NLS: update handling of Unicode

This patch (as1239) updates the kernel's treatment of Unicode.  The
character-set conversion routines are well behind the current state of
the Unicode specification: They don't recognize the existence of code
points beyond plane 0 or of surrogate pairs in the UTF-16 encoding.

The old wchar_t 16-bit type is retained because it's still used in
lots of places.  This shouldn't cause any new problems; if a
conversion now results in an invalid 16-bit code then before it must
have yielded an undefined code.

Difficult-to-read names like "utf_mbstowcs" are replaced with more
transparent names like "utf8s_to_utf16s" and the ordering of the
parameters is rationalized (buffer lengths come immediate after the
pointers they refer to, and the inputs precede the outputs).
Fortunately the low-level conversion routines are used in only a few
places; the interfaces to the higher-level uni2char and char2uni
methods have been left unchanged.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

fs/fat/dir.c

@@ -22,6 +22,19 @@
 #include <asm/uaccess.h>
 #include "fat.h"
 
+/*
+ * Maximum buffer size of short name.
+ * [(MSDOS_NAME + '.') * max one char + nul]
+ * For msdos style, ['.' (hidden) + MSDOS_NAME + '.' + nul]
+ */
+#define FAT_MAX_SHORT_SIZE	((MSDOS_NAME + 1) * NLS_MAX_CHARSET_SIZE + 1)
+/*
+ * Maximum buffer size of unicode chars from slots.
+ * [(max longname slots * 13 (size in a slot) + nul) * sizeof(wchar_t)]
+ */
+#define FAT_MAX_UNI_CHARS	((MSDOS_SLOTS - 1) * 13 + 1)
+#define FAT_MAX_UNI_SIZE	(FAT_MAX_UNI_CHARS * sizeof(wchar_t))
+
 static inline loff_t fat_make_i_pos(struct super_block *sb,
 				    struct buffer_head *bh,
 				    struct msdos_dir_entry *de)
@@ -171,7 +184,8 @@ static inline int fat_uni_to_x8(struct msdos_sb_info *sbi, const wchar_t *uni,
 				unsigned char *buf, int size)
 {
 	if (sbi->options.utf8)
-		return utf8_wcstombs(buf, uni, size);
+		return utf16s_to_utf8s(uni, FAT_MAX_UNI_CHARS,
+				UTF16_HOST_ENDIAN, buf, size);
 	else
 		return uni16_to_x8(buf, uni, size, sbi->options.unicode_xlate,
 				   sbi->nls_io);
@@ -324,19 +338,6 @@ parse_long:
 	return 0;
 }
 
-/*
- * Maximum buffer size of short name.
- * [(MSDOS_NAME + '.') * max one char + nul]
- * For msdos style, ['.' (hidden) + MSDOS_NAME + '.' + nul]
- */
-#define FAT_MAX_SHORT_SIZE	((MSDOS_NAME + 1) * NLS_MAX_CHARSET_SIZE + 1)
-/*
- * Maximum buffer size of unicode chars from slots.
- * [(max longname slots * 13 (size in a slot) + nul) * sizeof(wchar_t)]
- */
-#define FAT_MAX_UNI_CHARS	((MSDOS_SLOTS - 1) * 13 + 1)
-#define FAT_MAX_UNI_SIZE	(FAT_MAX_UNI_CHARS * sizeof(wchar_t))
-
 /*
  * Return values: negative -> error, 0 -> not found, positive -> found,
  * value is the total amount of slots, including the shortname entry.

fs/fat/namei_vfat.c

@@ -502,11 +502,11 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname,
 	if (utf8) {
 		int name_len = strlen(name);
 
-		*outlen = utf8_mbstowcs((wchar_t *)outname, name, PATH_MAX);
+		*outlen = utf8s_to_utf16s(name, PATH_MAX, (wchar_t *) outname);
 
 		/*
 		 * We stripped '.'s before and set len appropriately,
-		 * but utf8_mbstowcs doesn't care about len
+		 * but utf8s_to_utf16s doesn't care about len
 		 */
 		*outlen -= (name_len - len);