diff mbox series

tty/vt: UTF-8 parsing update according to RFC 3629, modern Unicode

Message ID 14027090-ca91-45ca-90d4-75456c0f2c76@gmail.com
State New
Headers show
Series tty/vt: UTF-8 parsing update according to RFC 3629, modern Unicode | expand

Commit Message

Roman Žilka Dec. 12, 2023, 3:13 p.m. UTC
vc_translate_unicode() and vc_sanitize_unicode() parse input to the
UTF-8-enabled console, marking invalid byte sequences and producing Unicode
codepoints. The current algorithm follows ancient Unicode and may accept invalid
byte sequences, pass on non-existent codepoints and reject valid sequences.

The patch restores the functions' compliance with modern Unicode (v15.1 + many
previous versions) as well as RFC 3629.
1. Codepoint space is limited to 0x10FFFF.
2. "Noncharacters", such as U+FFFE, U+FFFF, are no longer invalid in Unicode and
   will be accepted. Another option was to complete the set of noncharacters
   (used to be just those two, now there's more) and preserve the rejection
   step. This is indeed what Unicode suggests (v15.1, chap. 23.7) (not
   requires), but most codepoints are !iswprint(), so selecting just the
   noncharacters seemed arbitrary and futile (and unnecessary).

On the side:
3. What remained of vc_sanitize_unicode() is in vc_translate_unicode().
4. Corrected vc_translate_unicode() doc (@rescan).

This is not a security patch. I'm not aware of any present security implications
of the old code.

Signed-off-by: Roman Žilka <roman.zilka@gmail.com>
---
 drivers/tty/vt/vt.c | 36 +++++++-----------------------------
 1 file changed, 7 insertions(+), 29 deletions(-)


base-commit: a39b6ac3781d46ba18193c9dbb2110f31e9bffe9
diff mbox series

Patch

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 156efda7c80d..215e162ec8af 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -2587,23 +2587,11 @@  static inline int vc_translate_ascii(const struct vc_data *vc, int c)
 }
 
 
-/**
- * vc_sanitize_unicode - Replace invalid Unicode code points with U+FFFD
- * @c: the received character, or U+FFFD for invalid sequences.
- */
-static inline int vc_sanitize_unicode(const int c)
-{
-	if ((c >= 0xd800 && c <= 0xdfff) || c == 0xfffe || c == 0xffff)
-		return 0xfffd;
-
-	return c;
-}
-
 /**
  * vc_translate_unicode - Combine UTF-8 into Unicode in @vc_utf_char
  * @vc: virtual console
- * @c: character to translate
- * @rescan: we return true if we need more (continuation) data
+ * @c: UTF-8 byte to translate
+ * @rescan: true => @c wasn't translated here and needs to be re-processed
  *
  * @vc_utf_char is the being-constructed unicode character.
  * @vc_utf_count is the number of continuation bytes still expected to arrive.
@@ -2611,10 +2599,7 @@  static inline int vc_sanitize_unicode(const int c)
  */
 static int vc_translate_unicode(struct vc_data *vc, int c, bool *rescan)
 {
-	static const u32 utf8_length_changes[] = {
-		0x0000007f, 0x000007ff, 0x0000ffff,
-		0x001fffff, 0x03ffffff, 0x7fffffff
-	};
+	static const u32 utf8_length_changes[] = {0x7f, 0x7ff, 0xffff, 0x10ffff};
 
 	/* Continuation byte received */
 	if ((c & 0xc0) == 0x80) {
@@ -2629,12 +2614,12 @@  static int vc_translate_unicode(struct vc_data *vc, int c, bool *rescan)
 
 		/* Got a whole character */
 		c = vc->vc_utf_char;
-		/* Reject overlong sequences */
+		/* Reject overlong sequences and surrogates */
 		if (c <= utf8_length_changes[vc->vc_npar - 1] ||
-				c > utf8_length_changes[vc->vc_npar])
+				c > utf8_length_changes[vc->vc_npar] ||
+				(c & 0xfff800) == 0x00d800)
 			return 0xfffd;
-
-		return vc_sanitize_unicode(c);
+		return c;
 	}
 
 	/* Single ASCII byte or first byte of a sequence received */
@@ -2660,14 +2645,7 @@  static int vc_translate_unicode(struct vc_data *vc, int c, bool *rescan)
 	} else if ((c & 0xf8) == 0xf0) {
 		vc->vc_utf_count = 3;
 		vc->vc_utf_char = (c & 0x07);
-	} else if ((c & 0xfc) == 0xf8) {
-		vc->vc_utf_count = 4;
-		vc->vc_utf_char = (c & 0x03);
-	} else if ((c & 0xfe) == 0xfc) {
-		vc->vc_utf_count = 5;
-		vc->vc_utf_char = (c & 0x01);
 	} else {
-		/* 254 and 255 are invalid */
 		return 0xfffd;
 	}