_dma_mmap,
+	.map_page		= arm_dma_map_page,
+	.unmap_page		= arm_dma_unmap_page,
+	.map_sg			= arm_dma_map_sg,
+	.unmap_sg		= arm_dma_unmap_sg,
+	.sync_single_for_cpu	= arm_dma_sync_single_for_cpu,
+	.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,
+	.set_dma_mask		= arm_dma_set_mask,
+};
+EXPORT_SYMBOL(arm_dma_ops);
 
 static u64 get_coherent_dma_mask(struct device *dev)
 {
···
 	return mask;
 }
 
+static void __dma_clear_buffer(struct page *page, size_t size)
+{
+	void *ptr;
+	/*
+	 * Ensure that the allocated pages are zeroed, and that any data
+	 * lurking in the kernel direct-mapped region is invalidated.
+	 */
+	ptr = page_address(page);
+	if (ptr) {
+		memset(ptr, 0, size);
+		dmac_flush_range(ptr, ptr + size);
+		outer_flush_range(__pa(ptr), __pa(ptr) + size);
+	}
+}
+
 /*
  * Allocate a DMA buffer for 'dev' of size 'size' using the
  * specified gfp mask.  Note that 'size' must be page aligned.
···
 {
 	unsigned long order = get_order(size);
 	struct page *page, *p, *e;
-	void *ptr;
-	u64 mask = get_coherent_dma_mask(dev);
-
-#ifdef CONFIG_DMA_API_DEBUG
-	u64 limit = (mask + 1) & ~mask;
-	if (limit && size >= limit) {
-		dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n",
-			size, mask);
-		return NULL;
-	}
-#endif
-
-	if (!mask)
-		return NULL;
-
-	if (mask < 0xffffffffULL)
-		gfp |= GFP_DMA;
 
 	page = alloc_pages(gfp, order);
 	if (!page)
···
 	for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
 		__free_page(p);
 
-	/*
-	 * Ensure that the allocated pages are zeroed, and that any data
-	 * lurking in the kernel direct-mapped region is invalidated.
-	 */
-	ptr = page_address(page);
-	memset(ptr, 0, size);
-	dmac_flush_range(ptr, ptr + size);
-	outer_flush_range(__pa(ptr), __pa(ptr) + size);
+	__dma_clear_buffer(page, size);
 
 	return page;
 }
···
 	unsigned long base = consistent_base;
 	unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
 
+#ifndef CONFIG_ARM_DMA_USE_IOMMU
+	if (cpu_architecture() >= CPU_ARCH_ARMv6)
+		return 0;
+#endif
+
 	consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
 	if (!consistent_pte) {
 		pr_err("%s: no memory\n", __func__);
···
 
 		pud = pud_alloc(&init_mm, pgd, base);
 		if (!pud) {
-			printk(KERN_ERR "%s: no pud tables\n", __func__);
+			pr_err("%s: no pud tables\n", __func__);
 			ret = -ENOMEM;
 			break;
 		}
 
 		pmd = pmd_alloc(&init_mm, pud, base);
 		if (!pmd) {
-			printk(KERN_ERR "%s: no pmd tables\n", __func__);
+			pr_err("%s: no pmd tables\n", __func__);
 			ret = -ENOMEM;
 			break;
 		}
···
 
 		pte = pte_alloc_kernel(pmd, base);
 		if (!pte) {
-			printk(KERN_ERR "%s: no pte tables\n", __func__);
+			pr_err("%s: no pte tables\n", __func__);
 			ret = -ENOMEM;
 			break;
 		}
···
 
 	return ret;
 }
-
 core_initcall(consistent_init);
+
+static void *__alloc_from_contiguous(struct device *dev, size_t size,
+				     pgprot_t prot, struct page **ret_page);
+
+static struct arm_vmregion_head coherent_head = {
+	.vm_lock	= __SPIN_LOCK_UNLOCKED(&coherent_head.vm_lock),
+	.vm_list	= LIST_HEAD_INIT(coherent_head.vm_list),
+};
+
+size_t coherent_pool_size = DEFAULT_CONSISTENT_DMA_SIZE / 8;
+
+static int __init early_coherent_pool(char *p)
+{
+	coherent_pool_size = memparse(p, &p);
+	return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+/*
+ * Initialise the coherent pool for atomic allocations.
+ */
+static int __init coherent_init(void)
+{
+	pgprot_t prot = pgprot_dmacoherent(pgprot_kernel);
+	size_t size = coherent_pool_size;
+	struct page *page;
+	void *ptr;
+
+	if (cpu_architecture() < CPU_ARCH_ARMv6)
+		return 0;
+
+	ptr = __alloc_from_contiguous(NULL, size, prot, &page);
+	if (ptr) {
+		coherent_head.vm_start = (unsigned long) ptr;
+		coherent_head.vm_end = (unsigned long) ptr + size;
+		printk(KERN_INFO "DMA: preallocated %u KiB pool for atomic coherent allocations\n",
+		       (unsigned)size / 1024);
+		return 0;
+	}
+	printk(KERN_ERR "DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
+	       (unsigned)size / 1024);
+	return -ENOMEM;
+}
+/*
+ * CMA is activated by core_initcall, so we must be called after it.
+ */
+postcore_initcall(coherent_init);
+
+struct dma_contig_early_reserve {
+	phys_addr_t base;
+	unsigned long size;
+};
+
+static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata;
+
+static int dma_mmu_remap_num __initdata;
+
+void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+	dma_mmu_remap[dma_mmu_remap_num].base = base;
+	dma_mmu_remap[dma_mmu_remap_num].size = size;
+	dma_mmu_remap_num++;
+}
+
+void __init dma_contiguous_remap(void)
+{
+	int i;
+	for (i = 0; i < dma_mmu_remap_num; i++) {
+		phys_addr_t start = dma_mmu_remap[i].base;
+		phys_addr_t end = start + dma_mmu_remap[i].size;
+		struct map_desc map;
+		unsigned long addr;
+
+		if (end > arm_lowmem_limit)
+			end = arm_lowmem_limit;
+		if (start >= end)
+			return;
+
+		map.pfn = __phys_to_pfn(start);
+		map.virtual = __phys_to_virt(start);
+		map.length = end - start;
+		map.type = MT_MEMORY_DMA_READY;
+
+		/*
+		 * Clear previous low-memory mapping
+		 */
+		for (addr = __phys_to_virt(start); addr < __phys_to_virt(end);
+		     addr += PMD_SIZE)
+			pmd_clear(pmd_off_k(addr));
+
+		iotable_init(&map, 1);
+	}
+}
 
 static void *
 __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
···
 	int bit;
 
 	if (!consistent_pte) {
-		printk(KERN_ERR "%s: not initialised\n", __func__);
+		pr_err("%s: not initialised\n", __func__);
 		dump_stack();
 		return NULL;
 	}
···
 		u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
 
 		pte = consistent_pte[idx] + off;
-		c->vm_pages = page;
+		c->priv = page;
 
 		do {
 			BUG_ON(!pte_none(*pte));
···
 
 	c = arm_vmregion_find_remove(&consistent_head, (unsigned long)cpu_addr);
 	if (!c) {
-		printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
+		pr_err("%s: trying to free invalid coherent area: %p\n",
 		       __func__, cpu_addr);
 		dump_stack();
 		return;
 	}
 
 	if ((c->vm_end - c->vm_start) != size) {
-		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
+		pr_err("%s: freeing wrong coherent size (%ld != %d)\n",
 		       __func__, c->vm_end - c->vm_start, size);
 		dump_stack();
 		size = c->vm_end - c->vm_start;
···
 		}
 
 		if (pte_none(pte) || !pte_present(pte))
-			printk(KERN_CRIT "%s: bad page in kernel page table\n",
-			       __func__);
+			pr_crit("%s: bad page in kernel page table\n",
+				__func__);
 	} while (size -= PAGE_SIZE);
 
 	flush_tlb_kernel_range(c->vm_start, c->vm_end);
···
 	arm_vmregion_free(&consistent_head, c);
 }
 
+static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr,
+			    void *data)
+{
+	struct page *page = virt_to_page(addr);
+	pgprot_t prot = *(pgprot_t *)data;
+
+	set_pte_ext(pte, mk_pte(page, prot), 0);
+	return 0;
+}
+
+static void __dma_remap(struct page *page, size_t size, pgprot_t prot)
+{
+	unsigned long start = (unsigned long) page_address(page);
+	unsigned end = start + size;
+
+	apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot);
+	dsb();
+	flush_tlb_kernel_range(start, end);
+}
+
+static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
+				 pgprot_t prot, struct page **ret_page,
+				 const void *caller)
+{
+	struct page *page;
+	void *ptr;
+	page = __dma_alloc_buffer(dev, size, gfp);
+	if (!page)
+		return NULL;
+
+	ptr = __dma_alloc_remap(page, size, gfp, prot, caller);
+	if (!ptr) {
+		__dma_free_buffer(page, size);
+		return NULL;
+	}
+
+	*ret_page = page;
+	return ptr;
+}
+
+static void *__alloc_from_pool(struct device *dev, size_t size,
+			       struct page **ret_page, const void *caller)
+{
+	struct arm_vmregion *c;
+	size_t align;
+
+	if (!coherent_head.vm_start) {
+		printk(KERN_ERR "%s: coherent pool not initialised!\n",
+		       __func__);
+		dump_stack();
+		return NULL;
+	}
+
+	/*
+	 * Align the region allocation - allocations from pool are rather
+	 * small, so align them to their order in pages, minimum is a page
+	 * size. This helps reduce fragmentation of the DMA space.
+	 */
+	align = PAGE_SIZE << get_order(size);
+	c = arm_vmregion_alloc(&coherent_head, align, size, 0, caller);
+	if (c) {
+		void *ptr = (void *)c->vm_start;
+		struct page *page = virt_to_page(ptr);
+		*ret_page = page;
+		return ptr;
+	}
+	return NULL;
+}
+
+static int __free_from_pool(void *cpu_addr, size_t size)
+{
+	unsigned long start = (unsigned long)cpu_addr;
+	unsigned long end = start + size;
+	struct arm_vmregion *c;
+
+	if (start < coherent_head.vm_start || end > coherent_head.vm_end)
+		return 0;
+
+	c = arm_vmregion_find_remove(&coherent_head, (unsigned long)start);
+
+	if ((c->vm_end - c->vm_start) != size) {
+		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
+		       __func__, c->vm_end - c->vm_start, size);
+		dump_stack();
+		size = c->vm_end - c->vm_start;
+	}
+
+	arm_vmregion_free(&coherent_head, c);
+	return 1;
+}
+
+static void *__alloc_from_contiguous(struct device *dev, size_t size,
+				     pgprot_t prot, struct page **ret_page)
+{
+	unsigned long order = get_order(size);
+	size_t count = size >> PAGE_SHIFT;
+	struct page *page;
+
+	page = dma_alloc_from_contiguous(dev, count, order);
+	if (!page)
+		return NULL;
+
+	__dma_clear_buffer(page, size);
+	__dma_remap(page, size, prot);
+
+	*ret_page = page;
+	return page_address(page);
+}
+
+static void __free_from_contiguous(struct device *dev, struct page *page,
+				   size_t size)
+{
+	__dma_remap(page, size, pgprot_kernel);
+	dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
+}
+
+static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
+{
+	prot = dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs) ?
+			    pgprot_writecombine(prot) :
+			    pgprot_dmacoherent(prot);
+	return prot;
+}
+
+#define nommu() 0
+
 #else	/* !CONFIG_MMU */
 
-#define __dma_alloc_remap(page, size, gfp, prot, c)	page_address(page)
-#define __dma_free_remap(addr, size)			do { } while (0)
+#define nommu() 1
+
+#define __get_dma_pgprot(attrs, prot)	__pgprot(0)
+#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c)	NULL
+#define __alloc_from_pool(dev, size, ret_page, c)		NULL
+#define __alloc_from_contiguous(dev, size, prot, ret)		NULL
+#define __free_from_pool(cpu_addr, size)			0
+#define __free_from_contiguous(dev, page, size)			do { } while (0)
+#define __dma_free_remap(cpu_addr, size)			do { } while (0)
 
 #endif	/* CONFIG_MMU */
 
-static void *
-__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
-	    pgprot_t prot, const void *caller)
+static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
+				   struct page **ret_page)
 {
 	struct page *page;
+	page = __dma_alloc_buffer(dev, size, gfp);
+	if (!page)
+		return NULL;
+
+	*ret_page = page;
+	return page_address(page);
+}
+
+
+
+static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+			 gfp_t gfp, pgprot_t prot, const void *caller)
+{
+	u64 mask = get_coherent_dma_mask(dev);
+	struct page *page;
 	void *addr;
+
+#ifdef CONFIG_DMA_API_DEBUG
+	u64 limit = (mask + 1) & ~mask;
+	if (limit && size >= limit) {
+		dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n",
+			size, mask);
+		return NULL;
+	}
+#endif
+
+	if (!mask)
+		return NULL;
+
+	if (mask < 0xffffffffULL)
+		gfp |= GFP_DMA;
 
 	/*
 	 * Following is a work-around (a.k.a. hack) to prevent pages
···
 	 */
 	gfp &= ~(__GFP_COMP);
 
-	*handle = ~0;
+	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
-	page = __dma_alloc_buffer(dev, size, gfp);
-	if (!page)
-		return NULL;
-
-	if (!arch_is_coherent())
-		addr = __dma_alloc_remap(page, size, gfp, prot, caller);
+	if (arch_is_coherent() || nommu())
+		addr = __alloc_simple_buffer(dev, size, gfp, &page);
+	else if (cpu_architecture() < CPU_ARCH_ARMv6)
+		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
+	else if (gfp & GFP_ATOMIC)
+		addr = __alloc_from_pool(dev, size, &page, caller);
 	else
-		addr = page_address(page);
+		addr = __alloc_from_contiguous(dev, size, prot, &page);
 
 	if (addr)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
-	else
-		__dma_free_buffer(page, size);
 
 	return addr;
 }
···
  * Allocate DMA-coherent memory space and return both the kernel remapped
  * virtual and bus address for that space.
  */
-void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
+void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		    gfp_t gfp, struct dma_attrs *attrs)
 {
+	pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
 		return memory;
 
