From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753012AbbHENer (ORCPT ); Wed, 5 Aug 2015 09:34:47 -0400 Received: from mx1.redhat.com ([209.132.183.28]:50963 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752122AbbHENeq (ORCPT ); Wed, 5 Aug 2015 09:34:46 -0400 Date: Wed, 5 Aug 2015 15:34:43 +0200 From: Radim =?utf-8?B?S3LEjW3DocWZ?= To: Paolo Bonzini Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org Subject: Re: [PATCH 3/5] KVM: add KVM_USER_EXIT vm ioctl for userspace exit Message-ID: <20150805133442.GA31952@potion.brq.redhat.com> References: <1438780877-31838-1-git-send-email-rkrcmar@redhat.com> <1438780877-31838-4-git-send-email-rkrcmar@redhat.com> <55C20FD2.8020607@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <55C20FD2.8020607@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 2015-08-05 15:29+0200, Paolo Bonzini: > On 05/08/2015 15:21, Radim Krčmář wrote: >> + kvm_for_each_vcpu(idx, vcpu, kvm) >> + if (vcpu->vcpu_id == vcpu_id) { >> + kvm_make_request(KVM_REQ_EXIT, vcpu); >> + kvm_vcpu_kick(vcpu); >> + >> + return 0; >> + } >> + > > Why not a vcpu ioctl? kvm_for_each_vcpu can become pretty expensive if > you have a few dozen VCPUs. Yeah, it will be slow, the only bright side is low frequency of calls. vcpu ioctl should only be issued by the vcpu thread so it would significantly limit use.