Consolidate wctomb/mbtowc calls for POSIX-1.2008

- Remove charset parameter from low level __foo_wctomb/__foo_mbtowc calls.
- Instead, create array of function for ISO and Windows codepages to point
  to function which does not require to evaluate the charset string on
  each call.  Create matching helper functions.  I.e., __iso_wctomb,
  __iso_mbtowc, __cp_wctomb and __cp_mbtowc are functions returning the
  right function pointer now.
- Create __WCTOMB/__MBTOWC macros utilizing per-reent locale and replace
  calls to __wctomb/__mbtowc with calls to __WCTOMB/__MBTOWC.
- Drop global __wctomb/__mbtowc vars.
- Utilize aforementioned changes in Cygwin to get rid of charset in other,
  calling functions and simplify the code.
- In Cygwin restrict global cygheap locale info to the job performed
  by internal_setlocale.  Use UTF-8 instead of ASCII on the fly in
  internal conversion functions.
- In Cygwin dll_entry, make sure to initialize a TLS area with a NULL
  _REENT->_locale pointer.  Add comment to explain why.

Signed-off by: Corinna Vinschen <corinna@vinschen.de>

3 files changed, 64 insertions, 61 deletions

diff --git a/newlib/libc/locale/locale.c b/newlib/libc/locale/locale.c
index eb08dade5..0430f1f53 100644
--- a/newlib/libc/locale/locale.c
+++ b/newlib/libc/locale/locale.c
@@ -459,12 +459,11 @@ loadlocale(struct _reent *p, int category)
      dependent on the cateogry. */
   char *locale = NULL;
   char charset[ENCODING_LEN + 1];
-  unsigned long val;
+  long val = 0;
   char *end, *c = NULL;
   int mbc_max;
-  int (*l_wctomb) (struct _reent *, char *, wchar_t, const char *, mbstate_t *);
-  int (*l_mbtowc) (struct _reent *, wchar_t *, const char *, size_t,
-		   const char *, mbstate_t *);
+  wctomb_p l_wctomb;
+  mbtowc_p l_mbtowc;
   int cjknarrow = 0;
 
