Message-Id: <20220409003847.819686-2-seanjc@google.com>
Date:   Sat,  9 Apr 2022 00:38:42 +0000
From:   Sean Christopherson <seanjc@...gle.com>
To:     Paolo Bonzini <pbonzini@...hat.com>
Cc:     Sean Christopherson <seanjc@...gle.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org, Mingwei Zhang <mizhang@...gle.com>
Subject: [PATCH 1/6] KVM: x86/mmu: Tag disallowed NX huge pages even if
 they're not tracked

Tag shadow pages that cannot be replaced with an NX huge page even if
zapping the page would not allow KVM to create a huge page, e.g. because
something else prevents creating a huge page.  This will allow a future
patch to more precisely apply the mitigation by checking if an existing
shadow page can be replaced by a NX huge page.  Currently, KVM assumes
that any existing shadow page encountered cannot be replaced by a NX huge
page (if the mitigation is enabled), which prevents KVM from replacing
no-longer-necessary shadow pages with huge pages, e.g. after disabling
dirty logging, zapping from the mmu_notifier due to page migration,
etc...

Failure to tag shadow pages appropriately could theoretically lead to
false negatives, e.g. if a fetch fault requests a small page and thus
isn't tracked, and a read/write fault later requests a huge page, KVM
will not reject the huge page as it should.

To avoid yet another flag, initialize the list_head and use list_empty()
to determine whether or not a page is on the list of NX huge pages that
should be recovered.

Opportunstically rename most of the variables/functions involved to
provide consistency, e.g. lpage vs huge page and NX huge vs huge NX, and
clarity, e.g. to make it obvious the flag applies only to the NX huge
page mitigation, not to any condition that prevents creating a huge page.

Fixes: 5bcaf3e1715f ("KVM: x86/mmu: Account NX huge page disallowed iff huge page was requested")
Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
 arch/x86/include/asm/kvm_host.h |  6 +--
 arch/x86/kvm/mmu/mmu.c          | 75 ++++++++++++++++++++++-----------
 arch/x86/kvm/mmu/mmu_internal.h | 22 ++++++++--
 arch/x86/kvm/mmu/paging_tmpl.h  |  6 +--
 arch/x86/kvm/mmu/tdp_mmu.c      |  8 ++--
 5 files changed, 79 insertions(+), 38 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2c20f715f009..e4f7e7998928 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1063,7 +1063,7 @@ struct kvm_arch {
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	struct list_head active_mmu_pages;
 	struct list_head zapped_obsolete_pages;
-	struct list_head lpage_disallowed_mmu_pages;
+	struct list_head possible_nx_huge_pages;
 	struct kvm_page_track_notifier_node mmu_sp_tracker;
 	struct kvm_page_track_notifier_head track_notifier_head;
 	/*
@@ -1219,8 +1219,8 @@ struct kvm_arch {
 	 *  - tdp_mmu_roots (above)
 	 *  - tdp_mmu_pages (above)
 	 *  - the link field of struct kvm_mmu_pages used by the TDP MMU
-	 *  - lpage_disallowed_mmu_pages
-	 *  - the lpage_disallowed_link field of struct kvm_mmu_pages used
+	 *  - possible_nx_huge_pages;
+	 *  - the possible_nx_huge_page_link field of struct kvm_mmu_pages used
 	 *    by the TDP MMU
 	 * It is acceptable, but not necessary, to acquire this lock when
 	 * the thread holds the MMU lock in write mode.
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 69a30d6d1e2b..d230d2d78ace 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -809,15 +809,43 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 }
 
-void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+static void untrack_possible_nx_huge_page(struct kvm *kvm,
+					  struct kvm_mmu_page *sp)
 {
-	if (sp->lpage_disallowed)
+	if (list_empty(&sp->possible_nx_huge_page_link))
+		return;
+
+	--kvm->stat.nx_lpage_splits;
+	list_del_init(&sp->possible_nx_huge_page_link);
+}
+
+void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	sp->nx_huge_page_disallowed = false;
+
+	untrack_possible_nx_huge_page(kvm, sp);
+}
+
+static void track_possible_nx_huge_page(struct kvm *kvm,
+					struct kvm_mmu_page *sp)
+{
+	if (!list_empty(&sp->possible_nx_huge_page_link))
 		return;
 
 	++kvm->stat.nx_lpage_splits;
-	list_add_tail(&sp->lpage_disallowed_link,
-		      &kvm->arch.lpage_disallowed_mmu_pages);
-	sp->lpage_disallowed = true;
+	list_add_tail(&sp->possible_nx_huge_page_link,
+		      &kvm->arch.possible_nx_huge_pages);
+}
+
+void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+			  bool nx_huge_page_possible)
+{
+	sp->nx_huge_page_disallowed = true;
+
+	if (!nx_huge_page_possible)
+		untrack_possible_nx_huge_page(kvm, sp);
+	else
+		track_possible_nx_huge_page(kvm, sp);
 }
 
 static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -837,13 +865,6 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
 
-void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
-{
-	--kvm->stat.nx_lpage_splits;
-	sp->lpage_disallowed = false;
-	list_del(&sp->lpage_disallowed_link);
-}
-
 static struct kvm_memory_slot *
 gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 			    bool no_dirty_log)
@@ -1713,6 +1734,8 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct
 		sp->gfns = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_gfn_array_cache);
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 
+	INIT_LIST_HEAD(&sp->possible_nx_huge_page_link);
+
 	/*
 	 * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
 	 * depends on valid pages being added to the head of the list.  See
@@ -2352,8 +2375,8 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 		zapped_root = !is_obsolete_sp(kvm, sp);
 	}
 
