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

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

(cherry picked from commit f496b28e61d0342f579bf794c71b80e9c7d0b1b5)

diff --git a/ChangeLog b/ChangeLog
index a642c37b63ca81839d25e3618007e336df1927c6..8c614045a4b504b1c072756abcf149911f47cf28 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,25 @@
+2018-06-21  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.
+
 2018-07-03  Florian Weimer  <fweimer@redhat.com>
 
        [BZ #23363]

diff --git a/NEWS b/NEWS
index 7b74fc79d5e64624811f1bf82117e77964e3069b..2e7e7837ac77eeba947536eeee76234c8ae276c1 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -79,6 +79,7 @@ The following bugs are resolved with this release:
   [23171] Fix parameter type in C++ version of iseqsig
   [23196] __mempcpy_avx512_no_vzeroupper mishandles large copies
   [23236] Harden function pointers in _IO_str_fields
+  [23253] Set 387 and SSE2 rounding mode for tgamma on i386
   [23259] Unsubstituted ${ORIGIN} remains in DT_NEEDED for AT_SECURE
   [23264] libc: posix_spawnp wrongly executes ENOEXEC in non compat mode
   [23313] libio: Disable vtable validation in case of interposition

diff --git a/sysdeps/generic/math_private.h b/sysdeps/generic/math_private.h
index e4b9d8697f2129095cee68773bc620cb239754ef..cff76149d6155f890713cc383afdab3e7b48e159 100644 (file)
--- a/sysdeps/generic/math_private.h
+++ b/sysdeps/generic/math_private.h
@@ -514,33 +514,6 @@ 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
@@ -548,7 +521,7 @@ 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;
 
@@ -562,7 +535,7 @@ 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))
@@ -570,7 +543,7 @@ 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.  */
@@ -582,12 +555,45 @@ 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 a1500454e5a977415b8bd120326f3db104d18df2..9c7078e33ce2228ea3d9957ae3b682cdfa2d12be 100644 (file)
--- 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 ($(subdir),math)
+# These functions change the rounding mode internally and need to
+# update both the SSE2 rounding mode and the 387 rounding mode.  See
+# the handling of MATH_SET_BOTH_ROUNDING_MODES in
+# sysdeps/i386/fpu/fenv_private.h.
+CFLAGS-e_gamma_r.c += -DMATH_SET_BOTH_ROUNDING_MODES
+endif
+
 ifeq ($(subdir),string)
 sysdep_routines += cacheinfo
 endif

diff --git a/sysdeps/i386/fpu/fenv_private.h b/sysdeps/i386/fpu/fenv_private.h
index 38fd0b92b55b71c1f0498604b7a888917edb2baf..03177bb1ed395d3b00a2f9b90b5b371d5986c883 100644 (file)
--- a/sysdeps/i386/fpu/fenv_private.h
+++ b/sysdeps/i386/fpu/fenv_private.h
@@ -491,11 +491,19 @@ 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