From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from omx2.sgi.com (omx2-ext.sgi.com [192.48.171.19]) by ozlabs.org (Postfix) with ESMTP id 138CA67A7F for ; Fri, 25 Mar 2005 12:25:06 +1100 (EST) From: Jesse Barnes To: Benjamin Herrenschmidt Date: Thu, 24 Mar 2005 08:55:54 -0800 References: <1111645464.5569.15.camel@gaston> <200503240854.45741.jbarnes@engr.sgi.com> In-Reply-To: <200503240854.45741.jbarnes@engr.sgi.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Message-Id: <200503240855.55154.jbarnes@engr.sgi.com> Cc: Andrew Morton , linuxppc-dev list , Linux Kernel list Subject: Re: [PATCH] ppc32/64: Map prefetchable PCI without guarded bit List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Thursday, March 24, 2005 8:54 am, Jesse Barnes wrote: > On Wednesday, March 23, 2005 10:24 pm, Benjamin Herrenschmidt wrote: > > While experimenting with framebuffer access performances, we noticed a > > very significant improvement in write access to it when not setting > > the "guarded" bit on the MMU mappings. This bit basically says that > > reads and writes won't have side effects (it allows speculation). It > > appears that it also disables write combining. > > Doesn't pgprot_writecombine imply non-guarded, so can't you use it instead? > Either way, you'll probably want to fix fbmem.c as well and turn off > _PAGE_GUARDED? Nevermind about this bit, I just scrolled a little further into your patch :) Jesse