[PATCHv2 0/2] arm:dma-mapping Refactoring iommu dma-mapping code

[PATCHv2 0/2] arm:dma-mapping Refactoring iommu dma-mapping code

[ritesh.harjani at gmail.com]

From: Ritesh Harjani <ritesh.harjani@gmail.com>

Hi All, 

This patch series is to refactor iommu related common code from
arch/arm/dma-mapping.c to lib/iommu-helper.c based on the various
discussions with the maintainers/experts [1].

Currently the only user of the common lib/iommu-helper code will
be ARM & ARM64 but later various architecture might try to use this
iommu lib helper functions.

Major change of this refactoring depends on bringing out struct dma_iommu_mapping 
*mapping variable from arch/arm/include/asm/device.h to include/linux/device.h
and by moving out complete structure definition of dma_iommu_mapping to
inclue/linux/iommu-helper.h. This is now done as a separate patch based on Will's
suggestion [2]. This patch series is based on top of that patch.

There are 1/2 more function definitions which I can think of moving out, but
those can be done once this patch series is approved as those are not very
big changes.

Also, this has been tested and verified on ARM hardware with IOMMU support.

Changes from v1:
1. Prefixed iommu_helper_* to all iommu-helper.h function instead of __iommu_*
2. Submitted changes in device.h as a separate patch on top of which this patch
   series is based upon[2].
3. Merged [PATCH 2/4] and [PATCH 3/4] from v1 patch series to [PATCHv2 1/2],
   based on Will Daecon suggestion [3].
4. Removed Change-id value from all v1 patches.

Links:
[1]: https://www.mail-archive.com/iommu at lists.linux-foundation.org/msg03458.html 
[2]: https://lkml.org/lkml/2014/6/4/41
[3]: http://www.spinics.net/lists/arm-kernel/msg336682.html


Ritesh Harjani (2):
  arm: dma-mapping: Refactor attach/detach, alloc/free func
  arm:dma-iommu: Move out complete func defs

 arch/arm/Kconfig             |  42 ++--
 arch/arm/mm/dma-mapping.c    | 572 ++++---------------------------------------
 include/linux/iommu-helper.h |  42 ++++
 lib/iommu-helper.c           | 562 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 673 insertions(+), 545 deletions(-)

-- 
1.8.1.3

[PATCHv2 1/2] arm: dma-mapping: Refactor attach/detach, alloc/free func

[ritesh.harjani at gmail.com]

From: Ritesh Harjani <ritesh.harjani@gmail.com>

Refactor following function calls to lib/iommu-helper.c

1.
arm_iommu_attach/detach device function calls.
arm_iommu_init/release_mapping function calls.

2. iommu_alloc/free_buffer can be moved out from
arm/dma-mapping.c to lib/iommu_helper.c

Signed-off-by: Ritesh Harjani <ritesh.harjani@gmail.com>
---
 arch/arm/mm/dma-mapping.c    | 200 ++++--------------------------------
 include/linux/iommu-helper.h |  18 ++++
 lib/iommu-helper.c           | 235 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 272 insertions(+), 181 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index b82561e..66cf96b 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1161,98 +1161,6 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping,
 	spin_unlock_irqrestore(&mapping->lock, flags);
 }
 
-static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
-					  gfp_t gfp, struct dma_attrs *attrs)
-{
-	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;
-
-	if (dma_get_attr(DMA_ATTR_FORCE_CONTIGUOUS, attrs))
-	{
-		unsigned long order = get_order(size);
-		struct page *page;
-
-		page = dma_alloc_from_contiguous(dev, count, order);
-		if (!page)
-			goto error;
-
-		__dma_clear_buffer(page, size);
-
-		for (i = 0; i < count; i++)
-			pages[i] = page + i;
-
-		return pages;
-	}
-
-	/*
-	 * IOMMU can map any pages, so himem can also be used here
-	 */
-	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
-
-	while (count) {
-		int j, order = __fls(count);
-
-		pages[i] = alloc_pages(gfp, order);
-		while (!pages[i] && order)
-			pages[i] = alloc_pages(gfp, --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, struct dma_attrs *attrs)
-{
-	int count = size >> PAGE_SHIFT;
-	int array_size = count * sizeof(struct page *);
-	int i;
-
-	if (dma_get_attr(DMA_ATTR_FORCE_CONTIGUOUS, attrs)) {
-		dma_release_from_contiguous(dev, pages[0], count);
-	} else {
-		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
  */
@@ -1417,7 +1325,8 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	 */
 	gfp &= ~(__GFP_COMP);
 
-	pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
+	pages = iommu_helper_alloc_buffer(dev, size, gfp, attrs,
+					__dma_clear_buffer);
 	if (!pages)
 		return NULL;
 
@@ -1438,7 +1347,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 err_mapping:
 	__iommu_remove_mapping(dev, *handle, size);
 err_buffer:
-	__iommu_free_buffer(dev, pages, size, attrs);
+	iommu_helper_free_buffer(dev, pages, size, attrs);
 	return NULL;
 }
 
