Re: [PATCH 0/3] KVM: arm64: Load the stage-2 MMU from vcpu_load() for VHE

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hey Marc,

On Fri, Oct 06, 2023 at 04:03:32PM +0100, Marc Zyngier wrote:
> On Fri, 06 Oct 2023 14:33:04 +0100,
> Marc Zyngier <maz@xxxxxxxxxx> wrote:
> 
> Still talking to myself! :D

Seems like you had a good bit of fun :)

> >
> > However, this isn't enough.
> > 
> > [   63.450113] Oh crap 400000435c001 vs 3000004430001
> > 
> > So there are situations where we end-up with the wrong VTTBR, rather
> > than the wrong VMID, which is even worse. Haven't worked out the
> > scenario yet, but it apparently involves being preempted by a vcpu
> > from a different VM and not doing the right thing.
> 
> Actually, no. It is the MMU notifiers kicking in and performing TLB
> invalidation for a guest while we're in the context of another. The
> joy of running 4 large VMs on a box with 2GB of RAM, basically running
> from swap.

Whelp, looks like my self-rule of no patches on the list after midnight
is in force again. Clearly this was all quite gently tested, thanks for
being the guinea pig.

> There's the sum of my hacks, which keeps the box alive.

Thanks! I'll roll it into v2 so we have something that actually works.

-- 
Thanks,
Oliver



[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux