On Tue, Jun 18, 2024 at 08:41:09AM +0900, Shunsuke Mie wrote: > Let's clarify the situation. > > The Virtio device and driver are not working properly due to a > combination of the following reasons: > > 1. Regarding VIRTIO_F_ACCESS_PLATFORM: > - The modern spec includes VIRTIO_F_ACCESS_PLATFORM, which allows > Physical DMAC to be used. > - This feature is not available in the legacy spec. ... because legacy drivers don't set it > 2. Regarding Virtio PCIe Capability: > - The modern spec requires Virtio PCIe Capability. It's a PCI capability actually. People have been asking about option to make it a pcie extended capability, but no one did the spec, qemu and driver work, yet. > - In some environments, Virtio PCIe Capability cannot be provided. why not? > Ideas to solve this problem: > 1. Introduce an ACCESS_PLATFORM-like flag in the legacy spec: > There are some unused bits, but it may be difficult to make changes to > the legacy spec at this stage. seems pointless - if you can not change the driver then it won't negotiate ACCESS_PLATFORM. if you can change the driver then use 1.0 interface, please. > 2. Mani's Idea: > I think it is best to add support for modern virtio PCI device to make > use of IOMMU. Legacy devices can continue to use physical address. > > The meaning of "Legacy devices can continue to use physical address" > is not fully understood. @mani Could you explain more? I don't know how this is different from 3. > 3. Wait until the HW supports the modern spec: > This depends on the chip vendor. Adding ACCESS_PLATFORM hacks would also depend on the chip vendor. > Option 3 is essentially doing nothing, so it would be preferable to > consider other ideas. Why because you have to do something, anything? > Best, > Shunsuke > > 2024年6月14日(金) 18:50 Manivannan Sadhasivam <mani@xxxxxxxxxx>: > > > > 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? > > > > And only in that case, it can expose VIRTIO_F_ACCESS_PLATFORM bit for making > > use of IOMMU translation. > > > > - Mani > > > > -- > > மணிவண்ணன் சதாசிவம்