@@ -1495,7 +1404,7 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	}
 
 	__iommu_remove_mapping(dev, handle, size);
-	__iommu_free_buffer(dev, pages, size, attrs);
+	iommu_helper_free_buffer(dev, pages, size, attrs);
 }
 
 static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
@@ -1924,7 +1833,8 @@ struct dma_map_ops iommu_coherent_ops = {
  * @base: start address of the valid IO address space
  * @size: maximum size of the valid IO address space
  *
- * Creates a mapping structure which holds information about used/unused
+ * Calls for lib/iommu-helper function which 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.
  *
@@ -1934,71 +1844,10 @@ struct dma_map_ops iommu_coherent_ops = {
 struct dma_iommu_mapping *
 arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size)
 {
-	unsigned int bits = size >> PAGE_SHIFT;
-	unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long);
-	struct dma_iommu_mapping *mapping;
-	int extensions = 1;
-	int err = -ENOMEM;
-
-	if (!bitmap_size)
-		return ERR_PTR(-EINVAL);
-
-	if (bitmap_size > PAGE_SIZE) {
-		extensions = bitmap_size / PAGE_SIZE;
-		bitmap_size = PAGE_SIZE;
-	}
-
-	mapping = kzalloc(sizeof(struct dma_iommu_mapping), GFP_KERNEL);
-	if (!mapping)
-		goto err;
-
-	mapping->bitmap_size = bitmap_size;
-	mapping->bitmaps = kzalloc(extensions * sizeof(unsigned long *),
-				GFP_KERNEL);
-	if (!mapping->bitmaps)
-		goto err2;
-
-	mapping->bitmaps[0] = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!mapping->bitmaps[0])
-		goto err3;
-
-	mapping->nr_bitmaps = 1;
-	mapping->extensions = extensions;
-	mapping->base = base;
-	mapping->bits = BITS_PER_BYTE * bitmap_size;
-
-	spin_lock_init(&mapping->lock);
-
-	mapping->domain = iommu_domain_alloc(bus);
-	if (!mapping->domain)
-		goto err4;
-
-	kref_init(&mapping->kref);
-	return mapping;
-err4:
-	kfree(mapping->bitmaps[0]);
-err3:
-	kfree(mapping->bitmaps);
-err2:
-	kfree(mapping);
-err:
-	return ERR_PTR(err);
+	return iommu_helper_init_mapping(bus, base, size);
 }
 EXPORT_SYMBOL_GPL(arm_iommu_create_mapping);
 
-static void release_iommu_mapping(struct kref *kref)
-{
-	int i;
-	struct dma_iommu_mapping *mapping =
-		container_of(kref, struct dma_iommu_mapping, kref);
-
-	iommu_domain_free(mapping->domain);
-	for (i = 0; i < mapping->nr_bitmaps; i++)
-		kfree(mapping->bitmaps[i]);
-	kfree(mapping->bitmaps);
-	kfree(mapping);
-}
-
 static int extend_iommu_mapping(struct dma_iommu_mapping *mapping)
 {
 	int next_bitmap;
@@ -2019,8 +1868,7 @@ static int extend_iommu_mapping(struct dma_iommu_mapping *mapping)
 
 void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
 {
-	if (mapping)
-		kref_put(&mapping->kref, release_iommu_mapping);
+	iommu_helper_release_mapping(mapping);
 }
 EXPORT_SYMBOL_GPL(arm_iommu_release_mapping);
 
@@ -2030,8 +1878,9 @@ EXPORT_SYMBOL_GPL(arm_iommu_release_mapping);
  * @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
+ * Calls for lib/iommu-helper which 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.
  */
@@ -2040,13 +1889,12 @@ int arm_iommu_attach_device(struct device *dev,
 {
 	int err;
 
-	err = iommu_attach_device(mapping->domain, dev);
-	if (err)
-		return err;
+	err = iommu_helper_attach_device(dev, mapping);
 
-	kref_get(&mapping->kref);
-	dev->mapping = mapping;
-	set_dma_ops(dev, &iommu_ops);
+	if (!err)
+		set_dma_ops(dev, &iommu_ops);
+	else
+		return err;
 
 	pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
 	return 0;
@@ -2057,24 +1905,14 @@ EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
  * arm_iommu_detach_device
  * @dev: valid struct device pointer
  *
- * Detaches the provided device from a previously attached map.
+ * Calls for lib/iommu-helper which detaches the provided
+ * device from a previously attached map.
  * This voids the dma operations (dma_map_ops pointer)
  */
 void arm_iommu_detach_device(struct device *dev)
 {
-	struct dma_iommu_mapping *mapping;
-
-	mapping = to_dma_iommu_mapping(dev);
-	if (!mapping) {
-		dev_warn(dev, "Not attached\n");
-		return;
-	}
-
-	iommu_detach_device(mapping->domain, dev);
-	kref_put(&mapping->kref, release_iommu_mapping);
-	dev->mapping = NULL;
+	iommu_helper_detach_device(dev);
 	set_dma_ops(dev, NULL);
-
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
 }
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h
index 0c5e4c7..9c4c2ae 100644
--- a/include/linux/iommu-helper.h
+++ b/include/linux/iommu-helper.h
@@ -2,6 +2,7 @@
 #define _LINUX_IOMMU_HELPER_H
 
