From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:47969) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UIjaA-00021A-Fw for qemu-devel@nongnu.org; Thu, 21 Mar 2013 13:47:21 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1UIja7-0003vH-Lg for qemu-devel@nongnu.org; Thu, 21 Mar 2013 13:47:18 -0400 Received: from mx1.redhat.com ([209.132.183.28]:15627) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UIja7-0003v2-Cw for qemu-devel@nongnu.org; Thu, 21 Mar 2013 13:47:15 -0400 Date: Thu, 21 Mar 2013 19:42:37 +0200 From: "Michael S. Tsirkin" Message-ID: <20130321174237.GA4060@redhat.com> References: <20130321061838.GA28319@redhat.com> <20130321070357.GD28328@redhat.com> <20130321085107.GE28328@redhat.com> <20130321093946.GG28328@redhat.com> <20130321171115.GA653@obsidianresearch.com> <20130321171525.GE2994@redhat.com> <20130321172150.GA3118@obsidianresearch.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20130321172150.GA3118@obsidianresearch.com> Subject: Re: [Qemu-devel] [PATCH] rdma: don't make pages writeable if not requiested List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Jason Gunthorpe Cc: Roland Dreier , qemu-devel@nongnu.org, "linux-rdma@vger.kernel.org" , Yishai Hadas , LKML , "Michael R. Hines" , Hal Rosenstock , Sean Hefty , Christoph Lameter On Thu, Mar 21, 2013 at 11:21:50AM -0600, Jason Gunthorpe wrote: > On Thu, Mar 21, 2013 at 07:15:25PM +0200, Michael S. Tsirkin wrote: > > > No because application does this: > > init page > > > > ... > > > > after a lot of time > > > > .. > > > > register > > send > > unregister > > > > so it can not be read only. > > mprotect(READONLY) > register > send > unregister > mprotect(WRITABLE) > > ? > With something like GIFT the app already has to give up writing to the > pages while they are moving, so changing the protection seems in line > with that? > > Jason It doesn't actually, and our app would sometimes write to these pages. It simply does not care which version does the remote get in this case since we track writes and resend later. Also this is per-page, MRs have byte granularity so easier to use. -- MST