summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorArmin Wolf <W_Armin@gmx.de>2025-11-11 14:11:22 +0100
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2025-12-18 14:03:33 +0100
commit4836f912acc702d6e70eab3f1d796895906a540d (patch)
treed6413db141531c563b6e730065c02c7db0d1b5b3
parentf0f456c327f5728ca632746cdfae0bf4f6bc5188 (diff)
downloadlinux-4836f912acc702d6e70eab3f1d796895906a540d.tar.gz
linux-4836f912acc702d6e70eab3f1d796895906a540d.tar.bz2
linux-4836f912acc702d6e70eab3f1d796895906a540d.zip
fs/nls: Fix utf16 to utf8 conversion
[ Upstream commit 25524b6190295577e4918c689644451365e6466d ] Currently the function responsible for converting between utf16 and utf8 strings will ignore any characters that cannot be converted. This however also includes multi-byte characters that do not fit into the provided string buffer. This can cause problems if such a multi-byte character is followed by a single-byte character. In such a case the multi-byte character might be ignored when the provided string buffer is too small, but the single-byte character might fit and is thus still copied into the resulting string. Fix this by stop filling the provided string buffer once a character does not fit. In order to be able to do this extend utf32_to_utf8() to return useful errno codes instead of -1. Fixes: 74675a58507e ("NLS: update handling of Unicode") Signed-off-by: Armin Wolf <W_Armin@gmx.de> Link: https://patch.msgid.link/20251111131125.3379-2-W_Armin@gmx.de Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
-rw-r--r--fs/nls/nls_base.c16
1 files changed, 12 insertions, 4 deletions
diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c
index 18d597e49a19..d434c4463a8f 100644
--- a/fs/nls/nls_base.c
+++ b/fs/nls/nls_base.c
@@ -94,7 +94,7 @@ int utf32_to_utf8(unicode_t u, u8 *s, int maxout)
l = u;
if (l > UNICODE_MAX || (l & SURROGATE_MASK) == SURROGATE_PAIR)
- return -1;
+ return -EILSEQ;
nc = 0;
for (t = utf8_table; t->cmask && maxout; t++, maxout--) {
@@ -110,7 +110,7 @@ int utf32_to_utf8(unicode_t u, u8 *s, int maxout)
return nc;
}
}
- return -1;
+ return -EOVERFLOW;
}
EXPORT_SYMBOL(utf32_to_utf8);
@@ -217,8 +217,16 @@ int utf16s_to_utf8s(const wchar_t *pwcs, int inlen, enum utf16_endian endian,
inlen--;
}
size = utf32_to_utf8(u, op, maxout);
- if (size == -1) {
- /* Ignore character and move on */
+ if (size < 0) {
+ if (size == -EILSEQ) {
+ /* Ignore character and move on */
+ continue;
+ }
+ /*
+ * Stop filling the buffer with data once a character
+ * does not fit anymore.
+ */
+ break;
} else {
op += size;
maxout -= size;