From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755211AbdLOJOc (ORCPT ); Fri, 15 Dec 2017 04:14:32 -0500 Received: from mail-wm0-f68.google.com ([74.125.82.68]:34414 "EHLO mail-wm0-f68.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755188AbdLOJO2 (ORCPT ); Fri, 15 Dec 2017 04:14:28 -0500 X-Google-Smtp-Source: ACJfBotHUklmh6OBacIIWTda1Q9pshVotuVNY0ilf7tenK1OALDP75m7G9hZeFYG/uHvjyqDiXgLOQ== Subject: Re: [PATCH v5 2/2] KVM: MMU: consider host cache mode in MMIO page check To: Haozhong Zhang , kvm@vger.kernel.org, x86@kernel.org Cc: linux-kernel@vger.kernel.org, rkrcmar@redhat.com, Xiao Guangrong , Dan Williams , ivan.d.cuevas.escareno@intel.com, karthik.kumar@intel.com, Konrad Rzeszutek Wilk , Olif Chapman , Mikulas Patocka , Ingo Molnar References: <20171108075630.16991-1-haozhong.zhang@intel.com> <20171108075630.16991-3-haozhong.zhang@intel.com> From: Paolo Bonzini Message-ID: <443f3841-51fa-4911-854a-7d1645d6d208@redhat.com> Date: Fri, 15 Dec 2017 10:14:24 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.5.0 MIME-Version: 1.0 In-Reply-To: <20171108075630.16991-3-haozhong.zhang@intel.com> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 08/11/2017 08:56, Haozhong Zhang wrote: > Some reserved pages, such as those from NVDIMM DAX devices, are not > for MMIO, and can be mapped with cached memory type for better > performance. However, the above check misconceives those pages as > MMIO. Because KVM maps MMIO pages with UC memory type, the > performance of guest accesses to those pages would be harmed. > Therefore, we check the host memory type in addition and only treat > UC/UC- pages as MMIO. > > Signed-off-by: Haozhong Zhang > Reported-by: Cuevas Escareno, Ivan D > Reported-by: Kumar, Karthik WC should be allowed as well, because the combination of EPT_PAT=UC and gPAT=WC gives WC effective memory type. Maybe it's better after all if the lookup_memtype call remains in kvm_is_mmio_pfn, like if (!pfn_valid(pfn)) return true; if (is_zero_pfn(pfn) || !PageReserved(pfn_to_page(pfn)) return false; /* ... long comment ... */ if (!pat_enabled() return true; else { cm = lookup_memtype(PFN_PHYS(pfn)); return cm == ... } or something like that. Thanks, Paolo > --- > arch/x86/kvm/mmu.c | 15 ++++++++++++++- > 1 file changed, 14 insertions(+), 1 deletion(-) > > diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c > index 0b481cc9c725..7715476bc5c9 100644 > --- a/arch/x86/kvm/mmu.c > +++ b/arch/x86/kvm/mmu.c > @@ -2708,7 +2708,20 @@ static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, > static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) > { > if (pfn_valid(pfn)) > - return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); > + return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) && > + /* > + * Some reserved pages, such as those from > + * NVDIMM DAX devices, are not for MMIO, and > + * can be mapped with cached memory type for > + * better performance. However, the above > + * check misconceives those pages as MMIO. > + * Because KVM maps MMIO pages with UC memory > + * type, the performance of guest accesses to > + * those pages would be harmed. Therefore, we > + * check the host memory type in addition and > + * only treat UC/UC- pages as MMIO. > + */ > + (!pat_enabled() || pat_pfn_is_uc_or_uc_minus(pfn)); > > return true; > } >