Hello,
This patch series introduces a new features to DMA mapping subsystem
to let drivers share the allocated buffers (preferably using recently
introduced dma_buf framework) easy and efficient.
The first extension is DMA_ATTR_NO_KERNEL_MAPPING attribute. It is
intended for use with dma_{alloc, mmap, free}_attrs functions. It can be
used to notify dma-mapping core that the driver will not use kernel
mapping for the allocated buffer at all, so the core can skip creating
it. This saves precious kernel virtual address space. Such buffer can be
accessed from userspace, after calling dma_mmap_attrs() for it (a
typical use case for multimedia buffers). The value returned by
dma_alloc_attrs() with this attribute should be considered as a DMA
cookie, which needs to be passed to dma_mmap_attrs() and
dma_free_attrs() funtions.
The second extension is required to let drivers to share the buffers
allocated by DMA-mapping subsystem. Right now the driver gets a dma
address of the allocated buffer and the kernel virtual mapping for it.
If it wants to share it with other device (= map into its dma address
space) it usually hacks around kernel virtual addresses to get pointers
to pages or assumes that both devices share the DMA address space. Both
solutions are just hacks for the special cases, which should be avoided
in the final version of buffer sharing. To solve this issue in a generic
way, a new call to DMA mapping has been introduced - dma_get_sgtable().
It allocates a scatter-list which describes the allocated buffer and
lets the driver(s) to use it with other device(s) by calling
dma_map_sg() on it.
The proposed patches have been generated on top of the ARM DMA-mapping
redesign patch series on Linux v3.4-rc7. They are also available on the
following GIT branch:
git://git.linaro.org/people/mszyprowski/linux-dma-mapping.git 3.4-rc7-arm-dma-v10-ext
with all require patches on top of vanilla v3.4-rc7 kernel.
Best regards
Marek Szyprowski
Samsung Poland R&D Center
Patch summary:
Marek Szyprowski (3):
common: DMA-mapping: add DMA_ATTR_NO_KERNEL_MAPPING attribute
ARM: dma-mapping: add support for DMA_ATTR_NO_KERNEL_MAPPING
attribute
ARM: dma-mapping: add support for dma_get_sgtable()
Documentation/DMA-attributes.txt | 18 +++++++++++++
arch/arm/include/asm/dma-mapping.h | 12 +++++++++
arch/arm/mm/dma-mapping.c | 51 ++++++++++++++++++++++++++++++++----
include/linux/dma-attrs.h | 1 +
include/linux/dma-mapping.h | 3 +++
5 files changed, 80 insertions(+), 5 deletions(-)
--
1.7.10.1
This patch adds dma_get_sgtable() function which is required to let
drivers to share the buffers allocated by DMA-mapping subsystem. Right
now the driver gets a dma address of the allocated buffer and the kernel
virtual mapping for it. If it wants to share it with other device (= map
into its dma address space) it usually hacks around kernel virtual
addresses to get pointers to pages or assumes that both devices share
the DMA address space. Both solutions are just hacks for the special
cases, which should be avoided in the final version of buffer sharing.
To solve this issue in a generic way, a new call to DMA mapping has been
introduced - dma_get_sgtable(). It allocates a scatter-list which
describes the allocated buffer and lets the driver(s) to use it with
other device(s) by calling dma_map_sg() on it.
This patch adds this extension only to ARM architecture, mainly to
demonstrate the buffer sharing. I plan to provide some generic
implementations for other architectures once this idea gets accepted.
Signed-off-by: Marek Szyprowski <[email protected]>
---
arch/arm/include/asm/dma-mapping.h | 12 ++++++++++++
arch/arm/mm/dma-mapping.c | 31 +++++++++++++++++++++++++++++++
include/linux/dma-mapping.h | 3 +++
3 files changed, 46 insertions(+)
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 80777d87..2e37778 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -221,6 +221,15 @@ static inline int dma_mmap_writecombine(struct device *dev, struct vm_area_struc
return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
}
+static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+ 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->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs);
+}
+
/*
* This can be called during boot to increase the size of the consistent
* DMA region above it's default value of 2MB. It must be called before the
@@ -280,6 +289,9 @@ extern void arm_dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
enum dma_data_direction);
extern void arm_dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
enum dma_data_direction);
+extern int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ struct dma_attrs *attrs);
#endif /* __KERNEL__ */
#endif
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 23d0ace..b140440 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -120,6 +120,7 @@ struct dma_map_ops arm_dma_ops = {
.alloc = arm_dma_alloc,
.free = arm_dma_free,
.mmap = arm_dma_mmap,
+ .get_sgtable = arm_dma_get_sgtable,
.map_page = arm_dma_map_page,
.unmap_page = arm_dma_unmap_page,
.map_sg = arm_dma_map_sg,
@@ -529,6 +530,21 @@ void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
__dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size);
}
+int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t handle, size_t size,
+ struct dma_attrs *attrs)
+{
+ struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+ int ret;
+
+ ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+ if (unlikely(ret))
+ return ret;
+
+ sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+ return 0;
+}
+
static void dma_cache_maint_page(struct page *page, unsigned long offset,
size_t size, enum dma_data_direction dir,
void (*op)(const void *, size_t, int))
@@ -1042,6 +1058,20 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
__iommu_free_buffer(dev, pages, size);
}
+static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t dma_addr,
+ size_t size, struct dma_attrs *attrs)
+{
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ struct page **pages = __iommu_get_pages(cpu_addr, attrs);
+
+ if (!pages)
+ return -ENXIO;
+
+ return sg_alloc_table_from_pages(sgt, pages, count, 0, size,
+ GFP_KERNEL);
+}
+
/*
* Map a part of the scatter-gather list into contiguous io address space
*/
@@ -1301,6 +1331,7 @@ struct dma_map_ops iommu_ops = {
.alloc = arm_iommu_alloc_attrs,
.free = arm_iommu_free_attrs,
.mmap = arm_iommu_mmap_attrs,
+ .get_sgtable = arm_iommu_get_sgtable,
.map_page = arm_iommu_map_page,
.unmap_page = arm_iommu_unmap_page,
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index dfc099e..94af418 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -18,6 +18,9 @@ struct dma_map_ops {
int (*mmap)(struct device *, struct vm_area_struct *,
void *, dma_addr_t, size_t, struct dma_attrs *attrs);
+ int (*get_sgtable)(struct device *dev, struct sg_table *sgt, void *,
+ dma_addr_t, size_t, struct dma_attrs *attrs);
+
dma_addr_t (*map_page)(struct device *dev, struct page *page,
unsigned long offset, size_t size,
enum dma_data_direction dir,
--
1.7.10.1
This patch adds DMA_ATTR_NO_KERNEL_MAPPING attribute which lets the
platform to avoid creating a kernel virtual mapping for the allocated
buffer. On some architectures creating such mapping is non-trivial task
and consumes very limited resources (like kernel virtual address space
or dma consistent address space). Buffers allocated with this attribute
can be only passed to user space by calling dma_mmap_attrs().