   /* Avoid doing everything twice if nothing has changed. */
@@ -674,8 +673,8 @@ restart:
       *c = '\0';
       mbc_max = 1;
 #ifdef _MB_EXTENDED_CHARSETS_ISO
-      l_wctomb = __iso_wctomb;
-      l_mbtowc = __iso_mbtowc;
+      l_wctomb = __iso_wctomb (val);
+      l_mbtowc = __iso_mbtowc (val);
 #else /* !_MB_EXTENDED_CHARSETS_ISO */
       l_wctomb = __ascii_wctomb;
       l_mbtowc = __ascii_mbtowc;
@@ -715,8 +714,8 @@ restart:
 	case 1258:
 	  mbc_max = 1;
 #ifdef _MB_EXTENDED_CHARSETS_WINDOWS
-	  l_wctomb = __cp_wctomb;
-	  l_mbtowc = __cp_mbtowc;
+	  l_wctomb = __cp_wctomb (val);
+	  l_mbtowc = __cp_mbtowc (val);
 #else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
 	  l_wctomb = __ascii_wctomb;
 	  l_mbtowc = __ascii_mbtowc;
@@ -740,15 +739,21 @@ restart:
       if (*c == '-')
 	++c;
       if (*c == 'R' || *c == 'r')
-	strcpy (charset, "CP20866");
+	{
+	  val = 20866;
+	  strcpy (charset, "CP20866");
+	}
       else if (*c == 'U' || *c == 'u')
-	strcpy (charset, "CP21866");
+	{
+	  val = 21866;
+	  strcpy (charset, "CP21866");
+	}
       else
 	FAIL;
       mbc_max = 1;
 #ifdef _MB_EXTENDED_CHARSETS_WINDOWS
-      l_wctomb = __cp_wctomb;
-      l_mbtowc = __cp_mbtowc;
+      l_wctomb = __cp_wctomb (val);
+      l_mbtowc = __cp_mbtowc (val);
 #else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
       l_wctomb = __ascii_wctomb;
       l_mbtowc = __ascii_mbtowc;
@@ -786,11 +791,12 @@ restart:
 	    ++c;
 	  if (strcasecmp (c, "PS"))
 	    FAIL;
+	  val = 101;
 	  strcpy (charset, "CP101");
 	  mbc_max = 1;
 #ifdef _MB_EXTENDED_CHARSETS_WINDOWS
-	  l_wctomb = __cp_wctomb;
-	  l_mbtowc = __cp_mbtowc;
+	  l_wctomb = __cp_wctomb (val);
+	  l_mbtowc = __cp_mbtowc (val);
 #else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
 	  l_wctomb = __ascii_wctomb;
 	  l_mbtowc = __ascii_mbtowc;
@@ -804,11 +810,12 @@ restart:
       /* PT154 */
       if (strcasecmp (charset, "PT154"))
 	FAIL;
+      val = 102;
       strcpy (charset, "CP102");
       mbc_max = 1;
 #ifdef _MB_EXTENDED_CHARSETS_WINDOWS
-      l_wctomb = __cp_wctomb;
-      l_mbtowc = __cp_mbtowc;
+      l_wctomb = __cp_wctomb (val);
+      l_mbtowc = __cp_mbtowc (val);
 #else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
       l_wctomb = __ascii_wctomb;
       l_mbtowc = __ascii_mbtowc;
@@ -826,8 +833,8 @@ restart:
       strcpy (charset, "CP874");
       mbc_max = 1;
 #ifdef _MB_EXTENDED_CHARSETS_WINDOWS
-      l_wctomb = __cp_wctomb;
-      l_mbtowc = __cp_mbtowc;
+      l_wctomb = __cp_wctomb (val);
+      l_mbtowc = __cp_mbtowc (val);
 #else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
       l_wctomb = __ascii_wctomb;
       l_mbtowc = __ascii_mbtowc;
@@ -859,8 +866,8 @@ restart:
 #ifdef __CYGWIN__
       __mb_cur_max = mbc_max;	/* Only for backward compat */
 #endif
-      __wctomb = l_wctomb;
-      __mbtowc = l_mbtowc;
+      __global_locale.wctomb = l_wctomb;
+      __global_locale.mbtowc = l_mbtowc;
       __set_ctype (NULL, charset);
       /* Determine the width for the "CJK Ambiguous Width" category of
          characters. This is used in wcwidth(). Assume single width for
@@ -943,16 +950,6 @@ __get_locale_env(struct _reent *p, int category)
 }
 #endif /* _MB_CAPABLE */
 
-char *
-_DEFUN_VOID(__locale_charset)
-{
-#ifdef __HAVE_LOCALE_INFO__
-  return __get_current_ctype_locale ()->codeset;
-#else
-  return __global_locale.ctype_codeset;
-#endif
-}
-
 int
 _DEFUN_VOID(__locale_mb_cur_max)
 {
@@ -963,36 +960,16 @@ _DEFUN_VOID(__locale_mb_cur_max)
 #endif
 }
 
-char *
-_DEFUN_VOID(__locale_msgcharset)
-{
-#ifdef __HAVE_LOCALE_INFO__
-  return (char *) __get_current_messages_locale ()->codeset;
-#else
-  return (char *) __global_locale.message_codeset;
-#endif
-}
-
-int
-_DEFUN_VOID(__locale_cjk_lang)
-{
-#ifdef __HAVE_LOCALE_INFO__
-  return __get_current_locale ()->cjk_lang;
-#else
-  return __global_locale.cjk_lang;
-#endif
-}
-
 #ifdef __HAVE_LOCALE_INFO__
 char *
 _DEFUN_VOID(__locale_ctype_ptr)
 {
   /* Only check if the current thread/reent has a locale.  ctype_ptr is unused
      in __global_locale, rather the global variable __ctype_ptr__ is used. */
+  extern char *__ctype_ptr__;
   return __get_locale_r (_REENT) ? __get_locale_r (_REENT)->ctype_ptr
 				 : __ctype_ptr__;
 }
-
 #endif
 