 #include <linux/kernel.h>
+#include <linux/dma-attrs.h>
 
 #ifdef CONFIG_DMA_USE_IOMMU_HELPER_MAPPING
 struct dma_iommu_mapping {
@@ -19,6 +20,23 @@ struct dma_iommu_mapping {
 	struct kref		kref;
 };
 
+extern struct page **iommu_helper_alloc_buffer(struct device *dev, size_t size,
+					  gfp_t gfp, struct dma_attrs *attrs,
+			void (*arch_clear_buffer_cb)(struct page*, size_t));
+
+extern int iommu_helper_free_buffer(struct device *dev, struct page **pages,
+			       size_t size, struct dma_attrs *attrs);
+
+extern void iommu_helper_detach_device(struct device *dev);
+
+extern void iommu_helper_release_mapping(struct dma_iommu_mapping *mapping);
+
+extern int iommu_helper_attach_device(struct device *dev,
+			    struct dma_iommu_mapping *mapping);
+
+extern struct dma_iommu_mapping *
+iommu_helper_init_mapping(struct bus_type *bus, dma_addr_t base, size_t size);
+
 #define to_dma_iommu_mapping(dev) ((dev)->mapping)
 #else
 #define to_dma_iommu_mapping(dev) NULL
diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c
index c27e269..3664709 100644
--- a/lib/iommu-helper.c
+++ b/lib/iommu-helper.c
@@ -6,6 +6,17 @@
 #include <linux/bitmap.h>
 #include <linux/bug.h>
 
+#ifdef CONFIG_DMA_USE_IOMMU_HELPER_MAPPING
+#include <linux/iommu.h>
+#include <linux/device.h>
+#include <linux/iommu-helper.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/errno.h>
+#include <linux/dma-contiguous.h>
+#include <linux/mm.h>
+#endif
+
 int iommu_is_span_boundary(unsigned int index, unsigned int nr,
 			   unsigned long shift,
 			   unsigned long boundary_size)
@@ -39,3 +50,227 @@ again:
 	return -1;
 }
 EXPORT_SYMBOL(iommu_area_alloc);
+
+#ifdef CONFIG_DMA_USE_IOMMU_HELPER_MAPPING
+
+struct page **iommu_helper_alloc_buffer(struct device *dev, size_t size,
+					  gfp_t gfp, struct dma_attrs *attrs,
+			void (*arch_clear_buffer_cb)(struct page*, size_t))
+{
+	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;
+
+	if (dma_get_attr(DMA_ATTR_FORCE_CONTIGUOUS, attrs)) {
+		unsigned long order = get_order(size);
+		struct page *page;
+
+		page = dma_alloc_from_contiguous(dev, count, order);
+		if (!page)
+			goto error;
+
+		if (arch_clear_buffer_cb)
+			arch_clear_buffer_cb(page, size);
+
+		for (i = 0; i < count; i++)
+			pages[i] = page + i;
+
+		return pages;
+	}
+
+	/*
+	 * IOMMU can map any pages, so himem can also be used here
+	 */
+	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
+
+	while (count) {
+		int j, order = __fls(count);
+
+		pages[i] = alloc_pages(gfp, order);
+		while (!pages[i] && order)
+			pages[i] = alloc_pages(gfp, --order);
+		if (!pages[i])
+			goto error;
+
+		if (order) {
+			split_page(pages[i], order);
+			j = 1 << order;
+			while (--j)
+				pages[i + j] = pages[i] + j;
+		}
+		if (arch_clear_buffer_cb)
+			arch_clear_buffer_cb(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;
+}
+
+int iommu_helper_free_buffer(struct device *dev, struct page **pages,
+			       size_t size, struct dma_attrs *attrs)
+{
+	int count = size >> PAGE_SHIFT;
+	int array_size = count * sizeof(struct page *);
+	int i;
+
+	if (dma_get_attr(DMA_ATTR_FORCE_CONTIGUOUS, attrs)) {
+		dma_release_from_contiguous(dev, pages[0], count);
+	} else {
+		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;
+}
+
+/**
+ * iommu_helper_init_mapping
+ * @bus: pointer to the bus holding the client device (for IOMMU calls)
+ * @base: start address of the valid IO address space
+ * @size: maximum size of the valid IO address space
+ *
+ * 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.
+ *
+ */
+
+struct dma_iommu_mapping *
+iommu_helper_init_mapping(struct bus_type *bus, dma_addr_t base, size_t size)
+{
+	unsigned int bits = size >> PAGE_SHIFT;
+	unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long);
+	struct dma_iommu_mapping *mapping;
+	int extensions = 1;
+	int err = -ENOMEM;
+
+	if (!bitmap_size)
+		return ERR_PTR(-EINVAL);
+
+	if (bitmap_size > PAGE_SIZE) {
+		extensions = bitmap_size / PAGE_SIZE;
+		bitmap_size = PAGE_SIZE;
+	}
+
+	mapping = kzalloc(sizeof(struct dma_iommu_mapping), GFP_KERNEL);
+	if (!mapping)
+		goto err;
+
+	mapping->bitmap_size = bitmap_size;
+	mapping->bitmaps = kzalloc(extensions * sizeof(unsigned long *),
+				GFP_KERNEL);
+	if (!mapping->bitmaps)
+		goto err2;
+
+	mapping->bitmaps[0] = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!mapping->bitmaps[0])
+		goto err3;
+
+	mapping->nr_bitmaps = 1;
+	mapping->extensions = extensions;
+	mapping->base = base;
+	mapping->bits = BITS_PER_BYTE * bitmap_size;
+
+	spin_lock_init(&mapping->lock);
+
+	mapping->domain = iommu_domain_alloc(bus);
+	if (!mapping->domain)
+		goto err4;
+
+	kref_init(&mapping->kref);
+	return mapping;
+err4:
+	kfree(mapping->bitmaps[0]);
+err3:
+	kfree(mapping->bitmaps);
+err2:
+	kfree(mapping);
+err:
+	return ERR_PTR(err);
+}
+
+static void release_iommu_mapping(struct kref *kref)
+{
+	int i;
+	struct dma_iommu_mapping *mapping =
+		container_of(kref, struct dma_iommu_mapping, kref);
+
+	iommu_domain_free(mapping->domain);
+	for (i = 0; i < mapping->nr_bitmaps; i++)
+		kfree(mapping->bitmaps[i]);
+	kfree(mapping->bitmaps);
+	kfree(mapping);
+}
+
+
+void iommu_helper_release_mapping(struct dma_iommu_mapping *mapping)
+{
+	if (mapping)
+		kref_put(&mapping->kref, release_iommu_mapping);
+}
+
+/**
+ * iommu_helper_detach_device
+ * @dev: valid struct device pointer
+ *
+ * Detaches the provided device from a previously attached map.
+ */
+void iommu_helper_detach_device(struct device *dev)
+{
+	struct dma_iommu_mapping *mapping;
+
+	mapping = to_dma_iommu_mapping(dev);
+	if (!mapping) {
+		dev_warn(dev, "Not attached\n");
+		return;
+	}
+
+	iommu_detach_device(mapping->domain, dev);
+	kref_put(&mapping->kref, release_iommu_mapping);
+	dev->mapping = NULL;
+}
+
+/**
+ * iommu_helper_attach_device
+ * @dev: valid struct device pointer
+ * @mapping: io address space mapping structure
+ *
+ * Attaches specified io address space mapping to the provided device.
+ */
+int iommu_helper_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->mapping = mapping;
+	return 0;
+}
+#endif
-- 
1.8.1.3

