Convert properly UTF-8 to UTF-16

Frediano Ziglio · smfrench · commit fd3ba42c76d3 · 2012-10-07T20:04:53.000-05:00
wchar_t is currently 16bit so converting a utf8 encoded characters not
in plane 0 (&gt;= 0x10000) to wchar_t (that is calling char2uni) lead to a
-EINVAL return. This patch detect utf8 in cifs_strtoUTF16 and add special
code calling utf8s_to_utf16s.

Signed-off-by: Frediano Ziglio &lt;frediano.ziglio@citrix.com&gt;
Acked-by: Jeff Layton &lt;jlayton@redhat.com&gt;
Signed-off-by: Steve French &lt;smfrench@gmail.com&gt;
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
@@ -203,6 +203,27 @@ cifs_strtoUTF16(__le16 *to, const char *from, int len,
 	int i;
 	wchar_t wchar_to; /* needed to quiet sparse */
 
+	/* special case for utf8 to handle no plane0 chars */
+	if (!strcmp(codepage->charset, "utf8")) {
+		/*
+		 * convert utf8 -> utf16, we assume we have enough space
+		 * as caller should have assumed conversion does not overflow
+		 * in destination len is length in wchar_t units (16bits)
+		 */
+		i  = utf8s_to_utf16s(from, len, UTF16_LITTLE_ENDIAN,
+				       (wchar_t *) to, len);
+
+		/* if success terminate and exit */
+		if (i >= 0)
+			goto success;
+		/*
+		 * if fails fall back to UCS encoding as this
+		 * function should not return negative values
+		 * currently can fail only if source contains
+		 * invalid encoded characters
+		 */
+	}
+
 	for (i = 0; len && *from; i++, from += charlen, len -= charlen) {
 		charlen = codepage->char2uni(from, len, &wchar_to);
 		if (charlen < 1) {
@@ -215,6 +236,7 @@ cifs_strtoUTF16(__le16 *to, const char *from, int len,
 		put_unaligned_le16(wchar_to, &to[i]);
 	}
 
+success:
 	put_unaligned_le16(0, &to[i]);
 	return i;
 }
