From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH v2 2/6] KVM: MMU: don't drop spte if overwrite it from W to RO Date: Wed, 17 Nov 2010 17:57:40 +0200 Message-ID: <4CE3FB74.8050705@redhat.com> References: <4CE355A0.6020907@cn.fujitsu.com> <4CE355CA.80106@cn.fujitsu.com> <20101117154241.GB18959@amt.cnet> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Xiao Guangrong , LKML , KVM To: Marcelo Tosatti Return-path: In-Reply-To: <20101117154241.GB18959@amt.cnet> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On 11/17/2010 05:42 PM, Marcelo Tosatti wrote: > On Wed, Nov 17, 2010 at 12:10:50PM +0800, Xiao Guangrong wrote: >> We just need flush tlb if overwrite a writable spte with a read-only >> one. >> >> And we should move this operation to set_spte() for sync_page path >> >> Signed-off-by: Xiao Guangrong >> --- >> arch/x86/kvm/mmu.c | 20 +++++++++----------- >> 1 files changed, 9 insertions(+), 11 deletions(-) >> >> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c >> index e008ae7..9bad960 100644 >> --- a/arch/x86/kvm/mmu.c >> +++ b/arch/x86/kvm/mmu.c >> @@ -1966,7 +1966,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, >> gfn_t gfn, pfn_t pfn, bool speculative, >> bool can_unsync, bool reset_host_protection) >> { >> - u64 spte; >> + u64 spte, entry = *sptep; >> int ret = 0; >> >> /* >> @@ -2039,6 +2039,14 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, >> >> set_pte: >> update_spte(sptep, spte); >> + /* >> + * If we overwrite a writable spte with a read-only one we >> + * should flush remote TLBs. Otherwise rmap_write_protect >> + * will find a read-only spte, even though the writable spte >> + * might be cached on a CPU's TLB. >> + */ >> + if (is_writable_pte(entry)&& !is_writable_pte(*sptep)) >> + kvm_flush_remote_tlbs(vcpu->kvm); > There is no need to flush on sync_page path since the guest is > responsible for it. > If we don't, the next rmap_write_protect() will incorrectly decide that there's no need to flush tlbs.