On Tue, 20 Jul 2021 19:44:53 +0100,
Joel Fernandes <joelaf@xxxxxxxxxx> wrote:
>
> On Mon, Jul 12, 2021 at 12:24 PM Marc Zyngier <maz@xxxxxxxxxx> wrote:
> >
> [...]
> > > void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
> > > {
> > > + kvm_update_vcpu_preempted(vcpu, true);
> >
> > This doesn't look right. With this, you are now telling the guest that
> > a vcpu that is blocked on WFI is preempted. This really isn't the
> > case, as it has voluntarily entered a low-power mode while waiting for
> > an interrupt. Indeed, the vcpu isn't running. A physical CPU wouldn't
> > be running either.
>
> Can that be cured by just checking vcpu->preempted before calling
> kvm_update_vcpu_preempted() ?
It isn't obvious to me that this is the right thing to do.
vcpu->preempted is always updated on sched-out from the preempt
notifier if the vcpu was on the run-queue, so my guess is that it will
always be set when switching to another task.
What you probably want is to check whether the vcpu is blocked by
introspecting the wait-queue with:
scuwait_active(kvm_arch_vcpu_get_wait(vcpu)
which will tell you whether you are blocking or not. We are already
using a similar construct for arming a background timer in this case.
M.
--
Without deviation from the norm, progress is not possible.
_______________________________________________
kvmarm mailing list
kvmarm@xxxxxxxxxxxxxxxxxxxxx
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
