Skip to contentSkip to conversation

shared/util: Refactor code from strisutf8 and strtoutf8

PATCH In review Frédéric Danis 3 participants 4 messages Jul 9, 2025 Bluetooth drivers

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 shared/util: Refactor code from strisutf8 and strtoutf8

Move duplicate code to static validateutf8() and fix boundary access on multi-byte character check.

---
 src/shared/util.c | 56 +++++++++++++++--------------------------------
 1 file changed, 18 insertions(+), 38 deletions(-)
src/shared/util.c +18 -38
index 4780f26b6..36c06188f 100644
@@ -1909,7 +1909,7 @@ char *strstrip(char *str)
 	return str;
 }
 
-bool strisutf8(const char *str, size_t len)
+static bool validateutf8(const char *str, size_t len, size_t *invalid_index)
 {
 	size_t i = 0;
 
@@ -1928,17 +1928,23 @@ bool strisutf8(const char *str, size_t len)
 			size = 3;
 		else if ((c & 0xF8) == 0xF0)
 			size = 4;
-		else
+		else {
 			/* Invalid UTF-8 sequence */
+			if (invalid_index)
+				*invalid_index = i;
 			return false;
+		}
 
 		/* Check the following bytes to ensure they have the correct
 		 * format.
 		 */
 		for (size_t j = 1; j < size; ++j) {
-			if (i + j > len || (str[i + j] & 0xC0) != 0x80)
+			if (i + j >= len || (str[i + j] & 0xC0) != 0x80) {
 				/* Invalid UTF-8 sequence */
+				if (invalid_index)
+					*invalid_index = i;
 				return false;
+			}
 		}
 
 		/* Move to the next character */
@@ -1948,6 +1954,11 @@ bool strisutf8(const char *str, size_t len)
 	return true;
 }
 
+bool strisutf8(const char *str, size_t len)
+{
+	return validateutf8(str, len, NULL);
+}
+
 bool argsisutf8(int argc, char *argv[])
 {
 	for (int i = 0; i < argc; i++) {
@@ -1962,42 +1973,11 @@ bool argsisutf8(int argc, char *argv[])
 
 char *strtoutf8(char *str, size_t len)
 {
-	size_t i = 0;
-
-	while (i < len) {
-		unsigned char c = str[i];
-		size_t size = 0;
-
-		/* Check the first byte to determine the number of bytes in the
-		 * UTF-8 character.
-		 */
-		if ((c & 0x80) == 0x00)
-			size = 1;
-		else if ((c & 0xE0) == 0xC0)
-			size = 2;
-		else if ((c & 0xF0) == 0xE0)
-			size = 3;
-		else if ((c & 0xF8) == 0xF0)
-			size = 4;
-		else
-			/* Invalid UTF-8 sequence */
-			goto done;
-
-		/* Check the following bytes to ensure they have the correct
-		 * format.
-		 */
-		for (size_t j = 1; j < size; ++j) {
-			if (i + j > len || (str[i + j] & 0xC0) != 0x80)
-				/* Invalid UTF-8 sequence */
-				goto done;
-		}
+	size_t invalid_index = 0;
 
-		/* Move to the next character */
-		i += size;
-	}
+	if (!validateutf8(str, len, &invalid_index))
+		/* Truncate to the longest valid UTF-8 string */
+		memset(str + invalid_index, 0, len - invalid_index);
 
-done:
-	/* Truncate to the longest valid UTF-8 string */
-	memset(str + i, 0, len - i);
 	return str;
 }
Signature · 1 line
2.43.0
#1 lore raw

This is automated email and please do not reply to this email!

