On Thu, Jul 29, 2010 at 04:26:55AM -0400, Arnd Bergmann wrote: > On Thursday 29 July 2010 05:35:48 FUJITA Tomonori wrote: > > > > > > From what I have been able to tell, the IOMMU interface was written by > > > AMD/Intel to allow the kvm code to work with a common IOMMU interface. To > > > > Don't confuse the IOMMU interface with the DMA API that Arnd > > mentioned. > > > > They are not related at all. Thats not 100% true. They are not strictly related, but they are related as they may use the same backend kernel drivers to provide their functionality. Both APIs exist for different purposes, of course. > Exactly, thanks for the clarification. I also didn't realize that there > is now an include/linux/iommu.h file that only describes the PCI SR-IOV > interfaces, unlike the generic IOMMU support that we have in your > include/linux/dma-mapping.h file. The IOMMU-API is not about SR-IOV. It is about the capabilities of modern IOMMU hardware that we can not provide to the kernel with the DMA-API such as the ability to choose ourself at which io-virtual address a given cpu physical address should be mapped. Also I wouldn't call the DMA-API an IOMMU interface. The API does not depend on an IOMMU which is an important difference to the IOMMU-API. The IOMMU-API is probably not generic enough to handle all kinds of IOMMUs but its closer to a generic IOMMU-API than the DMA-API. Joerg -- Joerg Roedel - AMD Operating System Research Center Advanced Micro Devices GmbH Einsteinring 24 85609 Dornach General Managers: Alberto Bozzo, Andrew Bowd Registration: Dornach, Landkr. Muenchen; Registerger. Muenchen, HRB Nr. 43632 -- To unsubscribe from this list: send the line "unsubscribe linux-arm-msm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