[PATCHv2 2/2] arm:dma-iommu: Move out complete func defs

[ritesh.harjani at gmail.com]

From: Ritesh Harjani <ritesh.harjani@gmail.com>

Move out complete function definitions from
arch/arm/dma-mapping to lib/iommu-helper

1. Moved out iova alloc/free routine and make them
statically defined.

2. Moved out complete function definitions which calls
alloc/free_iova routine to lib/iommu-helper.c

3. Seperated out cache maintainance from iommu_map/unmap
function routine, to be called from within arch/arm/dma-mapping.c

Signed-off-by: Ritesh Harjani <ritesh.harjani@gmail.com>
---
 arch/arm/Kconfig             |  42 ++---
 arch/arm/mm/dma-mapping.c    | 372 ++++---------------------------------------
 include/linux/iommu-helper.h |  28 +++-
 lib/iommu-helper.c           | 329 +++++++++++++++++++++++++++++++++++++-
 4 files changed, 404 insertions(+), 367 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 20717fb..977427d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -80,27 +80,6 @@ config ARM_DMA_USE_IOMMU
 	select NEED_SG_DMA_LENGTH
 	select DMA_USE_IOMMU_HELPER_MAPPING
 
-if ARM_DMA_USE_IOMMU
-
-config ARM_DMA_IOMMU_ALIGNMENT
-	int "Maximum PAGE_SIZE order of alignment for DMA IOMMU 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 waste of address space. Drivers which has
-	  relatively small addressing window (like 64Mib) might run out of
-	  virtual space with just a few allocations.
-
-	  With this parameter you can specify the maximum PAGE_SIZE order for
-	  DMA IOMMU 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.
-
-endif
-
 config HAVE_PWM
 	bool
 
@@ -1949,6 +1928,27 @@ config IOMMU_HELPER
 config DMA_USE_IOMMU_HELPER_MAPPING
 	def_bool n
 
+if DMA_USE_IOMMU_HELPER_MAPPING
+
+config DMA_IOMMU_ALIGNMENT
+	int "Maximum PAGE_SIZE order of alignment for DMA IOMMU 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 waste of address space. Drivers which has
+	  relatively small addressing window (like 64Mib) might run out of
+	  virtual space with just a few allocations.
+
+	  With this parameter you can specify the maximum PAGE_SIZE order for
+	  DMA IOMMU 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.
+
+endif
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 66cf96b..d2192d4 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1066,101 +1066,6 @@ fs_initcall(dma_debug_do_init);
 
