KVM: x86: Handle triple fault in L2 without killing L1

Synthesize a nested VM-Exit if L2 triggers an emulated triple fault
instead of exiting to userspace, which likely will kill L1.  Any flow
that does KVM_REQ_TRIPLE_FAULT is suspect, but the most common scenario
for L2 killing L1 is if L0 (KVM) intercepts a contributory exception that
is _not_intercepted by L1.  E.g. if KVM is intercepting #GPs for the
VMware backdoor, a #GP that occurs in L2 while vectoring an injected #DF
will cause KVM to emulate triple fault.

Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Jim Mattson <jmattson@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210302174515.2812275-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -1340,6 +1340,7 @@ struct kvm_x86_ops {
 struct kvm_x86_nested_ops {
 	int (*check_events)(struct kvm_vcpu *vcpu);
 	bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
+	void (*triple_fault)(struct kvm_vcpu *vcpu);
 	int (*get_state)(struct kvm_vcpu *vcpu,
 			 struct kvm_nested_state __user *user_kvm_nested_state,
 			 unsigned user_data_size);

arch/x86/kvm/lapic.c

@@ -2869,7 +2869,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 		return;
 
 	if (is_guest_mode(vcpu)) {
-		r = kvm_x86_ops.nested_ops->check_events(vcpu);
+		r = kvm_check_nested_events(vcpu);
 		if (r < 0)
 			return;
 		/*

arch/x86/kvm/svm/nested.c

@@ -661,6 +661,9 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	struct kvm_host_map map;
 	int rc;
 
+	/* Triple faults in L2 should never escape. */
+	WARN_ON_ONCE(kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu));
+
 	rc = kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.vmcb12_gpa), &map);
 	if (rc) {
 		if (rc == -EINVAL)
@@ -782,6 +785,16 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	return 0;
 }
 
+static void nested_svm_triple_fault(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	svm->vmcb->control.exit_code   = SVM_EXIT_SHUTDOWN;
+	svm->vmcb->control.exit_info_1 = 0;
+	svm->vmcb->control.exit_info_2 = 0;
+	nested_svm_vmexit(svm);
+}
+
 int svm_allocate_nested(struct vcpu_svm *svm)
 {
 	struct page *vmcb02_page;
@@ -1317,6 +1330,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 
 struct kvm_x86_nested_ops svm_nested_ops = {
 	.check_events = svm_check_nested_events,
+	.triple_fault = nested_svm_triple_fault,
 	.get_nested_state_pages = svm_get_nested_state_pages,
 	.get_state = svm_get_nested_state,
 	.set_state = svm_set_nested_state,

arch/x86/kvm/vmx/nested.c

@@ -4418,6 +4418,9 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	/* trying to cancel vmlaunch/vmresume is a bug */
 	WARN_ON_ONCE(vmx->nested.nested_run_pending);
 
+	/* Similarly, triple faults in L2 should never escape. */
+	WARN_ON_ONCE(kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu));
+
 	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 
 	/* Service the TLB flush request for L2 before switching to L1. */
@@ -4554,6 +4557,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	vmx->fail = 0;
 }
 
+static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu)
+{
+	nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
+}
+
 /*
  * Decode the memory-address operand of a vmx instruction, as recorded on an
  * exit caused by such an instruction (run by a guest hypervisor).
@@ -6590,6 +6598,7 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 struct kvm_x86_nested_ops vmx_nested_ops = {
 	.check_events = vmx_check_nested_events,
 	.hv_timer_pending = nested_vmx_preemption_timer_pending,
+	.triple_fault = nested_vmx_triple_fault,
 	.get_state = vmx_get_nested_state,
 	.set_state = vmx_set_nested_state,
 	.get_nested_state_pages = vmx_get_nested_state_pages,

arch/x86/kvm/x86.c

@@ -8329,6 +8329,19 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 	static_call(kvm_x86_update_cr8_intercept)(vcpu, tpr, max_irr);
 }
 
+int kvm_check_nested_events(struct kvm_vcpu *vcpu)
+{
+	if (WARN_ON_ONCE(!is_guest_mode(vcpu)))
+		return -EIO;
+
+	if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+		kvm_x86_ops.nested_ops->triple_fault(vcpu);
+		return 1;
+	}
+
+	return kvm_x86_ops.nested_ops->check_events(vcpu);
+}
+
 static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit)
 {
 	int r;
@@ -8374,7 +8387,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit
 	 * from L2 to L1.
 	 */
 	if (is_guest_mode(vcpu)) {
-		r = kvm_x86_ops.nested_ops->check_events(vcpu);
+		r = kvm_check_nested_events(vcpu);
 		if (r < 0)
 			goto busy;
 	}
@@ -8937,10 +8950,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
-			vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
-			vcpu->mmio_needed = 0;
-			r = 0;
-			goto out;
+			if (is_guest_mode(vcpu)) {
+				kvm_x86_ops.nested_ops->triple_fault(vcpu);
+			} else {
+				vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+				vcpu->mmio_needed = 0;
+				r = 0;
+				goto out;
+			}
 		}
 		if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
 			/* Page is swapped out. Do synthetic halt */
@@ -9238,7 +9255,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
 {
 	if (is_guest_mode(vcpu))
-		kvm_x86_ops.nested_ops->check_events(vcpu);
+		kvm_check_nested_events(vcpu);
 
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
 		!vcpu->arch.apf.halted);

arch/x86/kvm/x86.h

@@ -56,6 +56,8 @@ static inline unsigned int __shrink_ple_window(unsigned int val,
 
 #define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
 
+int kvm_check_nested_events(struct kvm_vcpu *vcpu);
+
 static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.exception.pending = false;