From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrea Arcangeli Subject: Re: missing kvm smp tlb flush in invlpg Date: Sun, 15 Mar 2009 17:30:26 +0100 Message-ID: <20090315163026.GI27823@random.random> References: <20090312171843.GU27823@random.random> <49BCDA04.1020602@redhat.com> <20090315161642.GH27823@random.random> <49BD2AAE.1040402@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: kvm@vger.kernel.org, Marcelo Tosatti To: Avi Kivity Return-path: Received: from mx2.redhat.com ([66.187.237.31]:43297 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752746AbZCOQab (ORCPT ); Sun, 15 Mar 2009 12:30:31 -0400 Received: from int-mx2.corp.redhat.com (int-mx2.corp.redhat.com [172.16.27.26]) by mx2.redhat.com (8.13.8/8.13.8) with ESMTP id n2FGUTG6021921 for ; Sun, 15 Mar 2009 12:30:29 -0400 Content-Disposition: inline In-Reply-To: <49BD2AAE.1040402@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On Sun, Mar 15, 2009 at 06:19:58PM +0200, Avi Kivity wrote: > I mentioned this: > >> I think we can fix this without taking the hit of the IPI by >> - running a local invlpg() >> - making need_flush a vm flag instead of a local >> - clearing need_flush whenever remote tlbs are flushed >> - flushing remote tlbs on an mmu_notifier call when need_flush is set Ah so this was a proposed fix for this bug, I thought you were talking about different bugs, and you didn't acknowledge this as a bug sorry! About the need_flush that could become a per-vcpu bit too cleared at every exit so perhaps we'll never have to flush, but it'd need to stay in the vcpu structure to avoid cacheline bouncing.