powerpc: Use faster means to access FPSCR when possible in some cases

Using 'mffs' instruction to read the Floating Point Status Control Register
(FPSCR) can force a processor flush in some cases, with undesirable
performance impact.  If the values of the bits in the FPSCR which force the
flush are not needed, an instruction that is new to POWER9 (ISA version 3.0),
'mffsl' can be used instead.

Cases included:  get_rounding_mode, fegetround, fegetmode, fegetexcept.

	* sysdeps/powerpc/bits/fenvinline.h (__fegetround): Use
	__fegetround_ISA300() or __fegetround_ISA2() as appropriate.
	(__fegetround_ISA300) New.
	(__fegetround_ISA2) New.
	* sysdeps/powerpc/fpu_control.h (IS_ISA300): New.
	(_FPU_MFFS): Move implementation...
	(_FPU_GETCW): Here.
	(_FPU_MFFSL): Move implementation....
	(_FPU_GET_RC_ISA300): Here. New.
	(_FPU_GET_RC): Use _FPU_GET_RC_ISA300() or _FPU_GETCW() as appropriate.
	* sysdeps/powerpc/fpu/fenv_libc.h (fegetenv_status_ISA300): New.
	(fegetenv_status): New.
	* sysdeps/powerpc/fpu/fegetmode.c (fegetmode): Use fegetenv_status()
	instead of fegetenv_register().
	* sysdeps/powerpc/fpu/fegetexcept.c (__fegetexcept): Likewise.

Reviewed-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>

1 files changed, 23 insertions, 21 deletions

diff --git a/sysdeps/powerpc/fpu_control.h b/sysdeps/powerpc/fpu_control.h
index fa04a67..d0fdad7 100644
--- a/sysdeps/powerpc/fpu_control.h
+++ b/sysdeps/powerpc/fpu_control.h
@@ -65,35 +65,37 @@ extern fpu_control_t __fpu_control;
 typedef unsigned int fpu_control_t;
 
 /* Macros for accessing the hardware control word.  */
-# define __FPU_MFFS()						\
-  ({register double __fr;					\
-    __asm__ __volatile__("mffs %0" : "=f" (__fr));		\
-    __fr;							\
-  })
-
 # define _FPU_GETCW(cw)						\
   ({union { double __d; unsigned long long __ll; } __u;		\
-    __u.__d = __FPU_MFFS();					\
+    __asm__ __volatile__("mffs %0" : "=f" (__u.__d));		\
     (cw) = (fpu_control_t) __u.__ll;				\
     (fpu_control_t) __u.__ll;					\
   })
 
-#ifdef _ARCH_PWR9
-# define __FPU_MFFSL()						\
-  ({register double __fr;					\
-    __asm__ __volatile__("mffsl %0" : "=f" (__fr));		\
-    __fr;							\
+# define _FPU_GET_RC_ISA300()						\
+  ({union { double __d; unsigned long long __ll; } __u;			\
+    __asm__ __volatile__(						\
+      ".machine push; .machine \"power9\"; mffsl %0; .machine pop" 	\
+      : "=f" (__u.__d));						\
+    (fpu_control_t) (__u.__ll & _FPU_MASK_RC);				\
   })
-#else
-# define __FPU_MFFSL() __FPU_MFFS()
-#endif
-    
-# define _FPU_GET_RC()						\
-  ({union { double __d; unsigned long long __ll; } __u;		\
-    __u.__d = __FPU_MFFSL();					\
-    __u.__ll &= _FPU_MASK_RC;					\
-    (fpu_control_t) __u.__ll;					\
+
+# ifdef _ARCH_PWR9
+#  define _FPU_GET_RC() _FPU_GET_RC_ISA300()
+# elif defined __BUILTIN_CPU_SUPPORTS__
+#  define _FPU_GET_RC()							\
+  ({fpu_control_t __rc;							\
+    __rc = __glibc_likely (__builtin_cpu_supports ("arch_3_00"))	\
+      ? _FPU_GET_RC_ISA300 ()						\
+      : _FPU_GETCW (__rc) & _FPU_MASK_RC;				\
+    __rc;								\
+  })
+# else
+#  define _FPU_GET_RC()						\
+  ({fpu_control_t __rc = _FPU_GETCW (__rc) & _FPU_MASK_RC;	\
+    __rc;							\
   })
+# endif
 
 # define _FPU_SETCW(cw)						\
   { union { double __d; unsigned long long __ll; } __u;		\