wcsmbs: optimize wcscat

This patch rewrites wcscat using wcslen and wcscpy.  This is similar to
the optimization done on strcat by 6e46de42fe.

The strcpy changes are mainly to add the internal alias to avoid PLT
calls.

Checked on x86_64-linux-gnu and a build against the affected
architectures.

	* include/wchar.h (__wcscpy): New prototype.
	* sysdeps/powerpc/powerpc32/power4/multiarch/wcscpy-ppc32.c
	(__wcscpy): Route internal symbol to generic implementation.
	* sysdeps/powerpc/powerpc32/power4/multiarch/wcscpy.c (wcscpy):
	Add internal __wcscpy alias.
	* sysdeps/powerpc/powerpc64/multiarch/wcscpy.c (wcscpy): Likewise.
	* sysdeps/s390/wcscpy.c (wcscpy): Likewise.
	* sysdeps/x86_64/multiarch/wcscpy.c (wcscpy): Likewise.
	* wcsmbs/wcscpy.c (wcscpy): Add
	* sysdeps/x86_64/multiarch/wcscpy-c.c (WCSCPY): Adjust macro to
	use generic implementation.
	* wcsmbs/wcscat.c (wcscat): Rewrite using wcslen and wcscpy.

1 files changed, 1 insertions, 20 deletions

diff --git a/wcsmbs/wcscat.c b/wcsmbs/wcscat.c
index 6a25b20..1a9d667 100644
--- a/wcsmbs/wcscat.c
+++ b/wcsmbs/wcscat.c
@@ -26,26 +26,7 @@
 wchar_t *
 __wcscat (wchar_t *dest, const wchar_t *src)
 {
-  wchar_t *s1 = dest;
-  const wchar_t *s2 = src;
-  wchar_t c;
-
-  /* Find the end of the string.  */
-  do
-    c = *s1++;
-  while (c != L'\0');
-
-  /* Make S1 point before the next character, so we can increment
-     it while memory is read (wins on pipelined cpus).	*/
-  s1 -= 2;
-
-  do
-    {
-      c = *s2++;
-      *++s1 = c;
-    }
-  while (c != L'\0');
-
+  __wcscpy (dest + __wcslen (dest), src);
   return dest;
 }
 #ifndef WCSCAT