math: Set 387 and SSE2 rounding mode for tgamma on i386 [BZ #23253]

[Florian Weimer <fweimer@redhat.com>]

[-- Attachment #1: Type: text/plain, Size: 223 bytes --]

This is my attempt at fixing a bunch of math test suite failures when 
compiling with -mfpmath=sse on i686.  I don't really know what I'm doing 
here, but the whole thing looks internally consistent to me.

Thanks,
Florian

[-- Attachment #2: bug23253.patch --]
[-- Type: text/x-patch, Size: 7477 bytes --]

Subject: [PATCH] math: Set 387 and SSE2 rounding mode for tgamma on i386 [BZ #23253]
To: libc-alpha@sourceware.org

Previously, only the SSE2 rounding mode was set, so the assembler
implementations using 387 were not following the expecting rounding
mode.

2018-06-20  Florian Weimer  <fweimer@redhat.com>

	[BZ #23253]
	* sysdeps/generic/math_private.h (default_libc_feholdsetround_ctx):
	Renamed from libc_feholdsetround_ctx.
	(default_libc_feresetround_ctx): Renamed from
	libc_feresetround_ctx.
	(default_libc_feholdsetround_noex_ctx): Renamed from
	libc_feholdsetround_noex_ctx.
	(default_libc_feresetround_noex_ctx): Renamed from
	libc_feresetround_noex_ctx.
	[!HAVE_RM_CTX] (libc_feholdsetround_ctx, libc_feresetround_ctx)
	(libc_feholdsetround_noex_ctx, libc_feresetround_noex_ctx): Macros
	forwardning to the old implementations under the new names.
	* sysdeps/i386/fpu/fenv_private.h [__SSE_MATH__]
	(libc_feholdexcept_setround_ctx, libc_fesetenv_ctx)
	(libc_feupdateenv_ctx, libc_feholdsetround_ctx)
	(libc_feresetround_ctx): Forward to default implements for i386
	and MATH_SET_BOTH_ROUNDING_MODES.
	* sysdeps/i386/Makefile [$(subdir) == math] (CFLAGS-e_gamma_r.c):
	Add -DMATH_SET_BOTH_ROUNDING_MODES.

diff --git a/sysdeps/generic/math_private.h b/sysdeps/generic/math_private.h
index b6612ba6bf..1212abaf47 100644
--- a/sysdeps/generic/math_private.h
+++ b/sysdeps/generic/math_private.h
@@ -428,33 +428,6 @@ default_libc_feupdateenv_test (fenv_t *e, int ex)
 # define HAVE_RM_CTX 0
 #endif
 
-#if HAVE_RM_CTX
-/* Set/Restore Rounding Modes only when necessary.  If defined, these functions
-   set/restore floating point state only if the state needed within the lexical
-   block is different from the current state.  This saves a lot of time when
-   the floating point unit is much slower than the fixed point units.  */
-
-# ifndef libc_feholdsetround_noex_ctx
-#   define libc_feholdsetround_noex_ctx  libc_feholdsetround_ctx
-# endif
-# ifndef libc_feholdsetround_noexf_ctx
-#   define libc_feholdsetround_noexf_ctx libc_feholdsetroundf_ctx
-# endif
-# ifndef libc_feholdsetround_noexl_ctx
-#   define libc_feholdsetround_noexl_ctx libc_feholdsetroundl_ctx
-# endif
-
-# ifndef libc_feresetround_noex_ctx
-#   define libc_feresetround_noex_ctx  libc_fesetenv_ctx
-# endif
-# ifndef libc_feresetround_noexf_ctx
-#   define libc_feresetround_noexf_ctx libc_fesetenvf_ctx
-# endif
-# ifndef libc_feresetround_noexl_ctx
-#   define libc_feresetround_noexl_ctx libc_fesetenvl_ctx
-# endif
-
-#else
 
 /* Default implementation using standard fenv functions.
    Avoid unnecessary rounding mode changes by first checking the
@@ -462,7 +435,7 @@ default_libc_feupdateenv_test (fenv_t *e, int ex)
    important for performance.  */
 
 static __always_inline void
-libc_feholdsetround_ctx (struct rm_ctx *ctx, int round)
+default_libc_feholdsetround_ctx (struct rm_ctx *ctx, int round)
 {
   ctx->updated_status = false;
 
@@ -476,7 +449,7 @@ libc_feholdsetround_ctx (struct rm_ctx *ctx, int round)
 }
 
 static __always_inline void
-libc_feresetround_ctx (struct rm_ctx *ctx)
+default_libc_feresetround_ctx (struct rm_ctx *ctx)
 {
   /* Restore the rounding mode if updated.  */
   if (__glibc_unlikely (ctx->updated_status))
@@ -484,7 +457,7 @@ libc_feresetround_ctx (struct rm_ctx *ctx)
 }
 
 static __always_inline void
-libc_feholdsetround_noex_ctx (struct rm_ctx *ctx, int round)
+default_libc_feholdsetround_noex_ctx (struct rm_ctx *ctx, int round)
 {
   /* Save exception flags and rounding mode, and disable exception
      traps.  */
@@ -496,12 +469,45 @@ libc_feholdsetround_noex_ctx (struct rm_ctx *ctx, int round)
 }
 
 static __always_inline void
-libc_feresetround_noex_ctx (struct rm_ctx *ctx)
+default_libc_feresetround_noex_ctx (struct rm_ctx *ctx)
 {
   /* Restore exception flags and rounding mode.  */
   __fesetenv (&ctx->env);
 }
 
