On Wed, Feb 15, 2023 at 10:03:27AM +0000, Jonathan Cameron wrote: > On Tue, 14 Feb 2023 16:54:02 -0500 > Gregory Price <gregory.price@xxxxxxxxxxxx> wrote: > > > Just clarifying one thing: Even with the patch, KVM blows up. > > Disabling KVM fixes this entirely. I haven't tested without KVM but > > with the patch, i will do that now. > > yup. The patch only fixes TCG so that's expected behavior. > > Fingers crossed on this 'working'. > > I'm open to suggestions on how to work around the problem with KVM > or indeed allow TCG to cache the instructions (right not it has > to fetch and emulate each instruction on it's own). > > I can envision how we might do it for KVM with userspace page fault handling > used to get a fault up to QEMU which can then stitch in a cache > of the underlying memory as a stage 2 translation to the page (a little > bit like how post migration copy works) though I've not prototyped > anything... > Just following up. With the patch applied and KVM turned off, no crash. I've been working with this for a while. We should move the instruction alignment issue into a separate discussion thread.
