KVM: nVMX: Handle pending #DB when injecting INIT VM-exit

SDM 27.3.4 states that the 'pending debug exceptions' VMCS field will
be populated if a VM-exit caused by an INIT signal takes priority over a
debug-trap. Emulate this behavior when synthesizing an INIT signal
VM-exit into L1.

Fixes: 4b9852f4f389 ("KVM: x86: Fix INIT signal handling in various CPU states")
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 28 insertions, 0 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 657c2eda357c..1586aaae3a6f 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3575,6 +3575,33 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
 	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
 }
 
+/*
+ * Returns true if a debug trap is pending delivery.
+ *
+ * In KVM, debug traps bear an exception payload. As such, the class of a #DB
+ * exception may be inferred from the presence of an exception payload.
+ */
+static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.exception.pending &&
+			vcpu->arch.exception.nr == DB_VECTOR &&
+			vcpu->arch.exception.payload;
+}
+
+/*
+ * Certain VM-exits set the 'pending debug exceptions' field to indicate a
+ * recognized #DB (data or single-step) that has yet to be delivered. Since KVM
+ * represents these debug traps with a payload that is said to be compatible
+ * with the 'pending debug exceptions' field, write the payload to the VMCS
+ * field if a VM-exit is delivered before the debug trap.
+ */
+static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu)
+{
+	if (vmx_pending_dbg_trap(vcpu))
+		vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+			    vcpu->arch.exception.payload);
+}
+
 static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -3587,6 +3614,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		if (block_nested_events)
 			return -EBUSY;
+		nested_vmx_update_pending_dbg(vcpu);
 		clear_bit(KVM_APIC_INIT, &apic->pending_events);
 		nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
 		return 0;