-	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_dmacoherent(pgprot_kernel),
+	return __dma_alloc(dev, size, handle, gfp, prot,
 			   __builtin_return_address(0));
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
 /*
- * Allocate a writecombining region, in much the same way as
- * dma_alloc_coherent above.
+ * Create userspace mapping for the DMA-coherent memory.
  */
-void *
-dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
-{
-	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_writecombine(pgprot_kernel),
-			   __builtin_return_address(0));
-}
-EXPORT_SYMBOL(dma_alloc_writecombine);
-
-static int dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		    void *cpu_addr, dma_addr_t dma_addr, size_t size)
+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)
 {
 	int ret = -ENXIO;
 #ifdef CONFIG_MMU
-	unsigned long user_size, kern_size;
-	struct arm_vmregion *c;
+	unsigned long pfn = dma_to_pfn(dev, dma_addr);
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
 
-	user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
 
-	c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
-	if (c) {
-		unsigned long off = vma->vm_pgoff;
-
-		kern_size = (c->vm_end - c->vm_start) >> PAGE_SHIFT;
-
-		if (off < kern_size &&
-		    user_size <= (kern_size - off)) {
-			ret = remap_pfn_range(vma, vma->vm_start,
-					      page_to_pfn(c->vm_pages) + off,
-					      user_size << PAGE_SHIFT,
-					      vma->vm_page_prot);
-		}
-	}
+	ret = remap_pfn_range(vma, vma->vm_start,
+			      pfn + vma->vm_pgoff,
+			      vma->vm_end - vma->vm_start,
+			      vma->vm_page_prot);
 #endif	/* CONFIG_MMU */
 
 	return ret;
 }
 
-int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
-		      void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
-	vma->vm_page_prot = pgprot_dmacoherent(vma->vm_page_prot);
-	return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
-}
-EXPORT_SYMBOL(dma_mmap_coherent);
-
-int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
-			  void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
-	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-	return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
-}
-EXPORT_SYMBOL(dma_mmap_writecombine);
-
 /*
- * free a page as defined by the above mapping.
- * Must not be called with IRQs disabled.
+ * Free a buffer as defined by the above mapping.
  */
-void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle)
+void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		  dma_addr_t handle, struct dma_attrs *attrs)
 {
-	WARN_ON(irqs_disabled());
+	struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
 
 	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
 		return;
 
 	size = PAGE_ALIGN(size);
 
-	if (!arch_is_coherent())
+	if (arch_is_coherent() || nommu()) {
+		__dma_free_buffer(page, size);
+	} else if (cpu_architecture() < CPU_ARCH_ARMv6) {
 		__dma_free_remap(cpu_addr, size);
-
-	__dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size);
-}
-EXPORT_SYMBOL(dma_free_coherent);
-
-/*
- * Make an area consistent for devices.
- * Note: Drivers should NOT use this function directly, as it will break
- * platforms with CONFIG_DMABOUNCE.
- * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
- */
-void ___dma_single_cpu_to_dev(const void *kaddr, size_t size,
-	enum dma_data_direction dir)
-{
-	unsigned long paddr;
-
-	BUG_ON(!virt_addr_valid(kaddr) || !virt_addr_valid(kaddr + size - 1));
-
-	dmac_map_area(kaddr, size, dir);
-
-	paddr = __pa(kaddr);
-	if (dir == DMA_FROM_DEVICE) {
-		outer_inv_range(paddr, paddr + size);
+		__dma_free_buffer(page, size);
 	} else {
-		outer_clean_range(paddr, paddr + size);
+		if (__free_from_pool(cpu_addr, size))
+			return;
+		/*
+		 * Non-atomic allocations cannot be freed with IRQs disabled
+		 */
+		WARN_ON(irqs_disabled());
+		__free_from_contiguous(dev, page, size);
 	}
-	/* FIXME: non-speculating: flush on bidirectional mappings? */
 }
-EXPORT_SYMBOL(___dma_single_cpu_to_dev);
-
-void ___dma_single_dev_to_cpu(const void *kaddr, size_t size,
-	enum dma_data_direction dir)
-{
-	BUG_ON(!virt_addr_valid(kaddr) || !virt_addr_valid(kaddr + size - 1));
-
-	/* FIXME: non-speculating: not required */
-	/* don't bother invalidating if DMA to device */
-	if (dir != DMA_TO_DEVICE) {
-		unsigned long paddr = __pa(kaddr);
-		outer_inv_range(paddr, paddr + size);
-	}
-
-	dmac_unmap_area(kaddr, size, dir);
-}
-EXPORT_SYMBOL(___dma_single_dev_to_cpu);
 
 static void dma_cache_maint_page(struct page *page, unsigned long offset,
 	size_t size, enum dma_data_direction dir,
···
 	} while (left);
 }
 
-void ___dma_page_cpu_to_dev(struct page *page, unsigned long off,
+/*
+ * Make an area consistent for devices.
+ * Note: Drivers should NOT use this function directly, as it will break
+ * platforms with CONFIG_DMABOUNCE.
+ * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
+ */
+static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
 	size_t size, enum dma_data_direction dir)
 {
 	unsigned long paddr;
···
 	}
 	/* FIXME: non-speculating: flush on bidirectional mappings? */
 }
-EXPORT_SYMBOL(___dma_page_cpu_to_dev);
 
-void ___dma_page_dev_to_cpu(struct page *page, unsigned long off,
+static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 	size_t size, enum dma_data_direction dir)
 {
 	unsigned long paddr = page_to_phys(page) + off;
···
 	if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
 		set_bit(PG_dcache_clean, &page->flags);
 }
-EXPORT_SYMBOL(___dma_page_dev_to_cpu);
 
 /**
- * dma_map_sg - map a set of SG buffers for streaming mode DMA
+ * arm_dma_map_sg - map a set of SG buffers for streaming mode DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @sg: list of buffers
  * @nents: number of buffers to map
···
  * Device ownership issues as mentioned for dma_map_single are the same
  * here.
  */
-int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir)
+int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, struct dma_attrs *attrs)
 {
+	struct dma_map_ops *ops = get_dma_ops(dev);
 	struct scatterlist *s;
 	int i, j;
 
-	BUG_ON(!valid_dma_direction(dir));
-
 	for_each_sg(sg, s, nents, i) {
-		s->dma_address = __dma_map_page(dev, sg_page(s), s->offset,
-						s->length, dir);
+#ifdef CONFIG_NEED_SG_DMA_LENGTH
+		s->dma_length = s->length;
+#endif
+		s->dma_address = ops->map_page(dev, sg_page(s), s->offset,
+						s->length, dir, attrs);
 		if (dma_mapping_error(dev, s->dma_address))
 			goto bad_mapping;
 	}
-	debug_dma_map_sg(dev, sg, nents, nents, dir);
 	return nents;
 
  bad_mapping:
 	for_each_sg(sg, s, i, j)
-		__dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+		ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs);
 	return 0;
 }
-EXPORT_SYMBOL(dma_map_sg);
 
 /**
- * dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
+ * arm_dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @sg: list of buffers
  * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
···
  * Unmap a set of streaming mode DMA translations.  Again, CPU access
  * rules concerning calls here are the same as for dma_unmap_single().
  */
-void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir)
+void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, struct dma_attrs *attrs)
 {
+	struct dma_map_ops *ops = get_dma_ops(dev);
 	struct scatterlist *s;
-	int i;
 
-	debug_dma_unmap_sg(dev, sg, nents, dir);
+	int i;
 
 	for_each_sg(sg, s, nents, i)
-		__dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+		ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs);
 }
-EXPORT_SYMBOL(dma_unmap_sg);
 
 /**
- * dma_sync_sg_for_cpu
+ * arm_dma_sync_sg_for_cpu
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @sg: list of buffers
  * @nents: number of buffers to map (returned from dma_map_sg)
  * @dir: DMA transfer direction (same as was passed to dma_map_sg)
  */
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 			int nents, enum dma_data_direction dir)
 {
+	struct dma_map_ops *ops = get_dma_ops(dev);
 	struct scatterlist *s;
 	int i;
 
-	for_each_sg(sg, s, nents, i) {
-		if (!dmabounce_sync_for_cpu(dev, sg_dma_address(s), 0,
-					    sg_dma_len(s), dir))
-			continue;
-
-		__dma_page_dev_to_cpu(sg_page(s), s->offset,
-				      s->length, dir);
-	}
-
-	debug_dma_sync_sg_for_cpu(dev, sg, nents, dir);
+	for_each_sg(sg, s, nents, i)
+		ops->sync_single_for_cpu(dev, sg_dma_address(s), s->length,
+					 dir);
 }
-EXPORT_SYMBOL(dma_sync_sg_for_cpu);
 
 /**
- * dma_sync_sg_for_device
+ * arm_dma_sync_sg_for_device
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @sg: list of buffers
  * @nents: number of buffers to map (returned from dma_map_sg)
  * @dir: DMA transfer direction (same as was passed to dma_map_sg)
  */
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 			int nents, enum dma_data_direction dir)
 {
+	struct dma_map_ops *ops = get_dma_ops(dev);
 	struct scatterlist *s;
 	int i;
 
-	for_each_sg(sg, s, nents, i) {
-		if (!dmabounce_sync_for_device(dev, sg_dma_address(s), 0,
-					sg_dma_len(s), dir))
-			continue;
-
-		__dma_page_cpu_to_dev(sg_page(s), s->offset,
-				      s->length, dir);
-	}
-
-	debug_dma_sync_sg_for_device(dev, sg, nents, dir);
+	for_each_sg(sg, s, nents, i)
+		ops->sync_single_for_device(dev, sg_dma_address(s), s->length,
+					    dir);
 }
-EXPORT_SYMBOL(dma_sync_sg_for_device);
 
 /*
  * Return whether the given device DMA address mask can be supported
···
 }
 EXPORT_SYMBOL(dma_supported);
 
-int dma_set_mask(struct device *dev, u64 dma_mask)
+static int arm_dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
 		return -EIO;
 
