Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751508AbdFZJoS (ORCPT ); Mon, 26 Jun 2017 05:44:18 -0400 Received: from bombadil.infradead.org ([65.50.211.133]:54193 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751372AbdFZJoM (ORCPT ); Mon, 26 Jun 2017 05:44:12 -0400 Date: Mon, 26 Jun 2017 02:44:10 -0700 From: Christoph Hellwig To: Vladimir Murzin Cc: Christoph Hellwig , linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, linux@armlinux.org.uk, sza@esh.hu, arnd@arndb.de, gregkh@linuxfoundation.org, akpm@linux-foundation.org, alexandre.torgue@st.com, robin.murphy@arm.com, benjamin.gaignard@linaro.org, kbuild-all@01.org, Michal Nazarewicz , Marek Szyprowski , Rob Herring , Mark Rutland Subject: Re: [PATCH v5 4/7] drivers: dma-coherent: Introduce default DMA pool Message-ID: <20170626094410.GC21570@infradead.org> References: <1495621472-9323-1-git-send-email-vladimir.murzin@arm.com> <1495621472-9323-5-git-send-email-vladimir.murzin@arm.com> <20170620134932.GB31496@infradead.org> <94e57caa-e7b9-d740-bca3-89950c10033e@arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <94e57caa-e7b9-d740-bca3-89950c10033e@arm.com> User-Agent: Mutt/1.8.0 (2017-02-23) X-SRS-Rewrite: SMTP reverse-path rewritten from by bombadil.infradead.org. See http://www.infradead.org/rpr.html Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 875 Lines: 14 On Thu, Jun 22, 2017 at 02:18:48PM +0100, Vladimir Murzin wrote: > It is how it has been started [1] - defining memory which is not cacheable > (i.e. suitable for coherent allocations) and building custom allocator on top > of it, like it was done for c6x and blackfin. The annoying thing was that we > needed to advertise such memory via command line parameter plus some "mem=" > adjustment to hide coherent memory from buddy allocator. So it was suggested > to use reserved memory and this makes things look much better, but on the > other hand require changes on dts side to "bind" devices with reserved memory > - default DMA pool removes such drawback. I like the idea in general, I'm just worried about the overlap with the per-device coherent memory, especially when we have slight semantic mismatches like the one about the physical (or rather dma) address earlier.