Backport python#128159 to Python 3.13.

Author: yilei

Include/internal/pycore_faulthandler.h

@@ -56,6 +56,7 @@ struct _faulthandler_runtime_state {
 #ifdef MS_WINDOWS
         void *exc_handler;
 #endif
+        int c_stack;
     } fatal_error;
 
     struct {

Include/internal/pycore_traceback.h

@@ -100,6 +100,9 @@ extern int _PyTraceBack_Print(
 extern int _Py_WriteIndentedMargin(int, const char*, PyObject *);
 extern int _Py_WriteIndent(int, PyObject *);
 
+// Export for the faulthandler module
+PyAPI_FUNC(void) _Py_DumpStack(int fd);
+
 #ifdef __cplusplus
 }
 #endif

Lib/test/test_faulthandler.py

@@ -45,6 +45,13 @@ def temporary_filename():
     finally:
         os_helper.unlink(filename)
 
+
+ADDRESS_EXPR = "0x[0-9a-f]+"
+C_STACK_REGEX = [
+    r"Current thread's C stack trace \(most recent call first\):",
+    fr'(  Binary file ".+"(, at .*(\+|-){ADDRESS_EXPR})? \[{ADDRESS_EXPR}\])|(<.+>)'
+]
+
 class FaultHandlerTests(unittest.TestCase):
 
     def get_output(self, code, filename=None, fd=None):
@@ -93,6 +100,7 @@ def check_error(self, code, lineno, fatal_error, *,
                     fd=None, know_current_thread=True,
                     py_fatal_error=False,
                     garbage_collecting=False,
+                    c_stack=True,
                     function='<module>'):
         """
         Check that the fault handler for fatal errors is enabled and check the
@@ -115,6 +123,8 @@ def check_error(self, code, lineno, fatal_error, *,
         if garbage_collecting:
             regex.append('  Garbage-collecting')
         regex.append(fr'  File "<string>", line {lineno} in {function}')
+        if c_stack:
+            regex.extend(C_STACK_REGEX)
         regex = '\n'.join(regex)
 
         if other_regex:
@@ -599,6 +609,50 @@ def test_dump_traceback_threads_file(self):
         with temporary_filename() as filename:
             self.check_dump_traceback_threads(filename)
 
+    def check_c_stack(self, *, filename=None, fd=None):
+        """
+        Explicitly call dump_c_stack() function and check its output.
+        Raise an error if the output doesn't match the expected format.
+        """
+        code = """
+            import faulthandler
+
+            filename = {filename!r}
+            fd = {fd}
+
+            def funcB():
+                if filename:
+                    with open(filename, "wb") as fp:
+                        faulthandler.dump_c_stack(fp)
+                elif fd is not None:
+                    faulthandler.dump_c_stack(fd)
+                else:
+                    faulthandler.dump_c_stack()
+
+            def funcA():
+                funcB()
+
+            funcA()
+            """
+        code = code.format(
+            filename=filename,
+            fd=fd,
+        )
+        trace, exitcode = self.get_output(code, filename, fd)
+        trace = '\n'.join(trace)
+        # The C stack trace should contain the header
+        self.assertRegex(trace, r"Current thread's C stack trace \(most recent call first\):")
+        # And at least one frame with an address
+        self.assertRegex(trace, r'\[0x[0-9a-f]+\]')
+        self.assertEqual(exitcode, 0)
+
+    def test_dump_c_stack(self):
+        self.check_c_stack()
+
+    def test_dump_c_stack_file(self):
+        with temporary_filename() as filename:
+            self.check_c_stack(filename=filename)
+
     def check_dump_traceback_later(self, repeat=False, cancel=False, loops=1,
                                    *, filename=None, fd=None):
         """

Lib/test/test_inspect/test_inspect.py

@@ -6228,7 +6228,7 @@ def test_errno_module_has_signatures(self):
 
     def test_faulthandler_module_has_signatures(self):
         import faulthandler
-        unsupported_signature = {'dump_traceback', 'dump_traceback_later', 'enable'}
+        unsupported_signature = {'dump_c_stack', 'dump_traceback', 'dump_traceback_later', 'enable'}
         unsupported_signature |= {name for name in ['register']
                                   if hasattr(faulthandler, name)}
         self._test_module_has_signatures(faulthandler, unsupported_signature=unsupported_signature)

Modules/faulthandler.c

@@ -218,6 +218,25 @@ faulthandler_dump_traceback(int fd, int all_threads,
     reentrant = 0;
 }
 