-#ifndef CONFIG_DMABOUNCE
 	*dev->dma_mask = dma_mask;
-#endif
 
 	return 0;
 }
-EXPORT_SYMBOL(dma_set_mask);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
···
 	return 0;
 }
 fs_initcall(dma_debug_do_init);
+
+#ifdef CONFIG_ARM_DMA_USE_IOMMU
+
+/* IOMMU */
+
+static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
+				      size_t size)
+{
+	unsigned int order = get_order(size);
+	unsigned int align = 0;
+	unsigned int count, start;
+	unsigned long flags;
+
+	count = ((PAGE_ALIGN(size) >> PAGE_SHIFT) +
+		 (1 << mapping->order) - 1) >> mapping->order;
+
+	if (order > mapping->order)
+		align = (1 << (order - mapping->order)) - 1;
+
+	spin_lock_irqsave(&mapping->lock, flags);
+	start = bitmap_find_next_zero_area(mapping->bitmap, mapping->bits, 0,
+					   count, align);
+	if (start > mapping->bits) {
+		spin_unlock_irqrestore(&mapping->lock, flags);
+		return DMA_ERROR_CODE;
+	}
+
+	bitmap_set(mapping->bitmap, start, count);
+	spin_unlock_irqrestore(&mapping->lock, flags);
+
+	return mapping->base + (start << (mapping->order + PAGE_SHIFT));
+}
+
+static inline void __free_iova(struct dma_iommu_mapping *mapping,
+			       dma_addr_t addr, size_t size)
+{
+	unsigned int start = (addr - mapping->base) >>
+			     (mapping->order + PAGE_SHIFT);
+	unsigned int count = ((size >> PAGE_SHIFT) +
+			      (1 << mapping->order) - 1) >> mapping->order;
+	unsigned long flags;
+
+	spin_lock_irqsave(&mapping->lock, flags);
+	bitmap_clear(mapping->bitmap, start, count);
+	spin_unlock_irqrestore(&mapping->lock, flags);
+}
+
+static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
+{
+	struct page **pages;
+	int count = size >> PAGE_SHIFT;
+	int array_size = count * sizeof(struct page *);
+	int i = 0;
+
+	if (array_size <= PAGE_SIZE)
+		pages = kzalloc(array_size, gfp);
+	else
+		pages = vzalloc(array_size);
+	if (!pages)
+		return NULL;
+
+	while (count) {
+		int j, order = __ffs(count);
+
+		pages[i] = alloc_pages(gfp | __GFP_NOWARN, order);
+		while (!pages[i] && order)
+			pages[i] = alloc_pages(gfp | __GFP_NOWARN, --order);
+		if (!pages[i])
+			goto error;
+
+		if (order)
+			split_page(pages[i], order);
+		j = 1 << order;
+		while (--j)
+			pages[i + j] = pages[i] + j;
+
+		__dma_clear_buffer(pages[i], PAGE_SIZE << order);
+		i += 1 << order;
+		count -= 1 << order;
+	}
+
+	return pages;
+error:
+	while (--i)
+		if (pages[i])
+			__free_pages(pages[i], 0);
+	if (array_size < PAGE_SIZE)
+		kfree(pages);
+	else
+		vfree(pages);
+	return NULL;
+}
+
+static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t size)
+{
+	int count = size >> PAGE_SHIFT;
+	int array_size = count * sizeof(struct page *);
+	int i;
+	for (i = 0; i < count; i++)
+		if (pages[i])
+			__free_pages(pages[i], 0);
+	if (array_size < PAGE_SIZE)
+		kfree(pages);
+	else
+		vfree(pages);
+	return 0;
+}
+
+/*
+ * Create a CPU mapping for a specified pages
+ */
+static void *
+__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot)
+{
+	struct arm_vmregion *c;
+	size_t align;
+	size_t count = size >> PAGE_SHIFT;
+	int bit;
+
+	if (!consistent_pte[0]) {
+		pr_err("%s: not initialised\n", __func__);
+		dump_stack();
+		return NULL;
+	}
+
+	/*
+	 * Align the virtual region allocation - maximum alignment is
+	 * a section size, minimum is a page size.  This helps reduce
+	 * fragmentation of the DMA space, and also prevents allocations
+	 * smaller than a section from crossing a section boundary.
+	 */
+	bit = fls(size - 1);
+	if (bit > SECTION_SHIFT)
+		bit = SECTION_SHIFT;
+	align = 1 << bit;
+
+	/*
+	 * Allocate a virtual address in the consistent mapping region.
+	 */
+	c = arm_vmregion_alloc(&consistent_head, align, size,
+			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM), NULL);
+	if (c) {
+		pte_t *pte;
+		int idx = CONSISTENT_PTE_INDEX(c->vm_start);
+		int i = 0;
+		u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
+
+		pte = consistent_pte[idx] + off;
+		c->priv = pages;
+
+		do {
+			BUG_ON(!pte_none(*pte));
+
+			set_pte_ext(pte, mk_pte(pages[i], prot), 0);
+			pte++;
+			off++;
+			i++;
+			if (off >= PTRS_PER_PTE) {
+				off = 0;
+				pte = consistent_pte[++idx];
+			}
+		} while (i < count);
+
+		dsb();
+
+		return (void *)c->vm_start;
+	}
+	return NULL;
+}
+
+/*
+ * Create a mapping in device IO address space for specified pages
+ */
+static dma_addr_t
+__iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
+{
+	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	dma_addr_t dma_addr, iova;
+	int i, ret = DMA_ERROR_CODE;
+
+	dma_addr = __alloc_iova(mapping, size);
+	if (dma_addr == DMA_ERROR_CODE)
+		return dma_addr;
+
+	iova = dma_addr;
+	for (i = 0; i < count; ) {
+		unsigned int next_pfn = page_to_pfn(pages[i]) + 1;
+		phys_addr_t phys = page_to_phys(pages[i]);
+		unsigned int len, j;
+
+		for (j = i + 1; j < count; j++, next_pfn++)
+			if (page_to_pfn(pages[j]) != next_pfn)
+				break;
+
+		len = (j - i) << PAGE_SHIFT;
+		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		if (ret < 0)
+			goto fail;
+		iova += len;
+		i = j;
+	}
+	return dma_addr;
+fail:
+	iommu_unmap(mapping->domain, dma_addr, iova-dma_addr);
+	__free_iova(mapping, dma_addr, size);
+	return DMA_ERROR_CODE;
+}
+
+static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size)
+{
+	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+
+	/*
+	 * add optional in-page offset from iova to size and align
+	 * result to page size
+	 */
+	size = PAGE_ALIGN((iova & ~PAGE_MASK) + size);
+	iova &= PAGE_MASK;
+
+	iommu_unmap(mapping->domain, iova, size);
+	__free_iova(mapping, iova, size);
+	return 0;
+}
+
+static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
+	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+	pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
+	struct page **pages;
+	void *addr = NULL;
+
+	*handle = DMA_ERROR_CODE;
+	size = PAGE_ALIGN(size);
+
+	pages = __iommu_alloc_buffer(dev, size, gfp);
+	if (!pages)
+		return NULL;
+
+	*handle = __iommu_create_mapping(dev, pages, size);
+	if (*handle == DMA_ERROR_CODE)
+		goto err_buffer;
+
+	addr = __iommu_alloc_remap(pages, size, gfp, prot);
+	if (!addr)
+		goto err_mapping;
+
+	return addr;
+
+err_mapping:
+	__iommu_remove_mapping(dev, *handle, size);
+err_buffer:
+	__iommu_free_buffer(dev, pages, size);
+	return NULL;
+}
+
+static int arm_iommu_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 arm_vmregion *c;
+
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
+	c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
+
+	if (c) {
+		struct page **pages = c->priv;
+
+		unsigned long uaddr = vma->vm_start;
+		unsigned long usize = vma->vm_end - vma->vm_start;
+		int i = 0;
+
+		do {
+			int ret;
+
+			ret = vm_insert_page(vma, uaddr, pages[i++]);
+			if (ret) {
+				pr_err("Remapping memory, error: %d\n", ret);
+				return ret;
+			}
+
+			uaddr += PAGE_SIZE;
+			usize -= PAGE_SIZE;
+		} while (usize > 0);
+	}
+	return 0;
+}
+
+/*
+ * free a page as defined by the above mapping.
+ * Must not be called with IRQs disabled.
+ */
+void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+			  dma_addr_t handle, struct dma_attrs *attrs)
+{
+	struct arm_vmregion *c;
+	size = PAGE_ALIGN(size);
+
+	c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
+	if (c) {
+		struct page **pages = c->priv;
+		__dma_free_remap(cpu_addr, size);
+		__iommu_remove_mapping(dev, handle, size);
+		__iommu_free_buffer(dev, pages, size);
+	}
+}
+
+/*
+ * Map a part of the scatter-gather list into contiguous io address space
+ */
+static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
+			  size_t size, dma_addr_t *handle,
+			  enum dma_data_direction dir)
+{
+	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	dma_addr_t iova, iova_base;
+	int ret = 0;
+	unsigned int count;
+	struct scatterlist *s;
+
+	size = PAGE_ALIGN(size);
+	*handle = DMA_ERROR_CODE;
+
+	iova_base = iova = __alloc_iova(mapping, size);
+	if (iova == DMA_ERROR_CODE)
+		return -ENOMEM;
+
+	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
+		phys_addr_t phys = page_to_phys(sg_page(s));
+		unsigned int len = PAGE_ALIGN(s->offset + s->length);
+
+		if (!arch_is_coherent())
+			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
+
+		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		if (ret < 0)
+			goto fail;
+		count += len >> PAGE_SHIFT;
+		iova += len;
+	}
+	*handle = iova_base;
+
+	return 0;
+fail:
+	iommu_unmap(mapping->domain, iova_base, count * PAGE_SIZE);
+	__free_iova(mapping, iova_base, size);
+	return ret;
+}
+
+/**
+ * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to map
+ * @dir: DMA transfer direction
+ *
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * The scatter gather list elements are merged together (if possible) and
+ * tagged with the appropriate dma address and length. They are obtained via
+ * sg_dma_{address,length}.
+ */
+int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+		     enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	struct scatterlist *s = sg, *dma = sg, *start = sg;
+	int i, count = 0;
+	unsigned int offset = s->offset;
+	unsigned int size = s->offset + s->length;
+	unsigned int max = dma_get_max_seg_size(dev);
+
+	for (i = 1; i < nents; i++) {
+		s = sg_next(s);
+
+		s->dma_address = DMA_ERROR_CODE;
+		s->dma_length = 0;
+
+		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
+			if (__map_sg_chunk(dev, start, size, &dma->dma_address,
+			    dir) < 0)
+				goto bad_mapping;
+
+			dma->dma_address += offset;
+			dma->dma_length = size - offset;
+
+			size = offset = s->offset;
+			start = s;
+			dma = sg_next(dma);
+			count += 1;
+		}
+		size += s->length;
+	}
+	if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir) < 0)
+		goto bad_mapping;
+
+	dma->dma_address += offset;
+	dma->dma_length = size - offset;
+
+	return count+1;
+
+bad_mapping:
+	for_each_sg(sg, s, count, i)
+		__iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s));
+	return 0;
+}
+
+/**
+ * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
+ * @dir: DMA transfer direction (same as was passed to dma_map_sg)
+ *
+ * Unmap a set of streaming mode DMA translations.  Again, CPU access
+ * rules concerning calls here are the same as for dma_unmap_single().
+ */
+void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
+			enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		if (sg_dma_len(s))
+			__iommu_remove_mapping(dev, sg_dma_address(s),
+					       sg_dma_len(s));
+		if (!arch_is_coherent())
+			__dma_page_dev_to_cpu(sg_page(s), s->offset,
+					      s->length, dir);
+	}
+}
+
+/**
+ * arm_iommu_sync_sg_for_cpu
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to map (returned from dma_map_sg)
+ * @dir: DMA transfer direction (same as was passed to dma_map_sg)
+ */
+void arm_iommu_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+			int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i)
+		if (!arch_is_coherent())
+			__dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir);
+
+}
+
+/**
+ * arm_iommu_sync_sg_for_device
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to map (returned from dma_map_sg)
+ * @dir: DMA transfer direction (same as was passed to dma_map_sg)
+ */
+void arm_iommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+			int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i)
+		if (!arch_is_coherent())
+			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
+}
+
+
+/**
+ * arm_iommu_map_page
+ * @dev: valid struct device pointer
+ * @page: page that buffer resides in
+ * @offset: offset into page for start of buffer
+ * @size: size of buffer to map
+ * @dir: DMA transfer direction
+ *
+ * IOMMU aware version of arm_dma_map_page()
+ */
+static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir,
+	     struct dma_attrs *attrs)
+{
+	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	dma_addr_t dma_addr;
+	int ret, len = PAGE_ALIGN(size + offset);
+
+	if (!arch_is_coherent())
+		__dma_page_cpu_to_dev(page, offset, size, dir);
+
+	dma_addr = __alloc_iova(mapping, len);
+	if (dma_addr == DMA_ERROR_CODE)
+		return dma_addr;
+
+	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, 0);
+	if (ret < 0)
+		goto fail;
+
+	return dma_addr + offset;
+fail:
+	__free_iova(mapping, dma_addr, len);
+	return DMA_ERROR_CODE;
+}
+
+/**
+ * arm_iommu_unmap_page
+ * @dev: valid struct device pointer
+ * @handle: DMA address of buffer
+ * @size: size of buffer (same as passed to dma_map_page)
+ * @dir: DMA transfer direction (same as passed to dma_map_page)
+ *
+ * IOMMU aware version of arm_dma_unmap_page()
+ */
+static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	dma_addr_t iova = handle & PAGE_MASK;
+	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+	int offset = handle & ~PAGE_MASK;
+	int len = PAGE_ALIGN(size + offset);
+
+	if (!iova)
+		return;
+
+	if (!arch_is_coherent())
+		__dma_page_dev_to_cpu(page, offset, size, dir);
+
+	iommu_unmap(mapping->domain, iova, len);
+	__free_iova(mapping, iova, len);
+}
+
+static void arm_iommu_sync_single_for_cpu(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	dma_addr_t iova = handle & PAGE_MASK;
+	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+	unsigned int offset = handle & ~PAGE_MASK;
+
+	if (!iova)
+		return;
+
+	if (!arch_is_coherent())
+		__dma_page_dev_to_cpu(page, offset, size, dir);
+}
+
+static void arm_iommu_sync_single_for_device(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	dma_addr_t iova = handle & PAGE_MASK;
+	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+	unsigned int offset = handle & ~PAGE_MASK;
+
+	if (!iova)
+		return;
+
+	__dma_page_cpu_to_dev(page, offset, size, dir);
+}
+
+struct dma_map_ops iommu_ops = {
+	.alloc		= arm_iommu_alloc_attrs,
+	.free		= arm_iommu_free_attrs,
+	.mmap		= arm_iommu_mmap_attrs,
+
+	.map_page		= arm_iommu_map_page,
+	.unmap_page		= arm_iommu_unmap_page,
+	.sync_single_for_cpu	= arm_iommu_sync_single_for_cpu,
+	.sync_single_for_device	= arm_iommu_sync_single_for_device,
+
+	.map_sg			= arm_iommu_map_sg,
+	.unmap_sg		= arm_iommu_unmap_sg,
+	.sync_sg_for_cpu	= arm_iommu_sync_sg_for_cpu,
+	.sync_sg_for_device	= arm_iommu_sync_sg_for_device,
+};
+
+/**
+ * arm_iommu_create_mapping
+ * @bus: pointer to the bus holding the client device (for IOMMU calls)
+ * @base: start address of the valid IO address space
+ * @size: size of the valid IO address space
+ * @order: accuracy of the IO addresses allocations
+ *
+ * Creates a mapping structure which holds information about used/unused
+ * IO address ranges, which is required to perform memory allocation and
+ * mapping with IOMMU aware functions.
+ *
+ * The client device need to be attached to the mapping with
+ * arm_iommu_attach_device function.
+ */
+struct dma_iommu_mapping *
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size,
+			 int order)
+{
+	unsigned int count = size >> (PAGE_SHIFT + order);
+	unsigned int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
+	struct dma_iommu_mapping *mapping;
+	int err = -ENOMEM;
+
+	if (!count)
+		return ERR_PTR(-EINVAL);
+
+	mapping = kzalloc(sizeof(struct dma_iommu_mapping), GFP_KERNEL);
+	if (!mapping)
+		goto err;
+
+	mapping->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!mapping->bitmap)
+		goto err2;
+
+	mapping->base = base;
+	mapping->bits = BITS_PER_BYTE * bitmap_size;
+	mapping->order = order;
+	spin_lock_init(&mapping->lock);
+
+	mapping->domain = iommu_domain_alloc(bus);
+	if (!mapping->domain)
+		goto err3;
+
+	kref_init(&mapping->kref);
+	return mapping;
+err3:
+	kfree(mapping->bitmap);
+err2:
+	kfree(mapping);
+err:
+	return ERR_PTR(err);
+}
+
+static void release_iommu_mapping(struct kref *kref)
+{
+	struct dma_iommu_mapping *mapping =
+		container_of(kref, struct dma_iommu_mapping, kref);
+
+	iommu_domain_free(mapping->domain);
+	kfree(mapping->bitmap);
+	kfree(mapping);
+}
+
+void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
+{
+	if (mapping)
+		kref_put(&mapping->kref, release_iommu_mapping);
+}
+
+/**
+ * arm_iommu_attach_device
+ * @dev: valid struct device pointer
+ * @mapping: io address space mapping structure (returned from
+ *	arm_iommu_create_mapping)
+ *
+ * Attaches specified io address space mapping to the provided device,
+ * this replaces the dma operations (dma_map_ops pointer) with the
+ * IOMMU aware version. More than one client might be attached to
+ * the same io address space mapping.
+ */
+int arm_iommu_attach_device(struct device *dev,
+			    struct dma_iommu_mapping *mapping)
+{
+	int err;
+
+	err = iommu_attach_device(mapping->domain, dev);
+	if (err)
+		return err;
+
+	kref_get(&mapping->kref);
+	dev->archdata.mapping = mapping;
+	set_dma_ops(dev, &iommu_ops);
+
+	pr_info("Attached IOMMU controller to %s device.\n", dev_name(dev));
+	return 0;
+}
+
+#endif

arch/arm/mm/init.c

···
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/mach-types.h>
 #include <asm/memblock.h>
···
 }
 #endif
 