+#if HAVE_RM_CTX
+/* Set/Restore Rounding Modes only when necessary.  If defined, these functions
+   set/restore floating point state only if the state needed within the lexical
+   block is different from the current state.  This saves a lot of time when
+   the floating point unit is much slower than the fixed point units.  */
+
+# ifndef libc_feholdsetround_noex_ctx
+#   define libc_feholdsetround_noex_ctx  libc_feholdsetround_ctx
+# endif
+# ifndef libc_feholdsetround_noexf_ctx
+#   define libc_feholdsetround_noexf_ctx libc_feholdsetroundf_ctx
+# endif
+# ifndef libc_feholdsetround_noexl_ctx
+#   define libc_feholdsetround_noexl_ctx libc_feholdsetroundl_ctx
+# endif
+
+# ifndef libc_feresetround_noex_ctx
+#   define libc_feresetround_noex_ctx  libc_fesetenv_ctx
+# endif
+# ifndef libc_feresetround_noexf_ctx
+#   define libc_feresetround_noexf_ctx libc_fesetenvf_ctx
+# endif
+# ifndef libc_feresetround_noexl_ctx
+#   define libc_feresetround_noexl_ctx libc_fesetenvl_ctx
+# endif
+
+#else
+
+# define libc_feholdsetround_ctx      default_libc_feholdsetround_ctx
+# define libc_feresetround_ctx        default_libc_feresetround_ctx
+# define libc_feholdsetround_noex_ctx default_libc_feholdsetround_noex_ctx
+# define libc_feresetround_noex_ctx   default_libc_feresetround_noex_ctx
+
 # define libc_feholdsetroundf_ctx libc_feholdsetround_ctx
 # define libc_feholdsetroundl_ctx libc_feholdsetround_ctx
 # define libc_feresetroundf_ctx   libc_feresetround_ctx
diff --git a/sysdeps/i386/Makefile b/sysdeps/i386/Makefile
index 1682394e76..e9302726cf 100644
--- a/sysdeps/i386/Makefile
+++ b/sysdeps/i386/Makefile
@@ -5,6 +5,14 @@ asm-CPPFLAGS += -DGAS_SYNTAX
 # The i386 `long double' is a distinct type we support.
 long-double-fcts = yes
 
+ifeq ($(subdir),math)
+# These functions change the rounding mode internally and need to
+# update both the SSE2 rounding mod and the 387 rounding mode.  See
+# the handling of MATH_SET_BOTH_ROUNDING_MODES in
+# sysdeps/i386/fpu/fenv_private.h.
+CFLAGS-e_gamma_r.c += -DMATH_SET_BOTH_ROUNDING_MODES
+endif
+
 ifeq ($(subdir),string)
 sysdep_routines += cacheinfo
 endif
diff --git a/sysdeps/i386/fpu/fenv_private.h b/sysdeps/i386/fpu/fenv_private.h
index 59e83d858a..637dae5f05 100644
--- a/sysdeps/i386/fpu/fenv_private.h
+++ b/sysdeps/i386/fpu/fenv_private.h
@@ -460,11 +460,19 @@ libc_feupdateenv_387_ctx (struct rm_ctx *ctx)
 #endif /* __SSE_MATH__ */
 
 #ifdef __SSE2_MATH__
-# define libc_feholdexcept_setround_ctx	libc_feholdexcept_setround_sse_ctx
-# define libc_fesetenv_ctx		libc_fesetenv_sse_ctx
-# define libc_feupdateenv_ctx		libc_feupdateenv_sse_ctx
-# define libc_feholdsetround_ctx	libc_feholdsetround_sse_ctx
-# define libc_feresetround_ctx		libc_feresetround_sse_ctx
+# if defined (__x86_64__) || !defined (MATH_SET_BOTH_ROUNDING_MODES)
+#  define libc_feholdexcept_setround_ctx libc_feholdexcept_setround_sse_ctx
+#  define libc_fesetenv_ctx		libc_fesetenv_sse_ctx
+#  define libc_feupdateenv_ctx		libc_feupdateenv_sse_ctx
+#  define libc_feholdsetround_ctx	libc_feholdsetround_sse_ctx
+#  define libc_feresetround_ctx		libc_feresetround_sse_ctx
+# else
+#  define libc_feholdexcept_setround_ctx default_libc_feholdexcept_setround_ctx
+#  define libc_fesetenv_ctx		default_libc_fesetenv_ctx
+#  define libc_feupdateenv_ctx		default_libc_feupdateenv_ctx
+#  define libc_feholdsetround_ctx	default_libc_feholdsetround_ctx
+#  define libc_feresetround_ctx		default_libc_feresetround_ctx
+# endif
 #else
 # define libc_feholdexcept_setround_ctx	libc_feholdexcept_setround_387_ctx
 # define libc_feupdateenv_ctx		libc_feupdateenv_387_ctx