From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marcelo Tosatti Subject: Re: [PATCH 4/4 v4] KVM: VMX: VMXON/VMXOFF usage changes. Date: Wed, 12 May 2010 16:58:26 -0300 Message-ID: <20100512195826.GD3308@amt.cnet> References: <20100512004320.GA20553@amt.cnet> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "kvm@vger.kernel.org" , Avi Kivity , Alexander Graf To: "Xu, Dongxiao" Return-path: Received: from mx1.redhat.com ([209.132.183.28]:47165 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751467Ab0ELUFx (ORCPT ); Wed, 12 May 2010 16:05:53 -0400 Content-Disposition: inline In-Reply-To: Sender: kvm-owner@vger.kernel.org List-ID: On Wed, May 12, 2010 at 02:13:26PM +0800, Xu, Dongxiao wrote: > >> - ept_sync_global(); > >> + if (vmm_exclusive) { > >> + kvm_cpu_vmxon(phys_addr); > >> + ept_sync_global(); > >> + } > >> > >> return 0; > > > > The documentation recommends usage of INVEPT all-context after > > execution of VMXON and prior to execution of VMXOFF. Is it not > > necessary? > > After adding the patch, when vCPU is scheduled in a CPU, it will call > tlb_flush() to invalidate the EPT and VPID cache/tlb for the vCPU. > Therefore the correctness for KVM is guaranteed. Correct. Applied all, thanks.