Dear submitter,

Thank you for submitting the patches to the linux bluetooth mailing list. This is a CI test results with your patch series:
PW Link:https://patchwork.kernel.org/project/bluetooth/list/?series=980429

---Test result---

Test Summary:

CheckPatch                    PENDING   0.36 seconds
GitLint                       PENDING   0.55 seconds
BuildEll                      PASS      20.07 seconds
BluezMake                     PASS      2575.82 seconds
MakeCheck                     PASS      20.22 seconds
MakeDistcheck                 PASS      182.18 seconds
CheckValgrind                 PASS      233.93 seconds
CheckSmatch                   PASS      302.45 seconds
bluezmakeextell               PASS      126.73 seconds
IncrementalBuild              PENDING   0.26 seconds
ScanBuild                     PASS      899.39 seconds

Details
##############################
Test: CheckPatch - PENDING
Desc: Run checkpatch.pl script
Output:

##############################
Test: GitLint - PENDING
Desc: Run gitlint
Output:

##############################
Test: IncrementalBuild - PENDING
Desc: Incremental build with the patches in the series Output:

---
Regards,
Linux Bluetooth

#2 lore raw
In reply to Frédéric Danis

Hi Frédéric,

Quoted 106 lines · Frédéric Danis

Move duplicate code to static validateutf8() and fix boundary access on multi-byte character check.

---
 src/shared/util.c | 56 +++++++++++++++--------------------------------
 1 file changed, 18 insertions(+), 38 deletions(-)
src/shared/util.c +18 -39
index 4780f26b6..36c06188f 100644
@@ -1909,7 +1909,7 @@ char *strstrip(char *str)
        return str;
 }
 
-bool strisutf8(const char *str, size_t len)
+static bool validateutf8(const char *str, size_t len, size_t *invalid_index)
 {
        size_t i = 0;
 
@@ -1928,17 +1928,23 @@ bool strisutf8(const char *str, size_t len)
                        size = 3;
                else if ((c & 0xF8) == 0xF0)
                        size = 4;
-               else
+               else {
                        /* Invalid UTF-8 sequence */
+                       if (invalid_index)
+                               *invalid_index = i;
                        return false;
+               }
 
                /* Check the following bytes to ensure they have the correct
                 * format.
                 */
                for (size_t j = 1; j < size; ++j) {
-                       if (i + j > len || (str[i + j] & 0xC0) != 0x80)
+                       if (i + j >= len || (str[i + j] & 0xC0) != 0x80) {
                                /* Invalid UTF-8 sequence */
+                               if (invalid_index)
+                                       *invalid_index = i;
                                return false;
+                       }
                }
 
                /* Move to the next character */
@@ -1948,6 +1954,11 @@ bool strisutf8(const char *str, size_t len)
        return true;
 }
 
+bool strisutf8(const char *str, size_t len)
+{
+       return validateutf8(str, len, NULL);
+}
+
 bool argsisutf8(int argc, char *argv[])
 {
        for (int i = 0; i < argc; i++) {
@@ -1962,42 +1973,11 @@ bool argsisutf8(int argc, char *argv[])
 
 char *strtoutf8(char *str, size_t len)
 {
-       size_t i = 0;
-
-       while (i < len) {
-               unsigned char c = str[i];
-               size_t size = 0;
-
-               /* Check the first byte to determine the number of bytes in the
-                * UTF-8 character.
-                */
-               if ((c & 0x80) == 0x00)
-                       size = 1;
-               else if ((c & 0xE0) == 0xC0)
-                       size = 2;
-               else if ((c & 0xF0) == 0xE0)
-                       size = 3;
-               else if ((c & 0xF8) == 0xF0)
-                       size = 4;
-               else
-                       /* Invalid UTF-8 sequence */
-                       goto done;
-
-               /* Check the following bytes to ensure they have the correct
-                * format.
-                */
-               for (size_t j = 1; j < size; ++j) {
-                       if (i + j > len || (str[i + j] & 0xC0) != 0x80)
-                               /* Invalid UTF-8 sequence */
-                               goto done;
-               }
+       size_t invalid_index = 0;
 
-               /* Move to the next character */
-               i += size;
-       }
+       if (!validateutf8(str, len, &invalid_index))
+               /* Truncate to the longest valid UTF-8 string */
+               memset(str + invalid_index, 0, len - invalid_index);
 
-done:
-       /* Truncate to the longest valid UTF-8 string */
-       memset(str + i, 0, len - i);
        return str;
 }
--
Quoted 2 lines

2.43.0

I did something similar yesterday:

https://patchwork.kernel.org/project/bluetooth/patch/[email protected]/

Let me know if you have any comments.

