bpo-34602: Quadruple stack size on macOS when compiling with UBSAN (GH-27309)

5 files changed, 146 insertions, 113 deletions

diff --git a/Misc/NEWS.d/next/macOS/2021-08-27-16-55-10.bpo-34602.ZjHsYJ.rst b/Misc/NEWS.d/next/macOS/2021-08-27-16-55-10.bpo-34602.ZjHsYJ.rst
new file mode 100644
index 0000000..29a6ff9
--- /dev/null
+++ b/Misc/NEWS.d/next/macOS/2021-08-27-16-55-10.bpo-34602.ZjHsYJ.rst
@@ -0,0 +1,3 @@
+When building CPython on macOS with ``./configure
+--with-undefined-behavior-sanitizer --with-pydebug``, the stack size is now
+quadrupled to allow for the entire test suite to pass.
diff --git a/Python/thread_pthread.h b/Python/thread_pthread.h
index ec7d737..a45d842 100644
--- a/Python/thread_pthread.h
+++ b/Python/thread_pthread.h
@@ -32,18 +32,17 @@
 #define THREAD_STACK_SIZE       0       /* use default stack size */
 #endif
 
-/* The default stack size for new threads on OSX and BSD is small enough that
+/* The default stack size for new threads on BSD is small enough that
  * we'll get hard crashes instead of 'maximum recursion depth exceeded'
  * exceptions.
  *
- * The default stack sizes below are the empirically determined minimal stack
+ * The default stack size below is the empirically determined minimal stack
  * sizes where a simple recursive function doesn't cause a hard crash.
+ *
+ * For macOS the value of THREAD_STACK_SIZE is determined in configure.ac
+ * as it also depends on the other configure options like chosen sanitizer
+ * runtimes.
  */
-#if defined(__APPLE__) && defined(THREAD_STACK_SIZE) && THREAD_STACK_SIZE == 0
-#undef  THREAD_STACK_SIZE
-/* Note: This matches the value of -Wl,-stack_size in configure.ac */
-#define THREAD_STACK_SIZE       0x1000000
-#endif
 #if defined(__FreeBSD__) && defined(THREAD_STACK_SIZE) && THREAD_STACK_SIZE == 0
 #undef  THREAD_STACK_SIZE
 #define THREAD_STACK_SIZE       0x400000
diff --git a/configure b/configure
index 050f183..4f12972 100755
--- a/configure
+++ b/configure
@@ -827,11 +827,11 @@ with_trace_refs
 with_assertions
 enable_optimizations
 with_lto
-with_hash_algorithm
-with_tzpath
 with_address_sanitizer
 with_memory_sanitizer
 with_undefined_behavior_sanitizer
+with_hash_algorithm
+with_tzpath
 with_libs
 with_system_expat
 with_system_ffi
@@ -1548,12 +1548,6 @@ Optional Packages:
   --with-lto=[full|thin|no|yes]
                           enable Link-Time-Optimization in any build (default
                           is no)
-  --with-hash-algorithm=[fnv|siphash24]
-                          select hash algorithm for use in Python/pyhash.c
-                          (default is SipHash24)
-  --with-tzpath=<list of absolute paths separated by pathsep>
-                           Select the default time zone search path for zoneinfo.TZPATH
-
   --with-address-sanitizer
                           enable AddressSanitizer memory error detector,
                           'asan' (default is no)
@@ -1562,6 +1556,12 @@ Optional Packages:
   --with-undefined-behavior-sanitizer
                           enable UndefinedBehaviorSanitizer undefined
                           behaviour detector, 'ubsan' (default is no)
+  --with-hash-algorithm=[fnv|siphash24]
+                          select hash algorithm for use in Python/pyhash.c
+                          (default is SipHash24)
+  --with-tzpath=<list of absolute paths separated by pathsep>
+                           Select the default time zone search path for zoneinfo.TZPATH
+
   --with-libs='lib1 ...'  link against additional libs (default is no)
   --with-system-expat     build pyexpat module using an installed expat
                           library, see Doc/library/pyexpat.rst (default is no)
@@ -9602,6 +9602,65 @@ $as_echo "no" >&6; }
 	;;
 esac
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for --with-address-sanitizer" >&5
+$as_echo_n "checking for --with-address-sanitizer... " >&6; }
+
+# Check whether --with-address_sanitizer was given.
+if test "${with_address_sanitizer+set}" = set; then :
+  withval=$with_address_sanitizer;
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $withval" >&5
+$as_echo "$withval" >&6; }
+BASECFLAGS="-fsanitize=address -fno-omit-frame-pointer $BASECFLAGS"
+LDFLAGS="-fsanitize=address $LDFLAGS"
+# ASan works by controlling memory allocation, our own malloc interferes.
+with_pymalloc="no"
+
+else
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for --with-memory-sanitizer" >&5
+$as_echo_n "checking for --with-memory-sanitizer... " >&6; }
+
+# Check whether --with-memory_sanitizer was given.
+if test "${with_memory_sanitizer+set}" = set; then :
+  withval=$with_memory_sanitizer;
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $withval" >&5
+$as_echo "$withval" >&6; }
+BASECFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 -fno-omit-frame-pointer $BASECFLAGS"
+LDFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 $LDFLAGS"
+# MSan works by controlling memory allocation, our own malloc interferes.
+with_pymalloc="no"
+
+else
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for --with-undefined-behavior-sanitizer" >&5
+$as_echo_n "checking for --with-undefined-behavior-sanitizer... " >&6; }
+
+# Check whether --with-undefined_behavior_sanitizer was given.
+if test "${with_undefined_behavior_sanitizer+set}" = set; then :
+  withval=$with_undefined_behavior_sanitizer;
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $withval" >&5
+$as_echo "$withval" >&6; }
+BASECFLAGS="-fsanitize=undefined $BASECFLAGS"
+LDFLAGS="-fsanitize=undefined $LDFLAGS"
+with_ubsan="yes"
+
+else
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+with_ubsan="no"
+
+fi
+
+
 # Set info about shared libraries.
 
