RE: [PATCH v2 7/8] KVM: PMU: support to save/restore the guest lbr stack on vCPU switching

[Gonglei (Arei)]

> -----Original Message-----
> From: Wei Wang [mailto:wei.w.wang@xxxxxxxxx]
> Sent: Tuesday, September 18, 2018 5:58 PM
> To: Andi Kleen <ak@xxxxxxxxxxxxxxx>; Gonglei (Arei) <arei.gonglei@xxxxxxxxxx>
> Cc: linux-kernel@xxxxxxxxxxxxxxx; kvm@xxxxxxxxxxxxxxx; pbonzini@xxxxxxxxxx;
> kan.liang@xxxxxxxxx; peterz@xxxxxxxxxxxxx; mingo@xxxxxxxxxx;
> rkrcmar@xxxxxxxxxx; like.xu@xxxxxxxxx
> Subject: Re: [PATCH v2 7/8] KVM: PMU: support to save/restore the guest lbr
> stack on vCPU switching
> 
> On 09/18/2018 10:56 AM, Andi Kleen wrote:
> >>> From: Like Xu <like.xu@xxxxxxxxx>
> >>>
> >>> This patch adds support to KVM to save/restore the lbr stack on vCPU
> >>> context switching.
> >>>
> >>> When the guest sets the ACTIVE bit of MSR_KVM_PV_LBR_CTRL, a perf
> event
> >>> is created on the host for the related vCPU. This perf event ensures the
> >>> LBR stack to be saved/restored when the vCPU thread is scheduled out/in.
> >>> The perf event is removed and freed when the guest clears the ACTIVE
> >>> bit.
> >>>
> >> What about live migration? Does LBR stack need to be saved on the source
> side and
> >> restored on the dest side with the passthrough mode?
> > Yes it should. Either for call stack LBR, or when it is frozen/disabled.
> >
> > When it's not frozen/disabled and not in call stack LBR mode it likely doesn't
> > hurt either, but it's not strictly needed because it will
> > be replaced so quickly.
> 
> Yes, should be supported. We are working on v3 with the suggested lazy
> save approach, and will send it out shortly.
> 
Nice~ 

Thanks,
-Gonglei