+void __init setup_dma_zone(struct machine_desc *mdesc)
+{
+#ifdef CONFIG_ZONE_DMA
+	if (mdesc->dma_zone_size) {
+		arm_dma_zone_size = mdesc->dma_zone_size;
+		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
+	} else
+		arm_dma_limit = 0xffffffff;
+#endif
+}
+
 static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
 	unsigned long max_high)
 {
···
 	 * Adjust the sizes according to any special requirements for
 	 * this machine type.
 	 */
-	if (arm_dma_zone_size) {
+	if (arm_dma_zone_size)
 		arm_adjust_dma_zone(zone_size, zhole_size,
 			arm_dma_zone_size >> PAGE_SHIFT);
-		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
-	} else
-		arm_dma_limit = 0xffffffff;
 #endif
 
 	free_area_init_node(0, zone_size, min, zhole_size);
···
 	/* reserve any platform specific memblock areas */
 	if (mdesc->reserve)
 		mdesc->reserve();
+
+	/*
+	 * reserve memory for DMA contigouos allocations,
+	 * must come from DMA area inside low memory
+	 */
+	dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit));
 
 	arm_memblock_steal_permitted = false;
 	memblock_allow_resize();

arch/arm/mm/mm.h

···
 #define arm_dma_limit ((u32)~0)
 #endif
 
+extern phys_addr_t arm_lowmem_limit;
+
 void __init bootmem_init(void);
 void arm_mm_memblock_reserve(void);
+void dma_contiguous_remap(void);

arch/arm/mm/mmu.c

···
 				PMD_SECT_UNCACHED | PMD_SECT_XN,
 		.domain    = DOMAIN_KERNEL,
 	},
+	[MT_MEMORY_DMA_READY] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
+		.prot_l1   = PMD_TYPE_TABLE,
+		.domain    = DOMAIN_KERNEL,
+	},
 };
 
 const struct mem_type *get_mem_type(unsigned int type)
···
 	if (arch_is_coherent() && cpu_is_xsc3()) {
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
 		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+		mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
 		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 	}
···
 			mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
 			mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
 			mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 		}
···
 	mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
 	mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+	mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot;
 	mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
 	mem_types[MT_ROM].prot_sect |= cp->pmd;
 
···
 	 * L1 entries, whereas PGDs refer to a group of L1 entries making
 	 * up one logical pointer to an L2 table.
 	 */
-	if (((addr | end | phys) & ~SECTION_MASK) == 0) {
+	if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) {
 		pmd_t *p = pmd;
 
 #ifndef CONFIG_ARM_LPAE
···
 }
 early_param("vmalloc", early_vmalloc);
 
-static phys_addr_t lowmem_limit __initdata = 0;
+phys_addr_t arm_lowmem_limit __initdata = 0;
 
 void __init sanity_check_meminfo(void)
 {
···
 			bank->size = newsize;
 		}
 #endif
-		if (!bank->highmem && bank->start + bank->size > lowmem_limit)
-			lowmem_limit = bank->start + bank->size;
+		if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit)
+			arm_lowmem_limit = bank->start + bank->size;
 
 		j++;
 	}
···
 	}
 #endif
 	meminfo.nr_banks = j;
-	high_memory = __va(lowmem_limit - 1) + 1;
-	memblock_set_current_limit(lowmem_limit);
+	high_memory = __va(arm_lowmem_limit - 1) + 1;
+	memblock_set_current_limit(arm_lowmem_limit);
 }
 
 static inline void prepare_page_table(void)
···
 	 * Find the end of the first block of lowmem.
 	 */
 	end = memblock.memory.regions[0].base + memblock.memory.regions[0].size;
-	if (end >= lowmem_limit)
-		end = lowmem_limit;
+	if (end >= arm_lowmem_limit)
+		end = arm_lowmem_limit;
 
 	/*
 	 * Clear out all the kernel space mappings, except for the first
···
 		phys_addr_t end = start + reg->size;
 		struct map_desc map;
 
-		if (end > lowmem_limit)
-			end = lowmem_limit;
+		if (end > arm_lowmem_limit)
+			end = arm_lowmem_limit;
 		if (start >= end)
 			break;
 
···
 {
 	void *zero_page;
 
-	memblock_set_current_limit(lowmem_limit);
+	memblock_set_current_limit(arm_lowmem_limit);
 
 	build_mem_type_table();
 	prepare_page_table();
 	map_lowmem();
+	dma_contiguous_remap();
 	devicemaps_init(mdesc);
 	kmap_init();
 

arch/arm/mm/vmregion.h

···
 	struct list_head	vm_list;
 	unsigned long		vm_start;
 	unsigned long		vm_end;
-	struct page		*vm_pages;
+	void			*priv;
 	int			vm_active;
 	const void		*caller;
 };

arch/x86/Kconfig

···
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_FRAME_POINTERS
 	select HAVE_DMA_ATTRS
+	select HAVE_DMA_CONTIGUOUS if !SWIOTLB
 	select HAVE_KRETPROBES
 	select HAVE_OPTPROBES
 	select HAVE_FTRACE_MCOUNT_RECORD

arch/x86/include/asm/dma-contiguous.h

···
+#ifndef ASMX86_DMA_CONTIGUOUS_H
+#define ASMX86_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm-generic/dma-contiguous.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
+#endif

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

···
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 #include <asm-generic/dma-coherent.h>
+#include <linux/dma-contiguous.h>
 
 #ifdef CONFIG_ISA
 # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
···
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_addr, gfp_t flag,
 					struct dma_attrs *attrs);
+
+extern void dma_generic_free_coherent(struct device *dev, size_t size,
+				      void *vaddr, dma_addr_t dma_addr,
+				      struct dma_attrs *attrs);
 
 #ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
 extern bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);

arch/x86/kernel/pci-dma.c

···
 				 struct dma_attrs *attrs)
 {
 	unsigned long dma_mask;
-	struct page *page;
+	struct page *page = NULL;
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	dma_addr_t addr;
 
 	dma_mask = dma_alloc_coherent_mask(dev, flag);
 
 	flag |= __GFP_ZERO;
 again:
-	page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
+	if (!(flag & GFP_ATOMIC))
+		page = dma_alloc_from_contiguous(dev, count, get_order(size));
+	if (!page)
+		page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
 	if (!page)
 		return NULL;
 
···
 
 	*dma_addr = addr;
 	return page_address(page);
+}
+
+void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
+			       dma_addr_t dma_addr, struct dma_attrs *attrs)
+{
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page *page = virt_to_page(vaddr);
+
+	if (!dma_release_from_contiguous(dev, page, count))
+		free_pages((unsigned long)vaddr, get_order(size));
 }
 
 /*

arch/x86/kernel/pci-nommu.c

···
 	return nents;
 }
 
-static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
-				dma_addr_t dma_addr, struct dma_attrs *attrs)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-
 static void nommu_sync_single_for_device(struct device *dev,
 			dma_addr_t addr, size_t size,
 			enum dma_data_direction dir)
···
 
 struct dma_map_ops nommu_dma_ops = {
 	.alloc			= dma_generic_alloc_coherent,
-	.free			= nommu_free_coherent,
+	.free			= dma_generic_free_coherent,
 	.map_sg			= nommu_map_sg,
 	.map_page		= nommu_map_page,
 	.sync_single_for_device = nommu_sync_single_for_device,

arch/x86/kernel/setup.c

···
 #include <asm/pci-direct.h>
 #include <linux/init_ohci1394_dma.h>
 #include <linux/kvm_para.h>
+#include <linux/dma-contiguous.h>
 
 #include <linux/errno.h>
 #include <linux/kernel.h>
···
 	}
 #endif
 	memblock.current_limit = get_max_mapped();
+	dma_contiguous_reserve(0);
 
 	/*
 	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.

drivers/base/Kconfig

···
 	  APIs extension; the file's descriptor can then be passed on to other
 	  driver.
 
+config CMA
+	bool "Contiguous Memory Allocator (EXPERIMENTAL)"
+	depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK && EXPERIMENTAL
+	select MIGRATION
+	help
+	  This enables the Contiguous Memory Allocator which allows drivers
+	  to allocate big physically-contiguous blocks of memory for use with
+	  hardware components that do not support I/O map nor scatter-gather.
+
+	  For more information see <include/linux/dma-contiguous.h>.
+	  If unsure, say "n".
+
+if CMA
+
+config CMA_DEBUG
+	bool "CMA debug messages (DEVELOPMENT)"
+	depends on DEBUG_KERNEL
+	help
+	  Turns on debug messages in CMA.  This produces KERN_DEBUG
+	  messages for every CMA call as well as various messages while
+	  processing calls such as dma_alloc_from_contiguous().
+	  This option does not affect warning and error messages.
+
+comment "Default contiguous memory area size:"
+
+config CMA_SIZE_MBYTES
+	int "Size in Mega Bytes"
+	depends on !CMA_SIZE_SEL_PERCENTAGE
+	default 16
+	help
+	  Defines the size (in MiB) of the default memory area for Contiguous
+	  Memory Allocator.
+
+config CMA_SIZE_PERCENTAGE
+	int "Percentage of total memory"
+	depends on !CMA_SIZE_SEL_MBYTES
+	default 10
+	help
+	  Defines the size of the default memory area for Contiguous Memory
+	  Allocator as a percentage of the total memory in the system.
+
+choice
+	prompt "Selected region size"
+	default CMA_SIZE_SEL_ABSOLUTE
+
+config CMA_SIZE_SEL_MBYTES
+	bool "Use mega bytes value only"
+
+config CMA_SIZE_SEL_PERCENTAGE
+	bool "Use percentage value only"
+
+config CMA_SIZE_SEL_MIN
+	bool "Use lower value (minimum)"
+
+config CMA_SIZE_SEL_MAX
+	bool "Use higher value (maximum)"
+
+endchoice
+
+config CMA_ALIGNMENT
+	int "Maximum PAGE_SIZE order of alignment for contiguous buffers"
+	range 4 9
+	default 8
+	help
+	  DMA mapping framework by default aligns all buffers to the smallest
+	  PAGE_SIZE order which is greater than or equal to the requested buffer
+	  size. This works well for buffers up to a few hundreds kilobytes, but
+	  for larger buffers it just a memory waste. With this parameter you can
+	  specify the maximum PAGE_SIZE order for contiguous buffers. Larger
+	  buffers will be aligned only to this specified order. The order is
+	  expressed as a power of two multiplied by the PAGE_SIZE.
+
+	  For example, if your system defaults to 4KiB pages, the order value
+	  of 8 means that the buffers will be aligned up to 1MiB only.
+
+	  If unsure, leave the default value "8".
+
+config CMA_AREAS
+	int "Maximum count of the CMA device-private areas"
+	default 7
+	help
+	  CMA allows to create CMA areas for particular devices. This parameter
+	  sets the maximum number of such device private CMA areas in the
+	  system.
+
+	  If unsure, leave the default value "7".
+
+endif
+
 endmenu

drivers/base/Makefile

···
 			   attribute_container.o transport_class.o \
 			   topology.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
+obj-$(CONFIG_CMA) += dma-contiguous.o
 obj-y			+= power/
 obj-$(CONFIG_HAS_DMA)	+= dma-mapping.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o

drivers/base/dma-coherent.c

···
 struct dma_coherent_mem {
 	void		*virt_base;
 	dma_addr_t	device_base;
+	phys_addr_t	pfn_base;
 	int		size;
 	int		flags;
 	unsigned long	*bitmap;
···
 
 	dev->dma_mem->virt_base = mem_base;
 	dev->dma_mem->device_base = device_addr;
+	dev->dma_mem->pfn_base = PFN_DOWN(bus_addr);
 	dev->dma_mem->size = pages;
 	dev->dma_mem->flags = flags;
 
···
 	return 0;
 }
 EXPORT_SYMBOL(dma_release_from_coherent);
+
+/**
+ * dma_mmap_from_coherent() - try to mmap the memory allocated from
+ * per-device coherent memory pool to userspace
+ * @dev:	device from which the memory was allocated
+ * @vma:	vm_area for the userspace memory
+ * @vaddr:	cpu address returned by dma_alloc_from_coherent
+ * @size:	size of the memory buffer allocated by dma_alloc_from_coherent
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, maps that memory to the provided vma.
+ *
+ * Returns 1 if we correctly mapped the memory, or 0 if
+ * dma_release_coherent() should proceed with mapping memory from
+ * generic pools.
+ */
+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;
+
+	if (mem && vaddr >= mem->virt_base && vaddr + size <=
+		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		unsigned long off = vma->vm_pgoff;
+		int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+		int user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+		int count = size >> PAGE_SHIFT;
+
+		*ret = -ENXIO;
+		if (off < count && user_count <= count - off) {
+			unsigned pfn = mem->pfn_base + start + off;
+			*ret = remap_pfn_range(vma, vma->vm_start, pfn,
+					       user_count << PAGE_SHIFT,
+					       vma->vm_page_prot);
+		}
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(dma_mmap_from_coherent);

