On Fri, Jun 14, 2024 at 03:20:33PM +0530, Manivannan Sadhasivam wrote: > On Mon, May 20, 2024 at 09:22:54AM -0400, Michael S. Tsirkin wrote: > > On Thu, May 16, 2024 at 02:59:13PM +0200, Manivannan Sadhasivam wrote: > > > On Thu, May 16, 2024 at 01:38:40PM +0900, Shunsuke Mie wrote: > > > > Hi virtio folks, > > > > > > > > > > You forgot to CC the actual Virtio folks. I've CCed them now. > > > > > > > I'm writing to discuss finding a workaround with Virtio drivers and legacy > > > > devices with limited memory access. > > > > > > > > # Background > > > > The Virtio specification defines a feature (VIRTIO_F_ACCESS_PLATFORM) to > > > > indicate devices requiring restricted memory access or IOMMU translation. This > > > > feature bit resides at position 33 in the 64-bit Features register on modern > > > > interfaces. When the linux virtio driver finds the flag, the driver uses DMA > > > > API that handles to use of appropriate memory. > > > > > > > > # Problem > > > > However, legacy devices only have a 32-bit register for the features bits. > > > > Consequently, these devices cannot represent the ACCESS_PLATFORM bit. As a > > > > result, legacy devices with restricted memory access cannot function > > > > properly[1]. This is a legacy spec issue, but I'd like to find a workaround. > > > > > > > > # Proposed Solutions > > > > I know these are not ideal, but I propose the following solution. > > > > Driver-side: > > > > - Implement special handling similar to xen_domain. > > > > In xen_domain, linux virtio driver enables to use the DMA API. > > > > - Introduce a CONFIG option to adjust the DMA API behavior. > > > > Device-side: > > > > Due to indistinguishability from the guest's perspective, a device-side > > > > solution might be difficult. > > > > > > > > I'm open to any comments or suggestions you may have on this issue or > > > > alternative approaches. > > > > > > > > [1] virtio-net PCI endpoint function using PCIe Endpoint Framework, > > > > https://lore.kernel.org/lkml/54ee46c3-c845-3df3-8ba0-0ee79a2acab1@xxxxxxxxxx/t/ > > > > The Linux PCIe endpoint framework is used to implement the virtio-net device on > > > > a legacy interface. This is necessary because of the framework and hardware > > > > limitation. > > > > > > > > > > We can fix the endpoint framework limitation, but the problem lies with some > > > platforms where we cannot write to vendor capability registers and still have > > > IOMMU. > > > > > > - Mani > > > > What are vendor capability registers and what do they have to do > > with the IOMMU? > > > > Virtio spec v1.2, sec 4.1.4 says, > > "Each structure can be mapped by a Base Address register (BAR) belonging to the > function, or accessed via the special VIRTIO_PCI_CAP_PCI_CFG field in the PCI > configuration space. > > The location of each structure is specified using a vendor-specific PCI > capability located on the capability list in PCI configuration space of the > device." > > So this means the device has to expose the virtio structures through vendor > specific capability isn't it? The location of the structures within BAR is specified through a vendor specific PCI capability, yes. Why is that a problem? People have been asking for alternative ways to do that, so if you can point out what your issue is specifically, it can be fixable. > And only in that case, it can expose VIRTIO_F_ACCESS_PLATFORM bit for making > use of IOMMU translation. > > - Mani virtio drivers won't even know where to access the features without the capability. > -- > மணிவண்ணன் சதாசிவம்
