[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 11 Nov 2019 16:58:33 +0100
From: Paolo Bonzini <pbonzini@...hat.com>
To: Joao Martins <joao.m.martins@...cle.com>
Cc: kvm@...r.kernel.org, linux-kernel@...r.kernel.org,
Radim Krčmář <rkrcmar@...hat.com>,
Sean Christopherson <sean.j.christopherson@...el.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>,
Liran Alon <liran.alon@...cle.com>,
Jag Raman <jag.raman@...cle.com>
Subject: Re: [PATCH v1 1/3] KVM: VMX: Consider PID.PIR to determine if vCPU
has pending interrupts
On 11/11/19 15:59, Joao Martins wrote:
>> Should we check the bitmap only if SN is false?
^^^^^
Of course it should be skipped if SN is false, as you correctly say below.
>> We have a precondition
>> that if SN is clear then non-empty PIR implies ON=1 (modulo the small
>> window in vmx_vcpu_pi_load of course), so that'd be a bit faster.
> Makes sense;
>
> The bitmap check was really meant for SN=1.
>
> Should SN=0 we would be saving ~22-27 cycles as far as I micro-benchmarked a few
> weeks ago. Now that you suggest it, it would be also good for older platforms too.
Or even newer platforms if they don't use VT-d.
Paolo
Powered by blists - more mailing lists