x86, fpu: Merge tolerant_fwait()

Commit e2e75c91 merged the math exception handler, allowing both 32-bit
and 64-bit to handle math exceptions from kernel mode.  Switch to using
the 64-bit version of tolerant_fwait() without fnclex, which simply
ignores the exception if one is still pending from userspace.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Acked-by: Pekka Enberg <penberg@kernel.org>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <1283563039-3466-4-git-send-email-brgerst@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

arch/x86/include/asm/i387.h

@@ -77,15 +77,6 @@ static inline void sanitize_i387_state(struct task_struct *tsk)
 }
 
 #ifdef CONFIG_X86_64
-
-/* Ignore delayed exceptions from user space */
-static inline void tolerant_fwait(void)
-{
-	asm volatile("1: fwait\n"
-		     "2:\n"
-		     _ASM_EXTABLE(1b, 2b));
-}
-
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
 	int err;
@@ -220,11 +211,6 @@ extern void finit_soft_fpu(struct i387_soft_struct *soft);
 static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
 #endif
 
-static inline void tolerant_fwait(void)
-{
-	asm volatile("fnclex ; fwait");
-}
-
 /* perform fxrstor iff the processor has extended states, otherwise frstor */
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
@@ -344,7 +330,10 @@ static inline void __unlazy_fpu(struct task_struct *tsk)
 static inline void __clear_fpu(struct task_struct *tsk)
 {
 	if (task_thread_info(tsk)->status & TS_USEDFPU) {
-		tolerant_fwait();
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
 		task_thread_info(tsk)->status &= ~TS_USEDFPU;
 		stts();
 	}