drivers/base/dma-contiguous.c

···
+/*
+ * Contiguous Memory Allocator for DMA mapping framework
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Written by:
+ *	Marek Szyprowski <[e-mail]>
+ *	Michal Nazarewicz <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+#define pr_fmt(fmt) "cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+#  define DEBUG
+#endif
+#endif
+
+#include <asm/page.h>
+#include <asm/dma-contiguous.h>
+
+#include <linux/memblock.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/page-isolation.h>
+#include <linux/slab.h>
+#include <linux/swap.h>
+#include <linux/mm_types.h>
+#include <linux/dma-contiguous.h>
+
+#ifndef SZ_1M
+#define SZ_1M (1 << 20)
+#endif
+
+struct cma {
+	unsigned long	base_pfn;
+	unsigned long	count;
+	unsigned long	*bitmap;
+};
+
+struct cma *dma_contiguous_default_area;
+
+#ifdef CONFIG_CMA_SIZE_MBYTES
+#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
+#else
+#define CMA_SIZE_MBYTES 0
+#endif
+
+/*
+ * Default global CMA area size can be defined in kernel's .config.
+ * This is usefull mainly for distro maintainers to create a kernel
+ * that works correctly for most supported systems.
+ * The size can be set in bytes or as a percentage of the total memory
+ * in the system.
+ *
+ * Users, who want to set the size of global CMA area for their system
+ * should use cma= kernel parameter.
+ */
+static const unsigned long size_bytes = CMA_SIZE_MBYTES * SZ_1M;
+static long size_cmdline = -1;
+
+static int __init early_cma(char *p)
+{
+	pr_debug("%s(%s)\n", __func__, p);
+	size_cmdline = memparse(p, &p);
+	return 0;
+}
+early_param("cma", early_cma);
+
+#ifdef CONFIG_CMA_SIZE_PERCENTAGE
+
+static unsigned long __init __maybe_unused cma_early_percent_memory(void)
+{
+	struct memblock_region *reg;
+	unsigned long total_pages = 0;
+
+	/*
+	 * We cannot use memblock_phys_mem_size() here, because
+	 * memblock_analyze() has not been called yet.
+	 */
+	for_each_memblock(memory, reg)
+		total_pages += memblock_region_memory_end_pfn(reg) -
+			       memblock_region_memory_base_pfn(reg);
+
+	return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
+}
+
+#else
+
+static inline __maybe_unused unsigned long cma_early_percent_memory(void)
+{
+	return 0;
+}
+
+#endif
+
+/**
+ * dma_contiguous_reserve() - reserve area for contiguous memory handling
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
+ */
+void __init dma_contiguous_reserve(phys_addr_t limit)
+{
+	unsigned long selected_size = 0;
+
+	pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
+
+	if (size_cmdline != -1) {
+		selected_size = size_cmdline;
+	} else {
+#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
+		selected_size = size_bytes;
+#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
+		selected_size = cma_early_percent_memory();
+#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
+		selected_size = min(size_bytes, cma_early_percent_memory());
+#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
+		selected_size = max(size_bytes, cma_early_percent_memory());
+#endif
+	}
+
+	if (selected_size) {
+		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+			 selected_size / SZ_1M);
+
+		dma_declare_contiguous(NULL, selected_size, 0, limit);
+	}
+};
+
+static DEFINE_MUTEX(cma_mutex);
+
+static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
+{
+	unsigned long pfn = base_pfn;
+	unsigned i = count >> pageblock_order;
+	struct zone *zone;
+
+	WARN_ON_ONCE(!pfn_valid(pfn));
+	zone = page_zone(pfn_to_page(pfn));
+
+	do {
+		unsigned j;
+		base_pfn = pfn;
+		for (j = pageblock_nr_pages; j; --j, pfn++) {
+			WARN_ON_ONCE(!pfn_valid(pfn));
+			if (page_zone(pfn_to_page(pfn)) != zone)
+				return -EINVAL;
+		}
+		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
+	} while (--i);
+	return 0;
+}
+
+static __init struct cma *cma_create_area(unsigned long base_pfn,
+				     unsigned long count)
+{
+	int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
+	struct cma *cma;
+	int ret = -ENOMEM;
+
+	pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count);
+
+	cma = kmalloc(sizeof *cma, GFP_KERNEL);
+	if (!cma)
+		return ERR_PTR(-ENOMEM);
+
+	cma->base_pfn = base_pfn;
+	cma->count = count;
+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+
+	if (!cma->bitmap)
+		goto no_mem;
+
+	ret = cma_activate_area(base_pfn, count);
+	if (ret)
+		goto error;
+
+	pr_debug("%s: returned %p\n", __func__, (void *)cma);
+	return cma;
+
+error:
+	kfree(cma->bitmap);
+no_mem:
+	kfree(cma);
+	return ERR_PTR(ret);
+}
+
+static struct cma_reserved {
+	phys_addr_t start;
+	unsigned long size;
+	struct device *dev;
+} cma_reserved[MAX_CMA_AREAS] __initdata;
+static unsigned cma_reserved_count __initdata;
+
+static int __init cma_init_reserved_areas(void)
+{
+	struct cma_reserved *r = cma_reserved;
+	unsigned i = cma_reserved_count;
+
+	pr_debug("%s()\n", __func__);
+
+	for (; i; --i, ++r) {
+		struct cma *cma;
+		cma = cma_create_area(PFN_DOWN(r->start),
+				      r->size >> PAGE_SHIFT);
+		if (!IS_ERR(cma))
+			dev_set_cma_area(r->dev, cma);
+	}
+	return 0;
+}
+core_initcall(cma_init_reserved_areas);
+
+/**
+ * dma_declare_contiguous() - reserve area for contiguous memory handling
+ *			      for particular device
+ * @dev:   Pointer to device structure.
+ * @size:  Size of the reserved memory.
+ * @base:  Start address of the reserved memory (optional, 0 for any).
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory for specified device. It should be
+ * called by board specific code when early allocator (memblock or bootmem)
+ * is still activate.
+ */
+int __init dma_declare_contiguous(struct device *dev, unsigned long size,
+				  phys_addr_t base, phys_addr_t limit)
+{
+	struct cma_reserved *r = &cma_reserved[cma_reserved_count];
+	unsigned long alignment;
+
+	pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__,
+		 (unsigned long)size, (unsigned long)base,
+		 (unsigned long)limit);
+
+	/* Sanity checks */
+	if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) {
+		pr_err("Not enough slots for CMA reserved regions!\n");
+		return -ENOSPC;
+	}
+
+	if (!size)
+		return -EINVAL;
+
+	/* Sanitise input arguments */
+	alignment = PAGE_SIZE << max(MAX_ORDER, pageblock_order);
+	base = ALIGN(base, alignment);
+	size = ALIGN(size, alignment);
+	limit &= ~(alignment - 1);
+
+	/* Reserve memory */
+	if (base) {
+		if (memblock_is_region_reserved(base, size) ||
+		    memblock_reserve(base, size) < 0) {
+			base = -EBUSY;
+			goto err;
+		}
+	} else {
+		/*
+		 * Use __memblock_alloc_base() since
+		 * memblock_alloc_base() panic()s.
+		 */
+		phys_addr_t addr = __memblock_alloc_base(size, alignment, limit);
+		if (!addr) {
+			base = -ENOMEM;
+			goto err;
+		} else if (addr + size > ~(unsigned long)0) {
+			memblock_free(addr, size);
+			base = -EINVAL;
+			goto err;
+		} else {
+			base = addr;
+		}
+	}
+
+	/*
+	 * Each reserved area must be initialised later, when more kernel
+	 * subsystems (like slab allocator) are available.
+	 */
+	r->start = base;
+	r->size = size;
+	r->dev = dev;
+	cma_reserved_count++;
+	pr_info("CMA: reserved %ld MiB at %08lx\n", size / SZ_1M,
+		(unsigned long)base);
+
+	/* Architecture specific contiguous memory fixup. */
+	dma_contiguous_early_fixup(base, size);
+	return 0;
+err:
+	pr_err("CMA: failed to reserve %ld MiB\n", size / SZ_1M);
+	return base;
+}
+
+/**
+ * dma_alloc_from_contiguous() - allocate pages from contiguous area
+ * @dev:   Pointer to device for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ *
+ * This function allocates memory buffer for specified device. It uses
+ * device specific contiguous memory area if available or the default
+ * global one. Requires architecture specific get_dev_cma_area() helper
+ * function.
+ */
+struct page *dma_alloc_from_contiguous(struct device *dev, int count,
+				       unsigned int align)
+{
+	unsigned long mask, pfn, pageno, start = 0;
+	struct cma *cma = dev_get_cma_area(dev);
+	int ret;
+
+	if (!cma || !cma->count)
+		return NULL;
+
+	if (align > CONFIG_CMA_ALIGNMENT)
+		align = CONFIG_CMA_ALIGNMENT;
+
+	pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma,
+		 count, align);
+
+	if (!count)
+		return NULL;
+
+	mask = (1 << align) - 1;
+
+	mutex_lock(&cma_mutex);
+
+	for (;;) {
+		pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
+						    start, count, mask);
+		if (pageno >= cma->count) {
+			ret = -ENOMEM;
+			goto error;
+		}
+
+		pfn = cma->base_pfn + pageno;
+		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
+		if (ret == 0) {
+			bitmap_set(cma->bitmap, pageno, count);
+			break;
+		} else if (ret != -EBUSY) {
+			goto error;
+		}
+		pr_debug("%s(): memory range at %p is busy, retrying\n",
+			 __func__, pfn_to_page(pfn));
+		/* try again with a bit different memory target */
+		start = pageno + mask + 1;
+	}
+
+	mutex_unlock(&cma_mutex);
+
+	pr_debug("%s(): returned %p\n", __func__, pfn_to_page(pfn));
+	return pfn_to_page(pfn);
+error:
+	mutex_unlock(&cma_mutex);
+	return NULL;
+}
+
+/**
+ * dma_release_from_contiguous() - release allocated pages
+ * @dev:   Pointer to device for which the pages were allocated.
+ * @pages: Allocated pages.
+ * @count: Number of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_from_contiguous().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count)
+{
+	struct cma *cma = dev_get_cma_area(dev);
+	unsigned long pfn;
+
+	if (!cma || !pages)
+		return false;
+
+	pr_debug("%s(page %p)\n", __func__, (void *)pages);
+
+	pfn = page_to_pfn(pages);
+
+	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
+		return false;
+
+	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);
+
+	mutex_lock(&cma_mutex);
+	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count);
+	free_contig_range(pfn, count);
+	mutex_unlock(&cma_mutex);
+
+	return true;
+}

include/asm-generic/dma-coherent.h

···
 
 #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
 /*
- * These two functions are only for dma allocator.
+ * These three functions are only for dma allocator.
  * Don't use them in device drivers.
  */
 int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 				       dma_addr_t *dma_handle, void **ret);
 int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
 
+int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
+			    void *cpu_addr, size_t size, int *ret);
 /*
  * Standard interface
  */

include/asm-generic/dma-contiguous.h

···
+#ifndef ASM_DMA_CONTIGUOUS_H
+#define ASM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_CMA
+
+#include <linux/device.h>
+#include <linux/dma-contiguous.h>
+
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	if (dev && dev->cma_area)
+		return dev->cma_area;
+	return dma_contiguous_default_area;
+}
+
+static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
+{
+	if (dev)
+		dev->cma_area = cma;
+	if (!dev || !dma_contiguous_default_area)
+		dma_contiguous_default_area = cma;
+}
+
+#endif
+#endif
+
+#endif

include/linux/device.h

···
 
 	struct dma_coherent_mem	*dma_mem; /* internal for coherent mem
 					     override */
+#ifdef CONFIG_CMA
+	struct cma *cma_area;		/* contiguous memory area for dma
+					   allocations */
+#endif
 	/* arch specific additions */
 	struct dev_archdata	archdata;
 

include/linux/dma-contiguous.h

···
+#ifndef __LINUX_CMA_H
+#define __LINUX_CMA_H
+
+/*
+ * Contiguous Memory Allocator for DMA mapping framework
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Written by:
+ *	Marek Szyprowski <[e-mail]>
+ *	Michal Nazarewicz <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+/*
+ * Contiguous Memory Allocator
+ *
+ *   The Contiguous Memory Allocator (CMA) makes it possible to
+ *   allocate big contiguous chunks of memory after the system has
+ *   booted.
+ *
+ * Why is it needed?
+ *
+ *   Various devices on embedded systems have no scatter-getter and/or
+ *   IO map support and require contiguous blocks of memory to
+ *   operate.  They include devices such as cameras, hardware video
+ *   coders, etc.
+ *
+ *   Such devices often require big memory buffers (a full HD frame
+ *   is, for instance, more then 2 mega pixels large, i.e. more than 6
+ *   MB of memory), which makes mechanisms such as kmalloc() or
+ *   alloc_page() ineffective.
+ *
+ *   At the same time, a solution where a big memory region is
+ *   reserved for a device is suboptimal since often more memory is
+ *   reserved then strictly required and, moreover, the memory is
+ *   inaccessible to page system even if device drivers don't use it.
+ *
+ *   CMA tries to solve this issue by operating on memory regions
+ *   where only movable pages can be allocated from.  This way, kernel
+ *   can use the memory for pagecache and when device driver requests
+ *   it, allocated pages can be migrated.
+ *
+ * Driver usage
+ *
+ *   CMA should not be used by the device drivers directly. It is
+ *   only a helper framework for dma-mapping subsystem.
+ *
+ *   For more information, see kernel-docs in drivers/base/dma-contiguous.c
+ */
+
+#ifdef __KERNEL__
+
+struct cma;
+struct page;
+struct device;
+
+#ifdef CONFIG_CMA
+
+/*
+ * There is always at least global CMA area and a few optional device
+ * private areas configured in kernel .config.
+ */
+#define MAX_CMA_AREAS	(1 + CONFIG_CMA_AREAS)
+
+extern struct cma *dma_contiguous_default_area;
+
+void dma_contiguous_reserve(phys_addr_t addr_limit);
+int dma_declare_contiguous(struct device *dev, unsigned long size,
+			   phys_addr_t base, phys_addr_t limit);
+
+struct page *dma_alloc_from_contiguous(struct device *dev, int count,
+				       unsigned int order);
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count);
+
+#else
+
+#define MAX_CMA_AREAS	(0)
+
+static inline void dma_contiguous_reserve(phys_addr_t limit) { }
+
+static inline
+int dma_declare_contiguous(struct device *dev, unsigned long size,
+			   phys_addr_t base, phys_addr_t limit)
+{
+	return -ENOSYS;
+}
+
+static inline
+struct page *dma_alloc_from_contiguous(struct device *dev, int count,
+				       unsigned int order)
+{
+	return NULL;
+}
+
+static inline
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count)
+{
+	return false;
+}
+
+#endif
+
+#endif
+
+#endif

include/linux/gfp.h

···
 }
 #endif /* CONFIG_PM_SLEEP */
 
+#ifdef CONFIG_CMA
+
+/* The below functions must be run on a range from a single zone. */
+extern int alloc_contig_range(unsigned long start, unsigned long end,
+			      unsigned migratetype);
+extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
+
+/* CMA stuff */
+extern void init_cma_reserved_pageblock(struct page *page);
+
+#endif
+
 #endif /* __LINUX_GFP_H */

include/linux/mmzone.h

···
  */
 #define PAGE_ALLOC_COSTLY_ORDER 3
 
-#define MIGRATE_UNMOVABLE     0
-#define MIGRATE_RECLAIMABLE   1
-#define MIGRATE_MOVABLE       2
-#define MIGRATE_PCPTYPES      3 /* the number of types on the pcp lists */
-#define MIGRATE_RESERVE       3
-#define MIGRATE_ISOLATE       4 /* can't allocate from here */
-#define MIGRATE_TYPES         5
+enum {
+	MIGRATE_UNMOVABLE,
+	MIGRATE_RECLAIMABLE,
+	MIGRATE_MOVABLE,
+	MIGRATE_PCPTYPES,	/* the number of types on the pcp lists */
+	MIGRATE_RESERVE = MIGRATE_PCPTYPES,
+#ifdef CONFIG_CMA
+	/*
+	 * MIGRATE_CMA migration type is designed to mimic the way
+	 * ZONE_MOVABLE works.  Only movable pages can be allocated
+	 * from MIGRATE_CMA pageblocks and page allocator never
+	 * implicitly change migration type of MIGRATE_CMA pageblock.
+	 *
+	 * The way to use it is to change migratetype of a range of
+	 * pageblocks to MIGRATE_CMA which can be done by
+	 * __free_pageblock_cma() function.  What is important though
+	 * is that a range of pageblocks must be aligned to
+	 * MAX_ORDER_NR_PAGES should biggest page be bigger then
+	 * a single pageblock.
+	 */
+	MIGRATE_CMA,
+#endif
+	MIGRATE_ISOLATE,	/* can't allocate from here */
+	MIGRATE_TYPES
+};
+
+#ifdef CONFIG_CMA
+#  define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
+#  define cma_wmark_pages(zone)	zone->min_cma_pages
+#else
+#  define is_migrate_cma(migratetype) false
+#  define cma_wmark_pages(zone) 0
+#endif
 
