From owner-svn-src-all@FreeBSD.ORG Tue Apr 21 19:29:54 2009 Return-Path: Delivered-To: svn-src-all@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 9BBC11065673; Tue, 21 Apr 2009 19:29:54 +0000 (UTC) (envelope-from xcllnt@mac.com) Received: from asmtpout019.mac.com (asmtpout019.mac.com [17.148.16.94]) by mx1.freebsd.org (Postfix) with ESMTP id 829CB8FC12; Tue, 21 Apr 2009 19:29:53 +0000 (UTC) (envelope-from xcllnt@mac.com) MIME-version: 1.0 Content-transfer-encoding: 7BIT Content-type: text/plain; charset=US-ASCII; format=flowed; delsp=yes Received: from macbook-pro.jnpr.net ([66.129.224.36]) by asmtp019.mac.com (Sun Java(tm) System Messaging Server 6.3-8.01 (built Dec 16 2008; 32bit)) with ESMTPSA id <0KIG00FZNU5SN370@asmtp019.mac.com>; Tue, 21 Apr 2009 12:29:53 -0700 (PDT) Message-id: <93F1ADEF-9B5D-4855-AB35-91E9687A3512@mac.com> From: Marcel Moolenaar To: Rafal Jaworowski In-reply-to: <2610CF8A-83E5-4CDF-9704-CC1BC1897F7C@semihalf.com> Date: Tue, 21 Apr 2009 12:28:31 -0700 References: <200904211704.n3LH41DN016572@svn.freebsd.org> <2610CF8A-83E5-4CDF-9704-CC1BC1897F7C@semihalf.com> X-Mailer: Apple Mail (2.930.3) Cc: svn-src-head@freebsd.org, svn-src-all@freebsd.org, Marcel Moolenaar , src-committers@freebsd.org Subject: Re: svn commit: r191362 - head/sys/powerpc/booke X-BeenThere: svn-src-all@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: "SVN commit messages for the entire src tree \(except for " user" and " projects" \)" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 21 Apr 2009 19:29:55 -0000 On Apr 21, 2009, at 11:00 AM, Rafal Jaworowski wrote: > On 2009-04-21, at 19:04, Marcel Moolenaar wrote: > >> o Carve out the first 1MB of physical memory. The MPC85xx has >> DMA problems with addresses below 1MB. Ideally busdma knows >> how to avoid allocating below 1MB for MPC85xx, but that >> requires a bit more work. For now, ignore the 1MB of DRAM. > > Could you elaborate a bit on the last item? What is the faulty > scenario, is this a known h/w defect documented somewhere? Not documented and no indication of a failure from PCI/PCI-X or PCI Express host controllers, nor the device doing the DMA and also not from the coherency engine on the MPC85xx. The only noticeable behaviour is a lack of data transfer by virtue of having unchanged memory after DMA write completion. Observed with MPC8544 PCI, MPC8544 PCI Express and MPC8548 PCI Express. FYI, -- Marcel Moolenaar xcllnt@mac.com