From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from nommos.sslcatacombnetworking.com (nommos.sslcatacombnetworking.com [67.18.224.114]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTP id 416F9DDF93 for ; Thu, 3 May 2007 06:21:13 +1000 (EST) In-Reply-To: <4638F0C4.2000406@freescale.com> References: <20070502195712.GA16541@ld0162-tx32.am.freescale.net> <4638F0C4.2000406@freescale.com> Mime-Version: 1.0 (Apple Message framework v752.2) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: From: Kumar Gala Subject: Re: [PATCH v2] gianfar: Add I/O barriers when touching buffer descriptor ownership. Date: Wed, 2 May 2007 15:20:25 -0500 To: Scott Wood Cc: netdev@vger.kernel.org, jgarzik@pobox.com, linuxppc-dev@ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On May 2, 2007, at 3:12 PM, Scott Wood wrote: > Kumar Gala wrote: >> I'd rather see a wmb() instead of eieio() to keep this code non- >> ppc specific. (also, we implement wmb as eieio, so I don't keep >> the comment about it being too heavy, unless you mean generically). > > wmb() is a sync, smp_wmb() is an eieio. Andy told me he would not > accept a sync in those spots. Sorry, was looking at the iobarrier code. > And the driver is already ppc-specific; it uses in/out_be32. True, but its hidden behind the gfar_read/write accessors. Your change is a bit more blatant. - k