Add support for sqrt asm redirects

This patch series cleans up the many uses of  __ieee754_sqrt(f/l) in GLIBC.
The goal is to enable GCC to do the inlining, and if this fails call the
__ieee754_sqrt function.  This is done by internally declaring sqrt with asm
redirects.  The compat symbols and sqrt wrappers need to disable the redirect.
The redirect is also disabled if there are already redirects defined when
using -ffinite-math-only.

All math functions (but not math tests, non-library code and libnldbl) are
built with -fno-math-errno which means GCC will typically inline sqrt as a
single instruction.  This means targets are no longer forced to add a special
inline for sqrt.

	* include/math.h (sqrt): Declare with asm redirect.
	(sqrtf): Likewise.
	(sqrtl): Likewise.
	(sqrtf128): Likewise.
	* Makeconfig: Add -fno-math-errno for libc/libm, but build testsuite,
	nonlib and libnldbl with -fmath-errno.
	* math/w_sqrt_compat.c: Define NO_MATH_REDIRECT.
	* math/w_sqrt_template.c: Likewise.
	* math/w_sqrtf_compat.c: Likewise.
	* math/w_sqrtl_compat.c: Likewise.
	* sysdeps/i386/fpu/w_sqrt.c: Likewise.
	* sysdeps/i386/fpu/w_sqrt_compat.c: Likewise.
	* sysdeps/generic/math-type-macros-float128.h: Remove math.h and
	complex.h.

10 files changed, 42 insertions, 3 deletions

diff --git a/ChangeLog b/ChangeLog
index 6c8c880243..1a497eaa68 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -27,6 +27,23 @@
 
 2018-03-15  Wilco Dijkstra  <wdijkstr@arm.com>
 
+	* include/math.h (sqrt): Declare with asm redirect.
+	(sqrtf): Likewise.
+	(sqrtl): Likewise.
+	(sqrtf128): Likewise.
+	* Makeconfig: Add -fno-math-errno for libc/libm, but build testsuite,
+	nonlib and libnldbl with -fmath-errno.
+	* math/w_sqrt_compat.c: Define NO_MATH_REDIRECT.
+	* math/w_sqrt_template.c: Likewise.
+	* math/w_sqrtf_compat.c: Likewise.
+	* math/w_sqrtl_compat.c: Likewise.
+	* sysdeps/i386/fpu/w_sqrt.c: Likewise.
+	* sysdeps/i386/fpu/w_sqrt_compat.c: Likewise.
+	* sysdeps/generic/math-type-macros-float128.h: Remove math.h and
+	complex.h.
+
+2018-03-15  Wilco Dijkstra  <wdijkstr@arm.com>
+
 	* benchtests/Makefile: Define _ISOMAC.
 	* benchtests/bench-strcoll.c: Add missing sys/stat.h include.
 	* benchtests/bench-string.h: Define inhibit_loop_to_libcall macro.
diff --git a/Makeconfig b/Makeconfig
index 86a71e5802..1afe86475c 100644
--- a/Makeconfig
+++ b/Makeconfig
@@ -831,6 +831,9 @@ endif
 # disable any optimization that assume default rounding mode.
 +math-flags = -frounding-math
 
+# Build libc/libm using -fno-math-errno, but run testsuite with -fmath-errno.
++extra-math-flags = $(if $(filter libnldbl nonlib testsuite,$(in-module)),-fmath-errno,-fno-math-errno)
+
 # We might want to compile with some stack-protection flag.
 ifneq ($(stack-protector),)
 +stack-protector=$(stack-protector)
@@ -966,6 +969,7 @@ endif
 
 override CFLAGS	= -std=gnu11 -fgnu89-inline $(config-extra-cflags) \
 		  $(filter-out %frame-pointer,$(+cflags)) $(+gccwarn-c) \
+		  $(+extra-math-flags) \
 		  $(sysdep-CFLAGS) $(CFLAGS-$(suffix $@)) $(CFLAGS-$(<F)) \
 		  $(CFLAGS-$(@F)) $(tls-model) \
 		  $(foreach lib,$(libof-$(basename $(@F))) \
diff --git a/include/math.h b/include/math.h
index 7ee291fc97..e21d34b868 100644
--- a/include/math.h
+++ b/include/math.h
@@ -54,5 +54,20 @@ libm_hidden_proto (__expf128)
 libm_hidden_proto (__expm1f128)
 # endif
 
