From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ingo Molnar Subject: Re: [PATCH] enable x2APIC without interrupt remapping under KVM Date: Fri, 10 Jul 2009 15:56:18 +0200 Message-ID: <20090710135618.GC26264@elte.hu> References: <20090701133007.GC27539@redhat.com> <1246482017.27006.10670.camel@localhost.localdomain> <20090703082905.GF21833@elte.hu> <20090705143254.GJ881@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Suresh Siddha , "linux-kernel@vger.kernel.org" , Sheng Yang , "kvm@vger.kernel.org" , "avi@redhat.com" To: Gleb Natapov Return-path: Received: from mx3.mail.elte.hu ([157.181.1.138]:52999 "EHLO mx3.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750983AbZGJN4d (ORCPT ); Fri, 10 Jul 2009 09:56:33 -0400 Content-Disposition: inline In-Reply-To: <20090705143254.GJ881@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: * Gleb Natapov wrote: > KVM would like to provide x2APIC interface to a guest without emulating > interrupt remapping device. The reason KVM prefers guest to use x2APIC > is that x2APIC interface is better virtualizable and provides better > performance than mmio xAPIC interface: > > - msr exits are faster than mmio (no page table walk, emulation) > - no need to read back ICR to look at the busy bit > - one 64 bit ICR write instead of two 32 bit writes > - shared code with the Hyper-V paravirt interface > > Included patch changes x2APIC enabling logic to enable it even if IR > initialization failed, but kernel runs under KVM and no apic id is > greater than 255 (if there is one spec requires BIOS to move to x2apic > mode before starting an OS). > > Signed-off-by: Gleb Natapov > Acked-by: Suresh Siddha > --- > > This is the same as v5 only rebased on x86 tree (a74d2cea). Looks good. Small detail: please run the patch through scripts/checkpatch.pl and fix the complaints it has - all 3 details it points out seem like valid complaints to me (at a quick glance) that should be fixed. Thanks, Ingo