From be95a4fe2951374676efc9454ffee8638faaf68d Mon Sep 17 00:00:00 2001
From: Akim Demaille <akim.demaille@gmail.com>
Date: Tue, 28 Jul 2020 18:51:30 +0200
Subject: scanner: don't crash on strings containing a NUL byte
We crash if the input contains a string containing a NUL byte.
Reported by Suhwan Song.
https://lists.gnu.org/r/bug-bison/2020-07/msg00051.html
* src/flex-scanner.h (STRING_FREE): Avoid accidental use of
last_string.
* src/scan-gram.l: Don't call STRING_FREE without calling
STRING_FINISH first.
* tests/input.at (Invalid inputs): Check that case.
---
THANKS | 1 +
src/flex-scanner.h | 10 +++++++++-
src/scan-gram.l | 3 ++-
tests/input.at | 48 ++++++++++++++++++++++++++++++++++++++----------
4 files changed, 50 insertions(+), 12 deletions(-)
diff --git a/THANKS b/THANKS
index ac073ea6..5c64da3c 100644
--- a/THANKS
+++ b/THANKS
@@ -185,6 +185,7 @@ Simon Sobisch simonsobisch@web.de
Stefano Lattarini stefano.lattarini@gmail.com
Stephen Cameron stephenmcameron@gmail.com
Steve Murphy murf@parsetree.com
+Suhwan Song prada960808@gmail.com
Sum Wu sum@geekhouse.org
Théophile Ranquet theophile.ranquet@gmail.com
Thiru Ramakrishnan thiru.ramakrishnan@gmail.com
diff --git a/src/flex-scanner.h b/src/flex-scanner.h
index 56ca7ce3..028847fd 100644
--- a/src/flex-scanner.h
+++ b/src/flex-scanner.h
@@ -112,7 +112,15 @@ static struct obstack obstack_for_string;
# define STRING_1GROW(Char) \
obstack_1grow (&obstack_for_string, Char)
-# define STRING_FREE() \
+# ifdef NDEBUG
+# define STRING_FREE() \
obstack_free (&obstack_for_string, last_string)
+# else
+# define STRING_FREE() \
+ do { \
+ obstack_free (&obstack_for_string, last_string); \
+ last_string = NULL; \
+ } while (0)
+#endif
#endif
diff --git a/src/scan-gram.l b/src/scan-gram.l
index f8d85f23..ad2904ce 100644
--- a/src/scan-gram.l
+++ b/src/scan-gram.l
@@ -403,6 +403,7 @@ eqopt ({sp}=)?
{
\0 {
complain (loc, complaint, _("invalid null character"));
+ STRING_FINISH ();
STRING_FREE ();
return GRAM_error;
}
@@ -599,7 +600,6 @@ eqopt ({sp}=)?
STRING_FINISH ();
BEGIN INITIAL;
loc->start = token_start;
- val->CHAR = last_string[0];
if (last_string[0] == '\0')
{
@@ -615,6 +615,7 @@ eqopt ({sp}=)?
}
else
{
+ val->CHAR = last_string[0];
STRING_FREE ();
return CHAR;
}
diff --git a/tests/input.at b/tests/input.at
index 4da63795..effcd1cc 100644
--- a/tests/input.at
+++ b/tests/input.at
@@ -1,4 +1,4 @@
-# Checking the Bison scanner. -*- Autotest -*-
+# Checking the Bison reader. -*- Autotest -*-
# Copyright (C) 2002-2015, 2018-2020 Free Software Foundation, Inc.
@@ -78,10 +78,13 @@ AT_CLEANUP
## Invalid inputs. ##
## ---------------- ##
+# The truly bad guys no human would write, but easily uncovered by
+# fuzzers.
AT_SETUP([Invalid inputs])
AT_DATA([input.y],
[[\000\001\002\377?
+"\000"
%%
?
default: 'a' }
@@ -92,16 +95,41 @@ default: 'a' }
]])
AT_PERL_REQUIRE([[-pi -e 's/\\(\d{3})/chr(oct($1))/ge' input.y]])
-AT_BISON_CHECK([input.y], [1], [],
+AT_BISON_CHECK([-fcaret input.y], [1], [], [stderr])
+
+# Autotest's diffing, when there are NUL bytes, just reports "binary
+# files differ". So don't leave NUL bytes.
+AT_PERL_CHECK([[-p -e 's{([\0\377])}{sprintf "\\x%02x", ord($1)}ge' stderr]], [],
[[input.y:1.1-2: error: invalid characters: '\0\001\002\377?'
-input.y:3.1: error: invalid character: '?'
-input.y:4.14: error: invalid character: '}'
-input.y:5.1: error: invalid character: '%'
-input.y:5.2: error: invalid character: '&'
-input.y:6.1-17: error: invalid directive: '%a-does-not-exist'
-input.y:7.1: error: invalid character: '%'
-input.y:7.2: error: invalid character: '-'
-input.y:8.1-9.0: error: missing '%}' at end of file
+ 1 | \x00\xff?
+ | ^~
+input.y:2.2: error: invalid null character
+ 2 | "\x00"
+ | ^
+input.y:4.1: error: invalid character: '?'
+ 4 | ?
+ | ^
+input.y:5.14: error: invalid character: '}'
+ 5 | default: 'a' }
+ | ^
+input.y:6.1: error: invalid character: '%'
+ 6 | %&
+ | ^
+input.y:6.2: error: invalid character: '&'
+ 6 | %&
+ | ^
+input.y:7.1-17: error: invalid directive: '%a-does-not-exist'
+ 7 | %a-does-not-exist
+ | ^~~~~~~~~~~~~~~~~
+input.y:8.1: error: invalid character: '%'
+ 8 | %-
+ | ^
+input.y:8.2: error: invalid character: '-'
+ 8 | %-
+ | ^
+input.y:9.1-10.0: error: missing '%}' at end of file
+ 9 | %{
+ | ^~
]])
AT_CLEANUP
--
cgit v1.2.1
