diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 1c040d80c6417820480c47cd0354e8e1ed2074b6..152312c1fafa3dcfd26cbf5583d27b688c8b3660 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -304,6 +304,7 @@ struct kvm_vcpu {
 	char *host_fx_image;
 	char *guest_fx_image;
 	int fpu_active;
+	int guest_fpu_loaded;
 
 	int mmio_needed;
 	int mmio_read_completed;
@@ -508,6 +509,8 @@ void fx_init(struct kvm_vcpu *vcpu);
 void load_msrs(struct vmx_msr_entry *e, int n);
 void save_msrs(struct vmx_msr_entry *e, int n);
 void kvm_resched(struct kvm_vcpu *vcpu);
+void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
+void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
 
 int kvm_read_guest(struct kvm_vcpu *vcpu,
 	       gva_t addr,
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index da985b31b17e09b5979e930b3ba9edf37c84f5aa..8f1f07adb04e914ce61ea6c595ce90ed53030e01 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -253,6 +253,28 @@ int kvm_write_guest(struct kvm_vcpu *vcpu, gva_t addr, unsigned long size,
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest);
 
+void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu->fpu_active || vcpu->guest_fpu_loaded)
+		return;
+
+	vcpu->guest_fpu_loaded = 1;
+	fx_save(vcpu->host_fx_image);
+	fx_restore(vcpu->guest_fx_image);
+}
+EXPORT_SYMBOL_GPL(kvm_load_guest_fpu);
+
+void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu->guest_fpu_loaded)
+		return;
+
+	vcpu->guest_fpu_loaded = 0;
+	fx_save(vcpu->guest_fx_image);
+	fx_restore(vcpu->host_fx_image);
+}
+EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
+
 /*
  * Switches to specified vcpu, until a matching vcpu_put()
  */
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index 184238e2ece4679ce04f68f455033d93b1710af5..c1ac106ace8c1c99193c9b87667396f4adbfb2c5 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -280,6 +280,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu)
 
 static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	kvm_put_guest_fpu(vcpu);
 	put_cpu();
 }
 
@@ -1847,10 +1848,8 @@ static int vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (vcpu->guest_debug.enabled)
 		kvm_guest_debug_pre(vcpu);
 
-	if (vcpu->fpu_active) {
-		fx_save(vcpu->host_fx_image);
-		fx_restore(vcpu->guest_fx_image);
-	}
+	kvm_load_guest_fpu(vcpu);
+
 	/*
 	 * Loading guest fpu may have cleared host cr0.ts
 	 */
@@ -2012,11 +2011,6 @@ static int vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 #endif
 
-	if (vcpu->fpu_active) {
-		fx_save(vcpu->guest_fx_image);
-		fx_restore(vcpu->host_fx_image);
-	}
-
 	vcpu->interrupt_window_open = (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0;
 
 	asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));