Fix incautious handling of possibly-miscoded strings in client code.

An incorrectly-encoded multibyte character near the end of a string
could cause various processing loops to run past the string's
terminating NUL, with results ranging from no detectable issue to
a program crash, depending on what happens to be in the following
memory.

This isn't an issue in the server, because we take care to verify
the encoding of strings before doing any interesting processing
on them.  However, that lack of care leaked into client-side code
which shouldn't assume that anyone has validated the encoding of
its input.

Although this is certainly a bug worth fixing, the PG security team
elected not to regard it as a security issue, primarily because
any untrusted text should be sanitized by PQescapeLiteral or
the like before being incorporated into a SQL or psql command.
(If an app fails to do so, the same technique can be used to
cause SQL injection, with probably much more dire consequences
than a mere client-program crash.)  Those functions were already
made proof against this class of problem, cf CVE-2006-2313.

To fix, invent PQmblenBounded() which is like PQmblen() except it
won't return more than the number of bytes remaining in the string.
In HEAD we can make this a new libpq function, as PQmblen() is.
It seems imprudent to change libpq's API in stable branches though,
so in the back branches define PQmblenBounded as a macro in the files
that need it.  (Note that just changing PQmblen's behavior would not
be a good idea; notably, it would completely break the escaping
functions' defense against this exact problem.  So we just want a
version for those callers that don't have any better way of handling
this issue.)

Per private report from houjingyi.  Back-patch to all supported branches.

8 files changed, 37 insertions, 21 deletions

diff --git a/src/bin/psql/common.c b/src/bin/psql/common.c
index 11200cc6a6f..1b57f85fb23 100644
--- a/src/bin/psql/common.c
+++ b/src/bin/psql/common.c
@@ -29,6 +29,8 @@
 #include "fe_utils/mbprint.h"
 
 
+#define PQmblenBounded(s, e)  strnlen(s, PQmblen(s, e))
+
 static bool DescribeQuery(const char *query, double *elapsed_msec);
 static bool ExecQueryUsingCursor(const char *query, double *elapsed_msec);
 static bool command_no_begin(const char *query);
@@ -2001,7 +2003,7 @@ skip_white_space(const char *query)
 
 	while (*query)
 	{
-		int			mblen = PQmblen(query, pset.encoding);
+		int			mblen = PQmblenBounded(query, pset.encoding);
 
 		/*
 		 * Note: we assume the encoding is a superset of ASCII, so that for
@@ -2038,7 +2040,7 @@ skip_white_space(const char *query)
 					query++;
 					break;
 				}
-				query += PQmblen(query, pset.encoding);
+				query += PQmblenBounded(query, pset.encoding);
 			}
 		}
 		else if (cnestlevel > 0)
@@ -2073,7 +2075,7 @@ command_no_begin(const char *query)
 	 */
 	wordlen = 0;
 	while (isalpha((unsigned char) query[wordlen]))
-		wordlen += PQmblen(&query[wordlen], pset.encoding);
+		wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 
 	/*
 	 * Transaction control commands.  These should include every keyword that
@@ -2104,7 +2106,7 @@ command_no_begin(const char *query)
 
 		wordlen = 0;
 		while (isalpha((unsigned char) query[wordlen]))
-			wordlen += PQmblen(&query[wordlen], pset.encoding);
+			wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 
 		if (wordlen == 11 && pg_strncasecmp(query, "transaction", 11) == 0)
 			return true;
@@ -2138,7 +2140,7 @@ command_no_begin(const char *query)
 
 		wordlen = 0;
 		while (isalpha((unsigned char) query[wordlen]))
-			wordlen += PQmblen(&query[wordlen], pset.encoding);
+			wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 
 		if (wordlen == 8 && pg_strncasecmp(query, "database", 8) == 0)
 			return true;
@@ -2154,7 +2156,7 @@ command_no_begin(const char *query)
 
 			wordlen = 0;
 			while (isalpha((unsigned char) query[wordlen]))
-				wordlen += PQmblen(&query[wordlen], pset.encoding);
+				wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 		}
 
 		if (wordlen == 5 && pg_strncasecmp(query, "index", 5) == 0)
@@ -2165,7 +2167,7 @@ command_no_begin(const char *query)
 
 			wordlen = 0;
 			while (isalpha((unsigned char) query[wordlen]))
-				wordlen += PQmblen(&query[wordlen], pset.encoding);
+				wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 
 			if (wordlen == 12 && pg_strncasecmp(query, "concurrently", 12) == 0)
 				return true;
@@ -2182,7 +2184,7 @@ command_no_begin(const char *query)
 
