On Fri, Dec 8, 2017 at 2:27 PM, Michael S. Tsirkin <m...@redhat.com> wrote: > On Fri, Dec 08, 2017 at 06:08:05AM +0000, Stefan Hajnoczi wrote: >> On Thu, Dec 7, 2017 at 11:54 PM, Michael S. Tsirkin <m...@redhat.com> wrote: >> > On Thu, Dec 07, 2017 at 06:28:19PM +0000, Stefan Hajnoczi wrote: >> >> On Thu, Dec 7, 2017 at 5:38 PM, Michael S. Tsirkin <m...@redhat.com> >> >> wrote: >> >> > On Thu, Dec 07, 2017 at 05:29:14PM +0000, Stefan Hajnoczi wrote: >> >> >> On Thu, Dec 7, 2017 at 4:47 PM, Michael S. Tsirkin <m...@redhat.com> >> >> >> wrote: >> >> >> > On Thu, Dec 07, 2017 at 04:29:45PM +0000, Stefan Hajnoczi wrote: >> >> >> >> On Thu, Dec 7, 2017 at 2:02 PM, Michael S. Tsirkin >> >> >> >> <m...@redhat.com> wrote: >> >> >> >> > On Thu, Dec 07, 2017 at 01:08:04PM +0000, Stefan Hajnoczi wrote: >> >> >> >> > Besides, this means implementing iotlb in both qemu and guest. >> >> >> >> It's free in the guest, the libvhost-user stack already has it. >> > >> > That library is designed to work with a unix domain socket >> > though. We'll need extra kernel code to make a device >> > pretend it's a socket. >> >> A kernel vhost-pci driver isn't necessary because I don't think there >> are in-kernel users. >> >> A vfio vhost-pci backend can go alongside the UNIX domain socket >> backend that exists today in libvhost-user. >> >> If we want to expose kernel vhost devices via vhost-pci then a >> libvhost-user program can translate the vhost-user protocol into >> kernel ioctls. For example: >> $ vhost-pci-proxy --vhost-pci-addr 00:04.0 --vhost-fd 3 3<>/dev/vhost-net >> >> The vhost-pci-proxy implements the vhost-user protocol callbacks and >> submits ioctls on the vhost kernel device fd. I haven't compared the >> kernel ioctl interface vs the vhost-user protocol to see if everything >> maps cleanly though. >> >> Stefan > > I don't really like this, it's yet another package to install, yet > another process to complicate debugging and yet another service that can > go down. > > Maybe vsock can do the trick though?
Not sure what you have in mind. An in-kernel vhost-pci driver is possible too. The neatest integration would be alongside drivers/vhost/vhost.c so that existing net, scsi, vsock vhost drivers can work with vhost-pci. Userspace still needs to configure the devices and associate them with a vhost-pci instance (e.g. which vhost-pci device should be a vhost_scsi target and the SCSI target configuration). But I think this approach is more work than the vhost-pci-proxy program I've described. Stefan