+static void
+faulthandler_dump_c_stack(int fd)
+{
+    static volatile int reentrant = 0;
+
+    if (reentrant) {
+        return;
+    }
+
+    reentrant = 1;
+
+    if (fatal_error.c_stack) {
+        PUTS(fd, "\n");
+        _Py_DumpStack(fd);
+    }
+
+    reentrant = 0;
+}
+
 static PyObject*
 faulthandler_dump_traceback_py(PyObject *self,
                                PyObject *args, PyObject *kwargs)
@@ -268,6 +287,33 @@ faulthandler_dump_traceback_py(PyObject *self,
     Py_RETURN_NONE;
 }
 
+static PyObject *
+faulthandler_dump_c_stack_py(PyObject *self,
+                             PyObject *args, PyObject *kwargs)
+{
+    static char *kwlist[] = {"file", NULL};
+    PyObject *file = NULL;
+
+    if (!PyArg_ParseTupleAndKeywords(args, kwargs,
+        "|O:dump_c_stack", kwlist,
+        &file)) {
+        return NULL;
+    }
+
+    int fd = faulthandler_get_fileno(&file);
+    if (fd < 0) {
+        return NULL;
+    }
+
+    _Py_DumpStack(fd);
+
+    if (PyErr_CheckSignals()) {
+        return NULL;
+    }
+
+    Py_RETURN_NONE;
+}
+
 static void
 faulthandler_disable_fatal_handler(fault_handler_t *handler)
 {
@@ -337,6 +383,7 @@ faulthandler_fatal_error(int signum)
 
     faulthandler_dump_traceback(fd, fatal_error.all_threads,
                                 fatal_error.interp);
+    faulthandler_dump_c_stack(fd);
 
     _Py_DumpExtensionModules(fd, fatal_error.interp);
 
@@ -413,6 +460,7 @@ faulthandler_exc_handler(struct _EXCEPTION_POINTERS *exc_info)
 
     faulthandler_dump_traceback(fd, fatal_error.all_threads,
                                 fatal_error.interp);
+    faulthandler_dump_c_stack(fd);
 
     /* call the next exception handler */
     return EXCEPTION_CONTINUE_SEARCH;
@@ -507,14 +555,15 @@ faulthandler_enable(void)
 static PyObject*
 faulthandler_py_enable(PyObject *self, PyObject *args, PyObject *kwargs)
 {
-    static char *kwlist[] = {"file", "all_threads", NULL};
+    static char *kwlist[] = {"file", "all_threads", "c_stack", NULL};
     PyObject *file = NULL;
     int all_threads = 1;
     int fd;
+    int c_stack = 1;
     PyThreadState *tstate;
 
     if (!PyArg_ParseTupleAndKeywords(args, kwargs,
-        "|Op:enable", kwlist, &file, &all_threads))
+        "|Opp:enable", kwlist, &file, &all_threads, &c_stack))
         return NULL;
 
     fd = faulthandler_get_fileno(&file);
@@ -531,6 +580,7 @@ faulthandler_py_enable(PyObject *self, PyObject *args, PyObject *kwargs)
     fatal_error.fd = fd;
     fatal_error.all_threads = all_threads;
     fatal_error.interp = PyThreadState_GetInterpreter(tstate);
+    fatal_error.c_stack = c_stack;
 
     if (faulthandler_enable() < 0) {
         return NULL;
@@ -1226,6 +1276,10 @@ static PyMethodDef module_methods[] = {
      PyDoc_STR("dump_traceback($module, /, file=sys.stderr, all_threads=True)\n--\n\n"
                "Dump the traceback of the current thread, or of all threads "
                "if all_threads is True, into file.")},
+     {"dump_c_stack",
+      _PyCFunction_CAST(faulthandler_dump_c_stack_py), METH_VARARGS|METH_KEYWORDS,
+      PyDoc_STR("dump_c_stack($module, /, file=sys.stderr)\n--\n\n"
+              "Dump the C stack of the current thread.")},
     {"dump_traceback_later",
      _PyCFunction_CAST(faulthandler_dump_traceback_later), METH_VARARGS|METH_KEYWORDS,
      PyDoc_STR("dump_traceback_later($module, /, timeout, repeat=False, file=sys.stderr, exit=False)\n--\n\n"

Python/traceback.c

@@ -21,7 +21,25 @@
 #ifdef HAVE_UNISTD_H
 #  include <unistd.h>             // lseek()
 #endif
+#if defined(HAVE_EXECINFO_H) && defined(HAVE_DLFCN_H) && defined(HAVE_LINK_H)
+#  include <execinfo.h>           // backtrace(), backtrace_symbols()
+#  include <dlfcn.h>              // dladdr1()
+#  include <link.h>               // struct DL_info
+#  if defined(HAVE_BACKTRACE) && defined(HAVE_BACKTRACE_SYMBOLS) && defined(HAVE_DLADDR1)
+#    define CAN_C_BACKTRACE
+#  endif
+#endif
 