 #define for_each_migratetype_order(order, type) \
 	for (order = 0; order < MAX_ORDER; order++) \
···
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/* see spanned/present_pages for more description */
 	seqlock_t		span_seqlock;
+#endif
+#ifdef CONFIG_CMA
+	/*
+	 * CMA needs to increase watermark levels during the allocation
+	 * process to make sure that the system is not starved.
+	 */
+	unsigned long		min_cma_pages;
 #endif
 	struct free_area	free_area[MAX_ORDER];
 

include/linux/page-isolation.h

···
 
 /*
  * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE.
- * If specified range includes migrate types other than MOVABLE,
+ * If specified range includes migrate types other than MOVABLE or CMA,
  * this will fail with -EBUSY.
  *
  * For isolating all pages in the range finally, the caller have to
···
  * test it.
  */
 extern int
-start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn);
+start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+			 unsigned migratetype);
 
 /*
  * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE.
  * target range is [start_pfn, end_pfn)
  */
 extern int
-undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn);
+undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+			unsigned migratetype);
 
 /*
- * test all pages in [start_pfn, end_pfn)are isolated or not.
+ * Test all pages in [start_pfn, end_pfn) are isolated or not.
  */
-extern int
-test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);
+int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);
 
 /*
- * Internal funcs.Changes pageblock's migrate type.
- * Please use make_pagetype_isolated()/make_pagetype_movable().
+ * Internal functions. Changes pageblock's migrate type.
  */
 extern int set_migratetype_isolate(struct page *page);
-extern void unset_migratetype_isolate(struct page *page);
+extern void unset_migratetype_isolate(struct page *page, unsigned migratetype);
 
 
 #endif

mm/Kconfig

···
 config MIGRATION
 	bool "Page migration"
 	def_bool y
-	depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION
+	depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA
 	help
 	  Allows the migration of the physical location of pages of processes
 	  while the virtual addresses are not changed. This is useful in

mm/Makefile

···
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
 			   page_isolation.o mm_init.o mmu_context.o percpu.o \
-			   $(mmu-y)
+			   compaction.o $(mmu-y)
 obj-y += init-mm.o
 
 ifdef CONFIG_NO_BOOTMEM
···
 obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
 obj-$(CONFIG_SLOB) += slob.o
-obj-$(CONFIG_COMPACTION) += compaction.o
 obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_KSM) += ksm.o
 obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o

mm/compaction.c

···
 #include <linux/sysfs.h>
 #include "internal.h"
 
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/compaction.h>
-
-/*
- * compact_control is used to track pages being migrated and the free pages
- * they are being migrated to during memory compaction. The free_pfn starts
- * at the end of a zone and migrate_pfn begins at the start. Movable pages
- * are moved to the end of a zone during a compaction run and the run
- * completes when free_pfn <= migrate_pfn
- */
-struct compact_control {
-	struct list_head freepages;	/* List of free pages to migrate to */
-	struct list_head migratepages;	/* List of pages being migrated */
-	unsigned long nr_freepages;	/* Number of isolated free pages */
-	unsigned long nr_migratepages;	/* Number of pages to migrate */
-	unsigned long free_pfn;		/* isolate_freepages search base */
-	unsigned long migrate_pfn;	/* isolate_migratepages search base */
-	bool sync;			/* Synchronous migration */
-
-	int order;			/* order a direct compactor needs */
-	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
-	struct zone *zone;
-};
 
 static unsigned long release_freepages(struct list_head *freelist)
 {
···
 	return count;
 }
 
-/* Isolate free pages onto a private freelist. Must hold zone->lock */
-static unsigned long isolate_freepages_block(struct zone *zone,
-				unsigned long blockpfn,
-				struct list_head *freelist)
+static void map_pages(struct list_head *list)
 {
-	unsigned long zone_end_pfn, end_pfn;
+	struct page *page;
+
+	list_for_each_entry(page, list, lru) {
+		arch_alloc_page(page, 0);
+		kernel_map_pages(page, 1, 1);
+	}
+}
+
+static inline bool migrate_async_suitable(int migratetype)
+{
+	return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE;
+}
+
+/*
+ * Isolate free pages onto a private freelist. Caller must hold zone->lock.
+ * If @strict is true, will abort returning 0 on any invalid PFNs or non-free
+ * pages inside of the pageblock (even though it may still end up isolating
+ * some pages).
+ */
+static unsigned long isolate_freepages_block(unsigned long blockpfn,
+				unsigned long end_pfn,
+				struct list_head *freelist,
+				bool strict)
+{
 	int nr_scanned = 0, total_isolated = 0;
 	struct page *cursor;
 
-	/* Get the last PFN we should scan for free pages at */
-	zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
-	end_pfn = min(blockpfn + pageblock_nr_pages, zone_end_pfn);
-
-	/* Find the first usable PFN in the block to initialse page cursor */
-	for (; blockpfn < end_pfn; blockpfn++) {
-		if (pfn_valid_within(blockpfn))
-			break;
-	}
 	cursor = pfn_to_page(blockpfn);
 
 	/* Isolate free pages. This assumes the block is valid */
···
 		int isolated, i;
 		struct page *page = cursor;
 
-		if (!pfn_valid_within(blockpfn))
+		if (!pfn_valid_within(blockpfn)) {
+			if (strict)
+				return 0;
 			continue;
+		}
 		nr_scanned++;
 
-		if (!PageBuddy(page))
+		if (!PageBuddy(page)) {
+			if (strict)
+				return 0;
 			continue;
+		}
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
+		if (!isolated && strict)
+			return 0;
 		total_isolated += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
···
 	return total_isolated;
 }
 
-/* Returns true if the page is within a block suitable for migration to */
-static bool suitable_migration_target(struct page *page)
-{
-
-	int migratetype = get_pageblock_migratetype(page);
-
-	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
-	if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
-		return false;
-
-	/* If the page is a large free page, then allow migration */
-	if (PageBuddy(page) && page_order(page) >= pageblock_order)
-		return true;
-
-	/* If the block is MIGRATE_MOVABLE, allow migration */
-	if (migratetype == MIGRATE_MOVABLE)
-		return true;
-
-	/* Otherwise skip the block */
-	return false;
-}
-
-/*
- * Based on information in the current compact_control, find blocks
- * suitable for isolating free pages from and then isolate them.
+/**
+ * isolate_freepages_range() - isolate free pages.
+ * @start_pfn: The first PFN to start isolating.
+ * @end_pfn:   The one-past-last PFN.
+ *
+ * Non-free pages, invalid PFNs, or zone boundaries within the
+ * [start_pfn, end_pfn) range are considered errors, cause function to
+ * undo its actions and return zero.
+ *
+ * Otherwise, function returns one-past-the-last PFN of isolated page
+ * (which may be greater then end_pfn if end fell in a middle of
+ * a free page).
  */
-static void isolate_freepages(struct zone *zone,
-				struct compact_control *cc)
+unsigned long
+isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn)
 {
-	struct page *page;
-	unsigned long high_pfn, low_pfn, pfn;
-	unsigned long flags;
-	int nr_freepages = cc->nr_freepages;
-	struct list_head *freelist = &cc->freepages;
+	unsigned long isolated, pfn, block_end_pfn, flags;
+	struct zone *zone = NULL;
+	LIST_HEAD(freelist);
 
-	/*
-	 * Initialise the free scanner. The starting point is where we last
-	 * scanned from (or the end of the zone if starting). The low point
-	 * is the end of the pageblock the migration scanner is using.
-	 */
-	pfn = cc->free_pfn;
-	low_pfn = cc->migrate_pfn + pageblock_nr_pages;
+	if (pfn_valid(start_pfn))
+		zone = page_zone(pfn_to_page(start_pfn));
 
-	/*
-	 * Take care that if the migration scanner is at the end of the zone
-	 * that the free scanner does not accidentally move to the next zone
-	 * in the next isolation cycle.
-	 */
-	high_pfn = min(low_pfn, pfn);
-
-	/*
-	 * Isolate free pages until enough are available to migrate the
-	 * pages on cc->migratepages. We stop searching if the migrate
-	 * and free page scanners meet or enough free pages are isolated.
-	 */
-	for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
-					pfn -= pageblock_nr_pages) {
-		unsigned long isolated;
-
-		if (!pfn_valid(pfn))
-			continue;
+	for (pfn = start_pfn; pfn < end_pfn; pfn += isolated) {
+		if (!pfn_valid(pfn) || zone != page_zone(pfn_to_page(pfn)))
+			break;
 
 		/*
-		 * Check for overlapping nodes/zones. It's possible on some
-		 * configurations to have a setup like
-		 * node0 node1 node0
-		 * i.e. it's possible that all pages within a zones range of
-		 * pages do not belong to a single zone.
+		 * On subsequent iterations ALIGN() is actually not needed,
+		 * but we keep it that we not to complicate the code.
 		 */
-		page = pfn_to_page(pfn);
-		if (page_zone(page) != zone)
-			continue;
+		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+		block_end_pfn = min(block_end_pfn, end_pfn);
 
-		/* Check the block is suitable for migration */
-		if (!suitable_migration_target(page))
-			continue;
-
-		/*
-		 * Found a block suitable for isolating free pages from. Now
-		 * we disabled interrupts, double check things are ok and
-		 * isolate the pages. This is to minimise the time IRQs
-		 * are disabled
-		 */
-		isolated = 0;
 		spin_lock_irqsave(&zone->lock, flags);
-		if (suitable_migration_target(page)) {
-			isolated = isolate_freepages_block(zone, pfn, freelist);
-			nr_freepages += isolated;
-		}
+		isolated = isolate_freepages_block(pfn, block_end_pfn,
+						   &freelist, true);
 		spin_unlock_irqrestore(&zone->lock, flags);
 
 		/*
-		 * Record the highest PFN we isolated pages from. When next
-		 * looking for free pages, the search will restart here as
-		 * page migration may have returned some pages to the allocator
+		 * In strict mode, isolate_freepages_block() returns 0 if
+		 * there are any holes in the block (ie. invalid PFNs or
+		 * non-free pages).
 		 */
-		if (isolated)
-			high_pfn = max(high_pfn, pfn);
+		if (!isolated)
+			break;
+
+		/*
+		 * If we managed to isolate pages, it is always (1 << n) *
+		 * pageblock_nr_pages for some non-negative n.  (Max order
+		 * page may span two pageblocks).
+		 */
 	}
 
 	/* split_free_page does not map the pages */
-	list_for_each_entry(page, freelist, lru) {
-		arch_alloc_page(page, 0);
-		kernel_map_pages(page, 1, 1);
+	map_pages(&freelist);
+
+	if (pfn < end_pfn) {
+		/* Loop terminated early, cleanup. */
+		release_freepages(&freelist);
+		return 0;
 	}
 
-	cc->free_pfn = high_pfn;
-	cc->nr_freepages = nr_freepages;
+	/* We don't use freelists for anything. */
+	return pfn;
 }
 
 /* Update the number of anon and file isolated pages in the zone */
···
 	return isolated > (inactive + active) / 2;
 }
 
-/* possible outcome of isolate_migratepages */
-typedef enum {
-	ISOLATE_ABORT,		/* Abort compaction now */
-	ISOLATE_NONE,		/* No pages isolated, continue scanning */
-	ISOLATE_SUCCESS,	/* Pages isolated, migrate */
-} isolate_migrate_t;
-
-/*
- * Isolate all pages that can be migrated from the block pointed to by
- * the migrate scanner within compact_control.
+/**
+ * isolate_migratepages_range() - isolate all migrate-able pages in range.
+ * @zone:	Zone pages are in.
+ * @cc:		Compaction control structure.
+ * @low_pfn:	The first PFN of the range.
+ * @end_pfn:	The one-past-the-last PFN of the range.
+ *
+ * Isolate all pages that can be migrated from the range specified by
+ * [low_pfn, end_pfn).  Returns zero if there is a fatal signal
+ * pending), otherwise PFN of the first page that was not scanned
+ * (which may be both less, equal to or more then end_pfn).
+ *
+ * Assumes that cc->migratepages is empty and cc->nr_migratepages is
+ * zero.
+ *
+ * Apart from cc->migratepages and cc->nr_migratetypes this function
+ * does not modify any cc's fields, in particular it does not modify
+ * (or read for that matter) cc->migrate_pfn.
  */
-static isolate_migrate_t isolate_migratepages(struct zone *zone,
-					struct compact_control *cc)
+unsigned long
+isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
+			   unsigned long low_pfn, unsigned long end_pfn)
 {
-	unsigned long low_pfn, end_pfn;
 	unsigned long last_pageblock_nr = 0, pageblock_nr;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
 	isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE;
-
-	/* Do not scan outside zone boundaries */
-	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
-
-	/* Only scan within a pageblock boundary */
-	end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages);
-
-	/* Do not cross the free scanner or scan within a memory hole */
-	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
-		cc->migrate_pfn = end_pfn;
-		return ISOLATE_NONE;
-	}
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
···
 	while (unlikely(too_many_isolated(zone))) {
 		/* async migration should just abort */
 		if (!cc->sync)
-			return ISOLATE_ABORT;
+			return 0;
 
