disable pymalloc tricks with the --with-valgrind option #2422

Patch from James Henstridge.

5 files changed, 225 insertions, 4 deletions

diff --git a/Misc/NEWS b/Misc/NEWS
index 92f9026..3ad7f23 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -487,6 +487,11 @@ Core and Builtins
 - Issue #3739: The unicode-internal encoder now reports the number of characters
   consumed like any other encoder (instead of the number of bytes).
 
+- Issue #2422: When compiled with the ``--with-valgrind`` option, the
+  pymalloc allocator will be automatically disabled when running under
+  Valgrind.  This gives improved memory leak detection when running
+  under Valgrind, while taking advantage of pymalloc at other times.
+
 Library
 -------
 
diff --git a/Objects/obmalloc.c b/Objects/obmalloc.c
index 9cf90c4..fa985da 100644
--- a/Objects/obmalloc.c
+++ b/Objects/obmalloc.c
@@ -2,6 +2,21 @@
 
 #ifdef WITH_PYMALLOC
 
+#ifdef WITH_VALGRIND
+#include <valgrind/valgrind.h>
+
+/* If we're using GCC, use __builtin_expect() to reduce overhead of
+   the valgrind checks */
+#if defined(__GNUC__) && (__GNUC__ > 2) && defined(__OPTIMIZE__)
+#  define UNLIKELY(value) __builtin_expect((value), 0)
+#else
+#  define UNLIKELY(value) (value)
+#endif
+
+/* -1 indicates that we haven't checked that we're running on valgrind yet. */
+static int running_on_valgrind = -1;
+#endif
+
 /* An object allocator for Python.
 
    Here is an introduction to the layers of the Python memory architecture,
@@ -728,6 +743,13 @@ PyObject_Malloc(size_t nbytes)
 	poolp next;
 	uint size;
 
+#ifdef WITH_VALGRIND
+	if (UNLIKELY(running_on_valgrind == -1))
+		running_on_valgrind = RUNNING_ON_VALGRIND;
+	if (UNLIKELY(running_on_valgrind))
+		goto redirect;
+#endif
+
 	/*
 	 * Limit ourselves to PY_SSIZE_T_MAX bytes to prevent security holes.
 	 * Most python internals blindly use a signed Py_ssize_t to track
@@ -927,6 +949,11 @@ PyObject_Free(void *p)
 	if (p == NULL)	/* free(NULL) has no effect */
 		return;
 
+#ifdef WITH_VALGRIND
+	if (UNLIKELY(running_on_valgrind > 0))
+		goto redirect;
+#endif
+
 	pool = POOL_ADDR(p);
 	if (Py_ADDRESS_IN_RANGE(p, pool)) {
 		/* We allocated this address. */
@@ -1121,6 +1148,9 @@ PyObject_Free(void *p)
 		return;
 	}
 
+#ifdef WITH_VALGRIND
+redirect:
+#endif
 	/* We didn't allocate this address. */
 	free(p);
 }
@@ -1150,6 +1180,12 @@ PyObject_Realloc(void *p, size_t nbytes)
 	if (nbytes > PY_SSIZE_T_MAX)
 		return NULL;
 
+#ifdef WITH_VALGRIND
+	/* Treat running_on_valgrind == -1 the same as 0 */
+	if (UNLIKELY(running_on_valgrind > 0))
+		goto redirect;
+#endif
+
 	pool = POOL_ADDR(p);
 	if (Py_ADDRESS_IN_RANGE(p, pool)) {
 		/* We're in charge of this block */
@@ -1177,6 +1213,9 @@ PyObject_Realloc(void *p, size_t nbytes)
 		}
 		return bp;
 	}
+#ifdef WITH_VALGRIND
+ redirect:
+#endif
 	/* We're not managing this block.  If nbytes <=
 	 * SMALL_REQUEST_THRESHOLD, it's tempting to try to take over this
 	 * block.  However, if we do, we need to copy the valid data from
diff --git a/configure b/configure
index 8391a17..8a110ed 100755
--- a/configure
+++ b/configure
@@ -1,5 +1,5 @@
 #! /bin/sh
-# From configure.in Revision: 76568 .
+# From configure.in Revision: 76636 .
 # Guess values for system-dependent variables and create Makefiles.
 # Generated by GNU Autoconf 2.61 for python 2.7.
 #
@@ -1362,6 +1362,7 @@ Optional Packages:
   --with(out)-doc-strings disable/enable documentation strings
   --with(out)-tsc         enable/disable timestamp counter profile
   --with(out)-pymalloc    disable/enable specialized mallocs
+  --with-valgrind         Enable Valgrind support
   --with-wctype-functions use wctype.h functions
   --with-fpectl           enable SIGFPE catching
   --with-libm=STRING      math library
@@ -17616,6 +17617,166 @@ fi
 { echo "$as_me:$LINENO: result: $with_pymalloc" >&5
 echo "${ECHO_T}$with_pymalloc" >&6; }
 
