pythongh-115382: Remove foreign import paths from cross compiles

Previously, when a build was configured to use a host interpreter via
--with-build-python, the PYTHON_FOR_BUILD config value included a path
in PYTHONPATH that pointed to the target's built external modules.

For "normal" foreign architecture cross compiles, when loading compiled
external libraries, the target libraries were processed first due to
their precedence in sys.path. These libraries are then ruled out because
of a mismatch in the SOABI so the import mechanism continues searching
in sys.path for modules until it finds the host's native modules.

However, if the host interpreter and the target python are on the same
version + SOABI combination, the host interpreter would attempt to load
the target's external modules due precedence in sys.path.

Despite the "match", the target build may be linked against a different
libc or may include instructions that are not supported on the host, so
loading/executing the target's external modules can lead to crashes.

Now, the path to the target's external modules is no longer in PYTHONPATH
to prevent accidentally loading these foreign modules.

Some build scripts need to interrogate sysconfig via `get_config_var{s}`
to determine what target modules were built as well as other target
specific config values.

This was previously done by specifying _PYTHON_SYSCONFIGDATA_NAME in the
environment and leveraging the target's module path in PYTHONPATH so it
could be imported in sysconfig._init_posix.

These build scripts now check if the environment is configured to use a
host interpreter and will now load the target's sysconfigdata module
based on the information in the environment and query it as necessary.

Signed-off-by: Vincent Fazio <[email protected]>

Author: vfazio

Lib/ensurepip/__init__.py

@@ -24,7 +24,29 @@
 # policies recommend against bundling dependencies. For example, Fedora
 # installs wheel packages in the /usr/share/python-wheels/ directory and don't
 # install the ensurepip._bundled package.
-_WHEEL_PKG_DIR = sysconfig.get_config_var('WHEEL_PKG_DIR')
+if '_PYTHON_HOST_PLATFORM' in os.environ:
+    # When invoked during a cross compile, use the sysconfigdata file from the build directory.
+    _WHEEL_PKG_DIR = None
+
+    from importlib.machinery import FileFinder, SourceFileLoader, SOURCE_SUFFIXES
+    from importlib.util import module_from_spec
+
+    build_dir = os.environ.get("_PYTHON_PROJECT_BASE")
+    pybuild = os.path.join(build_dir, "pybuilddir.txt")
+    if os.path.exists(pybuild):
+        with open(pybuild, encoding="utf-8") as f:
+            builddir = f.read()
+        target_lib_dir = os.path.join(build_dir, builddir)
+        spec = FileFinder(target_lib_dir ,(SourceFileLoader, SOURCE_SUFFIXES)).find_spec(
+            os.environ.get("_PYTHON_SYSCONFIGDATA_NAME")
+        )
+        if spec is not None:
+            target_module = module_from_spec(spec)
+            spec.loader.exec_module(target_module)
+
+            _WHEEL_PKG_DIR = target_module.build_time_vars.get('WHEEL_PKG_DIR')
+else:
+    _WHEEL_PKG_DIR = sysconfig.get_config_var('WHEEL_PKG_DIR')
 
 
 def _find_packages(path):

Tools/build/check_extension_modules.py

@@ -125,6 +125,41 @@ def __bool__(self):
 
 ModuleInfo = collections.namedtuple("ModuleInfo", "name state")
 
+class _SysConfigShim:
+    """
+    A class to shim the sysconfig data from the cross compile build directory.
+
+    It's not safe to include foreign import directories in sys.path as the host
+    compatible interpreter may attempt to load libraries it's incompatible with.
+
+    However, we need to interrogate the target build to check that modules were
+    compiled correctly so we need to load data from sysconfigdata that resides
+    in the build directory.
+    """
+    def __init__(self, lib_path: pathlib.Path):
+        from importlib.machinery import FileFinder, SourceFileLoader, SOURCE_SUFFIXES
+        from importlib.util import module_from_spec
+
+        configdata = os.environ.get("_PYTHON_SYSCONFIGDATA_NAME")
+        if configdata is None:
+            raise RuntimeError(f'_PYTHON_SYSCONFIGDATA_NAME is required for cross compilation')
+        spec = FileFinder(str(lib_path) ,(SourceFileLoader, SOURCE_SUFFIXES)).find_spec(configdata)
+        if spec is None:
+            raise RuntimeError(f'Could not find find sysconfig data for {configdata}')
+
+        self.target_module = module_from_spec(spec)
+        spec.loader.exec_module(self.target_module)
+
+    def get_config_var(self, name: str):
+        return self.get_config_vars().get(name)
+
+    def get_config_vars(self, *args):
+        if args:
+            vals = []
+            for name in args:
+                vals.append(self.target_module.build_time_vars.get(name))
+            return vals
+        return self.target_module.build_time_vars
 
 class ModuleChecker:
     pybuilddir_txt = "pybuilddir.txt"
@@ -139,10 +174,15 @@ class ModuleChecker:
 
     def __init__(self, cross_compiling: bool = False, strict: bool = False):
         self.cross_compiling = cross_compiling
+        self.builddir = self.get_builddir()
+        if self.cross_compiling:
+            shim = _SysConfigShim(self.builddir)
+            sysconfig.get_config_var = shim.get_config_var
+            sysconfig.get_config_vars = shim.get_config_vars
+
         self.strict_extensions_build = strict
         self.ext_suffix = sysconfig.get_config_var("EXT_SUFFIX")
         self.platform = sysconfig.get_platform()
-        self.builddir = self.get_builddir()
         self.modules = self.get_modules()
 
         self.builtin_ok = []

configure

@@ -164,7 +164,7 @@ AC_ARG_WITH([build-python],
     dnl Build Python interpreter is used for regeneration and freezing.
     ac_cv_prog_PYTHON_FOR_REGEN=$with_build_python
     PYTHON_FOR_FREEZE="$with_build_python"
-    PYTHON_FOR_BUILD='_PYTHON_PROJECT_BASE=$(abs_builddir) _PYTHON_HOST_PLATFORM=$(_PYTHON_HOST_PLATFORM) PYTHONPATH=$(shell test -f pybuilddir.txt && echo $(abs_builddir)/`cat pybuilddir.txt`:)$(srcdir)/Lib _PYTHON_SYSCONFIGDATA_NAME=_sysconfigdata_$(ABIFLAGS)_$(MACHDEP)_$(MULTIARCH) '$with_build_python
+    PYTHON_FOR_BUILD='_PYTHON_PROJECT_BASE=$(abs_builddir) _PYTHON_HOST_PLATFORM=$(_PYTHON_HOST_PLATFORM) PYTHONPATH=$(srcdir)/Lib _PYTHON_SYSCONFIGDATA_NAME=_sysconfigdata_$(ABIFLAGS)_$(MACHDEP)_$(MULTIARCH) '$with_build_python
     AC_MSG_RESULT([$with_build_python])
   ], [
     AS_VAR_IF([cross_compiling], [yes],