 		wordlen = 0;
 		while (isalpha((unsigned char) query[wordlen]))
-			wordlen += PQmblen(&query[wordlen], pset.encoding);
+			wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 
 		/* ALTER SYSTEM isn't allowed in xacts */
 		if (wordlen == 6 && pg_strncasecmp(query, "system", 6) == 0)
@@ -2205,7 +2207,7 @@ command_no_begin(const char *query)
 
 		wordlen = 0;
 		while (isalpha((unsigned char) query[wordlen]))
-			wordlen += PQmblen(&query[wordlen], pset.encoding);
+			wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 
 		if (wordlen == 8 && pg_strncasecmp(query, "database", 8) == 0)
 			return true;
@@ -2223,7 +2225,7 @@ command_no_begin(const char *query)
 
 			wordlen = 0;
 			while (isalpha((unsigned char) query[wordlen]))
-				wordlen += PQmblen(&query[wordlen], pset.encoding);
+				wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 
 			if (wordlen == 12 && pg_strncasecmp(query, "concurrently", 12) == 0)
 				return true;
@@ -2243,7 +2245,7 @@ command_no_begin(const char *query)
 
 		wordlen = 0;
 		while (isalpha((unsigned char) query[wordlen]))
-			wordlen += PQmblen(&query[wordlen], pset.encoding);
+			wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 
 		if (wordlen == 3 && pg_strncasecmp(query, "all", 3) == 0)
 			return true;
@@ -2279,7 +2281,7 @@ is_select_command(const char *query)
 	 */
 	wordlen = 0;
 	while (isalpha((unsigned char) query[wordlen]))
-		wordlen += PQmblen(&query[wordlen], pset.encoding);
+		wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
 
 	if (wordlen == 6 && pg_strncasecmp(query, "select", 6) == 0)
 		return true;
diff --git a/src/bin/psql/psqlscanslash.l b/src/bin/psql/psqlscanslash.l
index 2567ed80809..a7734506cf0 100644
--- a/src/bin/psql/psqlscanslash.l
+++ b/src/bin/psql/psqlscanslash.l
@@ -27,6 +27,8 @@
 %{
 #include "fe_utils/psqlscan_int.h"
 
+#define PQmblenBounded(s, e)  strnlen(s, PQmblen(s, e))
+
 /*
  * We must have a typedef YYSTYPE for yylex's first argument, but this lexer
  * doesn't presently make use of that argument, so just declare it as int.
@@ -752,7 +754,7 @@ dequote_downcase_identifier(char *str, bool downcase, int encoding)
 		{
 			if (downcase && !inquotes)
 				*cp = pg_tolower((unsigned char) *cp);
-			cp += PQmblen(cp, encoding);
+			cp += PQmblenBounded(cp, encoding);
 		}
 	}
 }
diff --git a/src/bin/psql/stringutils.c b/src/bin/psql/stringutils.c
index 29b9c9c7f03..762277bf75a 100644
--- a/src/bin/psql/stringutils.c
+++ b/src/bin/psql/stringutils.c
@@ -12,6 +12,8 @@
 #include "common.h"
 #include "stringutils.h"
 
+#define PQmblenBounded(s, e)  strnlen(s, PQmblen(s, e))
+
 
 /*
  * Replacement for strtok() (a.k.a. poor man's flex)
@@ -143,7 +145,7 @@ strtokx(const char *s,
 		/* okay, we have a quoted token, now scan for the closer */
 		char		thisquote = *p++;
 
-		for (; *p; p += PQmblen(p, encoding))
+		for (; *p; p += PQmblenBounded(p, encoding))
 		{
 			if (*p == escape && p[1] != '\0')
 				p++;			/* process escaped anything */
@@ -262,7 +264,7 @@ strip_quotes(char *source, char quote, char escape, int encoding)
 		else if (c == escape && src[1] != '\0')
 			src++;				/* process escaped character */
 
-		i = PQmblen(src, encoding);
+		i = PQmblenBounded(src, encoding);
 		while (i--)
 			*dst++ = *src++;
 	}
@@ -322,7 +324,7 @@ quote_if_needed(const char *source, const char *entails_quote,
 		else if (strchr(entails_quote, c))
 			need_quotes = true;
 
-		i = PQmblen(src, encoding);
+		i = PQmblenBounded(src, encoding);
 		while (i--)
 			*dst++ = *src++;
 	}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 7041248bbb2..d6b4a5bc31f 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -60,6 +60,8 @@ extern char *filename_completion_function();
 #define completion_matches rl_completion_matches
 #endif
 
