From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759780AbYHOOnx (ORCPT ); Fri, 15 Aug 2008 10:43:53 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754389AbYHOOnp (ORCPT ); Fri, 15 Aug 2008 10:43:45 -0400 Received: from mx3.mail.elte.hu ([157.181.1.138]:48854 "EHLO mx3.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753031AbYHOOno (ORCPT ); Fri, 15 Aug 2008 10:43:44 -0400 Date: Fri, 15 Aug 2008 16:43:12 +0200 From: Ingo Molnar To: Arjan van de Ven Cc: Shaohua Li , lkml , airlied@linux.ie, Andrew Morton , Ingo Molnar , Suresh Siddha , "Pallipadi, Venkatesh" , Thomas Gleixner , "H. Peter Anvin" Subject: Re: [patch 2/2] reduce tlb/cache flush times of agpgart memory allocation Message-ID: <20080815144312.GI12954@elte.hu> References: <1217832690.21811.9.camel@sli10-desk.sh.intel.com> <20080815143131.GF12954@elte.hu> <20080815074033.4817f876@infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080815074033.4817f876@infradead.org> User-Agent: Mutt/1.5.18 (2008-05-17) X-ELTE-VirusStatus: clean X-ELTE-SpamScore: 0.0 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=0.0 required=5.9 tests=none autolearn=no SpamAssassin version=3.2.3 _SUMMARY_ Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Arjan van de Ven wrote: > On Fri, 15 Aug 2008 16:31:31 +0200 > Ingo Molnar wrote: > > > > > * Shaohua Li wrote: > > > > > To reduce tlb/cache flush, makes agp memory allocation do one flush > > > after all pages in a region are changed to uc. > > > > > > All agp drivers except agp-sgi uses agp_generic_alloc_page() for > > > .agp_alloc_page, so the patch should work for them. agp-sgi is only > > > for ia64, so not a problem too. > > > > applied to tip/x86/pat - thanks! > > > > I've Cc:-ed more PAT folks - any objections? > > > > it really needs something else instead; it needs airlied's array > allocator otherwise you hit the second wall as well (the pat checks > per page) > > in reality an array version of ioremap (or set_pages_X) is what is > needed ok, agreed. Ingo