lib/ucs2_string: Split out ucs2_as_utf8_l() taking a separate limit

ucs2_as_utf8() takes a maxlength argument, which specifies how many
bytes the function is permitted to store into the destination buffer.

The same value is used as an upper bound for the ucs2_strnlen()
invocation, which is reasonable in the general case, as each UCS-2
character produces at least one byte of UTF-8 output, and so there is
never a need to process more than 'maxlength' UCS-2 characters.

However, if the UCS-2 string is not NUL terminated, ucs2_strnlen() may
read past the end of the buffer if 'maxlength' is set to a high value.

Current callers pass UCS-2 strings that are expected to be NUL
terminated, but for processing the load options in the EFI stub, a
version is needed that takes a separate limit argument. So split that
off from the current implementation.

Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
This commit is contained in:
Ard Biesheuvel 2026-09-09 10:10:03 +02:00
parent 4c0209bc31
commit 0f5a86b29f
2 changed files with 18 additions and 8 deletions

View File

@ -14,7 +14,16 @@ ssize_t ucs2_strscpy(ucs2_char_t *dst, const ucs2_char_t *src, size_t count);
int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len);
unsigned long ucs2_utf8size(const ucs2_char_t *src);
unsigned long
ucs2_as_utf8_l(u8 *dest, const ucs2_char_t *src, unsigned long limit,
unsigned long maxlength);
static inline
unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src,
unsigned long maxlength);
unsigned long maxlength)
{
return ucs2_as_utf8_l(dest, src, ucs2_strnlen(src, maxlength),
maxlength);
}
#endif /* _LINUX_UCS2_STRING_H_ */

View File

@ -123,18 +123,19 @@ ucs2_utf8size(const ucs2_char_t *src)
EXPORT_SYMBOL(ucs2_utf8size);
/*
* copy at most maxlength bytes of whole utf8 characters to dest from the
* ucs2 string src.
* Copy at most @limit whole utf8 characters to @dest from the ucs2 string
* @src, using no more than @maxlength bytes of buffer space.
*
* The return value is the number of characters copied, not including the
* final NUL character.
* The return value is the number of bytes copied, not including the final NUL
* character. No NUL character will be appended if the output length equals
* @maxlength.
*/
unsigned long
ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
ucs2_as_utf8_l(u8 *dest, const ucs2_char_t *src, unsigned long limit,
unsigned long maxlength)
{
unsigned int i;
unsigned long j = 0;
unsigned long limit = ucs2_strnlen(src, maxlength);
for (i = 0; maxlength && i < limit; i++) {
u16 c = src[i];
@ -161,7 +162,7 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
dest[j] = '\0';
return j;
}
EXPORT_SYMBOL(ucs2_as_utf8);
EXPORT_SYMBOL(ucs2_as_utf8_l);
#ifndef __DISABLE_EXPORTS
MODULE_DESCRIPTION("UCS2 string handling");