 /* IOMMU */
 
-static int extend_iommu_mapping(struct dma_iommu_mapping *mapping);
-
-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;
-	size_t mapping_size = mapping->bits << PAGE_SHIFT;
-	unsigned long flags;
-	dma_addr_t iova;
-	int i;
-
-	if (order > CONFIG_ARM_DMA_IOMMU_ALIGNMENT)
-		order = CONFIG_ARM_DMA_IOMMU_ALIGNMENT;
-
-	count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	align = (1 << order) - 1;
-
-	spin_lock_irqsave(&mapping->lock, flags);
-	for (i = 0; i < mapping->nr_bitmaps; i++) {
-		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
-				mapping->bits, 0, count, align);
-
-		if (start > mapping->bits)
-			continue;
-
-		bitmap_set(mapping->bitmaps[i], start, count);
-		break;
-	}
-
-	/*
-	 * No unused range found. Try to extend the existing mapping
-	 * and perform a second attempt to reserve an IO virtual
-	 * address range of size bytes.
-	 */
-	if (i == mapping->nr_bitmaps) {
-		if (extend_iommu_mapping(mapping)) {
-			spin_unlock_irqrestore(&mapping->lock, flags);
-			return DMA_ERROR_CODE;
-		}
-
-		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
-				mapping->bits, 0, count, align);
-
-		if (start > mapping->bits) {
-			spin_unlock_irqrestore(&mapping->lock, flags);
-			return DMA_ERROR_CODE;
-		}
-
-		bitmap_set(mapping->bitmaps[i], start, count);
-	}
-	spin_unlock_irqrestore(&mapping->lock, flags);
-
-	iova = mapping->base + (mapping_size * i);
-	iova += start << PAGE_SHIFT;
-
-	return iova;
-}
-
-static inline void __free_iova(struct dma_iommu_mapping *mapping,
-			       dma_addr_t addr, size_t size)
-{
-	unsigned int start, count;
-	size_t mapping_size = mapping->bits << PAGE_SHIFT;
-	unsigned long flags;
-	dma_addr_t bitmap_base;
-	u32 bitmap_index;
-
-	if (!size)
-		return;
-
-	bitmap_index = (u32) (addr - mapping->base) / (u32) mapping_size;
-	BUG_ON(addr < mapping->base || bitmap_index > mapping->extensions);
-
-	bitmap_base = mapping->base + mapping_size * bitmap_index;
-
-	start = (addr - bitmap_base) >>	PAGE_SHIFT;
-
-	if (addr + size > bitmap_base + mapping_size) {
-		/*
-		 * The address range to be freed reaches into the iova
-		 * range of the next bitmap. This should not happen as
-		 * we don't allow this in __alloc_iova (at the
-		 * moment).
-		 */
-		BUG();
-	} else
-		count = size >> PAGE_SHIFT;
-
-	spin_lock_irqsave(&mapping->lock, flags);
-	bitmap_clear(mapping->bitmaps[bitmap_index], start, count);
-	spin_unlock_irqrestore(&mapping->lock, flags);
-}
-
 /*
  * Create a CPU mapping for a specified pages
  */
@@ -1194,62 +1099,6 @@ err:
 	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->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,
-				IOMMU_READ|IOMMU_WRITE);
-		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->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 struct page **__atomic_get_pages(void *addr)
 {
 	struct dma_pool *pool = &atomic_pool;
@@ -1285,7 +1134,7 @@ static void *__iommu_alloc_atomic(struct device *dev, size_t size,
 	if (!addr)
 		return NULL;
 
-	*handle = __iommu_create_mapping(dev, &page, size);
+	*handle = iommu_helper_create_mapping(dev, &page, size);
 	if (*handle == DMA_ERROR_CODE)
 		goto err_mapping;
 
@@ -1299,7 +1148,7 @@ err_mapping:
 static void __iommu_free_atomic(struct device *dev, void *cpu_addr,
 				dma_addr_t handle, size_t size)
 {
-	__iommu_remove_mapping(dev, handle, size);
+	iommu_helper_remove_mapping(dev, handle, size);
 	__free_from_pool(cpu_addr, size);
 }
 
@@ -1330,7 +1179,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	if (!pages)
 		return NULL;
 
-	*handle = __iommu_create_mapping(dev, pages, size);
+	*handle = iommu_helper_create_mapping(dev, pages, size);
 	if (*handle == DMA_ERROR_CODE)
 		goto err_buffer;
 
@@ -1345,7 +1194,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	return addr;
 
 err_mapping:
-	__iommu_remove_mapping(dev, *handle, size);
+	iommu_helper_remove_mapping(dev, *handle, size);
 err_buffer:
 	iommu_helper_free_buffer(dev, pages, size, attrs);
 	return NULL;
@@ -1403,7 +1252,7 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		vunmap(cpu_addr);
 	}
 
-	__iommu_remove_mapping(dev, handle, size);
+	iommu_helper_remove_mapping(dev, handle, size);
 	iommu_helper_free_buffer(dev, pages, size, attrs);
 }
 
@@ -1421,120 +1270,6 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 					 GFP_KERNEL);
 }
 