+#if defined(__STDC_NO_VLA__) && (__STDC_NO_VLA__ == 1)
+/* Use alloca() for VLAs. */
+#  define VLA(type, name, size) type *name = alloca(size)
+#elif !defined(__STDC_NO_VLA__) || (__STDC_NO_VLA__ == 0)
+/* Use actual C VLAs.*/
+#  define VLA(type, name, size) type name[size]
+#elif defined(CAN_C_BACKTRACE)
+/* VLAs are not possible. Disable C stack trace functions. */
+#  undef CAN_C_BACKTRACE
+#endif
 
 #define OFF(x) offsetof(PyTracebackObject, x)
 #define PUTS(fd, str) (void)_Py_write_noraise(fd, str, (int)strlen(str))
@@ -1110,3 +1128,94 @@ _Py_DumpTracebackThreads(int fd, PyInterpreterState *interp,
     return NULL;
 }
 
+#ifdef CAN_C_BACKTRACE
+/* Based on glibc's implementation of backtrace_symbols(), but only uses stack memory. */
+void
+_Py_backtrace_symbols_fd(int fd, void *const *array, Py_ssize_t size)
+{
+    VLA(Dl_info, info, size);
+    VLA(int, status, size);
+    /* Fill in the information we can get from dladdr() */
+    for (Py_ssize_t i = 0; i < size; ++i) {
+        struct link_map *map;
+        status[i] = dladdr1(array[i], &info[i], (void **)&map, RTLD_DL_LINKMAP);
+        if (status[i] != 0
+            && info[i].dli_fname != NULL
+            && info[i].dli_fname[0] != '\0') {
+            /* The load bias is more useful to the user than the load
+               address. The use of these addresses is to calculate an
+               address in the ELF file, so its prelinked bias is not
+               something we want to subtract out */
+            info[i].dli_fbase = (void *) map->l_addr;
+        }
+    }
+    for (Py_ssize_t i = 0; i < size; ++i) {
+        if (status[i] == 0
+            || info[i].dli_fname == NULL
+            || info[i].dli_fname[0] == '\0'
+        ) {
+            dprintf(fd, "  Binary file '<unknown>' [%p]\n", array[i]);
+            continue;
+        }
+
+        if (info[i].dli_sname == NULL) {
+            /* We found no symbol name to use, so describe it as
+               relative to the file. */
+            info[i].dli_saddr = info[i].dli_fbase;
+        }
+
+        if (info[i].dli_sname == NULL
+            && info[i].dli_saddr == 0) {
+            dprintf(fd, "  Binary file \"%s\" [%p]\n",
+                    info[i].dli_fname,
+                    array[i]);
+        }
+        else {
+            char sign;
+            ptrdiff_t offset;
+            if (array[i] >= (void *) info[i].dli_saddr) {
+                sign = '+';
+                offset = array[i] - info[i].dli_saddr;
+            }
+            else {
+                sign = '-';
+                offset = info[i].dli_saddr - array[i];
+            }
+            const char *symbol_name = info[i].dli_sname != NULL ? info[i].dli_sname : "";
+            dprintf(fd, "  Binary file \"%s\", at %s%c%#tx [%p]\n",
+                    info[i].dli_fname,
+                    symbol_name,
+                    sign, offset, array[i]);
+        }
+    }
+}
+
+void
+_Py_DumpStack(int fd)
+{
+#define BACKTRACE_SIZE 32
+    PUTS(fd, "Current thread's C stack trace (most recent call first):\n");
+    VLA(void *, callstack, BACKTRACE_SIZE);
+    int frames = backtrace(callstack, BACKTRACE_SIZE);
+    if (frames == 0) {
+        // Some systems won't return anything for the stack trace
+        PUTS(fd, "  <system returned no stack trace>\n");
+        return;
+    }
+
+    _Py_backtrace_symbols_fd(fd, callstack, frames);
+    if (frames == BACKTRACE_SIZE) {
+        PUTS(fd, "  <truncated rest of calls>\n");
+    }
+
+#undef BACKTRACE_SIZE
+}
+#else
+void
+_Py_DumpStack(int fd)
+{
+    PUTS(fd, "Current thread's C stack trace (most recent call first):\n");
+    PUTS(fd, "  <cannot get C stack on this system>\n");
+}
+#endif
+

Tools/c-analyzer/cpython/ignored.tsv

@@ -160,6 +160,7 @@ Python/sysmodule.c	-	_preinit_xoptions	-
 # thread-safety
 # XXX need race protection?
 Modules/faulthandler.c	faulthandler_dump_traceback	reentrant	-
+Modules/faulthandler.c	faulthandler_dump_c_stack	reentrant	-
 Python/pylifecycle.c	_Py_FatalErrorFormat	reentrant	-
 Python/pylifecycle.c	fatal_error	reentrant	-