x86/fpu: Uninline kernel_fpu_begin()/end()

Both inline functions call an inline function unconditionally, so we
already pay the function call based clobbering cost. Uninline them.

This saves quite a bit of code in various performance sensitive
code paths:

   text            data    bss     dec             hex     filename
   13321334        2569888 1634304 17525526        10b6b16 vmlinux.before
   13320246        2569888 1634304 17524438        10b66d6 vmlinux.after
Reviewed-by: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/fpu/api.h

@@ -39,19 +39,8 @@ extern bool irq_fpu_usable(void);
  */
 extern void __kernel_fpu_begin(void);
 extern void __kernel_fpu_end(void);
-
-static inline void kernel_fpu_begin(void)
-{
-	preempt_disable();
-	WARN_ON_ONCE(!irq_fpu_usable());
-	__kernel_fpu_begin();
-}
-
-static inline void kernel_fpu_end(void)
-{
-	__kernel_fpu_end();
-	preempt_enable();
-}
+extern void kernel_fpu_begin(void);
+extern void kernel_fpu_end(void);
 
 /*
  * Some instructions like VIA's padlock instructions generate a spurious

arch/x86/kernel/fpu/core.c

@@ -125,6 +125,21 @@ void __kernel_fpu_end(void)
 }
 EXPORT_SYMBOL(__kernel_fpu_end);
 
+void kernel_fpu_begin(void)
+{
+	preempt_disable();
+	WARN_ON_ONCE(!irq_fpu_usable());
+	__kernel_fpu_begin();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+	__kernel_fpu_end();
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);
+
 static void __save_fpu(struct fpu *fpu)
 {
 	if (use_xsave()) {