-static int __dma_direction_to_prot(enum dma_data_direction dir)
-{
-	int prot;
-
-	switch (dir) {
-	case DMA_BIDIRECTIONAL:
-		prot = IOMMU_READ | IOMMU_WRITE;
-		break;
-	case DMA_TO_DEVICE:
-		prot = IOMMU_READ;
-		break;
-	case DMA_FROM_DEVICE:
-		prot = IOMMU_WRITE;
-		break;
-	default:
-		prot = 0;
-	}
-
-	return prot;
-}
-
-/*
- * 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_attrs *attrs,
-			  bool is_coherent)
-{
-	struct dma_iommu_mapping *mapping = dev->mapping;
-	dma_addr_t iova, iova_base;
-	int ret = 0;
-	unsigned int count;
-	struct scatterlist *s;
-	int prot;
-
-	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 (!is_coherent &&
-			!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
-			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
-
-		prot = __dma_direction_to_prot(dir);
-
-		ret = iommu_map(mapping->domain, iova, phys, len, prot);
-		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;
-}
-
-static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		     enum dma_data_direction dir, struct dma_attrs *attrs,
-		     bool is_coherent)
-{
-	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, attrs, is_coherent) < 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, attrs,
-		is_coherent) < 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_coherent_iommu_map_sg - map a set of SG buffers for streaming mode DMA
  * @dev: valid struct device pointer
@@ -1550,7 +1285,7 @@ bad_mapping:
 int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	return __iommu_map_sg(dev, sg, nents, dir, attrs, true);
+	return iommu_helper_map_sg(dev, sg, nents, dir, attrs);
 }
 
 /**
@@ -1568,25 +1303,15 @@ int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg,
 int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	return __iommu_map_sg(dev, sg, nents, dir, attrs, false);
-}
-
-static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, struct dma_attrs *attrs,
-		bool is_coherent)
-{
 	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 (!is_coherent &&
-		    !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
-			__dma_page_dev_to_cpu(sg_page(s), s->offset,
-					      s->length, dir);
+	int i, ret;
+	ret = iommu_helper_map_sg(dev, sg, nents, dir, attrs);
+	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) {
+		for_each_sg(sg, s, ret, i)
+			__dma_page_cpu_to_dev(sg_page(s), s->offset,
+					s->length, dir);
 	}
+	return ret;
 }
 
 /**
@@ -1602,7 +1327,7 @@ static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg,
 void arm_coherent_iommu_unmap_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	__iommu_unmap_sg(dev, sg, nents, dir, attrs, true);
+	iommu_helper_unmap_sg(dev, sg, nents, dir, attrs);
 }
 
 /**
@@ -1618,7 +1343,16 @@ void arm_coherent_iommu_unmap_sg(struct device *dev, struct scatterlist *sg,
 void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 			enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	__iommu_unmap_sg(dev, sg, nents, dir, attrs, false);
+	struct scatterlist *s;
+	int i;
+
+	iommu_helper_unmap_sg(dev, sg, nents, dir, attrs);
+
+	for_each_sg(sg, s, nents, i) {
+		if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+			__dma_page_dev_to_cpu(sg_page(s), s->offset,
+					      s->length, dir);
+	}
 }
 
 /**
@@ -1671,24 +1405,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	     unsigned long offset, size_t size, enum dma_data_direction dir,
 	     struct dma_attrs *attrs)
 {
-	struct dma_iommu_mapping *mapping = dev->mapping;
-	dma_addr_t dma_addr;
-	int ret, prot, len = PAGE_ALIGN(size + offset);
-
-	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == DMA_ERROR_CODE)
-		return dma_addr;
-
-	prot = __dma_direction_to_prot(dir);
-
-	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
-	if (ret < 0)
-		goto fail;
-
-	return dma_addr + offset;
-fail:
-	__free_iova(mapping, dma_addr, len);
-	return DMA_ERROR_CODE;
+	return iommu_helper_map_page(dev, page, offset, size, dir);
 }
 
 /**
@@ -1708,7 +1425,7 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
 	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 		__dma_page_cpu_to_dev(page, offset, size, dir);
 
-	return arm_coherent_iommu_map_page(dev, page, offset, size, dir, attrs);
+	return iommu_helper_map_page(dev, page, offset, size, dir);
 }
 
 /**
@@ -1724,16 +1441,7 @@ static void arm_coherent_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->mapping;
-	dma_addr_t iova = handle & PAGE_MASK;
-	int offset = handle & ~PAGE_MASK;
-	int len = PAGE_ALIGN(size + offset);
-
-	if (!iova)
-		return;
-
-	iommu_unmap(mapping->domain, iova, len);
-	__free_iova(mapping, iova, len);
+	iommu_helper_unmap_page(dev, handle, size, dir);
 }
 
 /**
@@ -1753,16 +1461,12 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 	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 (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 		__dma_page_dev_to_cpu(page, offset, size, dir);
 
-	iommu_unmap(mapping->domain, iova, len);
-	__free_iova(mapping, iova, len);
+	iommu_helper_unmap_page(dev, handle, size, dir);
+
 }
 
 static void arm_iommu_sync_single_for_cpu(struct device *dev,
@@ -1848,24 +1552,6 @@ arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size)
 }
 EXPORT_SYMBOL_GPL(arm_iommu_create_mapping);
 
