From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: [PATCH 3/4] KVM: MMU: Atomically check for accessed bit when dropping an spte Date: Sun, 6 Jun 2010 16:06:22 +0300 Message-ID: <1275829583-7117-4-git-send-email-avi@redhat.com> References: <1275829583-7117-1-git-send-email-avi@redhat.com> Cc: kvm@vger.kernel.org To: Marcelo Tosatti Return-path: Received: from mx1.redhat.com ([209.132.183.28]:19818 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756439Ab0FFNG0 (ORCPT ); Sun, 6 Jun 2010 09:06:26 -0400 Received: from int-mx05.intmail.prod.int.phx2.redhat.com (int-mx05.intmail.prod.int.phx2.redhat.com [10.5.11.18]) by mx1.redhat.com (8.13.8/8.13.8) with ESMTP id o56D6PSL014341 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Sun, 6 Jun 2010 09:06:25 -0400 Received: from cleopatra.tlv.redhat.com (cleopatra.tlv.redhat.com [10.35.255.11]) by int-mx05.intmail.prod.int.phx2.redhat.com (8.13.8/8.13.8) with ESMTP id o56D6O6b024279 for ; Sun, 6 Jun 2010 09:06:25 -0400 In-Reply-To: <1275829583-7117-1-git-send-email-avi@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: Currently, in the window between the check for the accessed bit, and actually dropping the spte, a vcpu can access the page through the spte and set the bit, which will be ignored by the mmu. Fix by using an exchange operation to atmoically fetch the spte and drop it. Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 26 +++++++++++++++++++++----- 1 files changed, 21 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f93948d..b565a14 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -290,6 +290,21 @@ static void __set_spte(u64 *sptep, u64 spte) #endif } +static u64 __xchg_spte(u64 *sptep, u64 new_spte) +{ +#ifdef CONFIG_X86_64 + return xchg(sptep, new_spte); +#else + u64 old_spte; + + do { + old_spte = *sptep; + } while (cmpxchg64(sptep, old_spte, new_spte) != old_spte); + + return old; +#endif +} + static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, struct kmem_cache *base_cache, int min) { @@ -661,16 +676,17 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) static void drop_spte(struct kvm *kvm, u64 *sptep, u64 new_spte) { pfn_t pfn; + u64 old_spte; - if (!is_rmap_spte(*sptep)) + old_spte = __xchg_spte(sptep, new_spte); + if (!is_rmap_spte(old_spte)) return; - pfn = spte_to_pfn(*sptep); - if (*sptep & shadow_accessed_mask) + pfn = spte_to_pfn(old_spte); + if (old_spte & shadow_accessed_mask) kvm_set_pfn_accessed(pfn); - if (is_writable_pte(*sptep)) + if (is_writable_pte(old_spte)) kvm_set_pfn_dirty(pfn); rmap_remove(kvm, sptep); - __set_spte(sptep, new_spte); } static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) -- 1.7.1