From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from de01egw01.freescale.net (de01egw01.freescale.net [192.88.165.102]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "de01egw01.freescale.net", Issuer "Thawte Premium Server CA" (verified OK)) by ozlabs.org (Postfix) with ESMTP id 385A7DDE0F for ; Wed, 19 Sep 2007 09:21:58 +1000 (EST) Date: Tue, 18 Sep 2007 09:55:03 -0500 From: Scott Wood To: Rune Torgersen Subject: Re: [PATCH 23/28] mpc82xx: Define CPU_FTR_NEED_COHERENT Message-ID: <20070918145503.GG441@ld0162-tx32.am.freescale.net> References: <20070917165643.GA6545@loki.buserror.net> <20070917165815.GW6563@loki.buserror.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: Cc: linuxppc-dev@ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Tue, Sep 18, 2007 at 09:34:31AM -0500, Rune Torgersen wrote: > > -----Original Message----- > > From: Scott Wood > > Sent: Monday, September 17, 2007 11:58 AM > > > > The 8272 (and presumably other PCI PQ2 chips) appear to have the > > same issue as the 83xx regarding PCI streaming DMA. > > > > Can you explain what this isssue is? We're using a 8280 and have had > some PCI busmaster DMA problems, and wonder if it is related. I'm not sure of the details, just that I get corrupted PCI DMA if I don't set it. BTW, if the problems you're seeing include lockups when using PCI DMA, check out the end of the PCI initialization in arch/powerpc/boot/cuboot-pq2.c; it requires certain non-default arbiter settings. -Scott