Skip to contentSkip to conversation

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

PATCH Superseded Roman Žilka 2 participants 7 messages Dec 12, 2023 – Jan 9, 2024 TTY layer and serial drivers

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 tty/vt: UTF-8 parsing update according to RFC 3629, modern Unicode

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.

---
 drivers/tty/vt/vt.c | 36 +++++++-----------------------------
 1 file changed, 7 insertions(+), 29 deletions(-)
drivers/tty/vt/vt.c +7 -29
index 156efda7c80d..215e162ec8af 100644
@@ -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;
 	}
 

base-commit: a39b6ac3781d46ba18193c9dbb2110f31e9bffe9

Signature · 1 line
2.41.0
maintainer
#1 lore raw
Quoted 102 lines · Roman Žilka

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.

---
 drivers/tty/vt/vt.c | 36 +++++++-----------------------------
 1 file changed, 7 insertions(+), 29 deletions(-)
drivers/tty/vt/vt.c +7 -29
index 156efda7c80d..215e162ec8af 100644
@@ -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;
 	}
 
Quoted 5 lines

base-commit: a39b6ac3781d46ba18193c9dbb2110f31e9bffe9

Signature · 1 line
2.41.0

Hi,

This is the friendly patch-bot of Greg Kroah-Hartman. You have sent him a patch that has triggered this response. He used to manually respond to these common problems, but in order to save his sanity (he kept writing the same thing over and over, yet to different people), I was created. Hopefully you will not take offence and will fix the problem in your patch and resubmit it so that it can be accepted into the Linux kernel tree.

You are receiving this message because of the following common error(s) as indicated below:

- Your patch did many different things all at once, making it difficult to review. All Linux kernel patches need to only do one thing at a time. If you need to do multiple things (such as clean up all coding style issues in a file/driver), do it in a sequence of patches, each one doing only one thing. This will make it easier to review the patches to ensure that they are correct, and to help alleviate any merge issues that larger patches can cause.

- This looks like a new version of a previously submitted patch, but you did not list below the --- line any changes from the previous version. Please read the section entitled "The canonical patch format" in the kernel file, Documentation/process/submitting-patches.rst for what needs to be done here to properly describe this.

If you wish to discuss this problem further, or you have questions about how to resolve this issue, please feel free to respond to this email and Greg will reply once he has dug out from the pending patches received from other developers.

thanks,

greg k-h's patch email bot

#2 lore raw

PATCH v2 1/1 tty/vt: UTF-8 parsing update according to RFC 3629, modern Unicode

From: Roman Žilka <[email protected]>

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.

---
v2: A more elaborate commit msg, e-mail formatting corrections.

 drivers/tty/vt/vt.c | 36 +++++++-----------------------------
 1 file changed, 7 insertions(+), 29 deletions(-)
drivers/tty/vt/vt.c +7 -29
index 156efda7c80d..215e162ec8af 100644
@@ -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;
 	}
 

base-commit: a39b6ac3781d46ba18193c9dbb2110f31e9bffe9

Signature · 1 line
2.41.0
#3 lore raw

PATCH v3 1/1 tty/vt: UTF-8 parsing update according to RFC 3629, modern Unicode

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 [1]
+ many previous versions) as well as RFC 3629 [2].
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. Corrected/improved the doc of the two functions (esp. @rescan).

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

[1] https://www.unicode.org/versions/Unicode15.1.0
[2] https://datatracker.ietf.org/doc/html/rfc3629

---

v2: A more elaborate commit msg, e-mail formatting corrections.
v3: Shortened patch as requested. The gist of it is unchanged. Added links
to commit msg. Changed base to current tty-next.

 drivers/tty/vt/vt.c | 20 +++++---------------
 1 file changed, 5 insertions(+), 15 deletions(-)
drivers/tty/vt/vt.c +5 -15
index 156efda7c80d..373f94f55ff2 100644
@@ -2589,11 +2589,11 @@ 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.
+ * @c: the received code point
  */
 static inline int vc_sanitize_unicode(const int c)
 {
-	if ((c >= 0xd800 && c <= 0xdfff) || c == 0xfffe || c == 0xffff)
+	if (c >= 0xd800 && c <= 0xdfff)
 		return 0xfffd;
 
 	return c;
@@ -2602,8 +2602,8 @@ static inline int vc_sanitize_unicode(const int 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 +2611,7 @@ 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) {
@@ -2660,14 +2657,7 @@ 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;
 	}
 

base-commit: e045e18dbf3eaac32cdeb2799a5ec84fa694636c

Signature · 1 line
2.41.0
maintainer
#4 lore raw
Quoted 9 lines · Roman Žilka

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 [1]
+ many previous versions) as well as RFC 3629 [2].
1. Codepoint space is limited to 0x10FFFF.

Wait, why? And shouldn't this be an individual patch on it's own? What is wrong with the checking we currently have.

Quoted 2 lines

2. "Noncharacters", such as U+FFFE, U+FFFF, are no longer invalid in Unicode and will be accepted.