-static int extend_iommu_mapping(struct dma_iommu_mapping *mapping)
-{
-	int next_bitmap;
-
-	if (mapping->nr_bitmaps > mapping->extensions)
-		return -EINVAL;
-
-	next_bitmap = mapping->nr_bitmaps;
-	mapping->bitmaps[next_bitmap] = kzalloc(mapping->bitmap_size,
-						GFP_ATOMIC);
-	if (!mapping->bitmaps[next_bitmap])
-		return -ENOMEM;
-
-	mapping->nr_bitmaps++;
-
-	return 0;
-}
-
 void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
 {
 	iommu_helper_release_mapping(mapping);
diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h
index 9c4c2ae..2ed8c8e 100644
--- a/include/linux/iommu-helper.h
+++ b/include/linux/iommu-helper.h
@@ -5,6 +5,12 @@
 #include <linux/dma-attrs.h>
 
 #ifdef CONFIG_DMA_USE_IOMMU_HELPER_MAPPING
+#include <linux/mm_types.h>
+#include <linux/dma-debug.h>
+#include <linux/kmemcheck.h>
+#include <linux/kref.h>
+#include <linux/dma-mapping.h>
+
 struct dma_iommu_mapping {
 	/* iommu specific data */
 	struct iommu_domain	*domain;
@@ -20,6 +26,25 @@ struct dma_iommu_mapping {
 	struct kref		kref;
 };
 
+extern dma_addr_t iommu_helper_create_mapping(struct device *dev, struct page **pages,
+					size_t size);
+
+extern int iommu_helper_remove_mapping(struct device *dev, dma_addr_t iova,
+				size_t size);
+
+extern dma_addr_t iommu_helper_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir);
+
+extern void iommu_helper_unmap_page(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir);
+
+extern int iommu_helper_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+		     enum dma_data_direction dir, struct dma_attrs *attrs);
+
+extern void iommu_helper_unmap_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir,
+		struct dma_attrs *attrs);
+
 extern struct page **iommu_helper_alloc_buffer(struct device *dev, size_t size,
 					  gfp_t gfp, struct dma_attrs *attrs,
 			void (*arch_clear_buffer_cb)(struct page*, size_t));
@@ -29,14 +54,13 @@ extern int iommu_helper_free_buffer(struct device *dev, struct page **pages,
 
 extern void iommu_helper_detach_device(struct device *dev);
 
-extern void iommu_helper_release_mapping(struct dma_iommu_mapping *mapping);
-
 extern int iommu_helper_attach_device(struct device *dev,
 			    struct dma_iommu_mapping *mapping);
 
 extern struct dma_iommu_mapping *
 iommu_helper_init_mapping(struct bus_type *bus, dma_addr_t base, size_t size);
 
+extern void iommu_helper_release_mapping(struct dma_iommu_mapping *mapping);
 #define to_dma_iommu_mapping(dev) ((dev)->mapping)
 #else
 #define to_dma_iommu_mapping(dev) NULL
diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c
index 3664709..320d885 100644
--- a/lib/iommu-helper.c
+++ b/lib/iommu-helper.c
@@ -8,13 +8,14 @@
 
 #ifdef CONFIG_DMA_USE_IOMMU_HELPER_MAPPING
 #include <linux/iommu.h>
-#include <linux/device.h>
 #include <linux/iommu-helper.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/errno.h>
 #include <linux/dma-contiguous.h>
 #include <linux/mm.h>
+
+#include <asm/dma-mapping.h>
 #endif
 
 int iommu_is_span_boundary(unsigned int index, unsigned int nr,
@@ -53,6 +54,195 @@ EXPORT_SYMBOL(iommu_area_alloc);
 
