For systems with IOMMU it is assumed all DMA translations use the IOMMU. There are, however, cases when IOMMU might map only limited range of the memory or when the cost of setting IOMMU dma mapping is too big. For those cases, this flag can be used to request the DMA-mapping subsystem to bypass the IOMMU if applicable. Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@xxxxxxxxxx> --- Documentation/DMA-attributes.txt | 9 +++++++++ include/linux/dma-attrs.h | 1 + 2 files changed, 10 insertions(+), 0 deletions(-) diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt index 18dc52c..1174afc 100644 --- a/Documentation/DMA-attributes.txt +++ b/Documentation/DMA-attributes.txt @@ -100,3 +100,12 @@ allocated by dma_alloc_attrs() function from individual pages if it can be mapped as contiguous chunk into device dma address space. By specifying this attribute the allocated buffer is forced to be contiguous also in physical memory. + +DMA_ATTR_IOMMU_BYPASS +--------------------- + +For systems with IOMMU it is assumed all DMA translations use the IOMMU. +There are, however, cases when IOMMU might map only limited range of the +memory or when the cost of setting IOMMU dma mapping is too big. For those +cases, this flag can be used to request the DMA-mapping subsystem to bypass +the IOMMU if applicable. diff --git a/include/linux/dma-attrs.h b/include/linux/dma-attrs.h index c8e1831..7c78691 100644 --- a/include/linux/dma-attrs.h +++ b/include/linux/dma-attrs.h @@ -18,6 +18,7 @@ enum dma_attr { DMA_ATTR_NO_KERNEL_MAPPING, DMA_ATTR_SKIP_CPU_SYNC, DMA_ATTR_FORCE_CONTIGUOUS, + DMA_ATTR_IOMMU_BYPASS, DMA_ATTR_MAX, }; -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-arch" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html