From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from gate.crashing.org (gate.crashing.org [63.228.1.57]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id AD5F6DDF07 for ; Sun, 22 Jun 2008 02:07:51 +1000 (EST) Message-Id: <81690AB9-9D0A-4CB4-8A0A-B0D8653FECE7@kernel.crashing.org> From: Kumar Gala To: benh@kernel.crashing.org In-Reply-To: <1214004193.8011.184.camel@pasglop> Content-Type: text/plain; charset=US-ASCII; format=flowed; delsp=yes Mime-Version: 1.0 (Apple Message framework v924) Subject: Re: [PATCH][WIP][RFC] powerpc: fixup lwsync at runtime Date: Sat, 21 Jun 2008 11:07:41 -0500 References: <1214004193.8011.184.camel@pasglop> Cc: linuxppc-dev@ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Jun 20, 2008, at 6:23 PM, Benjamin Herrenschmidt wrote: > On Fri, 2008-06-20 at 11:36 -0500, Kumar Gala wrote: >> This is a work in progress towards make lwsync fixed up at >> runtime. The >> patch is based (requires) the module refactoring patch. Some of >> this code >> should be reworked based on the code patching work from Michael. >> Also, >> ppc64 and vdso support needs a bit of cleaning up. >> >> Some questions: >> * How do we determine at runtime if we need to convert sync to >> lwsync. >> This is simliar to cpu_feature but has the issue that cpu_feature >> is about >> either having code in or not. >> >> * Do we simplify the section of fixup information and remove the >> mask and >> value since we don't use them and they double the size of the section > > Remind me why we want to do that ? ie. can't we just use lwsync > unconditionally ? It's supposed to degrade to sync on CPUs that don't > support it, or is that broken on some parts ? I believe its broken on e500v1/v2. However I'll double check. - k