From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Garzik Subject: Re: WARNING: at drivers/ata/libata-core.c:5988 ata_qc_issue() Date: Fri, 25 Jan 2008 02:20:20 -0500 Message-ID: <47998DB4.8000207@garzik.org> References: <4798ACCC.3040104@rtr.ca> <4798AE28.4000408@gmail.com> <4798B526.4020709@rtr.ca> <47992115.6050501@gmail.com> <479924B5.5060202@rtr.ca> <479925FF.4060501@gmail.com> <4799270D.3010009@rtr.ca> <4799285F.3060308@gmail.com> <47995EFD.8030102@rtr.ca> <479960DB.8050109@gmail.com> <479965C1.3070009@rtr.ca> <47996738.8030908@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from srv5.dvmed.net ([207.36.208.214]:34777 "EHLO mail.dvmed.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759446AbYAYHUW (ORCPT ); Fri, 25 Jan 2008 02:20:22 -0500 In-Reply-To: <47996738.8030908@gmail.com> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Tejun Heo Cc: Mark Lord , IDE/ATA development list Tejun Heo wrote: > Mark Lord wrote: >> Another one for those beers, is a way to tell the IOMMU code about >> physical segment limitations -- so we can stop having to allocate >> PRD tables 2X as big as necessary in drivers like sata_mv. > > Hmmm... What's the restriction for sata_mv? The same as BMDMA? We need > to update the block layer too to get the BMDMA right. Same as for BMDMA, specifically: after block/etc. merging is done, and things are passed to the IOMMU via dma_map_sg(), the IOMMU may merge -too- aggressively, merging across boundaries (like 64k bmdma boundary) because it is unaware of such restrictions. Jeff