From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marc Zyngier Subject: Re: should KVM or userspace be the one which decides what MIPIDR/affinity values to assign to vcpus? Date: Tue, 09 Jun 2015 15:35:21 +0100 Message-ID: <5576F9A9.6010501@arm.com> References: <5576C559.2000902@arm.com> <5576DBB5.3010100@arm.com> <5576F177.3090903@arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from localhost (localhost [127.0.0.1]) by mm01.cs.columbia.edu (Postfix) with ESMTP id 5CFD654019 for ; Tue, 9 Jun 2015 10:25:10 -0400 (EDT) Received: from mm01.cs.columbia.edu ([127.0.0.1]) by localhost (mm01.cs.columbia.edu [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id EubSbbA5XSXg for ; Tue, 9 Jun 2015 10:25:09 -0400 (EDT) Received: from foss.arm.com (foss.arm.com [217.140.101.70]) by mm01.cs.columbia.edu (Postfix) with ESMTP id 10B2E54017 for ; Tue, 9 Jun 2015 10:25:08 -0400 (EDT) In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: kvmarm-bounces@lists.cs.columbia.edu Sender: kvmarm-bounces@lists.cs.columbia.edu To: Peter Maydell Cc: Shlomo Pongratz , Shlomo Pongratz , Pavel Fedin , QEMU Developers , Shannon Zhao , Ashok Kumar , Igor Mammedov , "kvmarm@lists.cs.columbia.edu" List-Id: kvmarm@lists.cs.columbia.edu On 09/06/15 15:01, Peter Maydell wrote: > On 9 June 2015 at 15:00, Marc Zyngier wrote: >> >> Yeah, what I had in mind was something along the lines of: >> - kernel computes its "default MPDIR" >> - kernel exposes a new capability "KVM_ARM_ALLOW_MPIDR_OVERRIDE" (or >> something along those lines) >> - userspace does the right thing. > > You forgot the "???" step :-) Indeed. I also missed the step that says "kernel is able to convert arbitrary MPIDR to vcpu_id in an efficient manner...". GICv3 is definitely going to require this. N, -- Jazz is not dead. It just smells funny... From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:40454) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Z2Kcl-0002AL-Su for qemu-devel@nongnu.org; Tue, 09 Jun 2015 10:35:37 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Z2Kch-0004lA-72 for qemu-devel@nongnu.org; Tue, 09 Jun 2015 10:35:31 -0400 Received: from foss.arm.com ([217.140.101.70]:41846) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Z2Kch-0004kQ-1q for qemu-devel@nongnu.org; Tue, 09 Jun 2015 10:35:27 -0400 Message-ID: <5576F9A9.6010501@arm.com> Date: Tue, 09 Jun 2015 15:35:21 +0100 From: Marc Zyngier MIME-Version: 1.0 References: <5576C559.2000902@arm.com> <5576DBB5.3010100@arm.com> <5576F177.3090903@arm.com> In-Reply-To: Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] should KVM or userspace be the one which decides what MIPIDR/affinity values to assign to vcpus? List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Peter Maydell Cc: Shlomo Pongratz , Shlomo Pongratz , Pavel Fedin , QEMU Developers , Shannon Zhao , Ashok Kumar , Igor Mammedov , "kvmarm@lists.cs.columbia.edu" On 09/06/15 15:01, Peter Maydell wrote: > On 9 June 2015 at 15:00, Marc Zyngier wrote: >> >> Yeah, what I had in mind was something along the lines of: >> - kernel computes its "default MPDIR" >> - kernel exposes a new capability "KVM_ARM_ALLOW_MPIDR_OVERRIDE" (or >> something along those lines) >> - userspace does the right thing. > > You forgot the "???" step :-) Indeed. I also missed the step that says "kernel is able to convert arbitrary MPIDR to vcpu_id in an efficient manner...". GICv3 is definitely going to require this. N, -- Jazz is not dead. It just smells funny...