 
@@ -9812,9 +9871,20 @@ then
 		# Issue #18075: the default maximum stack size (8MBytes) is too
 		# small for the default recursion limit. Increase the stack size
 		# to ensure that tests don't crash
-		# Note: This matches the value of THREAD_STACK_SIZE in
-		# thread_pthread.h
-		LINKFORSHARED="-Wl,-stack_size,1000000 $LINKFORSHARED"
+    stack_size="1000000"  # 16 MB
+    if test "$with_ubsan" == "yes"
+    then
+        # Undefined behavior sanitizer requires an even deeper stack
+        stack_size="4000000"  # 64 MB
+    fi
+
+    LINKFORSHARED="-Wl,-stack_size,$stack_size $LINKFORSHARED"
+
+
+cat >>confdefs.h <<_ACEOF
+#define THREAD_STACK_SIZE 0x$stack_size
+_ACEOF
+
 
 		if test "$enable_framework"
 		then
@@ -10410,61 +10480,6 @@ fi
 
 
 
-{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for --with-address-sanitizer" >&5
-$as_echo_n "checking for --with-address-sanitizer... " >&6; }
-
-# Check whether --with-address_sanitizer was given.
-if test "${with_address_sanitizer+set}" = set; then :
-  withval=$with_address_sanitizer;
-{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $withval" >&5
-$as_echo "$withval" >&6; }
-BASECFLAGS="-fsanitize=address -fno-omit-frame-pointer $BASECFLAGS"
-LDFLAGS="-fsanitize=address $LDFLAGS"
-# ASan works by controlling memory allocation, our own malloc interferes.
-with_pymalloc="no"
-
-else
-  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
-$as_echo "no" >&6; }
-fi
-
-
-{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for --with-memory-sanitizer" >&5
-$as_echo_n "checking for --with-memory-sanitizer... " >&6; }
-
-# Check whether --with-memory_sanitizer was given.
-if test "${with_memory_sanitizer+set}" = set; then :
-  withval=$with_memory_sanitizer;
-{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $withval" >&5
-$as_echo "$withval" >&6; }
-BASECFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 -fno-omit-frame-pointer $BASECFLAGS"
-LDFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 $LDFLAGS"
-# MSan works by controlling memory allocation, our own malloc interferes.
-with_pymalloc="no"
-
-else
-  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
-$as_echo "no" >&6; }
-fi
-
-
-{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for --with-undefined-behavior-sanitizer" >&5
-$as_echo_n "checking for --with-undefined-behavior-sanitizer... " >&6; }
-
-# Check whether --with-undefined_behavior_sanitizer was given.
-if test "${with_undefined_behavior_sanitizer+set}" = set; then :
-  withval=$with_undefined_behavior_sanitizer;
-{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $withval" >&5
-$as_echo "$withval" >&6; }
-BASECFLAGS="-fsanitize=undefined $BASECFLAGS"
-LDFLAGS="-fsanitize=undefined $LDFLAGS"
-
-else
-  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