Accepted when?

Quoted 5 lines

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).

What is this change going to break with existing systems that were thinking these were invalid characters?

Quoted 2 lines

On the side:
3. Corrected/improved the doc of the two functions (esp. @rescan).

Again, a separate commit. When you have to list the changes out, that is a huge hint it needs to be broken up into smaller pieces.

thanks,

greg k-h

#5 lore raw
Quoted 7 lines · Greg KH
Quoted 6 lines · Roman Žilka

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.

Quoted 6 lines
Quoted 3 lines

The patch restores the functions' compliance with modern Unicode (v15.1 [1]
+ many previous versions) as well as RFC 3629 [2].
1. Codepoint space is limited to 0x10FFFF.

Wait, why? And shouldn't this be an individual patch on it's own? What is wrong with the checking we currently have.

This is the main point of this patch. The codepoint space got shortened in Unicode at some point between v3.0 (1999) and v4.0 (2003). The reason why is expressed by the first sentence in the commit msg. The affected functions validate input coming into the subsystem from the user, which makes it a red flag that they do not do so correctly (i.e., according to a generally accepted standard). As they stand, these functions are a potential source of compatibility and security issues. The may not be a bomb, they may be a time bomb.

Note how very old the old parsing algorithm is. I made a quick grep of the kernel source for tell-tale signs of utf8 parsing to see if there's any other place where the old algorithm is still being used. I found none, and I found these which do the 0x10ffff limiting (I didn't check the "noncharacters" handling):

fs/unicode/mkutf8data.c
fs/unicode/utf8-norm.c
fs/udf/unicode.c
fs/nls/nls_base.c (has many users outside fs/)
drivers/tty/vt/keyboard.c

I didn't check, but I have no doubt that Perl implements Unicode correctly as well.

Quoted 4 lines
Quoted 2 lines

2. "Noncharacters", such as U+FFFE, U+FFFF, are no longer invalid in Unicode and will be accepted.

Accepted when?

Currently, the two affected functions mark these codepoints as invalid by substituting them with the placeholder U+FFFD. After the patch, U+FFFE and U+FFFF are treated as ordinary valid codepoints.

Let me point out that I've never seen a utf8 validator where "noncharacters" were treated in a special way. Of course, there're only so many validator implementations that I have seen. Checking for iswprint()-ability is common, but that's something very different. IMHO, the validator in vt.c is not a place to pay any special regard to "noncharacters".

Quoted 8 lines
Quoted 5 lines

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).

What is this change going to break with existing systems that were thinking these were invalid characters?

This is mostly answered above. I don't work with the kernel in a developer capacity. I found this parsing error by accident while researching some CONFIG options. I'm not qualified to say that this patch won't break anything and it would take me an abhorrent amount of time to verify that to a reasonable degree. I don't write code for kbd or other console-related userspace tools either. I ran the patched kernel for a while, played around with fonts and various TUI utilities. I found no issues. The red flag, which I talked about earlier, was _the_ reason I submitted my patch.

Quoted 5 lines
Quoted 2 lines

On the side:
3. Corrected/improved the doc of the two functions (esp. @rescan).

Again, a separate commit. When you have to list the changes out, that is a huge hint it needs to be broken up into smaller pieces.

Ok, patch v4 coming up with this removed and I'll take care of it in a subsequent submission. That'll be one truly trivial commit, though.

-rz

#6 lore raw

PATCH v4 1/1 tty/vt: UTF-8 parsing update according to RFC 3629, modern Unicode

In reply to Greg KH

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 [1]
+ many previous versions) as well as RFC 3629 [2].
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 ([1] chap. 23.7) (not requires), but most codepoints are !iswprint(), so selecting just the noncharacters seemed arbitrary and futile (and unnecessary).

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

[1] https://www.unicode.org/versions/Unicode15.1.0
[2] https://datatracker.ietf.org/doc/html/rfc3629

---

v2: A more elaborate commit msg, e-mail formatting corrections.
v3: Shortened patch as requested. The gist of it is unchanged. Added links
to commit msg. Changed base to current tty-next.
v4: Removed func doc correction as requested. Updated base to current
tty-next.

 drivers/tty/vt/vt.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)
drivers/tty/vt/vt.c +2 -12
index 156efda7c80d..35c2ab8c5280 100644
@@ -2593,7 +2593,7 @@ static inline int vc_translate_ascii(const struct vc_data *vc, int c)
  */
 static inline int vc_sanitize_unicode(const int c)
 {
-	if ((c >= 0xd800 && c <= 0xdfff) || c == 0xfffe || c == 0xffff)
+	if (c >= 0xd800 && c <= 0xdfff)
 		return 0xfffd;
 
 	return c;
@@ -2611,10 +2611,7 @@ 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) {
@@ -2660,14 +2657,7 @@ 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;
 	}
 

base-commit: 0c84bea0cabc4e2b98a3de88eeb4ff798931f056

Signature · 1 line
2.41.0