Add float128 support for x86_64, x86.

This patch enables float128 support for x86_64 and x86.  All GCC
versions that can build glibc provide the required support, but since
GCC 6 and before don't provide __builtin_nanq / __builtin_nansq, sNaN
tests and some tests of NaN payloads need to be disabled with such
compilers (this does not affect the generated glibc binaries at all,
just the tests).  bits/floatn.h declares float128 support to be
available for GCC versions that provide the required libgcc support
(4.3 for x86_64, 4.4 for i386 GNU/Linux, 4.5 for i386 GNU/Hurd);
compilation-only support was present some time before then, but not
really useful without the libgcc functions.

fenv_private.h needed updating to avoid trying to put _Float128 values
in registers.  I make no assertion of optimality of the
math_opt_barrier / math_force_eval definitions for this case; they are
simply intended to be sufficient to work correctly.

Tested for x86_64 and x86, with GCC 7 and GCC 6.  (Testing for x32 was
compilation tests only with build-many-glibcs.py to verify the ABI
baseline updates.  I have not done any testing for Hurd, although the
float128 support is enabled there as for GNU/Linux.)

	* sysdeps/i386/Implies: Add ieee754/float128.
	* sysdeps/x86_64/Implies: Likewise.
	* sysdeps/x86/bits/floatn.h: New file.
	* sysdeps/x86/float128-abi.h: Likewise.
	* manual/math.texi (Mathematics): Document support for _Float128
	on x86_64 and x86.
	* sysdeps/i386/fpu/fenv_private.h: Include <bits/floatn.h>.
	(math_opt_barrier): Do not put _Float128 values in floating-point
	registers.
	(math_force_eval): Likewise.
	[__x86_64__] (SET_RESTORE_ROUNDF128): New macro.
	* sysdeps/x86/fpu/Makefile [$(subdir) = math] (CPPFLAGS): Append
	to Makefile variable.
	* sysdeps/x86/fpu/e_sqrtf128.c: New file.
	* sysdeps/x86/fpu/sfp-machine.h: Likewise.  Based on libgcc.
	* sysdeps/x86/math-tests.h: New file.
	* math/libm-test-support.h (XFAIL_FLOAT128_PAYLOAD): New macro.
	* math/libm-test-getpayload.inc (getpayload_test_data): Use
	XFAIL_FLOAT128_PAYLOAD.
	* math/libm-test-setpayload.inc (setpayload_test_data): Likewise.
	* math/libm-test-totalorder.inc (totalorder_test_data): Likewise.
	* math/libm-test-totalordermag.inc (totalordermag_test_data):
	Likewise.
	* sysdeps/unix/sysv/linux/i386/libc.abilist: Update.
	* sysdeps/unix/sysv/linux/i386/libm.abilist: Likewise.
	* sysdeps/unix/sysv/linux/x86_64/64/libc.abilist: Likewise.
	* sysdeps/unix/sysv/linux/x86_64/64/libm.abilist: Likewise.
	* sysdeps/unix/sysv/linux/x86_64/x32/libc.abilist: Likewise.
	* sysdeps/unix/sysv/linux/x86_64/x32/libm.abilist: Likewise.
	* sysdeps/i386/fpu/libm-test-ulps: Likewise.
	* sysdeps/i386/i686/fpu/multiarch/libm-test-ulps: Likewise.
	* sysdeps/x86_64/fpu/libm-test-ulps: Likewise.

1 files changed, 39 insertions, 22 deletions

diff --git a/sysdeps/i386/fpu/fenv_private.h b/sysdeps/i386/fpu/fenv_private.h
index e20e1f1662..38fd0b92b5 100644
--- a/sysdeps/i386/fpu/fenv_private.h
+++ b/sysdeps/i386/fpu/fenv_private.h
@@ -1,36 +1,46 @@
 #ifndef FENV_PRIVATE_H
 #define FENV_PRIVATE_H 1
 
+#include <bits/floatn.h>
 #include <fenv.h>
 #include <fpu_control.h>
 
 #ifdef __SSE2_MATH__
-# define math_opt_barrier(x) \
-  ({ __typeof(x) __x;					\
-     if (sizeof (x) <= sizeof (double))			\
-       __asm ("" : "=x" (__x) : "0" (x));		\
-     else						\
-       __asm ("" : "=t" (__x) : "0" (x));		\
+# define math_opt_barrier(x)						\
+  ({ __typeof(x) __x;							\
+     if (sizeof (x) <= sizeof (double)					\
+	|| __builtin_types_compatible_p (__typeof (x), _Float128))	\
+       __asm ("" : "=x" (__x) : "0" (x));				\
+     else								\
+       __asm ("" : "=t" (__x) : "0" (x));				\
      __x; })
-# define math_force_eval(x) \
-  do {							\
-    if (sizeof (x) <= sizeof (double))			\
-      __asm __volatile ("" : : "x" (x));		\
-    else						\
-      __asm __volatile ("" : : "f" (x));		\
+# define math_force_eval(x)						\
+  do {									\
+    if (sizeof (x) <= sizeof (double)					\
+	|| __builtin_types_compatible_p (__typeof (x), _Float128))	\
+      __asm __volatile ("" : : "x" (x));				\
+    else								\
+      __asm __volatile ("" : : "f" (x));				\
   } while (0)
 #else
-# define math_opt_barrier(x) \
-  ({ __typeof (x) __x;					\
-     __asm ("" : "=t" (__x) : "0" (x));			\
+# define math_opt_barrier(x)						\
+  ({ __typeof (x) __x;							\
+     if (__builtin_types_compatible_p (__typeof (x), _Float128))	\
+       {								\
+	 __x = (x);							\
+	 __asm ("" : "+m" (__x));					\
+       }								\
+     else								\
+       __asm ("" : "=t" (__x) : "0" (x));				\
      __x; })
-# define math_force_eval(x) \
-  do {							\
-    __typeof (x) __x = (x);				\
-    if (sizeof (x) <= sizeof (double))			\
-      __asm __volatile ("" : : "m" (__x));		\
-    else						\
-      __asm __volatile ("" : : "f" (__x));		\
+# define math_force_eval(x)						\
+  do {									\
+    __typeof (x) __x = (x);						\
+    if (sizeof (x) <= sizeof (double)					\
+	|| __builtin_types_compatible_p (__typeof (x), _Float128))	\
+      __asm __volatile ("" : : "m" (__x));				\
+    else								\
+      __asm __volatile ("" : : "f" (__x));				\
   } while (0)
 #endif
 
@@ -322,6 +332,13 @@ libc_feresetround_387 (fenv_t *e)
 # define libc_feholdsetround_53bit	libc_feholdsetround_387_53bit
 #endif
 
+#ifdef __x86_64__
+/* The SSE rounding mode is used by soft-fp (libgcc and glibc) on
+   x86_64, so that must be set for float128 computations.  */
+# define SET_RESTORE_ROUNDF128(RM) \
+  SET_RESTORE_ROUND_GENERIC (RM, libc_feholdsetround_sse, libc_feresetround_sse)
+#endif
+
 /* We have support for rounding mode context.  */
 #define HAVE_RM_CTX 1