From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 1/3v2] kvm-s390: Implement the directed yield (diag 9c) hypervisor call for KVM Date: Tue, 24 Apr 2012 19:22:38 +0300 Message-ID: <4F96D34E.4010405@redhat.com> References: <4F96A021.4000704@de.ibm.com> <1335272114-64505-1-git-send-email-borntraeger@de.ibm.com> <4F96A55E.1050703@redhat.com> <4F96CB16.8060700@de.ibm.com> <4F96D1B2.7040901@redhat.com> <4F96D2EF.1070505@de.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: Marcelo Tossati , Carsten Otte , Alexander Graf , Jens Freimann , Cornelia Huck , Heiko Carstens , Martin Schwidefsky , Heinz Graalfs , KVM , Konstantin Weitz To: Christian Borntraeger Return-path: Received: from mx1.redhat.com ([209.132.183.28]:18143 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755840Ab2DXQXF (ORCPT ); Tue, 24 Apr 2012 12:23:05 -0400 In-Reply-To: <4F96D2EF.1070505@de.ibm.com> Sender: kvm-owner@vger.kernel.org List-ID: On 04/24/2012 07:21 PM, Christian Borntraeger wrote: > On 24/04/12 18:15, Avi Kivity wrote: > >>> instead of looking like you're doing the processing for every vcpu. The > >>> loop is just a slow lookup which might some day be replaced by a table > >>> lookup. > >> > >> Ok. We might also have a kvm_vcpu_on_spin_directed in common code, > >> Would you prefer that? > > > > You mean a function that takes a vcpu and tries to yield_to() it? Or > > something else? > > Or a cpu id (number). But yes, something like that. > > I dont know if that will be of use for x86 (e.g. parvirtual > ticketlocks or something like that). > > It looks like kvm_vcpu_on_spin() can use it. -- error compiling committee.c: too many arguments to function