From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH] KVM: don't sent IPI if the vcpu is not online Date: Mon, 06 Sep 2010 12:14:43 +0300 Message-ID: <4C84B103.7020603@redhat.com> References: <4C807593.1050903@cn.fujitsu.com> <4C83445B.4020103@redhat.com> <4C844887.9090802@cn.fujitsu.com> <4C84801F.9060803@redhat.com> <4C84AC6B.4090306@redhat.com> <633F01D5-D6AD-40F3-8864-C3AE4D314E30@suse.de> <4C84AEF5.2070309@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Xiao Guangrong , Marcelo Tosatti , LKML , KVM To: Alexander Graf Return-path: In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On 09/06/2010 12:09 PM, Alexander Graf wrote: > >> It can also be running host kernel or user code. > In that case it's the same as running guest code, no? We'll pass by the vcpu entry check asap. Sure, but the IPI is wasted. If you spend 10% of your time in host code, you can avoid 10% of the IPIs. (actually less, since the atomic part of the guest switch has guest_mode enabled) -- error compiling committee.c: too many arguments to function