Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753426AbYKSKGQ (ORCPT ); Wed, 19 Nov 2008 05:06:16 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752746AbYKSKF7 (ORCPT ); Wed, 19 Nov 2008 05:05:59 -0500 Received: from hera.kernel.org ([140.211.167.34]:49453 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752621AbYKSKF7 (ORCPT ); Wed, 19 Nov 2008 05:05:59 -0500 Message-ID: <4923E4D5.4070202@kernel.org> Date: Wed, 19 Nov 2008 19:05:09 +0900 From: Tejun Heo User-Agent: Thunderbird 2.0.0.17 (X11/20080922) MIME-Version: 1.0 To: Leon Woestenberg CC: FUJITA Tomonori , jens.axboe@oracle.com, akpm@linux-foundation.org, linux-kernel@vger.kernel.org, James.Bottomley@hansenpartnership.com Subject: Re: pci_map_sg() does not coalesce adjacent physical memory? x86 References: <20081119142016E.fujita.tomonori@lab.ntt.co.jp> <20081119155847U.fujita.tomonori@lab.ntt.co.jp> <20081119165915A.fujita.tomonori@lab.ntt.co.jp> In-Reply-To: X-Enigmail-Version: 0.95.7 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.0 (hera.kernel.org [127.0.0.1]); Wed, 19 Nov 2008 10:05:14 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1151 Lines: 33 Leon Woestenberg wrote: > Hello, > > On Wed, Nov 19, 2008 at 8:58 AM, FUJITA Tomonori > wrote: >> On Wed, 19 Nov 2008 15:58:12 +0900 >> FUJITA Tomonori wrote: >>> On Wed, 19 Nov 2008 07:22:31 +0100 >> - pci_map_sg/dma_map_sg are used with a scatter gather list that >> doesn't come from the block layer (e.g. some network drivers do). >> > This is the point I then want to make: we have pci_map_sg() users in > other system than the block layer, the network and v4l2 subsystems, > why cannot they benefit from coalescing? Because pci_map_sg() doesn't know the memory access limits of the controller as block layer does. > Should they copy the block layer coalescing implementation, or should > that implementation be made more generic and live outside the block > sub system? The latter sounds like a good idea to me. Thanks. -- tejun -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/