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: Frediano Ziglio <[email protected]> --- fs/cifs/cifs_unicode.c | 14 ++++++++++++++ 1 files changed, 14 insertions(+), 0 deletions(-) diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 7dab9c0..a798e01 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -203,6 +203,19 @@ cifs_strtoUTF16(__le16 *to, const char *from, int len, int i; wchar_t wchar_to; /* needed to quiet sparse */ + if (!strcmp(codepage->charset, "utf8")) { + i = utf8s_to_utf16s(from, len, UTF16_LITTLE_ENDIAN, + (wchar_t *) to, len); + 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 +228,7 @@ 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; } -- 1.7.5.4
