From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753341AbYIJP34 (ORCPT ); Wed, 10 Sep 2008 11:29:56 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752021AbYIJP3s (ORCPT ); Wed, 10 Sep 2008 11:29:48 -0400 Received: from outbound-sin.frontbridge.com ([207.46.51.80]:31014 "EHLO SG2EHSOBE003.bigfish.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752019AbYIJP3s (ORCPT ); Wed, 10 Sep 2008 11:29:48 -0400 X-BigFish: VPS-23(zz1432R98dR1805M936fQ873fnzz10d3izz2f39iz32i6bh43j61h) X-Spam-TCS-SCL: 0:0 X-WSS-ID: 0K6ZKCT-04-HM4-01 Date: Wed, 10 Sep 2008 17:29:18 +0200 From: Joerg Roedel To: FUJITA Tomonori CC: linux-kernel@vger.kernel.org, mingo@elte.hu Subject: Re: [PATCH] x86: avoid unnecessary low zone allocation in AMD IOMMU's alloc_coherent Message-ID: <20080910152918.GD24392@amd.com> References: <20080910232446O.fujita.tomonori@lab.ntt.co.jp> <20080910233819T.fujita.tomonori@lab.ntt.co.jp> <20080910145249.GB24392@amd.com> <20080911000936R.fujita.tomonori@lab.ntt.co.jp> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <20080911000936R.fujita.tomonori@lab.ntt.co.jp> User-Agent: mutt-ng/devel-r804 (Linux) X-OriginalArrivalTime: 10 Sep 2008 15:29:18.0315 (UTC) FILETIME=[FD852BB0:01C91359] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Sep 11, 2008 at 12:09:43AM +0900, FUJITA Tomonori wrote: > On Wed, 10 Sep 2008 16:52:49 +0200 > Joerg Roedel wrote: > > > On Wed, Sep 10, 2008 at 11:39:00PM +0900, FUJITA Tomonori wrote: > > > > > btw, in tip/x86/iommu, GART's alloc_coherent always does virtual > > > mappings to allocate a size-aligned memory (as DMA-mapping.txt > > > defines). > > > > > > Because someone strongly insisted, I modified GART's alloc_coherent to > > > do so but as I said again and again, it's completely meaningless (only > > > POWER IOMMU does it and drivers don't depend on such requirement). > > > > > > I guess that it would be better to do virtual mappings only when > > > necessary as the current mainline does since GART I/O space is > > > precious in some systems. But I don't care much. What's your opinion > > > (as a AMD developer)? > > > > Very true. My original rewrite did the mapping only when necessary too. > > What were the reasons to do the mapping always? > > As I said above, it's for allocating a size-aligned memory. Look at > the description of pci_alloc_consistent in DMA-mapping.txt: > > The cpu return address and the DMA bus master address are both > guaranteed to be aligned to the smallest PAGE_SIZE order which > is greater than or equal to the requested size. This invariant > exists (for example) to guarantee that if you allocate a chunk > which is smaller than or equal to 64 kilobytes, the extent of the > buffer you receive will not cross a 64K boundary. > > You can't do this with __get_free_pages easily (you need some hacks to > do this). You can do this via iommu_area_alloc() for free. What hacks do you need with __get_free_pages? The memory it returns is _always_ aligned at its size. > > Well, actually you agreed with adding such requirement (though I said > again and again that it's totally meaningless...): The other possible way is removing this requirement from the documentation. But if the spec has this requirement the code _has_ to fullfill it, even if its meaningless for most drivers. > http://lkml.org/lkml/2008/7/24/162 This message stated nothing about _always_ map GART alloc_coherent allocations using the aperture. Joerg -- | AMD Saxony Limited Liability Company & Co. KG Operating | Wilschdorfer Landstr. 101, 01109 Dresden, Germany System | Register Court Dresden: HRA 4896 Research | General Partner authorized to represent: Center | AMD Saxony LLC (Wilmington, Delaware, US) | General Manager of AMD Saxony LLC: Dr. Hans-R. Deppe, Thomas McCoy