Use round functions not __round functions in glibc libm.

Continuing the move to use, within libm, public names for libm
functions that can be inlined as built-in functions on many
architectures, this patch moves calls to __round functions to call the
corresponding round names instead, with asm redirection to __round
when the calls are not inlined.

An additional complication arises in
sysdeps/ieee754/ldbl-128ibm/e_expl.c, where a call to roundl, with the
result converted to int, gets converted by the compiler to call
lroundl in the case of 32-bit long, so resulting in localplt test
failures.  It's logically correct to let the compiler make such an
optimization; an appropriate asm redirection of lroundl to __lroundl
is thus added to that file (it's not needed anywhere else).

Tested for x86_64, and with build-many-glibcs.py.

	* include/math.h [!_ISOMAC && !(__FINITE_MATH_ONLY__ &&
	__FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (round): Redirect
	using MATH_REDIRECT.
	* sysdeps/aarch64/fpu/s_round.c: Define NO_MATH_REDIRECT before
	header inclusion.
	* sysdeps/aarch64/fpu/s_roundf.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_round.c: Likewise.
	* sysdeps/ieee754/dbl-64/wordsize-64/s_round.c: Likewise.
	* sysdeps/ieee754/float128/s_roundf128.c: Likewise.
	* sysdeps/ieee754/flt-32/s_roundf.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_roundl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_roundl.c: Likewise.
	* sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_round.c: Likewise.
	* sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_roundf.c: Likewise.
	* sysdeps/powerpc/powerpc64/fpu/multiarch/s_round.c: Likewise.
	* sysdeps/powerpc/powerpc64/fpu/multiarch/s_roundf.c: Likewise.
	* sysdeps/riscv/rv64/rvd/s_round.c: Likewise.
	* sysdeps/riscv/rvf/s_roundf.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_roundl.c: Likewise.
	(round): Redirect to __round.
	(__roundl): Call round instead of __round.
	* sysdeps/powerpc/fpu/math_private.h [_ARCH_PWR5X] (__round):
	Remove macro.
	[_ARCH_PWR5X] (__roundf): Likewise.
	* sysdeps/ieee754/dbl-64/e_gamma_r.c (gamma_positive): Use round
	functions instead of __round variants.
	* sysdeps/ieee754/flt-32/e_gammaf_r.c (gammaf_positive): Likewise.
	* sysdeps/ieee754/ldbl-128/e_gammal_r.c (gammal_positive):
	Likewise.
	* sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c (gammal_positive):
	Likewise.
	* sysdeps/ieee754/ldbl-96/e_gammal_r.c (gammal_positive):
	Likewise.
	* sysdeps/x86/fpu/powl_helper.c (__powl_helper): Likewise.
	* sysdeps/ieee754/ldbl-128ibm/e_expl.c (lroundl): Redirect to
	__lroundl.
	(__ieee754_expl): Call roundl instead of __roundl.

3 files changed, 14 insertions, 6 deletions

diff --git a/sysdeps/ieee754/ldbl-128ibm/e_expl.c b/sysdeps/ieee754/ldbl-128ibm/e_expl.c
index a5024559dc..0c33d88010 100644
--- a/sysdeps/ieee754/ldbl-128ibm/e_expl.c
+++ b/sysdeps/ieee754/ldbl-128ibm/e_expl.c
@@ -134,6 +134,11 @@ static const long double C[] = {
  1.98412698413981650382436541785404286E-04L,
 };
 
+/* Avoid local PLT entry use from (int) roundl (...) being converted
+   to a call to lroundl in the case of 32-bit long and roundl not
+   inlined.  */
+long int lroundl (long double) asm ("__lroundl");
+
 long double
 __ieee754_expl (long double x)
 {
@@ -149,15 +154,15 @@ __ieee754_expl (long double x)
 
       SET_RESTORE_ROUND (FE_TONEAREST);
 
-      n = __roundl (x*M_1_LN2);
+      n = roundl (x*M_1_LN2);
       x = x-n*M_LN2_0;
       xl = n*M_LN2_1;
 
-      tval1 = __roundl (x*TWO8);
+      tval1 = roundl (x*TWO8);
       x -= __expl_table[T_EXPL_ARG1+2*tval1];
       xl -= __expl_table[T_EXPL_ARG1+2*tval1+1];
 
-      tval2 = __roundl (x*TWO15);
+      tval2 = roundl (x*TWO15);
       x -= __expl_table[T_EXPL_ARG2+2*tval2];
       xl -= __expl_table[T_EXPL_ARG2+2*tval2+1];
 
diff --git a/sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c b/sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c
index 36801213d4..6361d35428 100644
--- a/sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c
+++ b/sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c
@@ -95,7 +95,7 @@ gammal_positive (long double x, int *exp2_adj)
 	 starting by computing pow (X_ADJ, X_ADJ) with a power of 2
 	 factored out.  */
       long double exp_adj = -eps;
-      long double x_adj_int = __roundl (x_adj);
+      long double x_adj_int = roundl (x_adj);
       long double x_adj_frac = x_adj - x_adj_int;
       int x_adj_log2;
       long double x_adj_mant = __frexpl (x_adj, &x_adj_log2);
diff --git a/sysdeps/ieee754/ldbl-128ibm/s_roundl.c b/sysdeps/ieee754/ldbl-128ibm/s_roundl.c
index 94a62dcd6c..156be267a0 100644
--- a/sysdeps/ieee754/ldbl-128ibm/s_roundl.c
+++ b/sysdeps/ieee754/ldbl-128ibm/s_roundl.c
@@ -20,12 +20,15 @@
 /* This has been coded in assembler because GCC makes such a mess of it
    when it's coded in C.  */
 
+#define NO_MATH_REDIRECT
 #include <math.h>
 #include <math_private.h>
 #include <math_ldbl_opt.h>
 #include <float.h>
 #include <ieee754.h>
 
+double round (double) asm ("__round");
+
 
 long double
 __roundl (long double x)
@@ -39,7 +42,7 @@ __roundl (long double x)
 			&& __builtin_isless (__builtin_fabs (xh),
 					     __builtin_inf ()), 1))
     {
-      hi = __round (xh);
+      hi = round (xh);
       if (hi != xh)
 	{
 	  /* The high part is not an integer; the low part only
@@ -62,7 +65,7 @@ __roundl (long double x)
       else
 	{
 	  /* The high part is a nonzero integer.  */
-	  lo = __round (xl);
+	  lo = round (xl);
 	  if (fabs (lo - xl) == 0.5)
 	    {
 	      if (xh > 0 && xl < 0)