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		if (fatal_signal_pending(current))
-			return ISOLATE_ABORT;
+			return 0;
 	}
 
 	/* Time to isolate some pages for migration */
···
 		 */
 		pageblock_nr = low_pfn >> pageblock_order;
 		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
-				get_pageblock_migratetype(page) != MIGRATE_MOVABLE) {
+		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
 			low_pfn += pageblock_nr_pages;
 			low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
 			last_pageblock_nr = pageblock_nr;
···
 	acct_isolated(zone, cc);
 
 	spin_unlock_irq(&zone->lru_lock);
-	cc->migrate_pfn = low_pfn;
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
-	return ISOLATE_SUCCESS;
+	return low_pfn;
+}
+
+#endif /* CONFIG_COMPACTION || CONFIG_CMA */
+#ifdef CONFIG_COMPACTION
+
+/* Returns true if the page is within a block suitable for migration to */
+static bool suitable_migration_target(struct page *page)
+{
+
+	int migratetype = get_pageblock_migratetype(page);
+
+	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
+	if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
+		return false;
+
+	/* If the page is a large free page, then allow migration */
+	if (PageBuddy(page) && page_order(page) >= pageblock_order)
+		return true;
+
+	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
+	if (migrate_async_suitable(migratetype))
+		return true;
+
+	/* Otherwise skip the block */
+	return false;
+}
+
+/*
+ * Based on information in the current compact_control, find blocks
+ * suitable for isolating free pages from and then isolate them.
+ */
+static void isolate_freepages(struct zone *zone,
+				struct compact_control *cc)
+{
+	struct page *page;
+	unsigned long high_pfn, low_pfn, pfn, zone_end_pfn, end_pfn;
+	unsigned long flags;
+	int nr_freepages = cc->nr_freepages;
+	struct list_head *freelist = &cc->freepages;
+
+	/*
+	 * Initialise the free scanner. The starting point is where we last
+	 * scanned from (or the end of the zone if starting). The low point
+	 * is the end of the pageblock the migration scanner is using.
+	 */
+	pfn = cc->free_pfn;
+	low_pfn = cc->migrate_pfn + pageblock_nr_pages;
+
+	/*
+	 * Take care that if the migration scanner is at the end of the zone
+	 * that the free scanner does not accidentally move to the next zone
+	 * in the next isolation cycle.
+	 */
+	high_pfn = min(low_pfn, pfn);
+
+	zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+
+	/*
+	 * Isolate free pages until enough are available to migrate the
+	 * pages on cc->migratepages. We stop searching if the migrate
+	 * and free page scanners meet or enough free pages are isolated.
+	 */
+	for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
+					pfn -= pageblock_nr_pages) {
+		unsigned long isolated;
+
+		if (!pfn_valid(pfn))
+			continue;
+
+		/*
+		 * Check for overlapping nodes/zones. It's possible on some
+		 * configurations to have a setup like
+		 * node0 node1 node0
+		 * i.e. it's possible that all pages within a zones range of
+		 * pages do not belong to a single zone.
+		 */
+		page = pfn_to_page(pfn);
+		if (page_zone(page) != zone)
+			continue;
+
+		/* Check the block is suitable for migration */
+		if (!suitable_migration_target(page))
+			continue;
+
+		/*
+		 * Found a block suitable for isolating free pages from. Now
+		 * we disabled interrupts, double check things are ok and
+		 * isolate the pages. This is to minimise the time IRQs
+		 * are disabled
+		 */
+		isolated = 0;
+		spin_lock_irqsave(&zone->lock, flags);
+		if (suitable_migration_target(page)) {
+			end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn);
+			isolated = isolate_freepages_block(pfn, end_pfn,
+							   freelist, false);
+			nr_freepages += isolated;
+		}
+		spin_unlock_irqrestore(&zone->lock, flags);
+
+		/*
+		 * Record the highest PFN we isolated pages from. When next
+		 * looking for free pages, the search will restart here as
+		 * page migration may have returned some pages to the allocator
+		 */
+		if (isolated)
+			high_pfn = max(high_pfn, pfn);
+	}
+
+	/* split_free_page does not map the pages */
+	map_pages(freelist);
+
+	cc->free_pfn = high_pfn;
+	cc->nr_freepages = nr_freepages;
 }
 
 /*
···
 
 	cc->nr_migratepages = nr_migratepages;
 	cc->nr_freepages = nr_freepages;
+}
+
+/* possible outcome of isolate_migratepages */
+typedef enum {
+	ISOLATE_ABORT,		/* Abort compaction now */
+	ISOLATE_NONE,		/* No pages isolated, continue scanning */
+	ISOLATE_SUCCESS,	/* Pages isolated, migrate */
+} isolate_migrate_t;
+
+/*
+ * Isolate all pages that can be migrated from the block pointed to by
+ * the migrate scanner within compact_control.
+ */
+static isolate_migrate_t isolate_migratepages(struct zone *zone,
+					struct compact_control *cc)
+{
+	unsigned long low_pfn, end_pfn;
+
+	/* Do not scan outside zone boundaries */
+	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
+
+	/* Only scan within a pageblock boundary */
+	end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages);
+
+	/* Do not cross the free scanner or scan within a memory hole */
+	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
+		cc->migrate_pfn = end_pfn;
+		return ISOLATE_NONE;
+	}
+
+	/* Perform the isolation */
+	low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn);
+	if (!low_pfn)
+		return ISOLATE_ABORT;
+
+	cc->migrate_pfn = low_pfn;
+
+	return ISOLATE_SUCCESS;
 }
 
 static int compact_finished(struct zone *zone,
···
 	return device_remove_file(&node->dev, &dev_attr_compact);
 }
 #endif /* CONFIG_SYSFS && CONFIG_NUMA */
+
+#endif /* CONFIG_COMPACTION */

mm/internal.h

···
 extern bool is_free_buddy_page(struct page *page);
 #endif
 
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+
+/*
+ * in mm/compaction.c
+ */
+/*
+ * compact_control is used to track pages being migrated and the free pages
+ * they are being migrated to during memory compaction. The free_pfn starts
+ * at the end of a zone and migrate_pfn begins at the start. Movable pages
+ * are moved to the end of a zone during a compaction run and the run
+ * completes when free_pfn <= migrate_pfn
+ */
+struct compact_control {
+	struct list_head freepages;	/* List of free pages to migrate to */
+	struct list_head migratepages;	/* List of pages being migrated */
+	unsigned long nr_freepages;	/* Number of isolated free pages */
+	unsigned long nr_migratepages;	/* Number of pages to migrate */
+	unsigned long free_pfn;		/* isolate_freepages search base */
+	unsigned long migrate_pfn;	/* isolate_migratepages search base */
+	bool sync;			/* Synchronous migration */
+
+	int order;			/* order a direct compactor needs */
+	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
+	struct zone *zone;
+};
+
+unsigned long
+isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn);
+unsigned long
+isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
+			   unsigned long low_pfn, unsigned long end_pfn);
+
+#endif
 
 /*
  * function for dealing with page's order in buddy system.

mm/memory-failure.c

···
 		/* Not a free page */
 		ret = 1;
 	}
-	unset_migratetype_isolate(p);
+	unset_migratetype_isolate(p, MIGRATE_MOVABLE);
 	unlock_memory_hotplug();
 	return ret;
 }

mm/memory_hotplug.c

···
 	nr_pages = end_pfn - start_pfn;
 
 	/* set above range as isolated */
-	ret = start_isolate_page_range(start_pfn, end_pfn);
+	ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 	if (ret)
 		goto out;
 
···
 	   We cannot do rollback at this point. */
 	offline_isolated_pages(start_pfn, end_pfn);
 	/* reset pagetype flags and makes migrate type to be MOVABLE */
-	undo_isolate_page_range(start_pfn, end_pfn);
+	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 	/* removal success */
 	zone->present_pages -= offlined_pages;
 	zone->zone_pgdat->node_present_pages -= offlined_pages;
···
 		start_pfn, end_pfn);
 	memory_notify(MEM_CANCEL_OFFLINE, &arg);
 	/* pushback to free area */
-	undo_isolate_page_range(start_pfn, end_pfn);
+	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 
 out:
 	unlock_memory_hotplug();

mm/page_alloc.c

···
 #include <linux/ftrace_event.h>
 #include <linux/memcontrol.h>
 #include <linux/prefetch.h>
+#include <linux/migrate.h>
 #include <linux/page-debug-flags.h>
 
 #include <asm/tlbflush.h>
···
  * free pages of length of (1 << order) and marked with _mapcount -2. Page's
  * order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
- * other.  That is, if we allocate a small block, and both were   
- * free, the remainder of the region must be split into blocks.   
+ * other.  That is, if we allocate a small block, and both were
+ * free, the remainder of the region must be split into blocks.
  * If a block is freed, and its buddy is also free, then this
- * triggers coalescing into a block of larger size.            
+ * triggers coalescing into a block of larger size.
  *
  * -- wli
  */
···
 	__free_pages(page, order);
 }
 
+#ifdef CONFIG_CMA
+/* Free whole pageblock and set it's migration type to MIGRATE_CMA. */
+void __init init_cma_reserved_pageblock(struct page *page)
+{
+	unsigned i = pageblock_nr_pages;
+	struct page *p = page;
+
+	do {
+		__ClearPageReserved(p);
+		set_page_count(p, 0);
+	} while (++p, --i);
+
+	set_page_refcounted(page);
+	set_pageblock_migratetype(page, MIGRATE_CMA);
+	__free_pages(page, pageblock_order);
+	totalram_pages += pageblock_nr_pages;
+}
+#endif
 
 /*
  * The order of subdivision here is critical for the IO subsystem.
···
  * This array describes the order lists are fallen back to when
  * the free lists for the desirable migrate type are depleted
  */
-static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = {
-	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,   MIGRATE_RESERVE },
-	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,   MIGRATE_RESERVE },
-	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
-	[MIGRATE_RESERVE]     = { MIGRATE_RESERVE,     MIGRATE_RESERVE,   MIGRATE_RESERVE }, /* Never used */
+static int fallbacks[MIGRATE_TYPES][4] = {
+	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,     MIGRATE_RESERVE },
+	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,     MIGRATE_RESERVE },
+#ifdef CONFIG_CMA
+	[MIGRATE_MOVABLE]     = { MIGRATE_CMA,         MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
+	[MIGRATE_CMA]         = { MIGRATE_RESERVE }, /* Never used */
+#else
+	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE,   MIGRATE_RESERVE },
+#endif
+	[MIGRATE_RESERVE]     = { MIGRATE_RESERVE }, /* Never used */
+	[MIGRATE_ISOLATE]     = { MIGRATE_RESERVE }, /* Never used */
 };
 
 /*
···
 	/* Find the largest possible block of pages in the other list */
 	for (current_order = MAX_ORDER-1; current_order >= order;
 						--current_order) {
-		for (i = 0; i < MIGRATE_TYPES - 1; i++) {
+		for (i = 0;; i++) {
 			migratetype = fallbacks[start_migratetype][i];
 
 			/* MIGRATE_RESERVE handled later if necessary */
 			if (migratetype == MIGRATE_RESERVE)
-				continue;
+				break;
 
 			area = &(zone->free_area[current_order]);
 			if (list_empty(&area->free_list[migratetype]))
···
 			 * pages to the preferred allocation list. If falling
 			 * back for a reclaimable kernel allocation, be more
 			 * aggressive about taking ownership of free pages
+			 *
+			 * On the other hand, never change migration
+			 * type of MIGRATE_CMA pageblocks nor move CMA
+			 * pages on different free lists. We don't
+			 * want unmovable pages to be allocated from
+			 * MIGRATE_CMA areas.
 			 */
-			if (unlikely(current_order >= (pageblock_order >> 1)) ||
-					start_migratetype == MIGRATE_RECLAIMABLE ||
-					page_group_by_mobility_disabled) {
-				unsigned long pages;
+			if (!is_migrate_cma(migratetype) &&
+			    (unlikely(current_order >= pageblock_order / 2) ||
+			     start_migratetype == MIGRATE_RECLAIMABLE ||
+			     page_group_by_mobility_disabled)) {
+				int pages;
 				pages = move_freepages_block(zone, page,
 								start_migratetype);
 
···
 			rmv_page_order(page);
 
 			/* Take ownership for orders >= pageblock_order */
-			if (current_order >= pageblock_order)
+			if (current_order >= pageblock_order &&
+			    !is_migrate_cma(migratetype))
 				change_pageblock_range(page, current_order,
 							start_migratetype);
 
-			expand(zone, page, order, current_order, area, migratetype);
+			expand(zone, page, order, current_order, area,
+			       is_migrate_cma(migratetype)
+			     ? migratetype : start_migratetype);
 
 			trace_mm_page_alloc_extfrag(page, order, current_order,
 				start_migratetype, migratetype);
···
 	return page;
 }
 
