With GB18030, prevent SIGSEGV from reading past end of allocation.

With GB18030 as source encoding, applications could crash the server via
SQL functions convert() or convert_from().  Applications themselves
could crash after passing unterminated GB18030 input to libpq functions
PQescapeLiteral(), PQescapeIdentifier(), PQescapeStringConn(), or
PQescapeString().  Extension code could crash by passing unterminated
GB18030 input to jsonapi.h functions.  All those functions have been
intended to handle untrusted, unterminated input safely.

A crash required allocating the input such that the last byte of the
allocation was the last byte of a virtual memory page.  Some malloc()
implementations take measures against that, making the SIGSEGV hard to
reach.  Back-patch to v13 (all supported versions).

Author: Noah Misch <[email protected]>
Author: Andres Freund <[email protected]>
Reviewed-by: Masahiko Sawada <[email protected]>
Backpatch-through: 13
Security: CVE-2025-4207

2 files changed, 14 insertions, 6 deletions

diff --git a/src/test/regress/expected/conversion.out b/src/test/regress/expected/conversion.out
index d785f92561e..7dd1ef6161f 100644
--- a/src/test/regress/expected/conversion.out
+++ b/src/test/regress/expected/conversion.out
@@ -508,10 +508,13 @@ insert into gb18030_inputs  values
   ('\x666f6f84309c38',	'valid, translates to UTF-8 by mapping function'),
   ('\x666f6f84309c',	'incomplete char '),
   ('\x666f6f84309c0a',	'incomplete char, followed by newline '),
+  ('\x666f6f84',		'incomplete char at end'),
   ('\x666f6f84309c3800', 'invalid, NUL byte'),
   ('\x666f6f84309c0038', 'invalid, NUL byte');
--- Test GB18030 verification
-select description, inbytes, (test_conv(inbytes, 'gb18030', 'gb18030')).* from gb18030_inputs;
+-- Test GB18030 verification.  Round-trip through text so the backing of the
+-- bytea values is palloc, not shared_buffers.  This lets Valgrind detect
+-- reads past the end.
+select description, inbytes, (test_conv(inbytes::text::bytea, 'gb18030', 'gb18030')).* from gb18030_inputs;
                   description                   |      inbytes       |      result      |   errorat    |                               error                               
 ------------------------------------------------+--------------------+------------------+--------------+-------------------------------------------------------------------
  valid, pure ASCII                              | \x666f6f           | \x666f6f         |              | 
@@ -520,9 +523,10 @@ select description, inbytes, (test_conv(inbytes, 'gb18030', 'gb18030')).* from g
  valid, translates to UTF-8 by mapping function | \x666f6f84309c38   | \x666f6f84309c38 |              | 
  incomplete char                                | \x666f6f84309c     | \x666f6f         | \x84309c     | invalid byte sequence for encoding "GB18030": 0x84 0x30 0x9c
  incomplete char, followed by newline           | \x666f6f84309c0a   | \x666f6f         | \x84309c0a   | invalid byte sequence for encoding "GB18030": 0x84 0x30 0x9c 0x0a
+ incomplete char at end                         | \x666f6f84         | \x666f6f         | \x84         | invalid byte sequence for encoding "GB18030": 0x84
  invalid, NUL byte                              | \x666f6f84309c3800 | \x666f6f84309c38 | \x00         | invalid byte sequence for encoding "GB18030": 0x00
  invalid, NUL byte                              | \x666f6f84309c0038 | \x666f6f         | \x84309c0038 | invalid byte sequence for encoding "GB18030": 0x84 0x30 0x9c 0x00
-(8 rows)
+(9 rows)
 
 -- Test conversions from GB18030
 select description, inbytes, (test_conv(inbytes, 'gb18030', 'utf8')).* from gb18030_inputs;
@@ -534,9 +538,10 @@ select description, inbytes, (test_conv(inbytes, 'gb18030', 'utf8')).* from gb18
  valid, translates to UTF-8 by mapping function | \x666f6f84309c38   | \x666f6fefa8aa |              | 
  incomplete char                                | \x666f6f84309c     | \x666f6f       | \x84309c     | invalid byte sequence for encoding "GB18030": 0x84 0x30 0x9c
  incomplete char, followed by newline           | \x666f6f84309c0a   | \x666f6f       | \x84309c0a   | invalid byte sequence for encoding "GB18030": 0x84 0x30 0x9c 0x0a
+ incomplete char at end                         | \x666f6f84         | \x666f6f       | \x84         | invalid byte sequence for encoding "GB18030": 0x84
  invalid, NUL byte                              | \x666f6f84309c3800 | \x666f6fefa8aa | \x00         | invalid byte sequence for encoding "GB18030": 0x00
  invalid, NUL byte                              | \x666f6f84309c0038 | \x666f6f       | \x84309c0038 | invalid byte sequence for encoding "GB18030": 0x84 0x30 0x9c 0x00
-(8 rows)
+(9 rows)
 
 --
 -- ISO-8859-5
diff --git a/src/test/regress/sql/conversion.sql b/src/test/regress/sql/conversion.sql
index b567a1a5721..a80d62367a2 100644
--- a/src/test/regress/sql/conversion.sql
+++ b/src/test/regress/sql/conversion.sql
@@ -300,11 +300,14 @@ insert into gb18030_inputs  values
   ('\x666f6f84309c38',	'valid, translates to UTF-8 by mapping function'),
   ('\x666f6f84309c',	'incomplete char '),
   ('\x666f6f84309c0a',	'incomplete char, followed by newline '),
+  ('\x666f6f84',		'incomplete char at end'),
   ('\x666f6f84309c3800', 'invalid, NUL byte'),
   ('\x666f6f84309c0038', 'invalid, NUL byte');
 
--- Test GB18030 verification
-select description, inbytes, (test_conv(inbytes, 'gb18030', 'gb18030')).* from gb18030_inputs;
+-- Test GB18030 verification.  Round-trip through text so the backing of the
+-- bytea values is palloc, not shared_buffers.  This lets Valgrind detect
+-- reads past the end.
+select description, inbytes, (test_conv(inbytes::text::bytea, 'gb18030', 'gb18030')).* from gb18030_inputs;
 -- Test conversions from GB18030
 select description, inbytes, (test_conv(inbytes, 'gb18030', 'utf8')).* from gb18030_inputs;