1 files changed, 19 insertions, 10 deletions

diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index b627746f6b1..d5dd8081441 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin);
 
 void __kernel_fpu_end(void)
 {
-	if (use_eager_fpu())
-		math_state_restore();
-	else
+	if (use_eager_fpu()) {
+		/*
+		 * For eager fpu, most the time, tsk_used_math() is true.
+		 * Restore the user math as we are done with the kernel usage.
+		 * At few instances during thread exit, signal handling etc,
+		 * tsk_used_math() is false. Those few places will take proper
+		 * actions, so we don't need to restore the math here.
+		 */
+		if (likely(tsk_used_math(current)))
+			math_state_restore();
+	} else {
 		stts();
+	}
 }
 EXPORT_SYMBOL(__kernel_fpu_end);
 
@@ -100,7 +109,7 @@ void unlazy_fpu(struct task_struct *tsk)
 		__save_init_fpu(tsk);
 		__thread_fpu_end(tsk);
 	} else
-		tsk->fpu_counter = 0;
+		tsk->thread.fpu_counter = 0;
 	preempt_enable();
 }
 EXPORT_SYMBOL(unlazy_fpu);
@@ -108,15 +117,15 @@ EXPORT_SYMBOL(unlazy_fpu);
 unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
-static struct i387_fxsave_struct fx_scratch __cpuinitdata;
+static struct i387_fxsave_struct fx_scratch;
 
-static void __cpuinit mxcsr_feature_mask_init(void)
+static void mxcsr_feature_mask_init(void)
 {
 	unsigned long mask = 0;
 
 	if (cpu_has_fxsr) {
 		memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
-		asm volatile("fxsave %0" : : "m" (fx_scratch));
+		asm volatile("fxsave %0" : "+m" (fx_scratch));
 		mask = fx_scratch.mxcsr_mask;
 		if (mask == 0)
 			mask = 0x0000ffbf;
@@ -124,7 +133,7 @@ static void __cpuinit mxcsr_feature_mask_init(void)
 	mxcsr_feature_mask &= mask;
 }
 
-static void __cpuinit init_thread_xstate(void)
+static void init_thread_xstate(void)
 {
 	/*
 	 * Note that xstate_size might be overwriten later during
@@ -153,7 +162,7 @@ static void __cpuinit init_thread_xstate(void)
  * into all processes.
  */
 
-void __cpuinit fpu_init(void)
+void fpu_init(void)
 {
 	unsigned long cr0;
 	unsigned long cr4_mask = 0;
@@ -608,7 +617,7 @@ static int __init no_387(char *s)
 
 __setup("no387", no_387);
 
-void __cpuinit fpu_detect(struct cpuinfo_x86 *c)
+void fpu_detect(struct cpuinfo_x86 *c)
 {
 	unsigned long cr0;
 	u16 fsw, fcw;