From mboxrd@z Thu Jan  1 00:00:00 1970
From: Marcelo Tosatti <mtosatti@redhat.com>
Subject: Re: [PATCH 1/2] nVMX: Add KVM_REQ_IMMEDIATE_EXIT
Date: Mon, 26 Sep 2011 08:02:23 -0300
Message-ID: <20110926110223.GA5169@amt.cnet>
References: <1316688715-nyh@il.ibm.com>
 <201109221052.p8MAquAQ003115@rice.haifa.ibm.com>
 <20110923123633.GA30599@amt.cnet>
 <20110925081306.GA20035@fermat.math.technion.ac.il>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Avi Kivity <avi@redhat.com>, kvm@vger.kernel.org,
	Dave Allan <dallan@redhat.com>,
	Federico Simoncelli <fsimonce@redhat.com>,
	Abel Gordon <abelg@il.ibm.com>
To: "Nadav Har'El" <nyh@math.technion.ac.il>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:35956 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1751305Ab1IZLDK (ORCPT <rfc822;kvm@vger.kernel.org>);
	Mon, 26 Sep 2011 07:03:10 -0400
Content-Disposition: inline
In-Reply-To: <20110925081306.GA20035@fermat.math.technion.ac.il>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On Sun, Sep 25, 2011 at 11:13:06AM +0300, Nadav Har'El wrote:
> On Fri, Sep 23, 2011, Marcelo Tosatti wrote about "Re: [PATCH 1/2] nVMX: Add KVM_REQ_IMMEDIATE_EXIT":
> > On Thu, Sep 22, 2011 at 01:52:56PM +0300, Nadav Har'El wrote:
> > > This patch adds a new vcpu->requests bit, KVM_REQ_IMMEDIATE_EXIT.
> > > This bit requests that when next entering the guest, we should run it only
> > > for as little as possible, and exit again.
> > > 
> > > We use this new option in nested VMX: When L1 launches L2, but L0 wishes L1
> >...
> > > @@ -5647,6 +5648,8 @@ static int vcpu_enter_guest(struct kvm_v
> > >  		}
> > >  		if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
> > >  			record_steal_time(vcpu);
> > > +		req_immediate_exit =
> > > +			kvm_check_request(KVM_REQ_IMMEDIATE_EXIT, vcpu);
> >...
> > The immediate exit information can be lost if entry decides to bail out.
> > You can do 
> > 
> >         req_immediate_exit = kvm_check_request(KVM_REQ_IMMEDIATE_EXIT)
> > after preempt_disable()
> > and then transfer back the bit in the bail out case in
> > if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests
> 
> Thanks.
> 
> But thinking about this a bit, it seems to me that in my case *losing* this
> bit on a canceled entry is the correct thing to do, as turning on this bit was
> decided in the injection phase (in enable_irq_window()), and next time, if
> the reason to turn on this bit still exists (i.e., L0 has something to inject
> to L1, but L2 needs to run), we will turn it on again.

Correct, the loss is irrelevant.