 struct lconv *
diff --git a/newlib/libc/locale/nl_langinfo.c b/newlib/libc/locale/nl_langinfo.c
index ce6d8d8c2..46e8b0e92 100644
--- a/newlib/libc/locale/nl_langinfo.c
+++ b/newlib/libc/locale/nl_langinfo.c
@@ -172,8 +172,6 @@ static struct _nl_item_t
 
 #define _REL(BASE) ((int)item-BASE)
 
-extern char *__locale_charset ();
-
 char *
 _DEFUN(nl_langinfo, (item), 
        nl_item item) {
diff --git a/newlib/libc/locale/setlocale.h b/newlib/libc/locale/setlocale.h
index ffb1cf13e..50797db0c 100644
--- a/newlib/libc/locale/setlocale.h
+++ b/newlib/libc/locale/setlocale.h
@@ -159,8 +159,7 @@ typedef __uint32_t LCID;
 struct lc_collate_T
 {
   LCID  lcid;
-  int (*mbtowc) (struct _reent *, wchar_t *, const char *, size_t, const char *,
-		 mbstate_t *);
+  int (*mbtowc) (struct _reent *, wchar_t *, const char *, size_t, mbstate_t *);
   char codeset[ENCODING_LEN + 1];
 };
 extern const struct lc_collate_T _C_collate_locale;
@@ -169,13 +168,12 @@ extern const struct lc_collate_T _C_collate_locale;
 struct _thr_locale_t
 {
   char				 categories[_LC_LAST][ENCODING_LEN + 1];
-  int				(*__wctomb) (struct _reent *, char *, wchar_t,
-					     const char *, mbstate_t *);
-  int				(*__mbtowc) (struct _reent *, wchar_t *,
-					     const char *, size_t, const char *,
-					     mbstate_t *);
-  char				*ctype_ptr; /* Unused in __global_locale */
+  int				(*wctomb) (struct _reent *, char *, wchar_t,
+					   mbstate_t *);
+  int				(*mbtowc) (struct _reent *, wchar_t *,
+					   const char *, size_t, mbstate_t *);
   int				 cjk_lang;
+  char				*ctype_ptr; /* Unused in __global_locale */
 #ifndef __HAVE_LOCALE_INFO__
   char				 mb_cur_max[2];
   char				 ctype_codeset[ENCODING_LEN + 1];
@@ -264,6 +262,36 @@ __get_current_collate_locale (void)
 }
 #endif
 
+_ELIDABLE_INLINE const char *
+__locale_charset (void)
+{
+#ifdef __HAVE_LOCALE_INFO__
+  return __get_current_ctype_locale ()->codeset;
+#else
+  return __global_locale.ctype_codeset;
+#endif
+}
+
+_ELIDABLE_INLINE const char *
+__locale_msgcharset (void)
+{
+#ifdef __HAVE_LOCALE_INFO__
+  return (char *) __get_current_messages_locale ()->codeset;
+#else
+  return (char *) __global_locale.message_codeset;
+#endif
+}
+
+_ELIDABLE_INLINE int
+__locale_cjk_lang (void)
+{
+#ifdef __HAVE_LOCALE_INFO__
+  return __get_current_locale ()->cjk_lang;
+#else
+  return __global_locale.cjk_lang;
+#endif
+}
+
 int __ctype_load_locale (struct _thr_locale_t *, const char *, void *,
 			 const char *, int);
 int __monetary_load_locale (struct _thr_locale_t *, const char *, void *,