diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 74c607b37e873176e3e91c4cf5b3bf8e7ed18455..247904945d3f3055dccf6e9fd0c05474167f98d7 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -32,6 +32,8 @@ extern int init_fpu(struct task_struct *child);
 extern void math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
+DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+
 extern user_regset_active_fn fpregs_active, xfpregs_active;
 extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
 				xstateregs_get;
@@ -276,7 +278,7 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 		"emms\n\t"	  	/* clear stack tags */
 		"fildl %P[addr]",	/* set F?P to defined value */
 		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (tsk->thread.has_fpu));
+		[addr] "m" (tsk->thread.fpu.has_fpu));
 
 	return fpu_restore_checking(&tsk->thread.fpu);
 }
@@ -288,19 +290,21 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
  */
 static inline int __thread_has_fpu(struct task_struct *tsk)
 {
-	return tsk->thread.has_fpu;
+	return tsk->thread.fpu.has_fpu;
 }
 
 /* Must be paired with an 'stts' after! */
 static inline void __thread_clear_has_fpu(struct task_struct *tsk)
 {
-	tsk->thread.has_fpu = 0;
+	tsk->thread.fpu.has_fpu = 0;
+	percpu_write(fpu_owner_task, NULL);
 }
 
 /* Must be paired with a 'clts' before! */
 static inline void __thread_set_has_fpu(struct task_struct *tsk)
 {
-	tsk->thread.has_fpu = 1;
+	tsk->thread.fpu.has_fpu = 1;
+	percpu_write(fpu_owner_task, tsk);
 }
 
 /*
@@ -345,18 +349,22 @@ typedef struct { int preload; } fpu_switch_t;
  * We don't do that yet, so "fpu_lazy_restore()" always returns
  * false, but some day..
  */
-#define fpu_lazy_restore(tsk) (0)
-#define fpu_lazy_state_intact(tsk) do { } while (0)
+static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+{
+	return new == percpu_read_stable(fpu_owner_task) &&
+		cpu == new->thread.fpu.last_cpu;
+}
 
-static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new)
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
 {
 	fpu_switch_t fpu;
 
 	fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
 	if (__thread_has_fpu(old)) {
-		if (__save_init_fpu(old))
-			fpu_lazy_state_intact(old);
-		__thread_clear_has_fpu(old);
+		if (!__save_init_fpu(old))
+			cpu = ~0;
+		old->thread.fpu.last_cpu = cpu;
+		old->thread.fpu.has_fpu = 0;	/* But leave fpu_owner_task! */
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
@@ -367,9 +375,10 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 			stts();
 	} else {
 		old->fpu_counter = 0;
+		old->thread.fpu.last_cpu = ~0;
 		if (fpu.preload) {
 			new->fpu_counter++;
-			if (fpu_lazy_restore(new))
+			if (fpu_lazy_restore(new, cpu))
 				fpu.preload = 0;
 			else
 				prefetch(new->thread.fpu.state);
@@ -463,8 +472,10 @@ static inline void kernel_fpu_begin(void)
 		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
 		/* We do 'stts()' in kernel_fpu_end() */
-	} else
+	} else {
+		percpu_write(fpu_owner_task, NULL);
 		clts();
+	}
 }
 
 static inline void kernel_fpu_end(void)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f7c89e231c6c0ad74502946955dfe2d45cfc7c2f..58545c97d071c84dba4a05b59bad7be5d0b69b01 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -374,6 +374,8 @@ union thread_xstate {
 };
 
 struct fpu {
+	unsigned int last_cpu;
+	unsigned int has_fpu;
 	union thread_xstate *state;
 };
 
@@ -454,7 +456,6 @@ struct thread_struct {
 	unsigned long		trap_no;
 	unsigned long		error_code;
 	/* floating point and extended processor state */
-	unsigned long		has_fpu;
 	struct fpu		fpu;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d43cad74f1661c2180cc1f9277b9553b3de7cf63..b667148dfad70326fafc37a4633b7e453d8b5725 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1044,6 +1044,8 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) =
 
 DEFINE_PER_CPU(unsigned int, irq_count) = -1;
 
+DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+
 /*
  * Special IST stacks which the CPU switches to when it calls
  * an IST-marked descriptor entry. Up to 7 stacks (hardware
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index bc32761bc27ab00a3f5b1cfcd8235eafa071f7a0..c08d1ff12b7c4087dd01ad6f2ba8ea5bcc8ba04a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -304,7 +304,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	fpu = switch_fpu_prepare(prev_p, next_p);
+	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
 	/*
 	 * Reload esp0.
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 8ad880b3bc1c345dcb44e7ed4453baba4639395d..cfa5c90c01dbe0c170587ae8891a1fa419aa2e36 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -389,7 +389,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	unsigned fsindex, gsindex;
 	fpu_switch_t fpu;
 
-	fpu = switch_fpu_prepare(prev_p, next_p);
+	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
 	/*
 	 * Reload esp0, LDT and the page table pointer: