Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757646AbaDHSSw (ORCPT ); Tue, 8 Apr 2014 14:18:52 -0400 Received: from smtp.citrix.com ([66.165.176.89]:55793 "EHLO SMTP.CITRIX.COM" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754579AbaDHSSv (ORCPT ); Tue, 8 Apr 2014 14:18:51 -0400 X-IronPort-AV: E=Sophos;i="4.97,819,1389744000"; d="scan'208";a="119195990" Message-ID: <53443D88.6010202@citrix.com> Date: Tue, 8 Apr 2014 20:18:48 +0200 From: =?ISO-8859-1?Q?Roger_Pau_Monn=E9?= User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.7; rv:24.0) Gecko/20100101 Thunderbird/24.4.0 MIME-Version: 1.0 To: , , , , , , Subject: Re: [Xen-devel] [XEN PATCH 1/2] hvm: Support more than 32 VCPUS when migrating. References: <1396859560.22845.4.camel@kazak.uk.xensource.com> <1396977950-8789-1-git-send-email-konrad@kernel.org> <1396977950-8789-2-git-send-email-konrad@kernel.org> In-Reply-To: <1396977950-8789-2-git-send-email-konrad@kernel.org> X-Enigmail-Version: 1.6 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit X-DLP: MIA2 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 08/04/14 19:25, konrad@kernel.org wrote: > From: Konrad Rzeszutek Wilk > > When we migrate an HVM guest, by default our shared_info can > only hold up to 32 CPUs. As such the hypercall > VCPUOP_register_vcpu_info was introduced which allowed us to > setup per-page areas for VCPUs. This means we can boot PVHVM > guest with more than 32 VCPUs. During migration the per-cpu > structure is allocated fresh by the hypervisor (vcpu_info_mfn > is set to INVALID_MFN) so that the newly migrated guest > can do make the VCPUOP_register_vcpu_info hypercall. > > Unfortunatly we end up triggering this condition: > /* Run this command on yourself or on other offline VCPUS. */ > if ( (v != current) && !test_bit(_VPF_down, &v->pause_flags) ) > > which means we are unable to setup the per-cpu VCPU structures > for running vCPUS. The Linux PV code paths make this work by > iterating over every vCPU with: > > 1) is target CPU up (VCPUOP_is_up hypercall?) > 2) if yes, then VCPUOP_down to pause it. > 3) VCPUOP_register_vcpu_info > 4) if it was down, then VCPUOP_up to bring it back up > > But since VCPUOP_down, VCPUOP_is_up, and VCPUOP_up are > not allowed on HVM guests we can't do this. This patch > enables this. Hmmm, this looks like a very convoluted approach to something that could be solved more easily IMHO. What we do on FreeBSD is put all vCPUs into suspension, which means that all vCPUs except vCPU#0 will be in the cpususpend_handler, see: http://svnweb.freebsd.org/base/head/sys/amd64/amd64/mp_machdep.c?revision=263878&view=markup#l1460 Then on resume we unblock the "suspended" CPUs, and the first thing they do is call cpu_ops.cpu_resume which is basically going to setup the vcpu_info using VCPUOP_register_vcpu_info. Not sure if something similar is possible under Linux, but it seems easier and doesn't require any Xen-side changes. Roger. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/