From: Andres Freund <andres@anarazel.de>
Date: Mon, 10 Feb 2025 15:03:40 +0000 (-0500)
Subject: Back-patch pg_encoding_verifymbstr()/pg_encoding_verifymbchar() to v13.
X-Git-Tag: REL_13_19~9
X-Git-Url: http://git.postgresql.org/gitweb/?a=commitdiff_plain;h=00f1a1f665f078f5abadbf8baddc5c187fba80f8;p=postgresql.git

Back-patch pg_encoding_verifymbstr()/pg_encoding_verifymbchar() to v13.

A security fix will need those functions, so back-patch the v14+ functions to
v13.

When commit b80e10638e36b9d2f0b39170c613837af2ca2aac introduced the v14+
implementation of pg_encoding_verifymbstr(), it added a callback to each
pg_wchar_table entry.  For simplicity and ABI stability, this instead
implements the function in terms of the existing per-character callback.

Author: Noah Misch <noah@leadboat.com>
Author: Andres Freund <andres@anarazel.de>
Security: CVE-2025-1094
---

diff --git a/src/common/wchar.c b/src/common/wchar.c
index 08734802236..2d044ee4ffb 100644
--- a/src/common/wchar.c
+++ b/src/common/wchar.c
@@ -1597,6 +1597,72 @@ pg_encoding_verifymb(int encoding, const char *mbstr, int len)
 			pg_wchar_table[PG_SQL_ASCII].mbverify((const unsigned char *) mbstr, len));
 }
 
+/* v14+ function name, for easier backpatching */
+int
+pg_encoding_verifymbchar(int encoding, const char *mbstr, int len)
+{
+	int ok_bytes = pg_encoding_verifymb(encoding, mbstr, len);
+
+	if (ok_bytes == 0)
+		return -1;
+	return ok_bytes;
+}
+
+/* replace v14+ function, adapted from pg_verify_mbstr_len */
+int
+pg_encoding_verifymbstr(int encoding, const char *mbstr, int len)
+{
+	mbverifier	mbverify;
+	int			ok_bytes;
+
+	Assert(PG_VALID_ENCODING(encoding));
+
+	/*
+	 * In single-byte encodings, we need only reject nulls (\0).
+	 */
+	if (pg_encoding_max_length(encoding) <= 1)
+	{
+		const char *nullpos = memchr(mbstr, 0, len);
+
+		if (nullpos == NULL)
+			return len;
+		return nullpos - mbstr;
+	}
+
+	/* fetch function pointer just once */
+	mbverify = pg_wchar_table[encoding].mbverify;
+
+	ok_bytes = 0;
+
+	while (len > 0)
+	{
+		int			l;
+
+		/* fast path for ASCII-subset characters */
+		if (!IS_HIGHBIT_SET(*mbstr))
+		{
+			if (*mbstr != '\0')
+			{
+				ok_bytes++;
+				mbstr++;
+				len--;
+				continue;
+			}
+			return ok_bytes;
+		}
+
+		l = (*mbverify) ((const unsigned char *) mbstr, len);
+
+		if (l < 0)
+			return ok_bytes;
+
+		mbstr += l;
+		len -= l;
+		ok_bytes += l;
+	}
+	return ok_bytes;
+}
+
 /*
  * fetch maximum length of a given encoding
  */
diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h
index b43454b64ce..b0dbde45b33 100644
--- a/src/include/mb/pg_wchar.h
+++ b/src/include/mb/pg_wchar.h
@@ -556,6 +556,8 @@ extern int	pg_encoding_mblen(int encoding, const char *mbstr);
 extern int	pg_encoding_mblen_bounded(int encoding, const char *mbstr);
 extern int	pg_encoding_dsplen(int encoding, const char *mbstr);
 extern int	pg_encoding_verifymb(int encoding, const char *mbstr, int len);
+extern int	pg_encoding_verifymbchar(int encoding, const char *mbstr, int len);
+extern int	pg_encoding_verifymbstr(int encoding, const char *mbstr, int len);
 extern int	pg_encoding_max_length(int encoding);
 extern int	pg_valid_client_encoding(const char *name);
 extern int	pg_valid_server_encoding(const char *name);