Bug#45010: invalid memory reads during parsing some strange statements

The problem is that the lexer could inadvertently skip over the
end of a query being parsed if it encountered a malformed multibyte
character. A specially crated query string could cause the lexer
to jump up to six bytes past the end of the query buffer. Another
problem was that the laxer could use unfiltered user input as
a signed array index for the parser maps (having upper and lower
bounds 0 and 256 respectively).

The solution is to ensure that the lexer only skips over well-formed
multibyte characters and that the index value of the parser maps
is always a unsigned value.

mysql-test/r/ctype_recoding.result:
  Update test case result: ending backtick is not skipped over anymore.
sql/sql_lex.cc:
  Characters being analyzed must be unsigned as they can be
  used as indexes for the parser maps. Only skip over if the
  string is a valid multi-byte sequence.
tests/mysql_client_test.c:
  Add test case for Bug#45010

mysql-test/r/ctype_recoding.result

@@ -165,7 +165,7 @@ CREATE TABLE `good
 ERROR HY000: Invalid utf8 character string: ''
 SET NAMES utf8;
 CREATE TABLE `good` (a int);
-ERROR HY000: Invalid utf8 character string: '` (a int)'
+ERROR HY000: Invalid utf8 character string: ''
 set names latin1;
 create table t1 (a char(10) character set koi8r, b text character set koi8r);
 insert into t1 values ('test','test');

sql/sql_lex.cc

@@ -32,10 +32,10 @@ sys_var_long_ptr trg_new_row_fake_var(0, 0);
 
 /* Macros to look like lex */
 
-#define yyGet()		*(lip->ptr++)
-#define yyGetLast()	lip->ptr[-1]
-#define yyPeek()	lip->ptr[0]
-#define yyPeek2()	lip->ptr[1]
+#define yyGet()		((uchar)*(lip->ptr++))
+#define yyGetLast()	((uchar)lip->ptr[-1])
+#define yyPeek()	((uchar)lip->ptr[0])
+#define yyPeek2()	((uchar)lip->ptr[1])
 #define yyUnget()	lip->ptr--
 #define yySkip()	lip->ptr++
 #define yyLength()	((uint) (lip->ptr - lip->tok_start)-1)
@@ -813,9 +813,11 @@ int MYSQLlex(void *arg, void *yythd)
 	  }
 	}
 #ifdef USE_MB
-	else if (var_length < 1)
-	  break;				// Error
-	lip->ptr+= var_length-1;
+	else if (use_mb(cs))
+        {
+          if ((var_length= my_ismbchar(cs, lip->ptr-1, lip->end_of_query)))
+            lip->ptr+= var_length-1;
+        }
 #endif
       }
       if (double_quotes)

tests/mysql_client_test.c

@@ -16647,6 +16647,38 @@ static void test_bug41078(void)
   DBUG_VOID_RETURN;
 }
 
+
+/**
+  Bug#45010: invalid memory reads during parsing some strange statements
+*/
+
+static void test_bug45010()
+{
+  int rc;
+  const char query1[]= "select a.\x80",
+             query2[]= "describe `table\xef";
+
+  DBUG_ENTER("test_bug45010");
+  myheader("test_bug45010");
+
+  rc= mysql_query(mysql, "set names utf8");
+  myquery(rc);
+
+  /* \x80 (-128) could be used as a index of ident_map. */
+  rc= mysql_real_query(mysql, query1, sizeof(query1) - 1);
+  DIE_UNLESS(rc);
+
+  /* \xef (-17) could be used to skip 3 bytes past the buffer end. */
+  rc= mysql_real_query(mysql, query2, sizeof(query2) - 1);
+  DIE_UNLESS(rc);
+
+  rc= mysql_query(mysql, "set names default");
+  myquery(rc);
+
+  DBUG_VOID_RETURN;
+}
+
+
 /*
   Read and parse arguments and MySQL options from my.cnf
 */
@@ -16949,6 +16981,7 @@ static struct my_tests_st my_tests[]= {
 #endif
   { "test_bug41078", test_bug41078 },
   { "test_bug20023", test_bug20023 },
+  { "test_bug45010", test_bug45010 },
   { 0, 0 }
 };