From patchwork Mon Nov 30 18:26:10 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiao Guangrong X-Patchwork-Id: 7729081 Return-Path: X-Original-To: patchwork-kvm@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 74C729F1C0 for ; Mon, 30 Nov 2015 18:35:09 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 7CD762058E for ; Mon, 30 Nov 2015 18:35:08 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id BDF6320532 for ; Mon, 30 Nov 2015 18:35:02 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754950AbbK3Seu (ORCPT ); Mon, 30 Nov 2015 13:34:50 -0500 Received: from mga03.intel.com ([134.134.136.65]:23995 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754502AbbK3Sck (ORCPT ); Mon, 30 Nov 2015 13:32:40 -0500 Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by orsmga103.jf.intel.com with ESMTP; 30 Nov 2015 10:32:38 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.20,365,1444719600"; d="scan'208";a="610094041" Received: from xiaoreal1.sh.intel.com (HELO xiaoreal1.sh.intel.com.sh.intel.com) ([10.239.48.79]) by FMSMGA003.fm.intel.com with ESMTP; 30 Nov 2015 10:32:37 -0800 From: Xiao Guangrong To: pbonzini@redhat.com Cc: gleb@kernel.org, mtosatti@redhat.com, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, Xiao Guangrong Subject: [PATCH 08/11] KVM: MMU: use page track for non-leaf shadow pages Date: Tue, 1 Dec 2015 02:26:10 +0800 Message-Id: <1448907973-36066-9-git-send-email-guangrong.xiao@linux.intel.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1448907973-36066-1-git-send-email-guangrong.xiao@linux.intel.com> References: <1448907973-36066-1-git-send-email-guangrong.xiao@linux.intel.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP non-leaf shadow pages are always write protected, it can be the user of page track Signed-off-by: Xiao Guangrong --- arch/x86/include/asm/kvm_page_track.h | 8 +++++ arch/x86/kvm/mmu.c | 26 +++++++++++++--- arch/x86/kvm/page_track.c | 58 +++++++++++++++++++++++------------ 3 files changed, 67 insertions(+), 25 deletions(-) diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 6744234..3447dac 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -41,8 +41,16 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, void kvm_page_track_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); +void +kvm_slot_page_track_add_page_nolock(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn, + enum kvm_page_track_mode mode); void kvm_page_track_add_page(struct kvm *kvm, gfn_t gfn, enum kvm_page_track_mode mode); +void kvm_slot_page_track_remove_page_nolock(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn, + enum kvm_page_track_mode mode); void kvm_page_track_remove_page(struct kvm *kvm, gfn_t gfn, enum kvm_page_track_mode mode); bool kvm_page_track_check_mode(struct kvm_vcpu *vcpu, gfn_t gfn, diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b23f9fc..5a2ca73 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -806,11 +806,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) struct kvm_memory_slot *slot; gfn_t gfn; + kvm->arch.indirect_shadow_pages++; gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); + + /* the non-leaf shadow pages are keeping readonly. */ + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + return kvm_slot_page_track_add_page_nolock(kvm, slot, gfn, + KVM_PAGE_TRACK_WRITE); + kvm_mmu_gfn_disallow_lpage(slot, gfn); - kvm->arch.indirect_shadow_pages++; } static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -819,11 +825,15 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) struct kvm_memory_slot *slot; gfn_t gfn; + kvm->arch.indirect_shadow_pages--; gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + return kvm_slot_page_track_remove_page_nolock(kvm, slot, gfn, + KVM_PAGE_TRACK_WRITE); + kvm_mmu_gfn_allow_lpage(slot, gfn); - kvm->arch.indirect_shadow_pages--; } static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, @@ -2140,12 +2150,18 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, hlist_add_head(&sp->hash_link, &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]); if (!direct) { - if (rmap_write_protect(vcpu, gfn)) + /* + * we should do write protection before syncing pages + * otherwise the content of the synced shadow page may + * be inconsistent with guest page table. + */ + account_shadowed(vcpu->kvm, sp); + + if (level == PT_PAGE_TABLE_LEVEL && + rmap_write_protect(vcpu, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); if (level > PT_PAGE_TABLE_LEVEL && need_sync) kvm_sync_pages(vcpu, gfn); - - account_shadowed(vcpu->kvm, sp); } sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; init_shadow_page_table(sp); diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c index 84420df..87554d3 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/page_track.c @@ -77,6 +77,26 @@ static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn, WARN_ON(val < 0); } +void +kvm_slot_page_track_add_page_nolock(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn, + enum kvm_page_track_mode mode) +{ + WARN_ON(!check_mode(mode)); + + update_gfn_track(slot, gfn, mode, 1); + + /* + * new track stops large page mapping for the + * tracked page. + */ + kvm_mmu_gfn_disallow_lpage(slot, gfn); + + if (mode == KVM_PAGE_TRACK_WRITE) + if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn)) + kvm_flush_remote_tlbs(kvm); +} + /* * add guest page to the tracking pool so that corresponding access on that * page will be intercepted. @@ -101,21 +121,27 @@ void kvm_page_track_add_page(struct kvm *kvm, gfn_t gfn, slot = __gfn_to_memslot(slots, gfn); spin_lock(&kvm->mmu_lock); - update_gfn_track(slot, gfn, mode, 1); - - /* - * new track stops large page mapping for the - * tracked page. - */ - kvm_mmu_gfn_disallow_lpage(slot, gfn); - - if (mode == KVM_PAGE_TRACK_WRITE) - if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn)) - kvm_flush_remote_tlbs(kvm); + kvm_slot_page_track_add_page_nolock(kvm, slot, gfn, mode); spin_unlock(&kvm->mmu_lock); } } +void kvm_slot_page_track_remove_page_nolock(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn, + enum kvm_page_track_mode mode) +{ + WARN_ON(!check_mode(mode)); + + update_gfn_track(slot, gfn, mode, -1); + + /* + * allow large page mapping for the tracked page + * after the tracker is gone. + */ + kvm_mmu_gfn_allow_lpage(slot, gfn); +} + /* * remove the guest page from the tracking pool which stops the interception * of corresponding access on that page. It is the opposed operation of @@ -134,20 +160,12 @@ void kvm_page_track_remove_page(struct kvm *kvm, gfn_t gfn, struct kvm_memory_slot *slot; int i; - WARN_ON(!check_mode(mode)); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); slot = __gfn_to_memslot(slots, gfn); spin_lock(&kvm->mmu_lock); - update_gfn_track(slot, gfn, mode, -1); - - /* - * allow large page mapping for the tracked page - * after the tracker is gone. - */ - kvm_mmu_gfn_allow_lpage(slot, gfn); + kvm_slot_page_track_remove_page_nolock(kvm, slot, gfn, mode); spin_unlock(&kvm->mmu_lock); } }