-$as_echo "no" >&6; }
-fi
-
-
 # Most SVR4 platforms (e.g. Solaris) need -lsocket and -lnsl.
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for t_open in -lnsl" >&5
 $as_echo_n "checking for t_open in -lnsl... " >&6; }
diff --git a/configure.ac b/configure.ac
index aaff79f..e01e0c1 100644
--- a/configure.ac
+++ b/configure.ac
@@ -2595,6 +2595,47 @@ case $ac_sys_system/$ac_sys_release in
 	;;
 esac
 
+AC_MSG_CHECKING(for --with-address-sanitizer)
+AC_ARG_WITH(address_sanitizer,
+            AS_HELP_STRING([--with-address-sanitizer],
+                           [enable AddressSanitizer memory error detector, 'asan' (default is no)]),
+[
+AC_MSG_RESULT($withval)
+BASECFLAGS="-fsanitize=address -fno-omit-frame-pointer $BASECFLAGS"
+LDFLAGS="-fsanitize=address $LDFLAGS"
+# ASan works by controlling memory allocation, our own malloc interferes.
+with_pymalloc="no"
+],
+[AC_MSG_RESULT(no)])
+
+AC_MSG_CHECKING(for --with-memory-sanitizer)
+AC_ARG_WITH(memory_sanitizer,
+            AS_HELP_STRING([--with-memory-sanitizer],
+                           [enable MemorySanitizer allocation error detector, 'msan' (default is no)]),
+[
+AC_MSG_RESULT($withval)
+BASECFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 -fno-omit-frame-pointer $BASECFLAGS"
+LDFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 $LDFLAGS"
+# MSan works by controlling memory allocation, our own malloc interferes.
+with_pymalloc="no"
+],
+[AC_MSG_RESULT(no)])
+
+AC_MSG_CHECKING(for --with-undefined-behavior-sanitizer)
+AC_ARG_WITH(undefined_behavior_sanitizer,
+            AS_HELP_STRING([--with-undefined-behavior-sanitizer],
+                           [enable UndefinedBehaviorSanitizer undefined behaviour detector, 'ubsan' (default is no)]),
+[
+AC_MSG_RESULT($withval)
+BASECFLAGS="-fsanitize=undefined $BASECFLAGS"
+LDFLAGS="-fsanitize=undefined $LDFLAGS"
+with_ubsan="yes"
+],
+[
+AC_MSG_RESULT(no)
+with_ubsan="no"
+])
+
 # Set info about shared libraries.
 AC_SUBST(SHLIB_SUFFIX)
 AC_SUBST(LDSHARED)
@@ -2798,9 +2839,18 @@ then
 		# Issue #18075: the default maximum stack size (8MBytes) is too
 		# small for the default recursion limit. Increase the stack size
 		# to ensure that tests don't crash
-		# Note: This matches the value of THREAD_STACK_SIZE in
-		# thread_pthread.h
-		LINKFORSHARED="-Wl,-stack_size,1000000 $LINKFORSHARED"
+    stack_size="1000000"  # 16 MB
+    if test "$with_ubsan" == "yes"
+    then
+        # Undefined behavior sanitizer requires an even deeper stack
+        stack_size="4000000"  # 64 MB
+    fi
+
+    LINKFORSHARED="-Wl,-stack_size,$stack_size $LINKFORSHARED"
+
+    AC_DEFINE_UNQUOTED(THREAD_STACK_SIZE,
+        0x$stack_size,
+        [Custom thread stack size depending on chosen sanitizer runtimes.])
 
