From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Subject: Re: libata+SGIO: is .dma_boundary respected? Date: Tue, 21 Mar 2006 20:42:15 +0100 Message-ID: <20060321194215.GP4285@suse.de> References: <441F8478.50806@rtr.ca> <441F99AC.4000200@pobox.com> <442006BC.8020100@rtr.ca> <20060321184215.GJ4285@suse.de> <442051A0.1050200@rtr.ca> <4420541E.3070303@pobox.com> <44205484.9000702@rtr.ca> <44205525.20306@rtr.ca> <20060321193538.GO4285@suse.de> <44205642.7070302@pobox.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from ns.virtualhost.dk ([195.184.98.160]:54545 "EHLO virtualhost.dk") by vger.kernel.org with ESMTP id S1751170AbWCUTnK (ORCPT ); Tue, 21 Mar 2006 14:43:10 -0500 Content-Disposition: inline In-Reply-To: <44205642.7070302@pobox.com> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Jeff Garzik Cc: Mark Lord , IDE/ATA development list , James Bottomley , Benjamin Herrenschmidt On Tue, Mar 21 2006, Jeff Garzik wrote: > Jens Axboe wrote: > >My explanation was for the block layer part of course, I'm hoping (did > >not check) that the iommu has similar sane defaults. > > Part of the problem is that the iommu doesn't know as much as the block > layer. Right, this is what needs fixing. > >But this still really wants a unification of the dma restrictions... > > Strongly agreed. ISTR JamesB had some concrete thoughts in that > direction, but they never made it beyond an IRC channel and/or a few > emails. The pci dev already holds the dma address, we could add dma boundary and dma segment size as well? -- Jens Axboe