From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 4/4] Enabling Access bit when doing memory swapping Date: Mon, 21 May 2012 14:31:14 +0300 Message-ID: <4FBA2782.6090801@redhat.com> References: <20120516011230.GE14256@hp-xd.sh.intel.com> <20120518022241.GA14096@amt.cnet> <403610A45A2B5242BD291EDAE8B37D300FDC6BEE@SHSMSX102.ccr.corp.intel.com> <4FB9FD68.7000908@redhat.com> <403610A45A2B5242BD291EDAE8B37D300FDC6E99@SHSMSX102.ccr.corp.intel.com> <4FBA1D73.2030600@redhat.com> <403610A45A2B5242BD291EDAE8B37D300FDC6F2E@SHSMSX102.ccr.corp.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: Marcelo Tosatti , Xudong Hao , "kvm@vger.kernel.org" , "linux-kernel@vger.kernel.org" , "Shan, Haitao" , "Zhang, Xiantao" To: "Hao, Xudong" Return-path: In-Reply-To: <403610A45A2B5242BD291EDAE8B37D300FDC6F2E@SHSMSX102.ccr.corp.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On 05/21/2012 02:17 PM, Hao, Xudong wrote: > > -----Original Message----- > > From: Avi Kivity [mailto:avi@redhat.com] > > Sent: Monday, May 21, 2012 6:48 PM > > To: Hao, Xudong > > Cc: Marcelo Tosatti; Xudong Hao; kvm@vger.kernel.org; > > linux-kernel@vger.kernel.org; Shan, Haitao; Zhang, Xiantao > > Subject: Re: [PATCH 4/4] Enabling Access bit when doing memory swapping > > > > On 05/21/2012 01:35 PM, Hao, Xudong wrote: > > > > > > > > That doesn't answer the question. An atomic operation is now > > non-atomic. > > > > > > > > You can calculate shadow_accessed_bit and keep on using clear_bit(), or > > > > switch to cmpxchg64(), but don't just drop the dirty bit here. > > > > > > > > > > I know your meaning. How about this changes: > > > > > > ... > > > young = 1; > > > + if (enable_ept_ad_bits) > > > + clear_bit(ffs(shadow_accessed_mask), (unsigned long > > *)spte); > > > > ffs() returns an off-by-one result, so this needs to be adjusted. > > Yes, it need to decrease 1, I'll send v3 version for patch4, any other comments? I think it's fine. > > IIRC > > bsfl is slow, but this shouldn't be a problem here. > > > > I do not know the story... > No story, bsf is a relatively slow instruction, but it shouldn't affect us here; this isn't a fast path and in any case it's only a few cycles. -- error compiling committee.c: too many arguments to function