From mboxrd@z Thu Jan 1 00:00:00 1970 From: Herbert Xu Subject: Re: RFC: [0/2] Remove netloop by lazy copying in netback Date: Wed, 28 Mar 2007 06:46:40 +1000 Message-ID: <20070327204640.GA30552@gondor.apana.org.au> References: <20070327111151.GA26126@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Keir Fraser Cc: Isaku Yamahata , Xen Development Mailing List List-Id: xen-devel@lists.xenproject.org On Tue, Mar 27, 2007 at 02:50:19PM +0100, Keir Fraser wrote: > > PV-on-otherwise-unmodified-guest). Of course we'd only be introducing a > dependency for a *backend* driver here. Well I'm still hoping to have a zero-copy dom0 => domU path :) > Your thought of using the accessed bit is rather neat. I believe it is > guaranteed that if we test-and-clear a pte, and see A==0, then no TLB can > cache that pte. If so, I think this could be a winner. Yes that assumption is used elsewhere too so it should be fine. I've checked again and the accessed bit is certainly present on ppc as well as ia64. The only I don't know is if it's present on the nested page tables on ia64 but I see no reasons why it wouldn't be. Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt