From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from grove.modra.org (CPE-144-136-172-108.sa.bigpond.net.au [144.136.172.108]) by ozlabs.org (Postfix) with ESMTP id 35B94679E9 for ; Thu, 11 May 2006 11:04:39 +1000 (EST) Date: Thu, 11 May 2006 10:34:38 +0930 From: Alan Modra To: Paul Mackerras Subject: Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables Message-ID: <20060511010438.GE24458@bubble.grove.modra.org> References: <17505.26159.807484.477212@cargo.ozlabs.ibm.com> <20060510154702.GA28938@twiddle.net> <20060510.124003.04457042.davem@davemloft.net> <17506.21908.857189.645889@cargo.ozlabs.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <17506.21908.857189.645889@cargo.ozlabs.ibm.com> Cc: linux-arch@vger.kernel.org, linuxppc-dev@ozlabs.org, rth@twiddle.net, "David S. Miller" , linux-kernel@vger.kernel.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Thu, May 11, 2006 at 07:05:24AM +1000, Paul Mackerras wrote: > No, Richard has a point, it's not the value that is the concern, it's > the address, which gcc could assume is still valid after a barrier. > Drat. That may never happen, at least with a compiler that knows how to optimise away the addi. You're using -mtls-size=16 so all your accesses should look like lwz rn,per_cpu_var@tprel(13) gcc shouldn't think there is any reason to cache the address. -- Alan Modra IBM OzLabs - Linux Technology Centre