Commit fd3ba42c authored by Frediano Ziglio's avatar Frediano Ziglio Committed by Steve French
Browse files

Convert properly UTF-8 to UTF-16 



wchar_t is currently 16bit so converting a utf8 encoded characters not
in plane 0 (>= 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: default avatarFrediano Ziglio <frediano.ziglio@citrix.com>
Acked-by: default avatarJeff Layton <jlayton@redhat.com>
Signed-off-by: default avatarSteve French <smfrench@gmail.com>
parent b7a10626

fs/cifs/cifs_unicode.c

+22 −0
Original line number Diff line number Diff line
@@ -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;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE