linux-kernel - [PATCH v4 01/18] KVM: x86/mmu: Zap invalid roots with mmu

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20240718211230.1492011-2-rick.p.edgecombe@intel.com>
Date: Thu, 18 Jul 2024 14:12:13 -0700
From: Rick Edgecombe <rick.p.edgecombe@...el.com>
To: seanjc@...gle.com,
	pbonzini@...hat.com,
	kvm@...r.kernel.org
Cc: kai.huang@...el.com,
	dmatlack@...gle.com,
	erdemaktas@...gle.com,
	isaku.yamahata@...il.com,
	linux-kernel@...r.kernel.org,
	sagis@...gle.com,
	yan.y.zhao@...el.com,
	rick.p.edgecombe@...el.com
Subject: [PATCH v4 01/18] KVM: x86/mmu: Zap invalid roots with mmu_lock holding for write at uninit

Add a bool parameter to kvm_tdp_mmu_zap_invalidated_roots() to specify
zapping invalid roots under mmu_lock held for read or write. Hold mmu_lock
for write when kvm_tdp_mmu_zap_invalidated_roots() is called by
kvm_mmu_uninit_tdp_mmu().

kvm_mmu_uninit_tdp_mmu() is invoked either before or after executing any
atomic operations on SPTEs by vCPU threads. Therefore, it will not impact
vCPU threads performance if kvm_tdp_mmu_zap_invalidated_roots() acquires
mmu_lock for write to zap invalid roots.

This is a preparation for future TDX patch which asserts that "Users of
atomic zapping don't operate on mirror roots".

Co-developed-by: Yan Zhao <yan.y.zhao@...el.com>
Signed-off-by: Yan Zhao <yan.y.zhao@...el.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@...el.com>
---
v4:
 - New patch
---
 arch/x86/kvm/mmu/mmu.c     |  2 +-
 arch/x86/kvm/mmu/tdp_mmu.c | 16 +++++++++++-----
 arch/x86/kvm/mmu/tdp_mmu.h |  2 +-
 3 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f6b7391fe438..6f721ab0cd33 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6473,7 +6473,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
 	 * lead to use-after-free.
 	 */
 	if (tdp_mmu_enabled)
-		kvm_tdp_mmu_zap_invalidated_roots(kvm);
+		kvm_tdp_mmu_zap_invalidated_roots(kvm, true);
 }
 
 static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index ff27e1eadd54..b92dcd5b266f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -38,7 +38,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	 * ultimately frees all roots.
 	 */
 	kvm_tdp_mmu_invalidate_all_roots(kvm);
-	kvm_tdp_mmu_zap_invalidated_roots(kvm);
+	kvm_tdp_mmu_zap_invalidated_roots(kvm, false);
 
 	WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
@@ -927,11 +927,14 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
  * Zap all invalidated roots to ensure all SPTEs are dropped before the "fast
  * zap" completes.
  */
-void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared)
 {
 	struct kvm_mmu_page *root;
 
-	read_lock(&kvm->mmu_lock);
+	if (shared)
+		read_lock(&kvm->mmu_lock);
+	else
+		write_lock(&kvm->mmu_lock);
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		if (!root->tdp_mmu_scheduled_root_to_zap)
@@ -949,7 +952,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 		 * that may be zapped, as such entries are associated with the
 		 * ASID on both VMX and SVM.
 		 */
-		tdp_mmu_zap_root(kvm, root, true);
+		tdp_mmu_zap_root(kvm, root, shared);
 
 		/*
 		 * The referenced needs to be put *after* zapping the root, as
@@ -959,7 +962,10 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 		kvm_tdp_mmu_put_root(kvm, root);
 	}
 
-	read_unlock(&kvm->mmu_lock);
+	if (shared)
+		read_unlock(&kvm->mmu_lock);
+	else
+		write_unlock(&kvm->mmu_lock);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 1b74e058a81c..14421d080fe6 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -23,7 +23,7 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
 bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
 void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
-void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm);
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared);
 
 int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
 
-- 
2.34.1