+# Check for Valgrind support
+{ echo "$as_me:$LINENO: checking for --with-valgrind" >&5
+echo $ECHO_N "checking for --with-valgrind... $ECHO_C" >&6; }
+
+# Check whether --with-valgrind was given.
+if test "${with_valgrind+set}" = set; then
+  withval=$with_valgrind;
+else
+  with_valgrind=no
+fi
+
+{ echo "$as_me:$LINENO: result: $with_valgrind" >&5
+echo "${ECHO_T}$with_valgrind" >&6; }
+if test "$with_valgrind" != no; then
+    if test "${ac_cv_header_valgrind_valgrind_h+set}" = set; then
+  { echo "$as_me:$LINENO: checking for valgrind/valgrind.h" >&5
+echo $ECHO_N "checking for valgrind/valgrind.h... $ECHO_C" >&6; }
+if test "${ac_cv_header_valgrind_valgrind_h+set}" = set; then
+  echo $ECHO_N "(cached) $ECHO_C" >&6
+fi
+{ echo "$as_me:$LINENO: result: $ac_cv_header_valgrind_valgrind_h" >&5
+echo "${ECHO_T}$ac_cv_header_valgrind_valgrind_h" >&6; }
+else
+  # Is the header compilable?
+{ echo "$as_me:$LINENO: checking valgrind/valgrind.h usability" >&5
+echo $ECHO_N "checking valgrind/valgrind.h usability... $ECHO_C" >&6; }
+cat >conftest.$ac_ext <<_ACEOF
+/* confdefs.h.  */
+_ACEOF
+cat confdefs.h >>conftest.$ac_ext
+cat >>conftest.$ac_ext <<_ACEOF
+/* end confdefs.h.  */
+$ac_includes_default
+#include <valgrind/valgrind.h>
+_ACEOF
+rm -f conftest.$ac_objext
+if { (ac_try="$ac_compile"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5
+  (eval "$ac_compile") 2>conftest.er1
+  ac_status=$?
+  grep -v '^ *+' conftest.er1 >conftest.err
+  rm -f conftest.er1
+  cat conftest.err >&5
+  echo "$as_me:$LINENO: \$? = $ac_status" >&5
+  (exit $ac_status); } && {
+	 test -z "$ac_c_werror_flag" ||
+	 test ! -s conftest.err
+       } && test -s conftest.$ac_objext; then
+  ac_header_compiler=yes
+else
+  echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+	ac_header_compiler=no
+fi
+
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+{ echo "$as_me:$LINENO: result: $ac_header_compiler" >&5
+echo "${ECHO_T}$ac_header_compiler" >&6; }
+
+# Is the header present?
+{ echo "$as_me:$LINENO: checking valgrind/valgrind.h presence" >&5
+echo $ECHO_N "checking valgrind/valgrind.h presence... $ECHO_C" >&6; }
+cat >conftest.$ac_ext <<_ACEOF
+/* confdefs.h.  */
+_ACEOF
+cat confdefs.h >>conftest.$ac_ext
+cat >>conftest.$ac_ext <<_ACEOF
+/* end confdefs.h.  */
+#include <valgrind/valgrind.h>
+_ACEOF
+if { (ac_try="$ac_cpp conftest.$ac_ext"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5
+  (eval "$ac_cpp conftest.$ac_ext") 2>conftest.er1
+  ac_status=$?
+  grep -v '^ *+' conftest.er1 >conftest.err
+  rm -f conftest.er1
+  cat conftest.err >&5
+  echo "$as_me:$LINENO: \$? = $ac_status" >&5
+  (exit $ac_status); } >/dev/null && {
+	 test -z "$ac_c_preproc_warn_flag$ac_c_werror_flag" ||
+	 test ! -s conftest.err
+       }; then
+  ac_header_preproc=yes
+else
+  echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+  ac_header_preproc=no
+fi
+
+rm -f conftest.err conftest.$ac_ext
+{ echo "$as_me:$LINENO: result: $ac_header_preproc" >&5
+echo "${ECHO_T}$ac_header_preproc" >&6; }
+
+# So?  What about this header?
+case $ac_header_compiler:$ac_header_preproc:$ac_c_preproc_warn_flag in
+  yes:no: )
+    { echo "$as_me:$LINENO: WARNING: valgrind/valgrind.h: accepted by the compiler, rejected by the preprocessor!" >&5
+echo "$as_me: WARNING: valgrind/valgrind.h: accepted by the compiler, rejected by the preprocessor!" >&2;}
+    { echo "$as_me:$LINENO: WARNING: valgrind/valgrind.h: proceeding with the compiler's result" >&5
+echo "$as_me: WARNING: valgrind/valgrind.h: proceeding with the compiler's result" >&2;}
+    ac_header_preproc=yes
+    ;;
+  no:yes:* )
+    { echo "$as_me:$LINENO: WARNING: valgrind/valgrind.h: present but cannot be compiled" >&5
+echo "$as_me: WARNING: valgrind/valgrind.h: present but cannot be compiled" >&2;}
+    { echo "$as_me:$LINENO: WARNING: valgrind/valgrind.h:     check for missing prerequisite headers?" >&5
+echo "$as_me: WARNING: valgrind/valgrind.h:     check for missing prerequisite headers?" >&2;}
+    { echo "$as_me:$LINENO: WARNING: valgrind/valgrind.h: see the Autoconf documentation" >&5
+echo "$as_me: WARNING: valgrind/valgrind.h: see the Autoconf documentation" >&2;}
+    { echo "$as_me:$LINENO: WARNING: valgrind/valgrind.h:     section \"Present But Cannot Be Compiled\"" >&5
+echo "$as_me: WARNING: valgrind/valgrind.h:     section \"Present But Cannot Be Compiled\"" >&2;}
+    { echo "$as_me:$LINENO: WARNING: valgrind/valgrind.h: proceeding with the preprocessor's result" >&5
+echo "$as_me: WARNING: valgrind/valgrind.h: proceeding with the preprocessor's result" >&2;}
+    { echo "$as_me:$LINENO: WARNING: valgrind/valgrind.h: in the future, the compiler will take precedence" >&5
+echo "$as_me: WARNING: valgrind/valgrind.h: in the future, the compiler will take precedence" >&2;}
+    ( cat <<\_ASBOX
+## -------------------------------------- ##
+## Report this to http://bugs.python.org/ ##
+## -------------------------------------- ##
+_ASBOX
+     ) | sed "s/^/$as_me: WARNING:     /" >&2
+    ;;
+esac
+{ echo "$as_me:$LINENO: checking for valgrind/valgrind.h" >&5
+echo $ECHO_N "checking for valgrind/valgrind.h... $ECHO_C" >&6; }
+if test "${ac_cv_header_valgrind_valgrind_h+set}" = set; then
+  echo $ECHO_N "(cached) $ECHO_C" >&6
+else
+  ac_cv_header_valgrind_valgrind_h=$ac_header_preproc
+fi
+{ echo "$as_me:$LINENO: result: $ac_cv_header_valgrind_valgrind_h" >&5
+echo "${ECHO_T}$ac_cv_header_valgrind_valgrind_h" >&6; }
+
+fi
+if test $ac_cv_header_valgrind_valgrind_h = yes; then
+
+cat >>confdefs.h <<\_ACEOF
+#define WITH_VALGRIND 1
+_ACEOF
+
+else
+  { { echo "$as_me:$LINENO: error: Valgrind support requested but headers not available" >&5
+echo "$as_me: error: Valgrind support requested but headers not available" >&2;}
+   { (exit 1); exit 1; }; }
+
+fi
+
+
+fi
+
 # Check for --with-wctype-functions
 { echo "$as_me:$LINENO: checking for --with-wctype-functions" >&5
 echo $ECHO_N "checking for --with-wctype-functions... $ECHO_C" >&6; }
diff --git a/configure.in b/configure.in
index e7e6b91..a395c97 100644
--- a/configure.in
+++ b/configure.in
@@ -2472,6 +2472,19 @@ then
 fi
 AC_MSG_RESULT($with_pymalloc)
 
