4 files changed, 48 insertions, 4 deletions
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1b203abf76e1..c41f03e5090a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1198,10 +1198,13 @@ static void init_vmcb(struct vcpu_svm *svm)
 	set_intercept(svm, INTERCEPT_CLGI);
 	set_intercept(svm, INTERCEPT_SKINIT);
 	set_intercept(svm, INTERCEPT_WBINVD);
-	set_intercept(svm, INTERCEPT_MONITOR);
-	set_intercept(svm, INTERCEPT_MWAIT);
 	set_intercept(svm, INTERCEPT_XSETBV);
 
+	if (!kvm_mwait_in_guest()) {
+		set_intercept(svm, INTERCEPT_MONITOR);
+		set_intercept(svm, INTERCEPT_MWAIT);
+	}
+
 	control->iopm_base_pa = iopm_base;
 	control->msrpm_base_pa = __pa(svm->msrpm);
 	control->int_ctl = V_INTR_MASKING_MASK;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c1a12b94e1fd..a4ef63718101 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3527,11 +3527,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	      CPU_BASED_USE_IO_BITMAPS |
 	      CPU_BASED_MOV_DR_EXITING |
 	      CPU_BASED_USE_TSC_OFFSETING |
-	      CPU_BASED_MWAIT_EXITING |
-	      CPU_BASED_MONITOR_EXITING |
 	      CPU_BASED_INVLPG_EXITING |
 	      CPU_BASED_RDPMC_EXITING;
 
+	if (!kvm_mwait_in_guest())
+		min |= CPU_BASED_MWAIT_EXITING |
+			CPU_BASED_MONITOR_EXITING;
+
 	opt = CPU_BASED_TPR_SHADOW |
 	      CPU_BASED_USE_MSR_BITMAPS |
 	      CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 49a69c0a0d50..2f9fe6bf7091 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2687,6 +2687,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ADJUST_CLOCK:
 		r = KVM_CLOCK_TSC_STABLE;
 		break;
+	case KVM_CAP_X86_GUEST_MWAIT:
+		r = kvm_mwait_in_guest();
+		break;
 	case KVM_CAP_X86_SMM:
 		/* SMBASE is usually relocated above 1M on modern chipsets,
 		 * and SMM handlers might indeed rely on 4G segment limits,
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index e8ff3e4ce38a..612067074905 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -1,6 +1,8 @@
 #ifndef ARCH_X86_KVM_X86_H
 #define ARCH_X86_KVM_X86_H
 
+#include <asm/processor.h>
+#include <asm/mwait.h>
 #include <linux/kvm_host.h>
 #include <asm/pvclock.h>
 #include "kvm_cache_regs.h"
@@ -212,4 +214,38 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
 	    __rem;						\
 	 })
 
+static inline bool kvm_mwait_in_guest(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	if (!cpu_has(&boot_cpu_data, X86_FEATURE_MWAIT))
+		return false;
+
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+		/* All AMD CPUs have a working MWAIT implementation */
+		return true;
+	case X86_VENDOR_INTEL:
+		/* Handle Intel below */
+		break;
+	default:
+		return false;
+	}
+
+	/*
+	 * Intel CPUs without CPUID5_ECX_INTERRUPT_BREAK are problematic as
+	 * they would allow guest to stop the CPU completely by disabling
+	 * interrupts then invoking MWAIT.
+	 */
+	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+		return false;
+
+	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
+
+	if (!(ecx & CPUID5_ECX_INTERRUPT_BREAK))
+		return false;
+
+	return true;
+}
+
 #endif