 #ifdef CONFIG_DMA_USE_IOMMU_HELPER_MAPPING
 
+/* IOMMU */
+static int extend_iommu_mapping(struct dma_iommu_mapping *mapping)
+{
+	int next_bitmap;
+
+	if (mapping->nr_bitmaps > mapping->extensions)
+		return -EINVAL;
+
+	next_bitmap = mapping->nr_bitmaps;
+	mapping->bitmaps[next_bitmap] = kzalloc(mapping->bitmap_size,
+						GFP_ATOMIC);
+	if (!mapping->bitmaps[next_bitmap])
+		return -ENOMEM;
+
+	mapping->nr_bitmaps++;
+
+	return 0;
+}
+
+static int __dma_direction_to_prot(enum dma_data_direction dir)
+{
+	int prot;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		prot = IOMMU_READ | IOMMU_WRITE;
+		break;
+	case DMA_TO_DEVICE:
+		prot = IOMMU_READ;
+		break;
+	case DMA_FROM_DEVICE:
+		prot = IOMMU_WRITE;
+		break;
+	default:
+		prot = 0;
+	}
+
+	return prot;
+}
+
+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;
+	size_t mapping_size = mapping->bits << PAGE_SHIFT;
+	unsigned long flags;
+	dma_addr_t iova;
+	int i;
+
+	if (order > CONFIG_DMA_IOMMU_ALIGNMENT)
+		order = CONFIG_DMA_IOMMU_ALIGNMENT;
+
+	count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	align = (1 << order) - 1;
+
+	spin_lock_irqsave(&mapping->lock, flags);
+	for (i = 0; i < mapping->nr_bitmaps; i++) {
+		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
+				mapping->bits, 0, count, align);
+
+		if (start > mapping->bits)
+			continue;
+
+		bitmap_set(mapping->bitmaps[i], start, count);
+		break;
+	}
+
+	/*
+	 * No unused range found. Try to extend the existing mapping
+	 * and perform a second attempt to reserve an IO virtual
+	 * address range of size bytes.
+	 */
+	if (i == mapping->nr_bitmaps) {
+		if (extend_iommu_mapping(mapping)) {
+			spin_unlock_irqrestore(&mapping->lock, flags);
+			return DMA_ERROR_CODE;
+		}
+
+		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
+				mapping->bits, 0, count, align);
+
+		if (start > mapping->bits) {
+			spin_unlock_irqrestore(&mapping->lock, flags);
+			return DMA_ERROR_CODE;
+		}
+
+		bitmap_set(mapping->bitmaps[i], start, count);
+	}
+	spin_unlock_irqrestore(&mapping->lock, flags);
+
+	iova = mapping->base + (mapping_size * i);
+	iova += start << PAGE_SHIFT;
+
+	return iova;
+}
+
+static inline void __free_iova(struct dma_iommu_mapping *mapping,
+			       dma_addr_t addr, size_t size)
+{
+	unsigned int start, count;
+	size_t mapping_size = mapping->bits << PAGE_SHIFT;
+	unsigned long flags;
+	dma_addr_t bitmap_base;
+	u32 bitmap_index;
+
+	if (!size)
+		return;
+
+	bitmap_index = (u32) (addr - mapping->base) / (u32) mapping_size;
+	BUG_ON(addr < mapping->base || bitmap_index > mapping->extensions);
+
+	bitmap_base = mapping->base + mapping_size * bitmap_index;
+
+	start = (addr - bitmap_base) >>	PAGE_SHIFT;
+
+	if (addr + size > bitmap_base + mapping_size) {
+		/*
+		 * The address range to be freed reaches into the iova
+		 * range of the next bitmap. This should not happen as
+		 * we don't allow this in __alloc_iova (at the
+		 * moment).
+		 */
+		BUG();
+	} else
+		count = size >> PAGE_SHIFT;
+
+	spin_lock_irqsave(&mapping->lock, flags);
+	bitmap_clear(mapping->bitmaps[bitmap_index], start, count);
+	spin_unlock_irqrestore(&mapping->lock, flags);
+}
+
+/*
+ * Create a mapping in device IO address space for specified pages
+ */
+dma_addr_t
+iommu_helper_create_mapping(struct device *dev, struct page **pages, size_t size)
+{
+	struct dma_iommu_mapping *mapping = dev->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,
+				IOMMU_READ|IOMMU_WRITE);
+		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;
+}
+
+int iommu_helper_remove_mapping(struct device *dev, dma_addr_t iova, size_t size)
+{
+	struct dma_iommu_mapping *mapping = dev->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;
+}
+
 struct page **iommu_helper_alloc_buffer(struct device *dev, size_t size,
 					  gfp_t gfp, struct dma_attrs *attrs,
 			void (*arch_clear_buffer_cb)(struct page*, size_t))
@@ -146,6 +336,143 @@ int iommu_helper_free_buffer(struct device *dev, struct page **pages,
 	return 0;
 }
 
+/*
+ * 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_attrs *attrs)
+{
+	struct dma_iommu_mapping *mapping = dev->mapping;
+	dma_addr_t iova, iova_base;
+	int ret = 0;
+	unsigned int count;
+	struct scatterlist *s;
+	int prot;
+
+	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);
+
+		prot = __dma_direction_to_prot(dir);
+
+		ret = iommu_map(mapping->domain, iova, phys, len, prot);
+		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;
+}
+
+int iommu_helper_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, attrs) < 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, attrs) < 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_helper_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s));
+	return 0;
+}
+
+void iommu_helper_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_helper_remove_mapping(dev, sg_dma_address(s),
+					       sg_dma_len(s));
+}
+}
+
+dma_addr_t iommu_helper_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir)
+{
+	struct dma_iommu_mapping *mapping = dev->mapping;
+	dma_addr_t dma_addr;
+	int ret, prot, len = PAGE_ALIGN(size + offset);
+
+	dma_addr = __alloc_iova(mapping, len);
+	if (dma_addr == DMA_ERROR_CODE)
+		return dma_addr;
+
+	prot = __dma_direction_to_prot(dir);
+
+	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
+	if (ret < 0)
+		goto fail;
+
+	return dma_addr + offset;
+fail:
+	__free_iova(mapping, dma_addr, len);
+	return DMA_ERROR_CODE;
+}
+
+void iommu_helper_unmap_page(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
+{
+	struct dma_iommu_mapping *mapping = dev->mapping;
+	dma_addr_t iova = handle & PAGE_MASK;
+	int offset = handle & ~PAGE_MASK;
+	int len = PAGE_ALIGN(size + offset);
+
+	if (!iova)
+		return;
+
+	iommu_unmap(mapping->domain, iova, len);
+	__free_iova(mapping, iova, len);
+}
+
 /**
  * iommu_helper_init_mapping
  * @bus: pointer to the bus holding the client device (for IOMMU calls)
-- 
1.8.1.3