 		if test "$enable_framework"
 		then
@@ -3044,43 +3094,6 @@ esac
  AC_MSG_RESULT("$TZPATH")])
 AC_SUBST(TZPATH)
 
-AC_MSG_CHECKING(for --with-address-sanitizer)
-AC_ARG_WITH(address_sanitizer,
-            AS_HELP_STRING([--with-address-sanitizer],
-                           [enable AddressSanitizer memory error detector, 'asan' (default is no)]),
-[
-AC_MSG_RESULT($withval)
-BASECFLAGS="-fsanitize=address -fno-omit-frame-pointer $BASECFLAGS"
-LDFLAGS="-fsanitize=address $LDFLAGS"
-# ASan works by controlling memory allocation, our own malloc interferes.
-with_pymalloc="no"
-],
-[AC_MSG_RESULT(no)])
-
-AC_MSG_CHECKING(for --with-memory-sanitizer)
-AC_ARG_WITH(memory_sanitizer,
-            AS_HELP_STRING([--with-memory-sanitizer],
-                           [enable MemorySanitizer allocation error detector, 'msan' (default is no)]),
-[
-AC_MSG_RESULT($withval)
-BASECFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 -fno-omit-frame-pointer $BASECFLAGS"
-LDFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 $LDFLAGS"
-# MSan works by controlling memory allocation, our own malloc interferes.
-with_pymalloc="no"
-],
-[AC_MSG_RESULT(no)])
-
-AC_MSG_CHECKING(for --with-undefined-behavior-sanitizer)
-AC_ARG_WITH(undefined_behavior_sanitizer,
-            AS_HELP_STRING([--with-undefined-behavior-sanitizer],
-                           [enable UndefinedBehaviorSanitizer undefined behaviour detector, 'ubsan' (default is no)]),
-[
-AC_MSG_RESULT($withval)
-BASECFLAGS="-fsanitize=undefined $BASECFLAGS"
-LDFLAGS="-fsanitize=undefined $LDFLAGS"
-],
-[AC_MSG_RESULT(no)])
-
 # Most SVR4 platforms (e.g. Solaris) need -lsocket and -lnsl.
 AC_CHECK_LIB(nsl, t_open, [LIBS="-lnsl $LIBS"]) # SVR4
 AC_CHECK_LIB(socket, socket, [LIBS="-lsocket $LIBS"], [], $LIBS) # SVR4 sockets
diff --git a/pyconfig.h.in b/pyconfig.h.in
index 63438d8..49407ab 100644
--- a/pyconfig.h.in
+++ b/pyconfig.h.in
@@ -1509,6 +1509,9 @@
    (which you can't on SCO ODT 3.0). */
 #undef SYS_SELECT_WITH_SYS_TIME
 
+/* Custom thread stack size depending on chosen sanitizer runtimes. */
+#undef THREAD_STACK_SIZE
+
 /* Library needed by timemodule.c: librt may be needed for clock_gettime() */
 #undef TIMEMODULE_LIB