From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 3/4] Nested SVM: Implement INVLPGA v2 Date: Tue, 19 May 2009 16:56:48 +0300 Message-ID: <4A12BAA0.5010401@redhat.com> References: <1242730443-15656-1-git-send-email-agraf@suse.de> <1242730443-15656-2-git-send-email-agraf@suse.de> <1242730443-15656-3-git-send-email-agraf@suse.de> <1242730443-15656-4-git-send-email-agraf@suse.de> <4A12AD0C.9030402@redhat.com> <20090519135416.GA4397@amt.cnet> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Alexander Graf , kvm@vger.kernel.org, joerg.roedel@amd.com To: Marcelo Tosatti Return-path: Received: from mx2.redhat.com ([66.187.237.31]:36425 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750849AbZESN4z (ORCPT ); Tue, 19 May 2009 09:56:55 -0400 In-Reply-To: <20090519135416.GA4397@amt.cnet> Sender: kvm-owner@vger.kernel.org List-ID: Marcelo Tosatti wrote: >> I think that for ASID!=0 you can actually do nothing. The guest entry >> is a cr3 switch, so we'll both get a tlb flush and a resync on any >> modified ptes. >> >> For ASID==0 you can do the invlpg thing. >> >> Marcelo? >> > > kvm_mmu_invlpg is cheap, better just invalidate the entry. If hyper-v > uses invlpga to invalidate TLB entries which it has updated pte's in > memory for, and you skip the invalidation now and somehow later use an > unsync spte, you're toast. > But won't the guest entry cause a resync? Doing nothing is even cheaper. -- error compiling committee.c: too many arguments to function