-/* 
+/*
  * Obtain a specified number of elements from the buddy allocator, all under
  * a single hold of the lock, for efficiency.  Add them to the supplied list.
  * Returns the number of new pages which were placed at *list.
  */
-static int rmqueue_bulk(struct zone *zone, unsigned int order, 
+static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			unsigned long count, struct list_head *list,
 			int migratetype, int cold)
 {
-	int i;
-	
+	int mt = migratetype, i;
+
 	spin_lock(&zone->lock);
 	for (i = 0; i < count; ++i) {
 		struct page *page = __rmqueue(zone, order, migratetype);
···
 			list_add(&page->lru, list);
 		else
 			list_add_tail(&page->lru, list);
-		set_page_private(page, migratetype);
+		if (IS_ENABLED(CONFIG_CMA)) {
+			mt = get_pageblock_migratetype(page);
+			if (!is_migrate_cma(mt) && mt != MIGRATE_ISOLATE)
+				mt = migratetype;
+		}
+		set_page_private(page, mt);
 		list = &page->lru;
 	}
 	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
···
 
 	if (order >= pageblock_order - 1) {
 		struct page *endpage = page + (1 << order) - 1;
-		for (; page < endpage; page += pageblock_nr_pages)
-			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+		for (; page < endpage; page += pageblock_nr_pages) {
+			int mt = get_pageblock_migratetype(page);
+			if (mt != MIGRATE_ISOLATE && !is_migrate_cma(mt))
+				set_pageblock_migratetype(page,
+							  MIGRATE_MOVABLE);
+		}
 	}
 
 	return 1 << order;
···
 }
 #endif /* CONFIG_COMPACTION */
 
-/* The really slow allocator path where we enter direct reclaim */
-static inline struct page *
-__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
-	struct zonelist *zonelist, enum zone_type high_zoneidx,
-	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress)
+/* Perform direct synchronous page reclaim */
+static int
+__perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist,
+		  nodemask_t *nodemask)
 {
-	struct page *page = NULL;
 	struct reclaim_state reclaim_state;
-	bool drained = false;
+	int progress;
 
 	cond_resched();
 
···
 	reclaim_state.reclaimed_slab = 0;
 	current->reclaim_state = &reclaim_state;
 
-	*did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
+	progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
 
 	current->reclaim_state = NULL;
 	lockdep_clear_current_reclaim_state();
···
 
 	cond_resched();
 
+	return progress;
+}
+
+/* The really slow allocator path where we enter direct reclaim */
+static inline struct page *
+__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
+	int migratetype, unsigned long *did_some_progress)
+{
+	struct page *page = NULL;
+	bool drained = false;
+
+	*did_some_progress = __perform_reclaim(gfp_mask, order, zonelist,
+					       nodemask);
 	if (unlikely(!(*did_some_progress)))
 		return NULL;
 
···
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	pgdat->kswapd_max_order = 0;
 	pgdat_page_cgroup_init(pgdat);
-	
+
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize, memmap_pages;
···
 	calculate_totalreserve_pages();
 }
 
-/**
- * setup_per_zone_wmarks - called when min_free_kbytes changes
- * or when memory is hot-{added|removed}
- *
- * Ensures that the watermark[min,low,high] values for each zone are set
- * correctly with respect to min_free_kbytes.
- */
-void setup_per_zone_wmarks(void)
+static void __setup_per_zone_wmarks(void)
 {
 	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
 	unsigned long lowmem_pages = 0;
···
 
 		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+
+		zone->watermark[WMARK_MIN] += cma_wmark_pages(zone);
+		zone->watermark[WMARK_LOW] += cma_wmark_pages(zone);
+		zone->watermark[WMARK_HIGH] += cma_wmark_pages(zone);
+
 		setup_zone_migrate_reserve(zone);
 		spin_unlock_irqrestore(&zone->lock, flags);
 	}
 
 	/* update totalreserve_pages */
 	calculate_totalreserve_pages();
+}
+
+/**
+ * setup_per_zone_wmarks - called when min_free_kbytes changes
+ * or when memory is hot-{added|removed}
+ *
+ * Ensures that the watermark[min,low,high] values for each zone are set
+ * correctly with respect to min_free_kbytes.
+ */
+void setup_per_zone_wmarks(void)
+{
+	mutex_lock(&zonelists_mutex);
+	__setup_per_zone_wmarks();
+	mutex_unlock(&zonelists_mutex);
 }
 
 /*
···
 __count_immobile_pages(struct zone *zone, struct page *page, int count)
 {
 	unsigned long pfn, iter, found;
+	int mt;
+
 	/*
 	 * For avoiding noise data, lru_add_drain_all() should be called
 	 * If ZONE_MOVABLE, the zone never contains immobile pages
 	 */
 	if (zone_idx(zone) == ZONE_MOVABLE)
 		return true;
-
-	if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE)
+	mt = get_pageblock_migratetype(page);
+	if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt))
 		return true;
 
 	pfn = page_to_pfn(page);
···
 	return ret;
 }
 
-void unset_migratetype_isolate(struct page *page)
+void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 {
 	struct zone *zone;
 	unsigned long flags;
···
 	spin_lock_irqsave(&zone->lock, flags);
 	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
 		goto out;
-	set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-	move_freepages_block(zone, page, MIGRATE_MOVABLE);
+	set_pageblock_migratetype(page, migratetype);
+	move_freepages_block(zone, page, migratetype);
 out:
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
+
+#ifdef CONFIG_CMA
+
+static unsigned long pfn_max_align_down(unsigned long pfn)
+{
+	return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
+			     pageblock_nr_pages) - 1);
+}
+
+static unsigned long pfn_max_align_up(unsigned long pfn)
+{
+	return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
+				pageblock_nr_pages));
+}
+
+static struct page *
+__alloc_contig_migrate_alloc(struct page *page, unsigned long private,
+			     int **resultp)
+{
+	return alloc_page(GFP_HIGHUSER_MOVABLE);
+}
+
+/* [start, end) must belong to a single zone. */
+static int __alloc_contig_migrate_range(unsigned long start, unsigned long end)
+{
+	/* This function is based on compact_zone() from compaction.c. */
+
+	unsigned long pfn = start;
+	unsigned int tries = 0;
+	int ret = 0;
+
+	struct compact_control cc = {
+		.nr_migratepages = 0,
+		.order = -1,
+		.zone = page_zone(pfn_to_page(start)),
+		.sync = true,
+	};
+	INIT_LIST_HEAD(&cc.migratepages);
+
+	migrate_prep_local();
+
+	while (pfn < end || !list_empty(&cc.migratepages)) {
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+
+		if (list_empty(&cc.migratepages)) {
+			cc.nr_migratepages = 0;
+			pfn = isolate_migratepages_range(cc.zone, &cc,
+							 pfn, end);
+			if (!pfn) {
+				ret = -EINTR;
+				break;
+			}
+			tries = 0;
+		} else if (++tries == 5) {
+			ret = ret < 0 ? ret : -EBUSY;
+			break;
+		}
+
+		ret = migrate_pages(&cc.migratepages,
+				    __alloc_contig_migrate_alloc,
+				    0, false, MIGRATE_SYNC);
+	}
+
+	putback_lru_pages(&cc.migratepages);
+	return ret > 0 ? 0 : ret;
+}
+
+/*
+ * Update zone's cma pages counter used for watermark level calculation.
+ */
+static inline void __update_cma_watermarks(struct zone *zone, int count)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&zone->lock, flags);
+	zone->min_cma_pages += count;
+	spin_unlock_irqrestore(&zone->lock, flags);
+	setup_per_zone_wmarks();
+}
+
+/*
+ * Trigger memory pressure bump to reclaim some pages in order to be able to
+ * allocate 'count' pages in single page units. Does similar work as
+ *__alloc_pages_slowpath() function.
+ */
+static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count)
+{
+	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+	struct zonelist *zonelist = node_zonelist(0, gfp_mask);
+	int did_some_progress = 0;
+	int order = 1;
+
+	/*
+	 * Increase level of watermarks to force kswapd do his job
+	 * to stabilise at new watermark level.
+	 */
+	__update_cma_watermarks(zone, count);
+
+	/* Obey watermarks as if the page was being allocated */
+	while (!zone_watermark_ok(zone, 0, low_wmark_pages(zone), 0, 0)) {
+		wake_all_kswapd(order, zonelist, high_zoneidx, zone_idx(zone));
+
+		did_some_progress = __perform_reclaim(gfp_mask, order, zonelist,
+						      NULL);
+		if (!did_some_progress) {
+			/* Exhausted what can be done so it's blamo time */
+			out_of_memory(zonelist, gfp_mask, order, NULL, false);
+		}
+	}
+
+	/* Restore original watermark levels. */
+	__update_cma_watermarks(zone, -count);
+
+	return count;
+}
+
+/**
+ * alloc_contig_range() -- tries to allocate given range of pages
+ * @start:	start PFN to allocate
+ * @end:	one-past-the-last PFN to allocate
+ * @migratetype:	migratetype of the underlaying pageblocks (either
+ *			#MIGRATE_MOVABLE or #MIGRATE_CMA).  All pageblocks
+ *			in range must have the same migratetype and it must
+ *			be either of the two.
+ *
+ * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
+ * aligned, however it's the caller's responsibility to guarantee that
+ * we are the only thread that changes migrate type of pageblocks the
+ * pages fall in.
+ *
+ * The PFN range must belong to a single zone.
+ *
+ * Returns zero on success or negative error code.  On success all
+ * pages which PFN is in [start, end) are allocated for the caller and
+ * need to be freed with free_contig_range().
+ */
+int alloc_contig_range(unsigned long start, unsigned long end,
+		       unsigned migratetype)
+{
+	struct zone *zone = page_zone(pfn_to_page(start));
+	unsigned long outer_start, outer_end;
+	int ret = 0, order;
+
+	/*
+	 * What we do here is we mark all pageblocks in range as
+	 * MIGRATE_ISOLATE.  Because pageblock and max order pages may
+	 * have different sizes, and due to the way page allocator
+	 * work, we align the range to biggest of the two pages so
+	 * that page allocator won't try to merge buddies from
+	 * different pageblocks and change MIGRATE_ISOLATE to some
+	 * other migration type.
+	 *
+	 * Once the pageblocks are marked as MIGRATE_ISOLATE, we
+	 * migrate the pages from an unaligned range (ie. pages that
+	 * we are interested in).  This will put all the pages in
+	 * range back to page allocator as MIGRATE_ISOLATE.
+	 *
+	 * When this is done, we take the pages in range from page
+	 * allocator removing them from the buddy system.  This way
+	 * page allocator will never consider using them.
+	 *
+	 * This lets us mark the pageblocks back as
+	 * MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the
+	 * aligned range but not in the unaligned, original range are
+	 * put back to page allocator so that buddy can use them.
+	 */
+
+	ret = start_isolate_page_range(pfn_max_align_down(start),
+				       pfn_max_align_up(end), migratetype);
+	if (ret)
+		goto done;
+
+	ret = __alloc_contig_migrate_range(start, end);
+	if (ret)
+		goto done;
+
+	/*
+	 * Pages from [start, end) are within a MAX_ORDER_NR_PAGES
+	 * aligned blocks that are marked as MIGRATE_ISOLATE.  What's
+	 * more, all pages in [start, end) are free in page allocator.
+	 * What we are going to do is to allocate all pages from
+	 * [start, end) (that is remove them from page allocator).
+	 *
+	 * The only problem is that pages at the beginning and at the
+	 * end of interesting range may be not aligned with pages that
+	 * page allocator holds, ie. they can be part of higher order
+	 * pages.  Because of this, we reserve the bigger range and
+	 * once this is done free the pages we are not interested in.
+	 *
+	 * We don't have to hold zone->lock here because the pages are
+	 * isolated thus they won't get removed from buddy.
+	 */
+
+	lru_add_drain_all();
+	drain_all_pages();
+
+	order = 0;
+	outer_start = start;
+	while (!PageBuddy(pfn_to_page(outer_start))) {
+		if (++order >= MAX_ORDER) {
+			ret = -EBUSY;
+			goto done;
+		}
+		outer_start &= ~0UL << order;
+	}
+
+	/* Make sure the range is really isolated. */
+	if (test_pages_isolated(outer_start, end)) {
+		pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n",
+		       outer_start, end);
+		ret = -EBUSY;
+		goto done;
+	}
+
+	/*
+	 * Reclaim enough pages to make sure that contiguous allocation
+	 * will not starve the system.
+	 */
+	__reclaim_pages(zone, GFP_HIGHUSER_MOVABLE, end-start);
+
+	/* Grab isolated pages from freelists. */
+	outer_end = isolate_freepages_range(outer_start, end);
+	if (!outer_end) {
+		ret = -EBUSY;
+		goto done;
+	}
+
+	/* Free head and tail (if any) */
+	if (start != outer_start)
+		free_contig_range(outer_start, start - outer_start);
+	if (end != outer_end)
+		free_contig_range(end, outer_end - end);
+
+done:
+	undo_isolate_page_range(pfn_max_align_down(start),
+				pfn_max_align_up(end), migratetype);
+	return ret;
+}
+
+void free_contig_range(unsigned long pfn, unsigned nr_pages)
+{
+	for (; nr_pages--; ++pfn)
+		__free_page(pfn_to_page(pfn));
+}
+#endif
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /*

mm/page_isolation.c

···
  * to be MIGRATE_ISOLATE.
  * @start_pfn: The lower PFN of the range to be isolated.
  * @end_pfn: The upper PFN of the range to be isolated.
+ * @migratetype: migrate type to set in error recovery.
  *
  * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
  * the range will never be allocated. Any free pages and pages freed in the
···
  * start_pfn/end_pfn must be aligned to pageblock_order.
  * Returns 0 on success and -EBUSY if any part of range cannot be isolated.
  */
-int
-start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn)
+int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+			     unsigned migratetype)
 {
 	unsigned long pfn;
 	unsigned long undo_pfn;
···
 	for (pfn = start_pfn;
 	     pfn < undo_pfn;
 	     pfn += pageblock_nr_pages)
-		unset_migratetype_isolate(pfn_to_page(pfn));
+		unset_migratetype_isolate(pfn_to_page(pfn), migratetype);
 
 	return -EBUSY;
 }
···
 /*
  * Make isolated pages available again.
  */
-int
-undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn)
+int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+			    unsigned migratetype)
 {
 	unsigned long pfn;
 	struct page *page;
···
 		page = __first_valid_page(pfn, pageblock_nr_pages);
 		if (!page || get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
 			continue;
-		unset_migratetype_isolate(page);
+		unset_migratetype_isolate(page, migratetype);
 	}
 	return 0;
 }
···
  * all pages in [start_pfn...end_pfn) must be in the same zone.
  * zone->lock must be held before call this.
  *
- * Returns 1 if all pages in the range is isolated.
+ * Returns 1 if all pages in the range are isolated.
  */
 static int
 __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)

mm/vmstat.c

···
 	"Reclaimable",
 	"Movable",
 	"Reserve",
+#ifdef CONFIG_CMA
+	"CMA",
+#endif
 	"Isolate",
 };