Signed-off-by: Marek Szyprowski <[email protected]>
---
Documentation/DMA-attributes.txt | 18 ++++++++++++++++++
include/linux/dma-attrs.h | 1 +
2 files changed, 19 insertions(+)
diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
index 5c72eed..725580d 100644
--- a/Documentation/DMA-attributes.txt
+++ b/Documentation/DMA-attributes.txt
@@ -49,3 +49,21 @@ DMA_ATTR_NON_CONSISTENT lets the platform to choose to return either
consistent or non-consistent memory as it sees fit. By using this API,
you are guaranteeing to the platform that you have all the correct and
necessary sync points for this memory in the driver.
+
+DMA_ATTR_NO_KERNEL_MAPPING
+--------------------------
+
+DMA_ATTR_NO_KERNEL_MAPPING lets the platform to avoid creating a kernel
+virtual mapping for the allocated buffer. On some architectures creating
+such mapping is non-trivial task and consumes very limited resources
+(like kernel virtual address space or dma consistent address space).
+Buffers allocated with this attribute can be only passed to user space
+by calling dma_mmap_attrs(). By using this API, you are guaranteeing
+that you won't dereference the pointer returned by dma_alloc_attr(). You
+can threat it as a cookie that must be passed to dma_mmap_attrs() and
+dma_free_attrs(). Make sure that both of these also get this attribute
+set on each call.
+
+Since it is optional for platforms to implement
+DMA_ATTR_NO_KERNEL_MAPPING, those that do not will simply ignore the
+attribute and exhibit default behavior.
diff --git a/include/linux/dma-attrs.h b/include/linux/dma-attrs.h
index 547ab56..a37c10c 100644
--- a/include/linux/dma-attrs.h
+++ b/include/linux/dma-attrs.h
@@ -15,6 +15,7 @@ enum dma_attr {
DMA_ATTR_WEAK_ORDERING,
DMA_ATTR_WRITE_COMBINE,
DMA_ATTR_NON_CONSISTENT,
+ DMA_ATTR_NO_KERNEL_MAPPING,
DMA_ATTR_MAX,
};
--
1.7.10.1
This patch adds support for DMA_ATTR_NO_KERNEL_MAPPING attribute for
IOMMU allocations, what let drivers to save precious kernel virtual
address space for large buffers that are intended to be accessed only
from userspace.
This patch is heavily based on initial work kindly provided by Abhinav
Kochhar <[email protected]>.
Signed-off-by: Marek Szyprowski <[email protected]>
---
arch/arm/mm/dma-mapping.c | 20 +++++++++++++++-----
1 file changed, 15 insertions(+), 5 deletions(-)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 2e98403..23d0ace 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -940,9 +940,13 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si
return 0;
}
-static struct page **__iommu_get_pages(void *cpu_addr)
+static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
{
struct vm_struct *area;
+
+ if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
+ return cpu_addr;
+
read_lock(&vmlist_lock);
area = find_vm_area(cpu_addr);
read_unlock(&vmlist_lock);
@@ -969,6 +973,9 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
if (*handle == DMA_ERROR_CODE)
goto err_buffer;
+ if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
+ return pages;
+
addr = __iommu_alloc_remap(pages, size, gfp, prot,
__builtin_return_address(0));
if (!addr)
@@ -989,7 +996,7 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
{
unsigned long uaddr = vma->vm_start;
unsigned long usize = vma->vm_end - vma->vm_start;
- struct page **pages = __iommu_get_pages(cpu_addr);
+ struct page **pages = __iommu_get_pages(cpu_addr, attrs);
vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
@@ -1016,7 +1023,7 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
dma_addr_t handle, struct dma_attrs *attrs)
{
- struct page **pages = __iommu_get_pages(cpu_addr);
+ struct page **pages = __iommu_get_pages(cpu_addr, attrs);
size = PAGE_ALIGN(size);
if (!pages) {
@@ -1026,8 +1033,11 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
return;
}
- unmap_kernel_range((unsigned long)cpu_addr, size);
- vunmap(cpu_addr);
+ if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
+ unmap_kernel_range((unsigned long)cpu_addr, size);
+ vunmap(cpu_addr);
+ }
+
__iommu_remove_mapping(dev, handle, size);
__iommu_free_buffer(dev, pages, size);
}
--
1.7.10.1