diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index ea04132..75cb757 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -519,10 +519,9 @@
 Part II - Non-coherent DMA allocations
 --------------------------------------
 
-These APIs allow to allocate pages in the kernel direct mapping that are
-guaranteed to be DMA addressable.  This means that unlike dma_alloc_coherent,
-virt_to_page can be called on the resulting address, and the resulting
-struct page can be used for everything a struct page is suitable for.
+These APIs allow to allocate pages that are guaranteed to be DMA addressable
+by the passed in device, but which need explicit management of memory ownership
+for the kernel vs the device.
 
 If you don't understand how cache line coherency works between a processor and
 an I/O device, you should not be using this part of the API.
@@ -537,7 +536,7 @@
 This routine allocates a region of <size> bytes of consistent memory.  It
 returns a pointer to the allocated region (in the processor's virtual address
 space) or NULL if the allocation failed.  The returned memory may or may not
-be in the kernels direct mapping.  Drivers must not call virt_to_page on
+be in the kernel direct mapping.  Drivers must not call virt_to_page on
 the returned memory region.
 
 It also returns a <dma_handle> which may be cast to an unsigned integer the
@@ -565,7 +564,45 @@
 Free a region of memory previously allocated using dma_alloc_noncoherent().
 dev, size and dma_handle and dir must all be the same as those passed into
 dma_alloc_noncoherent().  cpu_addr must be the virtual address returned by
-the dma_alloc_noncoherent().
+dma_alloc_noncoherent().
+
+::
+
+	struct page *
+	dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle,
+			enum dma_data_direction dir, gfp_t gfp)
+
+This routine allocates a region of <size> bytes of non-coherent memory.  It
+returns a pointer to first struct page for the region, or NULL if the
+allocation failed. The resulting struct page can be used for everything a
+struct page is suitable for.
+
+It also returns a <dma_handle> which may be cast to an unsigned integer the
+same width as the bus and given to the device as the DMA address base of
+the region.
+
+The dir parameter specified if data is read and/or written by the device,
+see dma_map_single() for details.
+
+The gfp parameter allows the caller to specify the ``GFP_`` flags (see
+kmalloc()) for the allocation, but rejects flags used to specify a memory
+zone such as GFP_DMA or GFP_HIGHMEM.
+
+Before giving the memory to the device, dma_sync_single_for_device() needs
+to be called, and before reading memory written by the device,
+dma_sync_single_for_cpu(), just like for streaming DMA mappings that are
+reused.
+
+::
+
+	void
+	dma_free_pages(struct device *dev, size_t size, struct page *page,
+			dma_addr_t dma_handle, enum dma_data_direction dir)
+
+Free a region of memory previously allocated using dma_alloc_pages().
+dev, size and dma_handle and dir must all be the same as those passed into
+dma_alloc_noncoherent().  page must be the pointer returned by
+dma_alloc_pages().
 
 ::
 
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index c98ebae..f89c1ea 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -22,7 +22,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 8029f7e..a5f89fc 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -203,6 +203,29 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
+int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
+
+struct page **dma_common_find_pages(void *cpu_addr);
+void *dma_common_contiguous_remap(struct page *page, size_t size, pgprot_t prot,
+		const void *caller);
+void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot,
+		const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size);
+
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t flags,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
+bool dma_free_from_pool(struct device *dev, void *start, size_t size);
+
 #ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
 #include <asm/dma-coherence.h>
 #elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 3f029af..9561510 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -389,30 +389,6 @@ static inline void dma_sync_sgtable_for_device(struct device *dev,
 #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
 #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0)
 
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
-struct page *dma_common_alloc_pages(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
-void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr,
-		dma_addr_t dma_handle, enum dma_data_direction dir);
-struct page **dma_common_find_pages(void *cpu_addr);
-void *dma_common_contiguous_remap(struct page *page, size_t size,
-			pgprot_t prot, const void *caller);
-
-void *dma_common_pages_remap(struct page **pages, size_t size,
-			pgprot_t prot, const void *caller);
-void dma_common_free_remap(void *cpu_addr, size_t size);
-
-struct page *dma_alloc_from_pool(struct device *dev, size_t size,
-		void **cpu_addr, gfp_t flags,
-		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
-bool dma_free_from_pool(struct device *dev, void *start, size_t size);
-
-int
-dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr,
-		dma_addr_t dma_addr, size_t size, unsigned long attrs);
-
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index 78b23f0..905c3fa 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (c) 2014 The Linux Foundation
  */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>