+#define PQmblenBounded(s, e)  strnlen(s, PQmblen(s, e))
+
 /* word break characters */
 #define WORD_BREAKS		"\t\n@$><=;|&{() "
 
@@ -4128,7 +4130,7 @@ _complete_from_query(const char *simple_query,
 		while (*pstr)
 		{
 			char_length++;
-			pstr += PQmblen(pstr, pset.encoding);
+			pstr += PQmblenBounded(pstr, pset.encoding);
 		}
 
 		/* Free any prior result */
diff --git a/src/bin/scripts/common.c b/src/bin/scripts/common.c
index f018aa87db7..223862f9442 100644
--- a/src/bin/scripts/common.c
+++ b/src/bin/scripts/common.c
@@ -22,6 +22,8 @@
 #include "fe_utils/string_utils.h"
 
 
+#define PQmblenBounded(s, e)  strnlen(s, PQmblen(s, e))
+
 static PGcancel *volatile cancelConn = NULL;
 bool		CancelRequested = false;
 
@@ -303,7 +305,7 @@ split_table_columns_spec(const char *spec, int encoding,
 			cp++;
 		}
 		else
-			cp += PQmblen(cp, encoding);
+			cp += PQmblenBounded(cp, encoding);
 	}
 	*table = pg_strdup(spec);
 	(*table)[cp - spec] = '\0'; /* no strndup */
diff --git a/src/fe_utils/print.c b/src/fe_utils/print.c
index 22f67710d2a..dba19c28f59 100644
--- a/src/fe_utils/print.c
+++ b/src/fe_utils/print.c
@@ -3528,6 +3528,9 @@ strlen_max_width(unsigned char *str, int *target_width, int encoding)
 		curr_width += char_width;
 
 		str += PQmblen((char *) str, encoding);
+
+		if (str > end)			/* Don't overrun invalid string */
+			str = end;
 	}
 
 	*target_width = curr_width;
diff --git a/src/interfaces/libpq/fe-print.c b/src/interfaces/libpq/fe-print.c
index 95de270b933..f07adf0b760 100644
--- a/src/interfaces/libpq/fe-print.c
+++ b/src/interfaces/libpq/fe-print.c
@@ -36,6 +36,7 @@
 #include "libpq-fe.h"
 #include "libpq-int.h"
 
+#define PQmblenBounded(s, e)  strnlen(s, PQmblen(s, e))
 
 static void do_field(const PQprintOpt *po, const PGresult *res,
 		 const int i, const int j, const int fs_len,
@@ -365,7 +366,7 @@ do_field(const PQprintOpt *po, const PGresult *res,
 			/* Detect whether field contains non-numeric data */
 			char		ch = '0';
 
-			for (p = pval; *p; p += PQmblen(p, res->client_encoding))
+			for (p = pval; *p; p += PQmblenBounded(p, res->client_encoding))
 			{
 				ch = *p;
 				if (!((ch >= '0' && ch <= '9') ||
diff --git a/src/interfaces/libpq/fe-protocol3.c b/src/interfaces/libpq/fe-protocol3.c
index f1d0820510b..5ede5ce3989 100644
--- a/src/interfaces/libpq/fe-protocol3.c
+++ b/src/interfaces/libpq/fe-protocol3.c
@@ -41,6 +41,8 @@
 	((id) == 'T' || (id) == 'D' || (id) == 'd' || (id) == 'V' || \
 	 (id) == 'E' || (id) == 'N' || (id) == 'A')
 
+#define PQmblenBounded(s, e)  strnlen(s, PQmblen(s, e))
+
 
 static void handleSyncLoss(PGconn *conn, char id, int msgLength);
 static int	getRowDescriptions(PGconn *conn, int msgLength);
@@ -1227,7 +1229,7 @@ reportErrorPosition(PQExpBuffer msg, const char *query, int loc, int encoding)
 			if (w <= 0)
 				w = 1;
 			scroffset += w;
-			qoffset += pg_encoding_mblen(encoding, &wquery[qoffset]);
+			qoffset += PQmblenBounded(&wquery[qoffset], encoding);
 		}
 		else
 		{
@@ -1295,7 +1297,7 @@ reportErrorPosition(PQExpBuffer msg, const char *query, int loc, int encoding)
 		 * width.
 		 */
 		scroffset = 0;
-		for (; i < msg->len; i += pg_encoding_mblen(encoding, &msg->data[i]))
+		for (; i < msg->len; i += PQmblenBounded(&msg->data[i], encoding))
 		{
 			int			w = pg_encoding_dsplen(encoding, &msg->data[i]);