From: Simon Horman Subject: Re: [rfc 00/18] ioemu: use devfn instead of slots as the unit for passthrough Date: Mon, 2 Mar 2009 20:53:32 +1100 Message-ID: <20090302095329.GA21933@verge.net.au> References: <20090302041432.GA22360@verge.net.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Keir Fraser Cc: Yuji Shimada , "xen-devel@lists.xensource.com" , Ian Jackson List-Id: xen-devel@lists.xenproject.org On Mon, Mar 02, 2009 at 08:44:42AM +0000, Keir Fraser wrote: > On 02/03/2009 04:14, "Simon Horman" wrote: > > >> That was what I had in mind in my original proposal. > >> I'll try coding it up and see what it looks like. > > > > As per the patch below I tried coding this up. > > > > Unfortuantely in my test cases it seems that an rtl8139 ioemu device > > doesn't work unless its given the same girq that the original mapping > > yeilded. I guess this is because the patch below isn't sufficient to wire > > up the girq for the ioemu case. I am investigating why. > > Not really what I had in mind. Xend can do the GSI->slot mapping, to ensure > non-conflicting GSIs. I don't think any hypervisor changes are required, let > alone substantial ones. Is the idea that xend would allocate a gsi to a device and then pass that gsi along as part of the device configuration to the device model? If so, I think something similar to what I wrote, but moved into xend could work quite well. But I sense that wasn't what you had in mind either. -- Simon Horman VA Linux Systems Japan K.K., Sydney, Australia Satellite Office H: www.vergenet.net/~horms/ W: www.valinux.co.jp/en