From: Keir Fraser Subject: Re: [PATCH 06/16] vmx: nest: handling VMX instruction exits Date: Mon, 20 Sep 2010 10:41:40 +0100 Message-ID: References: <1A42CE6F5F474C41B63392A5F80372B22A95FB06@shsmsx501.ccr.corp.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1A42CE6F5F474C41B63392A5F80372B22A95FB06@shsmsx501.ccr.corp.intel.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: "Dong, Eddie" , Christoph Egger , "xen-devel@lists.xensource.com" Cc: Tim Deegan , "He, Qing" List-Id: xen-devel@lists.xenproject.org On 20/09/2010 10:33, "Dong, Eddie" wrote: >> Are you suggesting to always emulate instead of always inject-to-L1? >> That's still not accurate virtualisation of this VMX feature. > > L2 PIO is always exiting to L0. So we wither inject to L1, or emulate it in > L0, base on L1 I/O exiting and bitmap setting. > >> >> Hmm... Are you currently setting up to always vmexit on I/O port >> accesses by L2? Even if you are, that doesn't stop you looking at the > > Yes. > >> virtual I/O bitmap from in your L0 vmexit handler, and doing the > > No, we checked the L1 settings. Right, okay, I think this issue about write-protecting the I/O bitmap and maintaining an accurate shadow bitmap is entirely orthogonal to the issue of emulation versus injection. The former issue is a performance optimisation only afaics, and I wouldn't care about that in a first checkin of nestedhvm. -- Keir