-	if (sp->lpage_disallowed)
-		unaccount_huge_nx_page(kvm, sp);
+	if (sp->nx_huge_page_disallowed)
+		unaccount_nx_huge_page(kvm, sp);
 
 	sp->role.invalid = 1;
 
@@ -2931,9 +2954,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 				      it.level - 1, true, ACC_ALL);
 
 		link_shadow_page(vcpu, it.sptep, sp);
-		if (fault->is_tdp && fault->huge_page_disallowed &&
-		    fault->req_level >= it.level)
-			account_huge_nx_page(vcpu->kvm, sp);
+		if (fault->is_tdp && fault->huge_page_disallowed)
+			account_nx_huge_page(vcpu->kvm, sp,
+					     fault->req_level >= it.level);
 	}
 
 	if (WARN_ON_ONCE(it.level != fault->goal_level))
@@ -5717,7 +5740,7 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
-	INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
+	INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
 	spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
 
 	r = kvm_mmu_init_tdp_mmu(kvm);
@@ -6328,23 +6351,25 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 	ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
 	to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0;
 	for ( ; to_zap; --to_zap) {
-		if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages))
+		if (list_empty(&kvm->arch.possible_nx_huge_pages))
 			break;
 
 		/*
 		 * We use a separate list instead of just using active_mmu_pages
-		 * because the number of lpage_disallowed pages is expected to
-		 * be relatively small compared to the total.
+		 * because the number of shadow pages that can be replaced with
+		 * an NX huge page is expected to be relatively small compared
+		 * to the total number of shadow pages.  And because the TDP MMU
+		 * doesn't use active_mmu_pages.
 		 */
-		sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
+		sp = list_first_entry(&kvm->arch.possible_nx_huge_pages,
 				      struct kvm_mmu_page,
-				      lpage_disallowed_link);
-		WARN_ON_ONCE(!sp->lpage_disallowed);
+				      possible_nx_huge_page_link);
+		WARN_ON_ONCE(!sp->nx_huge_page_disallowed);
 		if (is_tdp_mmu_page(sp)) {
 			flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
 		} else {
 			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
-			WARN_ON_ONCE(sp->lpage_disallowed);
+			WARN_ON_ONCE(sp->nx_huge_page_disallowed);
 		}
 
 		if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 1bff453f7cbe..5c460c727407 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -43,7 +43,13 @@ struct kvm_mmu_page {
 	bool tdp_mmu_page;
 	bool unsync;
 	u8 mmu_valid_gen;
-	bool lpage_disallowed; /* Can't be replaced by an equiv large page */
+
+	 /*
+	  * The shadow page can't be replaced by an equivalent huge page
+	  * because it is being used to map an executable page in the guest
+	  * and the NX huge page mitigation is enabled.
+	  */
+	bool nx_huge_page_disallowed;
 
 	/*
 	 * The following two entries are used to key the shadow page in the
@@ -73,7 +79,14 @@ struct kvm_mmu_page {
 		};
 	};
 
-	struct list_head lpage_disallowed_link;
+	/*
+	 * Use to track shadow pages that, if zapped, would allow KVM to create
+	 * an NX huge page.  A shadow page will have nx_huge_page_disallowed
+	 * set but not be on the list if a huge page is disallowed for other
+	 * reasons, e.g. because KVM is shadowing a PTE at the same gfn, the
+	 * memslot isn't properly aligned, etc...
+	 */
+	struct list_head possible_nx_huge_page_link;
 #ifdef CONFIG_X86_32
 	/*
 	 * Used out of the mmu-lock to avoid reading spte values while an
@@ -168,7 +181,8 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
 
 void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 
-void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
-void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+			  bool nx_huge_page_possible);
+void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp);
 
 #endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 66f1acf153c4..6c4549454a14 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -708,9 +708,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 			sp = kvm_mmu_get_page(vcpu, base_gfn, fault->addr,
 					      it.level - 1, true, direct_access);
 			link_shadow_page(vcpu, it.sptep, sp);
-			if (fault->huge_page_disallowed &&
-			    fault->req_level >= it.level)
-				account_huge_nx_page(vcpu->kvm, sp);
+			if (fault->huge_page_disallowed)
+				account_nx_huge_page(vcpu->kvm, sp,
+						     fault->req_level >= it.level);
 		}
 	}
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 566548a3efa7..7f949d48724b 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -284,6 +284,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu)
 static void tdp_mmu_init_sp(struct kvm_mmu_page *sp, tdp_ptep_t sptep,
 			    gfn_t gfn, union kvm_mmu_page_role role)
 {
+	INIT_LIST_HEAD(&sp->possible_nx_huge_page_link);
+
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 
 	sp->role = role;
@@ -390,8 +392,8 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
 		lockdep_assert_held_write(&kvm->mmu_lock);
 
 	list_del(&sp->link);
-	if (sp->lpage_disallowed)
-		unaccount_huge_nx_page(kvm, sp);
+	if (sp->nx_huge_page_disallowed)
+		unaccount_nx_huge_page(kvm, sp);
 
 	if (shared)
 		spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
@@ -1125,7 +1127,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
 	spin_lock(&kvm->arch.tdp_mmu_pages_lock);
 	list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
 	if (account_nx)
-		account_huge_nx_page(kvm, sp);
+		account_nx_huge_page(kvm, sp, true);
 	spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
 
 	return 0;
-- 
2.35.1.1178.g4f1659d476-goog

Powered by blists - more mailing lists