KVM: nVMX/nSVM: Don't intercept #UD when running L2

When running L2, #UD should be intercepted by L1 or just forwarded
directly to L2. It should not reach L0 x86 emulator.
Therefore, set intercept for #UD only based on L1 exception-bitmap.

Also add WARN_ON_ONCE() on L0 #UD intercept handlers to make sure
it is never reached while running L2.

This improves commit ae1f57670703 ("KVM: nVMX: Do not emulate #UD while
in guest mode") by removing an unnecessary exit from L2 to L0 on #UD
when L1 doesn't intercept it.

In addition, SVM L0 #UD intercept handler doesn't handle correctly the
case it is raised from L2. In this case, it should forward the #UD to
guest instead of x86 emulator. As done in VMX #UD intercept handler.
This commit fixes this issue as-well.

Signed-off-by: Liran Alon <liran.alon@oracle.com>
Reviewed-by: Nikita Leshenko <nikita.leshchenko@oracle.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>

2 files changed, 12 insertions, 6 deletions

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 59e13a79c2e3..1bf7c09d97e6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -361,6 +361,7 @@ static void recalc_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *c, *h;
 	struct nested_state *g;
+	u32 h_intercept_exceptions;
 
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 
@@ -371,9 +372,14 @@ static void recalc_intercepts(struct vcpu_svm *svm)
 	h = &svm->nested.hsave->control;
 	g = &svm->nested;
 
+	/* No need to intercept #UD if L1 doesn't intercept it */
+	h_intercept_exceptions =
+		h->intercept_exceptions & ~(1U << UD_VECTOR);
+
 	c->intercept_cr = h->intercept_cr | g->intercept_cr;
 	c->intercept_dr = h->intercept_dr | g->intercept_dr;
-	c->intercept_exceptions = h->intercept_exceptions | g->intercept_exceptions;
+	c->intercept_exceptions =
+		h_intercept_exceptions | g->intercept_exceptions;
 	c->intercept = h->intercept | g->intercept;
 }
 
@@ -2196,6 +2202,7 @@ static int ud_interception(struct vcpu_svm *svm)
 {
 	int er;
 
+	WARN_ON_ONCE(is_guest_mode(&svm->vcpu));
 	er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD);
 	if (er != EMULATE_DONE)
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 714a0673ec3c..d319e2666ad5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1887,7 +1887,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 {
 	u32 eb;
 
-	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
+	eb = (1u << PF_VECTOR) | (1u << MC_VECTOR) |
 	     (1u << DB_VECTOR) | (1u << AC_VECTOR);
 	if ((vcpu->guest_debug &
 	     (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
@@ -1905,6 +1905,8 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	 */
 	if (is_guest_mode(vcpu))
 		eb |= get_vmcs12(vcpu)->exception_bitmap;
+	else
+		eb |= 1u << UD_VECTOR;
 
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
@@ -5915,10 +5917,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		return 1;  /* already handled by vmx_vcpu_run() */
 
 	if (is_invalid_opcode(intr_info)) {
-		if (is_guest_mode(vcpu)) {
-			kvm_queue_exception(vcpu, UD_VECTOR);
-			return 1;
-		}
+		WARN_ON_ONCE(is_guest_mode(vcpu));
 		er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
 		if (er != EMULATE_DONE)
 			kvm_queue_exception(vcpu, UD_VECTOR);