From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Jan Beulich" Subject: Re: PCI MSI questions Date: Fri, 08 Aug 2008 11:09:13 +0100 Message-ID: <489C3769.76E4.0078.0@novell.com> References: <4888452A.76E4.0078.0@novell.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: Content-Disposition: inline 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: xen-devel@lists.xensource.com List-Id: xen-devel@lists.xenproject.org >>> Keir Fraser 24.07.08 09:20 >>> >On 24/7/08 08:02, "Jan Beulich" wrote: > >> 1) There currently seems to be a hidden requirement of NR_PIRQS in the >> kernel needing to be no smaller than NR_IRQS in the hypervisor. >> Otherwise, the pirq returned from PHYSDEVOP_map_pirq may collide >> with the dynamic IRQs in the kernel or even be out of range altogether. >> Therefore I think that NR_PIRQS has to become a variable defaulting >> to 256 but getting initialized from a hypervisor reported value = (perhaps >> in start_info, or else from a new (sub-)hypercall). > >Or have the kernel remap the return value of map_pirq into its own PIRQ >namespace, and maintain appropriate translation info? Although, it'd be = nice >to have dynamic NR_IRQS sizing anyway -- people who want to run lots of >domUs currently may have to recompile dom0 with more DYNIRQS. So what route would you prefer to go (so that if I'm able to get to it I wouldn't end up submitting a patch you'd have wanted done the other way around)? Jan