[PATCH v2 2/4] iommu: Implement common IOMMU ops for DMA mapping

[Yong Wu]

On Thu, 2015-06-11 at 16:54 +0100, Robin Murphy wrote:
> Taking inspiration from the existing arch/arm code, break out some
> generic functions to interface the DMA-API to the IOMMU-API. This will
> do the bulk of the heavy lifting for IOMMU-backed dma-mapping.
> 
> Signed-off-by: Robin Murphy <robin.murphy at arm.com>
> ---
>  drivers/iommu/Kconfig     |   7 +
>  drivers/iommu/Makefile    |   1 +
>  drivers/iommu/dma-iommu.c | 560 ++++++++++++++++++++++++++++++++++++++++++++++
>  include/linux/dma-iommu.h |  94 ++++++++
>  4 files changed, 662 insertions(+)
>  create mode 100644 drivers/iommu/dma-iommu.c
>  create mode 100644 include/linux/dma-iommu.h
> 
> diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
> index 1ae4e54..9107b6e 100644
> --- a/drivers/iommu/Kconfig
> +++ b/drivers/iommu/Kconfig
> @@ -48,6 +48,13 @@ config OF_IOMMU
>         def_bool y
>         depends on OF && IOMMU_API
>  
> +# IOMMU-agnostic DMA-mapping layer
> +config IOMMU_DMA
> +	bool
> +	depends on NEED_SG_DMA_LENGTH
> +	select IOMMU_API
> +	select IOMMU_IOVA
> +
>  config FSL_PAMU
>  	bool "Freescale IOMMU support"
>  	depends on PPC32
> diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
> index 080ffab..574b241 100644
> --- a/drivers/iommu/Makefile
> +++ b/drivers/iommu/Makefile
> @@ -1,6 +1,7 @@
>  obj-$(CONFIG_IOMMU_API) += iommu.o
>  obj-$(CONFIG_IOMMU_API) += iommu-traces.o
>  obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o
> +obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o
>  obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o
>  obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
>  obj-$(CONFIG_IOMMU_IOVA) += iova.o
[snip]
> +
> +/**
> + * iommu_dma_alloc - Allocate and map a buffer contiguous in IOVA space
> + * @dev: Device to allocate memory for. Must be a real device
> + *	 attached to an iommu_dma_domain
> + * @size: Size of buffer in bytes
> + * @gfp: Allocation flags
> + * @prot: IOMMU mapping flags
> + * @coherent: Which dma_mask to base IOVA allocation on
> + * @handle: Out argument for allocated DMA handle
> + * @flush_page: Arch callback to flush a single page from caches as
> + *		necessary. May be NULL for coherent allocations
> + *
> + * If @size is less than PAGE_SIZE, then a full CPU page will be allocated,
> + * but an IOMMU which supports smaller pages might not map the whole thing.
> + * For now, the buffer is unconditionally zeroed for compatibility
> + *
> + * Return: Array of struct page pointers describing the buffer,
> + *	   or NULL on failure.
> + */
> +struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
> +		int prot, bool coherent, dma_addr_t *handle,
> +		void (*flush_page)(const void *, phys_addr_t))
> +{
> +	struct iommu_dma_domain *dom = arch_get_dma_domain(dev);
> +	struct iova_domain *iovad = dom->iovad;
> +	struct iova *iova;
> +	struct page **pages;
> +	struct sg_table sgt;
> +	struct sg_mapping_iter miter;
> +	dma_addr_t dma_addr;
> +	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
> +
> +	*handle = DMA_ERROR_CODE;

Hi Robin,

  Compare with the dma before, You delete this line here.
    
          size = PAGE_ALIGN(size);

  Do you expect the user should make sure the size must be aligned?

  so do __iommu_free_attrs.

> +
> +	/* IOMMU can map any pages, so himem can also be used here */
> +	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
> +	pages = __iommu_dma_alloc_pages(count, gfp);
> +	if (!pages)
> +		return NULL;
> +
> +	iova = __alloc_iova(dev, size, coherent);
> +	if (!iova)
> +		goto out_free_pages;
> +
> +	if (sg_alloc_table_from_pages(&sgt, pages, count, 0, size, GFP_KERNEL))
> +		goto out_free_iova;
> +
> +	dma_addr = iova_dma_addr(iovad, iova);
> +	if (iommu_map_sg(dom->domain, dma_addr, sgt.sgl, sgt.orig_nents, prot)
> +			< size)
> +		goto out_free_sg;
> +
> +	/* Using the non-flushing flag since we're doing our own */
> +	sg_miter_start(&miter, sgt.sgl, sgt.orig_nents, SG_MITER_FROM_SG);
> +	while (sg_miter_next(&miter)) {
> +		memset(miter.addr, 0, PAGE_SIZE);
> +		if (flush_page)
> +			flush_page(miter.addr, page_to_phys(miter.page));
> +	}
> +	sg_miter_stop(&miter);
> +	sg_free_table(&sgt);
> +
> +	*handle = dma_addr;
> +	return pages;
> +
> +out_free_sg:
> +	sg_free_table(&sgt);
> +out_free_iova:
> +	__free_iova(iovad, iova);
> +out_free_pages:
> +	__iommu_dma_free_pages(pages, count);
> +	return NULL;
> +}
> +
[...]
> +
> +#endif	/* __KERNEL__ */
> +#endif	/* __DMA_IOMMU_H */