3 files changed, 40 insertions, 25 deletions

diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 324cd722b44..80bfe1ab003 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -299,10 +299,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 				 *next = &next_p->thread;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
+	fpu_switch_t fpu;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	__unlazy_fpu(prev_p);
+	fpu = switch_fpu_prepare(prev_p, next_p);
 
 	/*
 	 * Reload esp0.
@@ -357,6 +358,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
+	switch_fpu_finish(next_p, fpu);
+
 	percpu_write(current_task, next_p);
 
 	return prev_p;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 753e803f719..1fd94bc4279 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -386,8 +386,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
 	unsigned fsindex, gsindex;
+	fpu_switch_t fpu;
 
-	__unlazy_fpu(prev_p);
+	fpu = switch_fpu_prepare(prev_p, next_p);
 
 	/*
 	 * Reload esp0, LDT and the page table pointer:
@@ -457,6 +458,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
 	prev->gsindex = gsindex;
 
+	switch_fpu_finish(next_p, fpu);
+
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ad25e51f40c..77da5b475ad 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -571,6 +571,37 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
 }
 
 /*
+ * This gets called with the process already owning the
+ * FPU state, and with CR0.TS cleared. It just needs to
+ * restore the FPU register state.
+ */
+void __math_state_restore(struct task_struct *tsk)
+{
+	/* We need a safe address that is cheap to find and that is already
+	   in L1. We've just brought in "tsk->thread.has_fpu", so use that */
+#define safe_address (tsk->thread.has_fpu)
+
+	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+	   is pending.  Clear the x87 state here by setting it to fixed
+	   values. safe_address is a random variable that should be in L1 */
+	alternative_input(
+		ASM_NOP8 ASM_NOP2,
+		"emms\n\t"	  	/* clear stack tags */
+		"fildl %P[addr]",	/* set F?P to defined value */
+		X86_FEATURE_FXSAVE_LEAK,
+		[addr] "m" (safe_address));
+
+	/*
+	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
+	 */
+	if (unlikely(restore_fpu_checking(tsk))) {
+		__thread_fpu_end(tsk);
+		force_sig(SIGSEGV, tsk);
+		return;
+	}
+}
+
+/*
  * 'math_state_restore()' saves the current math information in the
  * old math state array, and gets the new ones from the current task
  *
@@ -584,10 +615,6 @@ void math_state_restore(void)
 {
 	struct task_struct *tsk = current;
 
-	/* We need a safe address that is cheap to find and that is already
-	   in L1. We're just bringing in "tsk->thread.has_fpu", so use that */
-#define safe_address (tsk->thread.has_fpu)
-
 	if (!tsk_used_math(tsk)) {
 		local_irq_enable();
 		/*
@@ -604,25 +631,7 @@ void math_state_restore(void)
 	}
 
 	__thread_fpu_begin(tsk);
-
-	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-	   is pending.  Clear the x87 state here by setting it to fixed
-	   values. safe_address is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"	  	/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (safe_address));
-
-	/*
-	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
-	 */
-	if (unlikely(restore_fpu_checking(tsk))) {
-		__thread_fpu_end(tsk);
-		force_sig(SIGSEGV, tsk);
-		return;
-	}
+	__math_state_restore(tsk);
 
 	tsk->fpu_counter++;
 }