Commit 5ef8acbd authored by Oliver Upton's avatar Oliver Upton Committed by Paolo Bonzini
Browse files

KVM: nVMX: Emulate MTF when performing instruction emulation 



Since commit 5f3d45e7 ("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: 5f3d45e7 ("kvm/x86: add support for MONITOR_TRAP_FLAG")
Signed-off-by: default avatarOliver Upton <oupton@google.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent dd58f3c9

arch/x86/include/asm/kvm_host.h

+1 −0
Original line number Diff line number Diff line
@@ -1122,6 +1122,7 @@ struct kvm_x86_ops { 
	int (*handle_exit)(struct kvm_vcpu *vcpu,

		enum exit_fastpath_completion exit_fastpath);

	int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);

	void (*update_emulated_instruction)(struct kvm_vcpu *vcpu);

	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);

	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);

	void (*patch_hypercall)(struct kvm_vcpu *vcpu,

arch/x86/include/uapi/asm/kvm.h

+1 −0
Original line number Diff line number Diff line
@@ -390,6 +390,7 @@ struct kvm_sync_regs { 
#define KVM_STATE_NESTED_GUEST_MODE	0x00000001

#define KVM_STATE_NESTED_RUN_PENDING	0x00000002

#define KVM_STATE_NESTED_EVMCS		0x00000004

#define KVM_STATE_NESTED_MTF_PENDING	0x00000008



#define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001

#define KVM_STATE_NESTED_SMM_VMXON	0x00000002

arch/x86/kvm/svm.c

+1 −0
Original line number Diff line number Diff line
@@ -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,

arch/x86/kvm/vmx/nested.c

+34 −1
Original line number Diff line number Diff line
@@ -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)
@@ -3621,6 +3628,26 @@ 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)) {

		if (block_nested_events)
@@ -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) {

arch/x86/kvm/vmx/nested.h

+5 −0
Original line number Diff line number Diff line
@@ -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);

CRA Git | Maintained and supported by SUSTech CRA and CCSE