Re: [PATCH v7 0/5] VIRTIO-IOMMU probe request support and MSI bypass on ARM

2020-07-03 Thread Peter Maydell
On Mon, 29 Jun 2020 at 08:04, Eric Auger wrote: > > By default the virtio-iommu translates MSI transactions. This > behavior is inherited from ARM SMMU. However the virt machine > code knows where the MSI doorbells are, so we can easily > declare those regions as VIRTIO_IOMMU_RESV_MEM_T_MSI. With

Re: [PATCH v7 0/5] VIRTIO-IOMMU probe request support and MSI bypass on ARM

2020-07-02 Thread Michael S. Tsirkin
On Thu, Jul 02, 2020 at 02:01:46PM +0200, Auger Eric wrote: > Hi Michael, > > On 7/2/20 1:28 PM, Michael S. Tsirkin wrote: > > On Mon, Jun 29, 2020 at 09:03:59AM +0200, Eric Auger wrote: > >> By default the virtio-iommu translates MSI transactions. This > >> behavior is inherited from ARM SMMU. Ho

Re: [PATCH v7 0/5] VIRTIO-IOMMU probe request support and MSI bypass on ARM

2020-07-02 Thread Auger Eric
Hi Michael, On 7/2/20 1:28 PM, Michael S. Tsirkin wrote: > On Mon, Jun 29, 2020 at 09:03:59AM +0200, Eric Auger wrote: >> By default the virtio-iommu translates MSI transactions. This >> behavior is inherited from ARM SMMU. However the virt machine >> code knows where the MSI doorbells are, so we

Re: [PATCH v7 0/5] VIRTIO-IOMMU probe request support and MSI bypass on ARM

2020-07-02 Thread Auger Eric
Hi, On 6/29/20 9:03 AM, Eric Auger wrote: > By default the virtio-iommu translates MSI transactions. This > behavior is inherited from ARM SMMU. However the virt machine > code knows where the MSI doorbells are, so we can easily > declare those regions as VIRTIO_IOMMU_RESV_MEM_T_MSI. With that > s

Re: [PATCH v7 0/5] VIRTIO-IOMMU probe request support and MSI bypass on ARM

2020-07-02 Thread Michael S. Tsirkin
On Mon, Jun 29, 2020 at 09:03:59AM +0200, Eric Auger wrote: > By default the virtio-iommu translates MSI transactions. This > behavior is inherited from ARM SMMU. However the virt machine > code knows where the MSI doorbells are, so we can easily > declare those regions as VIRTIO_IOMMU_RESV_MEM_T_M