citrus: Avoid invalid code points.

From the OpenBSD log:
The UTF-8 decoder should not accept byte sequences which decode to unicode
code positions U+D800 to U+DFFF (UTF-16 surrogates), U+FFFE, and U+FFFF.

http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
http://unicode.org/faq/utf_bom.html#utf8-4

Reported by:	Stefan Sperling
Obtained from:	OpenBSD
MFC after:	5 days

1 files changed, 8 insertions, 0 deletions

diff --git a/lib/libc/locale/utf8.c b/lib/libc/locale/utf8.c
index 40f0e17..ef5784a 100644
--- a/lib/libc/locale/utf8.c
+++ b/lib/libc/locale/utf8.c
@@ -203,6 +203,14 @@ _UTF8_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
 		errno = EILSEQ;
 		return ((size_t)-1);
 	}
+	if ((wch >= 0xd800 && wch <= 0xdfff) ||
+	    wch == 0xfffe || wch == 0xffff) {
+		/*
+		 * Malformed input; invalid code points.
+		 */
+		errno = EILSEQ;
+		return ((size_t)-1);
+	}
 	if (pwc != NULL)
 		*pwc = wch;
 	us->want = 0;