KVM: x86/mmu: Zap invalid roots with mmu_lock holding for write at uninit

Prepare for a future TDX patch which asserts that atomic zapping
(i.e. zapping with mmu_lock taken for read) don't operate on mirror roots.
When tearing down a VM, all roots have to be zapped (including mirror
roots once they're in place) so do that with the mmu_lock taken for write.

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.

Co-developed-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Message-ID: <20240718211230.1492011-2-rick.p.edgecombe@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Author: rpedgeco

arch/x86/kvm/mmu/mmu.c

@@ -6467,7 +6467,7 @@ 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);
 }
 
 void kvm_mmu_init_vm(struct kvm *kvm)

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));
@@ -883,11 +883,14 @@ 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)
@@ -905,7 +908,7 @@ 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
@@ -915,7 +918,10 @@ 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);
 }
 
 /*

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);