Re: [PATCH RFC] KVM: x86: emulate wait-for-SIPI and SIPI-VMExit

From: Paolo Bonzini
Date: Thu Sep 17 2020 - 04:56:30 EST

On 17/09/20 04:25, yadong.qi@xxxxxxxxx wrote:
> From: Yadong Qi <yadong.qi@xxxxxxxxx>
> Background: We have a lightweight HV, it needs INIT-VMExit and
> SIPI-VMExit to wake-up APs for guests since it do not monitoring
> the Local APIC. But currently virtual wait-for-SIPI(WFS) state
> is not supported in KVM, so when running on top of KVM, the L1
> HV cannot receive the INIT-VMExit and SIPI-VMExit which cause
> the L2 guest cannot wake up the APs.
> This patch is incomplete, it emulated wait-for-SIPI state by halt
> the vCPU and emulated SIPI-VMExit to L1 when trapped SIPI signal
> from L2. I am posting it RFC to gauge whether or not upstream
> KVM is interested in emulating wait-for-SIPI state before
> investing the time to finish the full support.

Yes, the patch makes sense and is a good addition. What exactly is
missing? (Apart from test cases in kvm-unit-tests!)


> According to Intel SDM Chapter 25.2 Other Causes of VM Exits,
> SIPIs cause VM exits when a logical processor is in
> wait-for-SIPI state.
> In this patch:
> 1. introduce SIPI exit reason,
> 2. introduce wait-for-SIPI state for nVMX,
> 3. advertise wait-for-SIPI support to guest.
> When L1 hypervisor is not monitoring Local APIC, L0 need to emulate
> INIT-VMExit and SIPI-VMExit to L1 to emulate INIT-SIPI-SIPI for
> L2. L2 LAPIC write would be traped by L0 Hypervisor(KVM), L0 should
> emulate the INIT/SIPI vmexit to L1 hypervisor to set proper state
> for L2's vcpu state.