lkml.org 
[lkml]   [2016]   [Mar]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH 1/4] ARM64: dma: Add support for NO_KERNEL_MAPPING attribute
From
Date
On 08/03/16 09:22, Stephen Boyd wrote:
> Both the IOMMU and non-IOMMU allocations don't respect the
> NO_KERNEL_MAPPING attribute, therefore drivers can't save virtual
> address space and time spent mapping large buffers that are
> intended only for userspace. Plumb this attribute into the code
> for both types of DMA ops.

I have to say I'm a little dubious about how much time we save by not
creating one mapping once, and instead going on to repeatedly create and
tear down lots of mappings - my initial hunch would place that number
somewhere below 0. Similarly for the degree of pressure on our hundreds
of gigabytes of vmalloc space, especially on "memory constrained" systems.

Some real data would be a lot more convincing ;)

Robin.

> Cc: Robin Murphy <robin.murphy@arm.com>
> Cc: Laura Abbott <lauraa@codeaurora.org>
> Cc: Arnd Bergmann <arnd@arndb.de>
> Cc: Marek Szyprowski <m.szyprowski@samsung.com>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Signed-off-by: Stephen Boyd <stephen.boyd@linaro.org>
> ---
> arch/arm64/mm/dma-mapping.c | 39 ++++++++++++++++++++++++++++++---------
> 1 file changed, 30 insertions(+), 9 deletions(-)
>
> diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
> index 331c4ca6205c..06a593653f23 100644
> --- a/arch/arm64/mm/dma-mapping.c
> +++ b/arch/arm64/mm/dma-mapping.c
> @@ -169,6 +169,9 @@ static void *__dma_alloc(struct device *dev, size_t size,
>
> /* create a coherent mapping */
> page = virt_to_page(ptr);
> + if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
> + return page;
> +
> coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
> prot, NULL);
> if (!coherent_ptr)
> @@ -194,7 +197,8 @@ static void __dma_free(struct device *dev, size_t size,
> if (!is_device_dma_coherent(dev)) {
> if (__free_from_pool(vaddr, size))
> return;
> - vunmap(vaddr);
> + if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
> + vunmap(vaddr);
> }
> __dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
> }
> @@ -567,6 +571,9 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
> if (!pages)
> return NULL;
>
> + if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
> + return pages;
> +
> addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
> __builtin_return_address(0));
> if (!addr)
> @@ -624,18 +631,32 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
> if (WARN_ON(!area || !area->pages))
> return;
> iommu_dma_free(dev, area->pages, iosize, &handle);
> - dma_common_free_remap(cpu_addr, size, VM_USERMAP);
> + if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
> + dma_common_free_remap(cpu_addr, size, VM_USERMAP);
> } else {
> iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
> __free_pages(virt_to_page(cpu_addr), get_order(size));
> }
> }
>
> +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;
> +
> + area = find_vm_area(cpu_addr);
> + if (area)
> + return area->pages;
> + return NULL;
> +}
> +
> static int __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 vm_struct *area;
> + struct page **pages;
> int ret;
>
> vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
> @@ -644,11 +665,11 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
> if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
> return ret;
>
> - area = find_vm_area(cpu_addr);
> - if (WARN_ON(!area || !area->pages))
> + pages = __iommu_get_pages(cpu_addr, attrs);
> + if (WARN_ON(!pages))
> return -ENXIO;
>
> - return iommu_dma_mmap(area->pages, size, vma);
> + return iommu_dma_mmap(pages, size, vma);
> }
>
> static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
> @@ -656,12 +677,12 @@ static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
> size_t size, struct dma_attrs *attrs)
> {
> unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
> - struct vm_struct *area = find_vm_area(cpu_addr);
> + struct page **pages = __iommu_get_pages(cpu_addr, attrs);
>
> - if (WARN_ON(!area || !area->pages))
> + if (WARN_ON(!pages))
> return -ENXIO;
>
> - return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size,
> + return sg_alloc_table_from_pages(sgt, pages, count, 0, size,
> GFP_KERNEL);
> }
>
>

\
 
 \ /
  Last update: 2016-03-08 15:41    [W:0.155 / U:0.236 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site