From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paolo Bonzini Subject: Re: [PATCH v4] KVM: nVMX: Fully support of nested VMX preemption timer Date: Mon, 16 Sep 2013 11:49:40 +0200 Message-ID: <5236D434.8000605@redhat.com> References: <1378433091-18233-1-git-send-email-yzt356@gmail.com> <5233481F.8060606@redhat.com> <20130916074422.GG17294@redhat.com> <5236C824.8090700@redhat.com> <20130916090911.GL17294@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: Arthur Chunqi Li , kvm@vger.kernel.org, jan.kiszka@web.de, yang.z.zhang@intel.com To: Gleb Natapov Return-path: Received: from mx1.redhat.com ([209.132.183.28]:9339 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755309Ab3IPJte (ORCPT ); Mon, 16 Sep 2013 05:49:34 -0400 In-Reply-To: <20130916090911.GL17294@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: Il 16/09/2013 11:09, Gleb Natapov ha scritto: > On Mon, Sep 16, 2013 at 10:58:12AM +0200, Paolo Bonzini wrote: >>>>> vmx->__launched = vmx->loaded_vmcs->launched; >>>>> + if (is_guest_mode(vcpu) && !(vmx->nested.nested_vmx_exit)) >>>>> + nested_adjust_preemption_timer(vcpu); >>>> >>>> Please leave the assignment to __launched last, since it's already >>>> initializing the asm below. >>>> >>>> I don't like the is_guest_mode check here... Maybe it's >>>> micro-optimizing, but I wonder if we already do too many checks in >>>> vmx_vcpu_run... For example, is_guest_mode could be changed (I think) >>>> to a check for "vmx->loaded_vmcs == &vmx->vmcs1". >>>> >>> Why this will be more efficient that HF_GUEST_MASK check? >> >> Because we have already loaded vmx->loaded_vmcs, so it's one memory >> access less. >> > But we will have to load vmx->vmcs1 instead :) That's not a memory load, it's an add. > Looks like very minor > optimization if at all. If we could avoid additional if() at all > somehow, may be mimicking vcpu->requests in vmx to get rid of most ifs > there. Yes. Paolo