diff mbox

[1/8] x86: Add macros to implement ifunce selection in C

Message ID 20170602194258.GA21335@lucon.org
State New
Headers show

Commit Message

H.J. Lu June 2, 2017, 7:42 p.m. UTC
Should they go into include/libc-symbols.h so that they are available
everywhere?

H.J.
---
These macros are used to implement ifunc selection in C.  To implement
an ifunc function, foo, which returns the address of __foo_sse2 or
__foo_avx2:

   __foo_avx2:

   #define foo __redirect_foo
   #define __foo __redirect___foo
   #include <foo.h>
   #undef foo
   #undef __foo
   #define SYMBOL_NAME foo
   #include <init-arch.h>

   extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden;
   extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden;

   static inline void *
   foo_selector (void)
   {
     if (use AVX2)
      return OPTIMIZE (avx2);

     return OPTIMIZE (sse2);
   }

   libc_ifunc_redirected (__redirect_foo, foo, foo_selector ());

2017-06-02  Adhemerval Zanella  <adhemerval.zanella@linaro.org>
	    H.J. Lu  <hongjiu.lu@intel.com>

	* sysdeps/x86/init-arch.h (PASTER1): New.
	(EVALUATOR1): Likewise.
	(PASTER2): Likewise.
	(EVALUATOR2): Likewise.
	(REDIRECT_NAME): Likewise.
	(OPTIMIZE): Likewise.
	(IFUNC_SELECTOR): Likewise.
---
 sysdeps/x86/init-arch.h | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

Comments

H.J. Lu June 5, 2017, 2:25 p.m. UTC | #1
On Fri, Jun 2, 2017 at 12:42 PM, H.J. Lu <hongjiu.lu@intel.com> wrote:
> Should they go into include/libc-symbols.h so that they are available
> everywhere?
>
> H.J.
> ---
> These macros are used to implement ifunc selection in C.  To implement
> an ifunc function, foo, which returns the address of __foo_sse2 or
> __foo_avx2:
>
>    __foo_avx2:
>
>    #define foo __redirect_foo
>    #define __foo __redirect___foo
>    #include <foo.h>
>    #undef foo
>    #undef __foo
>    #define SYMBOL_NAME foo
>    #include <init-arch.h>
>
>    extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden;
>    extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden;
>
>    static inline void *
>    foo_selector (void)
>    {
>      if (use AVX2)
>       return OPTIMIZE (avx2);
>
>      return OPTIMIZE (sse2);
>    }
>
>    libc_ifunc_redirected (__redirect_foo, foo, foo_selector ());
>
> 2017-06-02  Adhemerval Zanella  <adhemerval.zanella@linaro.org>
>             H.J. Lu  <hongjiu.lu@intel.com>
>
>         * sysdeps/x86/init-arch.h (PASTER1): New.
>         (EVALUATOR1): Likewise.
>         (PASTER2): Likewise.
>         (EVALUATOR2): Likewise.
>         (REDIRECT_NAME): Likewise.
>         (OPTIMIZE): Likewise.
>         (IFUNC_SELECTOR): Likewise.
> ---
>  sysdeps/x86/init-arch.h | 40 ++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 40 insertions(+)
>
> diff --git a/sysdeps/x86/init-arch.h b/sysdeps/x86/init-arch.h
> index 6cbc16b..15d3f09 100644
> --- a/sysdeps/x86/init-arch.h
> +++ b/sysdeps/x86/init-arch.h
> @@ -21,6 +21,46 @@
>  # include <ldsodefs.h>
>  #endif
>
> +/* These macros are used to implement ifunc selection in C.  To implement
> +   an ifunc function, foo, which returns the address of __foo_sse2 or
> +   __foo_avx2:
> +
> +   #define foo __redirect_foo
> +   #define __foo __redirect___foo
> +   #include <foo.h>
> +   #undef foo
> +   #undef __foo
> +   #define SYMBOL_NAME foo
> +   #include <init-arch.h>
> +
> +   extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden;
> +   extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden;
> +
> +   static inline void *
> +   foo_selector (void)
> +   {
> +     if (use AVX2)
> +      return OPTIMIZE (avx2);
> +
> +     return OPTIMIZE (sse2);
> +   }
> +
> +   libc_ifunc_redirected (__redirect_foo, foo, foo_selector ());
> +
> +*/
> +
> +#define PASTER1(x,y)   x##_##y
> +#define EVALUATOR1(x,y)        PASTER1 (x,y)
> +#define PASTER2(x,y)   __##x##_##y
> +#define EVALUATOR2(x,y)        PASTER2 (x,y)
> +
> +/* Basically set '__redirect_<symbol>' to use as type definition,
> +   '__<symbol>_<variant>' as the optimized implementation and
> +   '<symbol>_ifunc_selector' as the IFUNC selector.  */
> +#define REDIRECT_NAME  EVALUATOR1 (__redirect, SYMBOL_NAME)
> +#define OPTIMIZE(name) EVALUATOR2 (SYMBOL_NAME, name)
> +#define IFUNC_SELECTOR EVALUATOR1 (SYMBOL_NAME, ifunc_selector)
> +
>  #ifndef __x86_64__
>  /* Due to the reordering and the other nifty extensions in i686, it is
>     not really good to use heavily i586 optimized code on an i686.  It's
> --
> 2.9.4
>

I will check it in today to unblock my AVX2 patches.
diff mbox

Patch

diff --git a/sysdeps/x86/init-arch.h b/sysdeps/x86/init-arch.h
index 6cbc16b..15d3f09 100644
--- a/sysdeps/x86/init-arch.h
+++ b/sysdeps/x86/init-arch.h
@@ -21,6 +21,46 @@ 
 # include <ldsodefs.h>
 #endif
 
+/* These macros are used to implement ifunc selection in C.  To implement
+   an ifunc function, foo, which returns the address of __foo_sse2 or
+   __foo_avx2:
+
+   #define foo __redirect_foo
+   #define __foo __redirect___foo
+   #include <foo.h>
+   #undef foo
+   #undef __foo
+   #define SYMBOL_NAME foo
+   #include <init-arch.h>
+
+   extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden;
+   extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden;
+
+   static inline void *
+   foo_selector (void)
+   {
+     if (use AVX2)
+      return OPTIMIZE (avx2);
+
+     return OPTIMIZE (sse2);
+   }
+
+   libc_ifunc_redirected (__redirect_foo, foo, foo_selector ());
+
+*/
+
+#define PASTER1(x,y)	x##_##y
+#define EVALUATOR1(x,y)	PASTER1 (x,y)
+#define PASTER2(x,y)	__##x##_##y
+#define EVALUATOR2(x,y)	PASTER2 (x,y)
+
+/* Basically set '__redirect_<symbol>' to use as type definition,
+   '__<symbol>_<variant>' as the optimized implementation and
+   '<symbol>_ifunc_selector' as the IFUNC selector.  */
+#define REDIRECT_NAME	EVALUATOR1 (__redirect, SYMBOL_NAME)
+#define OPTIMIZE(name)	EVALUATOR2 (SYMBOL_NAME, name)
+#define IFUNC_SELECTOR	EVALUATOR1 (SYMBOL_NAME, ifunc_selector)
+
 #ifndef __x86_64__
 /* Due to the reordering and the other nifty extensions in i686, it is
    not really good to use heavily i586 optimized code on an i686.  It's