+# if !(defined __FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0)
+#  ifndef NO_MATH_REDIRECT
+/* Declare sqrt for use within GLIBC.  Compilers typically inline sqrt as a
+   single instruction.  Use an asm to avoid use of PLTs if it doesn't.  */
+float (sqrtf) (float) asm ("__ieee754_sqrtf");
+double (sqrt) (double) asm ("__ieee754_sqrt");
+#   ifndef __NO_LONG_DOUBLE_MATH
+long double (sqrtl) (long double) asm ("__ieee754_sqrtl");
+#   endif
+#   if __HAVE_DISTINCT_FLOAT128 > 0
+_Float128 (sqrtf128) (_Float128) asm ("__ieee754_sqrtf128");
+#   endif
+#  endif
+# endif
+
 #endif
 #endif
diff --git a/math/w_sqrt_compat.c b/math/w_sqrt_compat.c
index 7884d14633..e76a8079aa 100644
--- a/math/w_sqrt_compat.c
+++ b/math/w_sqrt_compat.c
@@ -16,6 +16,7 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
+#define NO_MATH_REDIRECT
 #include <math.h>
 #include <math_private.h>
 #include <math-svid-compat.h>
diff --git a/math/w_sqrt_template.c b/math/w_sqrt_template.c
index 52a21c0bf1..9c6ac75956 100644
--- a/math/w_sqrt_template.c
+++ b/math/w_sqrt_template.c
@@ -21,6 +21,7 @@
    for each floating-point type.  */
 #if __USE_WRAPPER_TEMPLATE
 
+# define NO_MATH_REDIRECT
 # include <errno.h>
 # include <fenv.h>
 # include <math.h>
diff --git a/math/w_sqrtf_compat.c b/math/w_sqrtf_compat.c
index 824ce0ed46..cad9b4ad77 100644
--- a/math/w_sqrtf_compat.c
+++ b/math/w_sqrtf_compat.c
@@ -16,6 +16,7 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
+#define NO_MATH_REDIRECT
 #include <math.h>
 #include <math_private.h>
 #include <math-svid-compat.h>
diff --git a/math/w_sqrtl_compat.c b/math/w_sqrtl_compat.c
index 56627a615d..16dda403b7 100644
--- a/math/w_sqrtl_compat.c
+++ b/math/w_sqrtl_compat.c
@@ -16,6 +16,7 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
+#define NO_MATH_REDIRECT
 #include <math.h>
 #include <math_private.h>
 #include <math-svid-compat.h>
diff --git a/sysdeps/generic/math-type-macros-float128.h b/sysdeps/generic/math-type-macros-float128.h
index 605996e0ba..485c13bb88 100644
--- a/sysdeps/generic/math-type-macros-float128.h
+++ b/sysdeps/generic/math-type-macros-float128.h
@@ -19,9 +19,6 @@
 #ifndef _MATH_TYPE_MACROS_FLOAT128
 #define _MATH_TYPE_MACROS_FLOAT128
 
-#include <math.h>
-#include <complex.h>
-
 #define M_LIT(c) __f128 (c)
 #define M_PFX FLT128
 #define M_SUF(c) c ## f128
diff --git a/sysdeps/i386/fpu/w_sqrt.c b/sysdeps/i386/fpu/w_sqrt.c
index d37a5d55bf..8bef04e68a 100644
--- a/sysdeps/i386/fpu/w_sqrt.c
+++ b/sysdeps/i386/fpu/w_sqrt.c
@@ -1,5 +1,6 @@
 /* The inline __ieee754_sqrt is not correctly rounding; it's OK for
    most internal uses in glibc, but not for sqrt itself.  */
+#define NO_MATH_REDIRECT
 #define __ieee754_sqrt __avoid_ieee754_sqrt
 #include <math.h>
 #include <math_private.h>
diff --git a/sysdeps/i386/fpu/w_sqrt_compat.c b/sysdeps/i386/fpu/w_sqrt_compat.c
index ddd36d0964..dd485f4b88 100644
--- a/sysdeps/i386/fpu/w_sqrt_compat.c
+++ b/sysdeps/i386/fpu/w_sqrt_compat.c
@@ -1,5 +1,6 @@
 /* The inline __ieee754_sqrt is not correctly rounding; it's OK for
    most internal uses in glibc, but not for sqrt itself.  */
+#define NO_MATH_REDIRECT
 #define __ieee754_sqrt __avoid_ieee754_sqrt
 #include <math.h>
 #include <math_private.h>