From mboxrd@z Thu Jan 1 00:00:00 1970 From: Benjamin Herrenschmidt Subject: Re: [kvmarm] [RFC PATCH 0/3] KVM: ARM: Get rid of hardcoded VGIC addresses Date: Thu, 18 Oct 2012 08:19:05 +1100 Message-ID: <1350508745.4678.95.camel@pasglop> References: <1350173065-35350-1-git-send-email-c.dall@virtualopensystems.com> <507F172D.2030802@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: Alexander Graf , kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org, kvm-ppc , Paul Mackerras To: Christoffer Dall Return-path: In-Reply-To: Sender: kvm-ppc-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On Wed, 2012-10-17 at 16:39 -0400, Christoffer Dall wrote: > > Have you talked to Ben about this one? He wanted to design a new, more > > flexible irqchip API that would work for XICS & MPIC. Maybe there's some > > room for cooperation here? > > > I have not - Ben, what do you have in mind? I've been sidetracked to some other stuff so for now Paul (CC) is taking over my interrupt patches. We initially changes IRQ_CREATE_IRQCHIP to take an argument but that was causing an x86 ABI breakage (ioctl number changing). So we'll probably be creating a new one. >>From there, nothing fancy really, just an ioctl with an IRQ chip type at the beginning followed by a union of type-specific parameters. The main problem we haven't sorted out yet is how to replace some of the horrors related to mapping interrupts that have tendrils all the way into virtio-pci etc... in kemu that don't apply to use (well mostly) and the interaction with in-kernel generated interrupts to avoid going through qemu for vhost ec... Cheers, Ben.