diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 6c3bd3782818..ed8089d69094 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -24,8 +24,32 @@ extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 extern void math_state_restore(void);
 
 extern bool irq_fpu_usable(void);
-extern void kernel_fpu_begin(void);
-extern void kernel_fpu_end(void);
+
+/*
+ * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
+ * and they don't touch the preempt state on their own.
+ * If you enable preemption after __kernel_fpu_begin(), preempt notifier
+ * should call the __kernel_fpu_end() to prevent the kernel/user FPU
+ * state from getting corrupted. KVM for example uses this model.
+ *
+ * All other cases use kernel_fpu_begin/end() which disable preemption
+ * during kernel FPU usage.
+ */
+extern void __kernel_fpu_begin(void);
+extern void __kernel_fpu_end(void);
+
+static inline void kernel_fpu_begin(void)
+{
+	WARN_ON_ONCE(!irq_fpu_usable());
+	preempt_disable();
+	__kernel_fpu_begin();
+}
+
+static inline void kernel_fpu_end(void)
+{
+	__kernel_fpu_end();
+	preempt_enable();
+}
 
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 6782e3983865..675a05012449 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -73,32 +73,29 @@ bool irq_fpu_usable(void)
 }
 EXPORT_SYMBOL(irq_fpu_usable);
 
-void kernel_fpu_begin(void)
+void __kernel_fpu_begin(void)
 {
 	struct task_struct *me = current;
 
-	WARN_ON_ONCE(!irq_fpu_usable());
-	preempt_disable();
 	if (__thread_has_fpu(me)) {
 		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
-		/* We do 'stts()' in kernel_fpu_end() */
+		/* We do 'stts()' in __kernel_fpu_end() */
 	} else if (!use_eager_fpu()) {
 		this_cpu_write(fpu_owner_task, NULL);
 		clts();
 	}
 }
-EXPORT_SYMBOL(kernel_fpu_begin);
+EXPORT_SYMBOL(__kernel_fpu_begin);
 
-void kernel_fpu_end(void)
+void __kernel_fpu_end(void)
 {
 	if (use_eager_fpu())
 		math_state_restore();
 	else
 		stts();
-	preempt_enable();
 }
-EXPORT_SYMBOL(kernel_fpu_end);
+EXPORT_SYMBOL(__kernel_fpu_end);
 
 void unlazy_fpu(struct task_struct *tsk)
 {
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03de1b79..70dfcec3c463 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1493,8 +1493,12 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
-	if (user_has_fpu())
-		clts();
+	/*
+	 * If the FPU is not active (through the host task or
+	 * the guest vcpu), then restore the cr0.TS bit.
+	 */
+	if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
+		stts();
 	load_gdt(&__get_cpu_var(host_gdt));
 }
 
@@ -3730,7 +3734,7 @@ static void vmx_set_constant_host_state(void)
 	unsigned long tmpl;
 	struct desc_ptr dt;
 
-	vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS);  /* 22.2.3 */
+	vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS);  /* 22.2.3 */
 	vmcs_writel(HOST_CR4, read_cr4());  /* 22.2.3, 22.2.5 */
 	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cf637f572bdd..02b2cd520693 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5972,7 +5972,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 */
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
-	kernel_fpu_begin();
+	__kernel_fpu_begin();
 	fpu_restore_checking(&vcpu->arch.guest_fpu);
 	trace_kvm_fpu(1);
 }
@@ -5986,7 +5986,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 
 	vcpu->guest_fpu_loaded = 0;
 	fpu_save_init(&vcpu->arch.guest_fpu);
-	kernel_fpu_end();
+	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
 	kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
 	trace_kvm_fpu(0);