From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gerd Hoffmann Subject: Re: [ANNOUNCE] kvm-43 release Date: Mon, 24 Sep 2007 12:11:52 +0200 Message-ID: <46F78D68.9020409@redhat.com> References: <46F358D2.9000009@qumranet.com> <46F3E1E7.7010602@redhat.com> <46F4B800.20408@qumranet.com> <46F786DF.7020600@redhat.com> <46F7889B.70000@qumranet.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: kvm-devel To: Avi Kivity Return-path: In-Reply-To: <46F7889B.70000-atKUWr5tajBWk0Htik3J/w@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: kvm-devel-bounces-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org Errors-To: kvm-devel-bounces-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org List-Id: kvm.vger.kernel.org >> I *think* it happens because I'm changing guest page tables from outside >> (i.e. host application), and the new intel pgtable optimization bits >> don't expect that (yes, it is a vt box). > > Well, the older implementation doesn't expect that either. You can > disable the optimization with bypass_guest_pf=0, though. Thanks. Using bypass_guest_pf=0 and irqchip_disable() brings things back to -41 level of functionality. kvm not expecting both guest and host app changing pagetables could explain other problems I'm seeing though, so maybe i better fix that. Long term it isn't planned to stay that way anyway, it's just handy for proof-of-concept because userspace is very easy to hack and debug ... thanks, Gerd ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2005. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/