Re: [PATCH/RFC 0/7] iommu: fixes extensions
On Fri, Sep 02, 2011 at 01:32:29PM -0400, Ohad Ben-Cohen wrote: 5 first patches are relatively small iommu fixes/cleanups. 2 last patches are proposals for core iommu extensions: - Add fault report mechanism, needed for recovery of remote processors trying to access unmapped addresses. - Add splitting of memory regions to pages in the iommu core itself (according to hardware capabilities as advertised by the iommu drivers). This is needed to prevent duplication of this logic by the iommu users/drivers themselves. The patches are based on Joerg's arm/omap branch. Tested with OMAP3 (omap3isp) + OMAP4 (rpmsg/remoteproc). Laurent Pinchart (1): iommu/omap-iovmm: support non page-aligned buffers in iommu_vmap Ohad Ben-Cohen (6): iommu/omap: cleanup: remove a redundant 'return' statement iommu/core: use the existing IS_ALIGNED macro iommu/omap: -unmap() should return order of unmapped page iommu/msm: -unmap() should return order of unmapped page iommu/core: add fault reporting iommu/core: split mapping to page sizes as supported by the hardware Ok, I applied 1-5 to their respective branches. Patch 6 needs some more discussion to make sure the interface is generally usable. Patch 7 seems to be a starting point for now. This definitly requires conversion of the other IOMMU drivers too. Please make individual patch-sets from patch 6 and 7 respectivly. Joerg -- 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-omap in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH/RFC 0/7] iommu: fixes extensions
On Tue, Sep 6, 2011 at 1:15 PM, Roedel, Joerg joerg.roe...@amd.com wrote: Ok, I applied 1-5 to their respective branches. Patch 6 needs some more discussion to make sure the interface is generally usable. Patch 7 seems to be a starting point for now. This definitly requires conversion of the other IOMMU drivers too. Please make individual patch-sets from patch 6 and 7 respectivly. Will do, thanks ! -- To unsubscribe from this list: send the line unsubscribe linux-omap in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH/RFC 0/7] iommu: fixes extensions
5 first patches are relatively small iommu fixes/cleanups. 2 last patches are proposals for core iommu extensions: - Add fault report mechanism, needed for recovery of remote processors trying to access unmapped addresses. - Add splitting of memory regions to pages in the iommu core itself (according to hardware capabilities as advertised by the iommu drivers). This is needed to prevent duplication of this logic by the iommu users/drivers themselves. The patches are based on Joerg's arm/omap branch. Tested with OMAP3 (omap3isp) + OMAP4 (rpmsg/remoteproc). Laurent Pinchart (1): iommu/omap-iovmm: support non page-aligned buffers in iommu_vmap Ohad Ben-Cohen (6): iommu/omap: cleanup: remove a redundant 'return' statement iommu/core: use the existing IS_ALIGNED macro iommu/omap: -unmap() should return order of unmapped page iommu/msm: -unmap() should return order of unmapped page iommu/core: add fault reporting iommu/core: split mapping to page sizes as supported by the hardware arch/arm/plat-omap/include/plat/iommu.h |3 +- drivers/iommu/iommu.c | 142 +++ drivers/iommu/msm_iommu.c | 15 +++- drivers/iommu/omap-iommu.c | 56 +++- drivers/iommu/omap-iovmm.c | 50 +++- drivers/media/video/omap3isp/isp.c |2 +- include/linux/iommu.h | 67 ++- virt/kvm/iommu.c|6 +- 8 files changed, 251 insertions(+), 90 deletions(-) -- 1.7.4.1 -- To unsubscribe from this list: send the line unsubscribe linux-omap in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html