From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754790Ab0CMCGV (ORCPT ); Fri, 12 Mar 2010 21:06:21 -0500 Received: from mga03.intel.com ([143.182.124.21]:29848 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753996Ab0CMCGT (ORCPT ); Fri, 12 Mar 2010 21:06:19 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.49,629,1262592000"; d="scan'208";a="254209269" Subject: Re: [Patch] x86,pat Update the page flags for memtype atomically instead of using memtype_lock. From: Suresh Siddha Reply-To: Suresh Siddha To: Thomas Gleixner Cc: Robin Holt , Ingo Molnar , "H. Peter Anvin" , "Pallipadi, Venkatesh" , Linux Kernel Mailing List , "x86@kernel.org" In-Reply-To: References: <20100311161700.GC5685@sgi.com> <1268439313.2793.148.camel@sbs-t61.sc.intel.com> <1268444762.2793.197.camel@sbs-t61.sc.intel.com> Content-Type: text/plain Organization: Intel Corp Date: Fri, 12 Mar 2010 18:05:23 -0800 Message-Id: <1268445923.2793.206.camel@sbs-t61.sc.intel.com> Mime-Version: 1.0 X-Mailer: Evolution 2.26.3 (2.26.3-1.fc11) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2010-03-12 at 17:52 -0800, Thomas Gleixner wrote: > On Fri, 12 Mar 2010, Suresh Siddha wrote: > > Just wanted to make sure that we address the perf aspect even for non > > RAM pages by converting the memtype_lock into rwlock before some one > > else reports a similar issue for non RAM pages. > > Care to explain why a rwlock is a good solution and which problem is > solved by the conversion of a spinlock to a rwlock ? Thomas, This is the original posting from Robin. http://marc.info/?l=linux-kernel&m=126720623119649&w=2 lookup_memtype() currently takes the memtype spinlock. Changing this to a readlock will allow multiple folks to go through this in parallel. thanks, suresh