From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [PATCH] [29/82] x86_64: Rename IOMMU option, fix help and mark option embedded. Date: Sun, 25 Jun 2006 21:32:41 +0200 Message-ID: <200606252132.41121.ak@suse.de> References: <449C852C.mailCZT11F9YB@suse.de> <200606251722.23294.ak@suse.de> <20060625190054.GA6570@devserv.devel.redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Return-path: Received: from cantor.suse.de ([195.135.220.2]:10176 "EHLO mx1.suse.de") by vger.kernel.org with ESMTP id S932231AbWFYTjm (ORCPT ); Sun, 25 Jun 2006 15:39:42 -0400 In-Reply-To: <20060625190054.GA6570@devserv.devel.redhat.com> Content-Disposition: inline Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Alan Cox Cc: torvalds@osdl.org, discuss@x86-64.org, akpm@osdl.org, markh@osdl.org, linux-scsi@vger.kernel.org, axboe@suse.de On Sunday 25 June 2006 21:00, Alan Cox wrote: > On Sun, Jun 25, 2006 at 05:22:23PM +0200, Andi Kleen wrote: > > > Older aacraid hardware cannot address the 3-4GB range where the iommu > > > remaps pages. As the PCI DMA implementation for the x86-64 is flawed and > > > doesn't support any nice way to deal with this via swiotlb instead the > > > driver handles it internally. > > > > Then you should just force a low bounce pfn < 0xfffffff for the block device - > > then the block layer should use GFP_DMA bouncing. > > From a tiny 16MB DMA pool that can't sustain the required load ? Or has that > bit changed. It should be ok because it blocks. It will be slow, but what else do you expect from broken hardware like this? -Andi