From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755358AbZG2NOY (ORCPT ); Wed, 29 Jul 2009 09:14:24 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755286AbZG2NOX (ORCPT ); Wed, 29 Jul 2009 09:14:23 -0400 Received: from sg2ehsobe004.messaging.microsoft.com ([207.46.51.78]:44246 "EHLO SG2EHSOBE004.bigfish.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1755014AbZG2NOW (ORCPT ); Wed, 29 Jul 2009 09:14:22 -0400 X-SpamScore: -15 X-BigFish: VPS-15(zz1432R98dNzz1202hzzz32i6bh203h61h) X-Spam-TCS-SCL: 0:0 X-WSS-ID: 0KNJORL-02-1CR-02 X-M-MSG: Date: Wed, 29 Jul 2009 15:13:19 +0200 From: Joerg Roedel To: Avi Kivity CC: Alexander Graf , kvm@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH 08/12] kvm/svm: cache nested intercepts Message-ID: <20090729131319.GF18313@amd.com> References: <1248872192-30881-1-git-send-email-joerg.roedel@amd.com> <1248872192-30881-9-git-send-email-joerg.roedel@amd.com> <4A704AFF.8070702@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <4A704AFF.8070702@redhat.com> Organization: Advanced Micro Devices =?iso-8859-1?Q?GmbH?= =?iso-8859-1?Q?=2C_Karl-Hammerschmidt-Str=2E_34=2C_85609_Dornach_bei_M=FC?= =?iso-8859-1?Q?nchen=2C_Gesch=E4ftsf=FChrer=3A_Thomas_M=2E_McCoy=2C_Giuli?= =?iso-8859-1?Q?ano_Meroni=2C_Sitz=3A_Dornach=2C_Gemeinde_Aschheim=2C_Land?= =?iso-8859-1?Q?kreis_M=FCnchen=2C_Registergericht_M=FCnchen?= =?iso-8859-1?Q?=2C?= HRB Nr. 43632 User-Agent: Mutt/1.5.20 (2009-06-14) X-OriginalArrivalTime: 29 Jul 2009 13:13:19.0891 (UTC) FILETIME=[57BBF630:01CA104E] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Jul 29, 2009 at 04:13:35PM +0300, Avi Kivity wrote: > > I don't see the benefit of this patch. Accessing the cache is just > as expensive as accessing the real vmcb. The benefit is that we don't have to gup and map the nested vmcb just for checking who will take the intercept. Another reason is that with this patch the behavior of nested SVM is more aligned to real hardware. Joerg