+# Check for Valgrind support
+AC_MSG_CHECKING([for --with-valgrind])
+AC_ARG_WITH([valgrind],
+  AC_HELP_STRING([--with-valgrind], [Enable Valgrind support]),,
+  with_valgrind=no)
+AC_MSG_RESULT([$with_valgrind])
+if test "$with_valgrind" != no; then
+    AC_CHECK_HEADER([valgrind/valgrind.h],
+      [AC_DEFINE([WITH_VALGRIND], 1, [Define if you want pymalloc to be disabled when running under valgrind])],
+      [AC_MSG_ERROR([Valgrind support requested but headers not available])]
+    )
+fi
+
 # Check for --with-wctype-functions
 AC_MSG_CHECKING(for --with-wctype-functions)
 AC_ARG_WITH(wctype-functions, 
diff --git a/pyconfig.h.in b/pyconfig.h.in
index fd58443..85d58d1 100644
--- a/pyconfig.h.in
+++ b/pyconfig.h.in
@@ -301,9 +301,6 @@
 /* Define to 1 if you have the `getpeername' function. */
 #undef HAVE_GETPEERNAME
 
-/* Define to 1 if you have the `initgroups' function. */
-#undef HAVE_INITGROUPS
-
 /* Define to 1 if you have the `getpgid' function. */
 #undef HAVE_GETPGID
 
@@ -358,6 +355,9 @@
 /* Define if you have the 'inet_pton' function. */
 #undef HAVE_INET_PTON
 
+/* Define to 1 if you have the `initgroups' function. */
+#undef HAVE_INITGROUPS
+
 /* Define to 1 if you have the <inttypes.h> header file. */
 #undef HAVE_INTTYPES_H
 
@@ -1061,6 +1061,9 @@
 /* Define to profile with the Pentium timestamp counter */
 #undef WITH_TSC
 
+/* Define if you want pymalloc to be disabled when running under valgrind */
+#undef WITH_VALGRIND
+
 /* Define to 1 if your processor stores words with the most significant byte
    first (like Motorola and SPARC, unlike Intel and VAX). */
 #undef WORDS_BIGENDIAN