On 09.03.2012, at 19:44, Alexander Golec wrote: > Hi all, > > I'm an undergrad at Columbia, and I'm working on a project for a class to implement virtio on kvm-arm for the Cortex A15. The goal is to get some form of virtio up and running and measure performance as best we can, given that we are looking at running on simulators right now. As someone who's new to the project, I'd appreciate some criticism of my current direction, the better to get on a promising track as soon as possible. > > My current approach is as follows: vanilla virtio uses PCI as its transport mechanism, which poses a problem for PCI-less ARM devices. I've looked at Peter Maydell's changes for using mmio as a transport for virtio, and I've hit on a an obstacle, namely that the code uses the post-39bff object API, which dropped just days after the kvm-a15 branch started. > > Here's what I was thinking: read up on both the new and old API and modify the changes to use the old API. This has the disadvantage of requiring more work should the changes eventually be merged in, but for the purposes of my student project it should suffice. Also, Peter mentioned he wanted to perform a refactor to abstract away the virtio transport, be it PCI or mmio, a concern I will be ignoring. > > Any thoughts or dire warnings? You can also go the easy route and hack yourself a PCI controller in ;) Alex
