From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from wf-out-1314.google.com (wf-out-1314.google.com [209.85.200.172]) by ozlabs.org (Postfix) with ESMTP id E25E4DDDA2 for ; Tue, 31 Mar 2009 19:17:00 +1100 (EST) Received: by wf-out-1314.google.com with SMTP id 24so2736312wfg.15 for ; Tue, 31 Mar 2009 01:16:59 -0700 (PDT) MIME-Version: 1.0 Sender: pku.leo@gmail.com In-Reply-To: <49D0FFBB.7000009@freescale.com> References: <1238089445-28396-1-git-send-email-Joakim.Tjernlund@transmode.se> <2a27d3730903270245k6e8633eehfb5cd3fcebd36240@mail.gmail.com> <49CCD3E8.9040007@freescale.com> <49D0FFBB.7000009@freescale.com> Date: Tue, 31 Mar 2009 16:16:58 +0800 Message-ID: <2a27d3730903310116r4d8602b8y41e466801bbb8d3e@mail.gmail.com> Subject: Re: [PATCH] ucc_geth: Rework the TX logic. From: Li Yang To: Scott Wood Content-Type: text/plain; charset=UTF-8 Cc: linuxppc-dev@ozlabs.org, Joakim Tjernlund , netdev@vger.kernel.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Tue, Mar 31, 2009 at 1:22 AM, Scott Wood wrote= : > Joakim Tjernlund wrote: >> >> gianfar does not seem to use in_/out_ functions for the BDs. Works just >> fine that too it seems. > > It does now that it has explicit barriers in a few places. =C2=A0Before t= hey were > added, it would sometimes fail under load. =C2=A0That was due to a compil= er > reordering, but CPU reordering was possible as well. I noticed that in gianfar these memory access is not protected by "volatile". Can this be the reason why the compiler did some unwanted optimization? - Leo