Signature · 1 line
Luiz Augusto von Dentz
#3 lore raw

Hi Luiz,

Quoted 113 lines · Luiz Augusto von Dentz

Hi Frédéric,

Quoted 105 lines · Frédéric Danis

Move duplicate code to static validateutf8() and fix boundary access on multi-byte character check.

---
  src/shared/util.c | 56 +++++++++++++++--------------------------------
  1 file changed, 18 insertions(+), 38 deletions(-)
src/shared/util.c +18 -39
index 4780f26b6..36c06188f 100644
@@ -1909,7 +1909,7 @@ char *strstrip(char *str)
         return str;
  }
 
-bool strisutf8(const char *str, size_t len)
+static bool validateutf8(const char *str, size_t len, size_t *invalid_index)
  {
         size_t i = 0;
 
@@ -1928,17 +1928,23 @@ bool strisutf8(const char *str, size_t len)
                         size = 3;
                 else if ((c & 0xF8) == 0xF0)
                         size = 4;
-               else
+               else {
                         /* Invalid UTF-8 sequence */
+                       if (invalid_index)
+                               *invalid_index = i;
                         return false;
+               }
 
                 /* Check the following bytes to ensure they have the correct
                  * format.
                  */
                 for (size_t j = 1; j < size; ++j) {
-                       if (i + j > len || (str[i + j] & 0xC0) != 0x80)
+                       if (i + j >= len || (str[i + j] & 0xC0) != 0x80) {
                                 /* Invalid UTF-8 sequence */
+                               if (invalid_index)
+                                       *invalid_index = i;
                                 return false;
+                       }
                 }
 
                 /* Move to the next character */
@@ -1948,6 +1954,11 @@ bool strisutf8(const char *str, size_t len)
         return true;
  }
 
+bool strisutf8(const char *str, size_t len)
+{
+       return validateutf8(str, len, NULL);
+}
+
  bool argsisutf8(int argc, char *argv[])
  {
         for (int i = 0; i < argc; i++) {
@@ -1962,42 +1973,11 @@ bool argsisutf8(int argc, char *argv[])
 
  char *strtoutf8(char *str, size_t len)
  {
-       size_t i = 0;
-
-       while (i < len) {
-               unsigned char c = str[i];
-               size_t size = 0;
-
-               /* Check the first byte to determine the number of bytes in the
-                * UTF-8 character.
-                */
-               if ((c & 0x80) == 0x00)
-                       size = 1;
-               else if ((c & 0xE0) == 0xC0)
-                       size = 2;
-               else if ((c & 0xF0) == 0xE0)
-                       size = 3;
-               else if ((c & 0xF8) == 0xF0)
-                       size = 4;
-               else
-                       /* Invalid UTF-8 sequence */
-                       goto done;
-
-               /* Check the following bytes to ensure they have the correct
-                * format.
-                */
-               for (size_t j = 1; j < size; ++j) {
-                       if (i + j > len || (str[i + j] & 0xC0) != 0x80)
-                               /* Invalid UTF-8 sequence */
-                               goto done;
-               }
+       size_t invalid_index = 0;
 
-               /* Move to the next character */
-               i += size;
-       }
+       if (!validateutf8(str, len, &invalid_index))
+               /* Truncate to the longest valid UTF-8 string */
+               memset(str + invalid_index, 0, len - invalid_index);
 
-done:
-       /* Truncate to the longest valid UTF-8 string */
-       memset(str + i, 0, len - i);
         return str;
  }
--
Quoted 2 lines

2.43.0

I did something similar yesterday:

Quoted 3 lines

https://patchwork.kernel.org/project/bluetooth/patch/[email protected]/

Let me know if you have any comments.

Sorry, I missed it, you can discard mine

Signature · 6 lines
Frédéric Danis
Senior Software Engineer

Collabora Ltd.
Platinum Building, St John's Innovation Park, Cambridge CB4 0DS, United Kingdom
Registered in England & Wales, no. 5513718