From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tejun Heo Subject: Re: [PATCH] sata_sil: add Large Block Transfer support Date: Tue, 23 Dec 2008 13:40:28 +0900 Message-ID: <49506BBC.8040600@kernel.org> References: <4945BDED.7050205@shaw.ca> <494F69C4.2060708@kernel.org> <49506AAF.3040400@shaw.ca> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Return-path: Received: from hera.kernel.org ([140.211.167.34]:54908 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754514AbYLWEke (ORCPT ); Mon, 22 Dec 2008 23:40:34 -0500 In-Reply-To: <49506AAF.3040400@shaw.ca> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Robert Hancock Cc: ide , linux-kernel Hello, Robert. Robert Hancock wrote: > Tejun Heo wrote: >> >> ioread/iowrite? > > We know the register's always MMIO on this controller, so it's slightly > more optimal to avoid the conditional in there. Yeah, by a small margin but I think the consensus was to use ioread/write no matter what if it's mapped using iomap. I don't think we guarantee iomapped address == mmio address after all. >> I know it's not specific to this change but does mb() really make >> sense here? I don't think we need any barrier here. > > Not sure. Documentation/memory-barriers.txt seems rather unfortunately > vague on whether MMIO writes are strongly ordered with respect to memory > writes. I seem to recall some debate on this a while ago, did it ever > get resolved? I remember that thread too but don't really any definite conclusion. Eh... I hate barriers lying around without exact explanation. :-( Thanks. -- tejun