Re: [PATCH v2 3/5] intel-iommu: integrate DMA CMA

[Marek Szyprowski <m.szyprowski-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>]

Hello,

On 2014-01-14 15:13, Akinobu Mita wrote:
> This adds support for the DMA Contiguous Memory Allocator for intel-iommu.
> This change enables dma_alloc_coherent() to allocate big contiguous
> memory.
>
> It is achieved in the same way as nommu_dma_ops currently does, i.e.
> trying to allocate memory by dma_alloc_from_contiguous() and alloc_pages()
> is used as a fallback.
>
> Cc: Marek Szyprowski <m.szyprowski-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>
> Cc: Konrad Rzeszutek Wilk <konrad.wilk-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
> Cc: David Woodhouse <dwmw2-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
> Cc: Don Dutile <ddutile-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> Cc: Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>
> Cc: Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> Cc: "H. Peter Anvin" <hpa-YMNOUZJC4hwAvxtiuMwx3w@public.gmane.org>
> Cc: Andi Kleen <andi-Vw/NltI1exuRpAAqCnN02g@public.gmane.org>
> Cc: x86-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org
> Cc: iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org
> Signed-off-by: Akinobu Mita <akinobu.mita-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> ---
> No change from the previous version
>
>   drivers/iommu/intel-iommu.c | 32 ++++++++++++++++++++++++--------
>   1 file changed, 24 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index fd426ca..172c2b0 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -3004,7 +3004,7 @@ static void *intel_alloc_coherent(struct device *hwdev, size_t size,
>   				  dma_addr_t *dma_handle, gfp_t flags,
>   				  struct dma_attrs *attrs)
>   {
> -	void *vaddr;
> +	struct page *page = NULL;
>   	int order;
>   
>   	size = PAGE_ALIGN(size);
> @@ -3019,17 +3019,31 @@ static void *intel_alloc_coherent(struct device *hwdev, size_t size,
>   			flags |= GFP_DMA32;
>   	}
>   
> -	vaddr = (void *)__get_free_pages(flags, order);
> -	if (!vaddr)
> +	if (!(flags & GFP_ATOMIC)) {

GFP_ATOMIC is not a flag, so please change the above check to:
            if (flags & __GFP_WAIT)

I will also fix the similar issue in arch/x86/kernel/pci-dma.c

> +		unsigned int count = size >> PAGE_SHIFT;
> +
> +		page = dma_alloc_from_contiguous(hwdev, count, order);
> +		if (page && iommu_no_mapping(hwdev) &&
> +		    page_to_phys(page) + size > hwdev->coherent_dma_mask) {
> +			dma_release_from_contiguous(hwdev, page, count);
> +			page = NULL;
> +		}
> +	}
> +
> +	if (!page)
> +		page = alloc_pages(flags, order);
> +	if (!page)
>   		return NULL;
> -	memset(vaddr, 0, size);
> +	memset(page_address(page), 0, size);
>   
> -	*dma_handle = __intel_map_single(hwdev, virt_to_bus(vaddr), size,
> +	*dma_handle = __intel_map_single(hwdev, page_to_phys(page), size,
>   					 DMA_BIDIRECTIONAL,
>   					 hwdev->coherent_dma_mask);
>   	if (*dma_handle)
> -		return vaddr;
> -	free_pages((unsigned long)vaddr, order);
> +		return page_address(page);
> +	if (!dma_release_from_contiguous(hwdev, page, size >> PAGE_SHIFT))
> +		__free_pages(page, order);
> +
>   	return NULL;
>   }
>   
> @@ -3037,12 +3051,14 @@ static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
>   				dma_addr_t dma_handle, struct dma_attrs *attrs)
>   {
>   	int order;
> +	struct page *page = virt_to_page(vaddr);
>   
>   	size = PAGE_ALIGN(size);
>   	order = get_order(size);
>   
>   	intel_unmap_page(hwdev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
> -	free_pages((unsigned long)vaddr, order);
> +	if (!dma_release_from_contiguous(hwdev, page, size >> PAGE_SHIFT))
> +		__free_pages(page, order);
>   }
>   
>   static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,

Best regards
-- 
Marek Szyprowski, PhD
Samsung R&D Institute Poland