kvm: x86: nVMX: maintain internal copy of current VMCS

KVM maintains L1's current VMCS in guest memory, at the guest physical
page identified by the argument to VMPTRLD. This makes hairy
time-of-check to time-of-use bugs possible,as VCPUs can be writing
the the VMCS page in memory while KVM is emulating VMLAUNCH and
VMRESUME.

The spec documents that writing to the VMCS page while it is loaded is
"undefined". Therefore it is reasonable to load the entire VMCS into
an internal cache during VMPTRLD and ignore writes to the VMCS page
-- the guest should be using VMREAD and VMWRITE to access the current
VMCS.

To adhere to the spec, KVM should flush the current VMCS during VMPTRLD,
and the target VMCS during VMCLEAR (as given by the operand to VMCLEAR).
Since this implementation of VMCS caching only maintains the the current
VMCS, VMCLEAR will only do a flush if the operand to VMCLEAR is the
current VMCS pointer.

KVM will also flush during VMXOFF, which is not mandated by the spec,
but also not in conflict with the spec.
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/vmx.c

@@ -405,6 +405,12 @@ struct nested_vmx {
 	/* The host-usable pointer to the above */
 	struct page *current_vmcs12_page;
 	struct vmcs12 *current_vmcs12;
+	/*
+	 * Cache of the guest's VMCS, existing outside of guest memory.
+	 * Loaded from guest memory during VMPTRLD. Flushed to guest
+	 * memory during VMXOFF, VMCLEAR, VMPTRLD.
+	 */
+	struct vmcs12 *cached_vmcs12;
 	struct vmcs *current_shadow_vmcs;
 	/*
 	 * Indicates if the shadow vmcs must be updated with the
@@ -858,7 +864,7 @@ static inline short vmcs_field_to_offset(unsigned long field)
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {
-	return to_vmx(vcpu)->nested.current_vmcs12;
+	return to_vmx(vcpu)->nested.cached_vmcs12;
 }
 
 static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
@@ -6987,10 +6993,16 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
+	vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
+	if (!vmx->nested.cached_vmcs12)
+		return -ENOMEM;
+
 	if (enable_shadow_vmcs) {
 		shadow_vmcs = alloc_vmcs();
-		if (!shadow_vmcs)
+		if (!shadow_vmcs) {
+			kfree(vmx->nested.cached_vmcs12);
 			return -ENOMEM;
+		}
 		/* mark vmcs as shadow */
 		shadow_vmcs->revision_id |= (1u << 31);
 		/* init shadow vmcs */
@@ -7061,6 +7073,11 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
 		vmcs_write64(VMCS_LINK_POINTER, -1ull);
 	}
 	vmx->nested.posted_intr_nv = -1;
+
+	/* Flush VMCS12 to guest memory */
+	memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12,
+	       VMCS12_SIZE);
+
 	kunmap(vmx->nested.current_vmcs12_page);
 	nested_release_page(vmx->nested.current_vmcs12_page);
 	vmx->nested.current_vmptr = -1ull;
@@ -7081,6 +7098,7 @@ static void free_nested(struct vcpu_vmx *vmx)
 	nested_release_vmcs12(vmx);
 	if (enable_shadow_vmcs)
 		free_vmcs(vmx->nested.current_shadow_vmcs);
+	kfree(vmx->nested.cached_vmcs12);
 	/* Unpin physical memory we referred to in current vmcs02 */
 	if (vmx->nested.apic_access_page) {
 		nested_release_page(vmx->nested.apic_access_page);
@@ -7484,6 +7502,13 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		vmx->nested.current_vmptr = vmptr;
 		vmx->nested.current_vmcs12 = new_vmcs12;
 		vmx->nested.current_vmcs12_page = page;
+		/*
+		 * Load VMCS12 from guest memory since it is not already
+		 * cached.
+		 */
+		memcpy(vmx->nested.cached_vmcs12,
+		       vmx->nested.current_vmcs12, VMCS12_SIZE);
+
 		if (enable_shadow_vmcs) {
 			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
 				      SECONDARY_EXEC_SHADOW_VMCS);
@@ -8456,7 +8481,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 	 * the next L2->L1 exit.
 	 */
 	if (!is_guest_mode(vcpu) ||
-	    !nested_cpu_has2(vmx->nested.current_vmcs12,
+	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
 			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
 }