KVM: nVMX: Emulate MTF when performing instruction emulation

Since commit 5f3d45e7f282 ("kvm/x86: add support for
MONITOR_TRAP_FLAG"), KVM has allowed an L1 guest to use the monitor trap
flag processor-based execution control for its L2 guest. KVM simply
forwards any MTF VM-exits to the L1 guest, which works for normal
instruction execution.

However, when KVM needs to emulate an instruction on the behalf of an L2
guest, the monitor trap flag is not emulated. Add the necessary logic to
kvm_skip_emulated_instruction() to synthesize an MTF VM-exit to L1 upon
instruction emulation for L2.

Fixes: 5f3d45e7f282 ("kvm/x86: add support for MONITOR_TRAP_FLAG")
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

6 files changed, 81 insertions, 2 deletions

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d9b5add5a211..ad3f5b178a03 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -7439,6 +7439,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.run = svm_vcpu_run,
 	.handle_exit = handle_exit,
 	.skip_emulated_instruction = skip_emulated_instruction,
+	.update_emulated_instruction = NULL,
 	.set_interrupt_shadow = svm_set_interrupt_shadow,
 	.get_interrupt_shadow = svm_get_interrupt_shadow,
 	.patch_hypercall = svm_patch_hypercall,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 2b3ba7d27be4..50d8dbb3616d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3609,8 +3609,15 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 	unsigned long exit_qual;
 	bool block_nested_events =
 	    vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
+	bool mtf_pending = vmx->nested.mtf_pending;
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
+	/*
+	 * Clear the MTF state. If a higher priority VM-exit is delivered first,
+	 * this state is discarded.
+	 */
+	vmx->nested.mtf_pending = false;
+
 	if (lapic_in_kernel(vcpu) &&
 		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		if (block_nested_events)
@@ -3621,8 +3628,28 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		return 0;
 	}
 
+	/*
+	 * Process any exceptions that are not debug traps before MTF.
+	 */
+	if (vcpu->arch.exception.pending &&
+	    !vmx_pending_dbg_trap(vcpu) &&
+	    nested_vmx_check_exception(vcpu, &exit_qual)) {
+		if (block_nested_events)
+			return -EBUSY;
+		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+		return 0;
+	}
+
+	if (mtf_pending) {
+		if (block_nested_events)
+			return -EBUSY;
+		nested_vmx_update_pending_dbg(vcpu);
+		nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0);
+		return 0;
+	}
+
 	if (vcpu->arch.exception.pending &&
-		nested_vmx_check_exception(vcpu, &exit_qual)) {
+	    nested_vmx_check_exception(vcpu, &exit_qual)) {
 		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
@@ -5712,6 +5739,9 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 
 			if (vmx->nested.nested_run_pending)
 				kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;
+
+			if (vmx->nested.mtf_pending)
+				kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING;
 		}
 	}
 
@@ -5892,6 +5922,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	vmx->nested.nested_run_pending =
 		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
 
+	vmx->nested.mtf_pending =
+		!!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING);
+
 	ret = -EINVAL;
 	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
 	    vmcs12->vmcs_link_pointer != -1ull) {
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 1c5fbff45d69..1db388f2a444 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -174,6 +174,11 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
 	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
 }
 
+static inline int nested_cpu_has_mtf(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
+}
+
 static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
 {
 	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 404dafedd778..dcca514ffd42 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1603,6 +1603,40 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+
+/*
+ * Recognizes a pending MTF VM-exit and records the nested state for later
+ * delivery.
+ */
+static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!is_guest_mode(vcpu))
+		return;
+
+	/*
+	 * Per the SDM, MTF takes priority over debug-trap exceptions besides
+	 * T-bit traps. As instruction emulation is completed (i.e. at the
+	 * instruction boundary), any #DB exception pending delivery must be a
+	 * debug-trap. Record the pending MTF state to be delivered in
+	 * vmx_check_nested_events().
+	 */
+	if (nested_cpu_has_mtf(vmcs12) &&
+	    (!vcpu->arch.exception.pending ||
+	     vcpu->arch.exception.nr == DB_VECTOR))
+		vmx->nested.mtf_pending = true;
+	else
+		vmx->nested.mtf_pending = false;
+}
+
+static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+	vmx_update_emulated_instruction(vcpu);
+	return skip_emulated_instruction(vcpu);
+}
+
 static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -7796,7 +7830,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 
 	.run = vmx_vcpu_run,
 	.handle_exit = vmx_handle_exit,
-	.skip_emulated_instruction = skip_emulated_instruction,
+	.skip_emulated_instruction = vmx_skip_emulated_instruction,
+	.update_emulated_instruction = vmx_update_emulated_instruction,
 	.set_interrupt_shadow = vmx_set_interrupt_shadow,
 	.get_interrupt_shadow = vmx_get_interrupt_shadow,
 	.patch_hypercall = vmx_patch_hypercall,
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 7f42cf3dcd70..e64da06c7009 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -150,6 +150,9 @@ struct nested_vmx {
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
 
+	/* Pending MTF VM-exit into L1.  */
+	bool mtf_pending;
+
 	struct loaded_vmcs vmcs02;
 
 	/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fb5d64ebc35d..359fcd395132 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6891,6 +6891,8 @@ restart:
 			kvm_rip_write(vcpu, ctxt->eip);
 			if (r && ctxt->tf)
 				r = kvm_vcpu_do_singlestep(vcpu);
+			if (kvm_x86_ops->update_emulated_instruction)
+				kvm_x86_ops->update_emulated_instruction(vcpu);
 			__kvm_set_rflags(vcpu, ctxt->eflags);
 		}