kvm: x86: emulate monitor and mwait instructions as nop

Treat monitor and mwait instructions as nop, which is architecturally
correct (but inefficient) behavior. We do this to prevent misbehaving
guests (e.g. OS X <= 10.7) from crashing after they fail to check for
monitor/mwait availability via cpuid.

Since mwait-based idle loops relying on these nop-emulated instructions
would keep the host CPU pegged at 100%, do NOT advertise their presence
via cpuid, to prevent compliant guests from using them inadvertently.

Signed-off-by: Gabriel L. Somlo <somlo@cmu.edu>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/cpuid.c

@@ -283,6 +283,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
 	/* cpuid 1.ecx */
 	const u32 kvm_supported_word4_x86_features =
+		/* NOTE: MONITOR (and MWAIT) are emulated as NOP,
+		 * but *not* advertised to guests via CPUID ! */
 		F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ |
 		0 /* DS-CPL, VMX, SMX, EST */ |
 		0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |

arch/x86/kvm/svm.c

@@ -2770,12 +2770,6 @@ static int xsetbv_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
-static int invalid_op_interception(struct vcpu_svm *svm)
-{
-	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
-	return 1;
-}
-
 static int task_switch_interception(struct vcpu_svm *svm)
 {
 	u16 tss_selector;
@@ -3287,6 +3281,24 @@ static int pause_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
+static int nop_interception(struct vcpu_svm *svm)
+{
+	skip_emulated_instruction(&(svm->vcpu));
+	return 1;
+}
+
+static int monitor_interception(struct vcpu_svm *svm)
+{
+	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
+	return nop_interception(svm);
+}
+
+static int mwait_interception(struct vcpu_svm *svm)
+{
+	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
+	return nop_interception(svm);
+}
+
 static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR0]			= cr_interception,
 	[SVM_EXIT_READ_CR3]			= cr_interception,
@@ -3344,8 +3356,8 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_CLGI]				= clgi_interception,
 	[SVM_EXIT_SKINIT]			= skinit_interception,
 	[SVM_EXIT_WBINVD]                       = emulate_on_interception,
-	[SVM_EXIT_MONITOR]			= invalid_op_interception,
-	[SVM_EXIT_MWAIT]			= invalid_op_interception,
+	[SVM_EXIT_MONITOR]			= monitor_interception,
+	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
 	[SVM_EXIT_NPF]				= pf_interception,
 };

arch/x86/kvm/vmx.c

@@ -5650,12 +5650,24 @@ static int handle_pause(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_invalid_op(struct kvm_vcpu *vcpu)
+static int handle_nop(struct kvm_vcpu *vcpu)
 {
-	kvm_queue_exception(vcpu, UD_VECTOR);
+	skip_emulated_instruction(vcpu);
 	return 1;
 }
 
+static int handle_mwait(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
+}
+
+static int handle_monitor(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
+}
+
 /*
  * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12.
  * We could reuse a single VMCS for all the L2 guests, but we also want the
@@ -6617,8 +6629,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
 	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
-	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_invalid_op,
-	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_invalid_op,
+	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_mwait,
+	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_monitor,
 	[EXIT_REASON_INVEPT]                  = handle_invept,
 };