gh-97670: Remove sys.getdxp() and analyze_dxp.py script (#97671)

Remove the sys.getdxp() function and the Tools/scripts/analyze_dxp.py
script. DXP stands for "dynamic execution pairs". They were related
to DYNAMIC_EXECUTION_PROFILE and DXPAIRS macros which have been
removed in Python 3.11. Python can now be built with "./configure
--enable-pystats" to gather statistics on Python opcodes.

6 files changed, 7 insertions, 201 deletions

diff --git a/Lib/test/test_tools/test_sundry.py b/Lib/test/test_tools/test_sundry.py
index 52369ec..ed03c2f 100644
--- a/Lib/test/test_tools/test_sundry.py
+++ b/Lib/test/test_tools/test_sundry.py
@@ -25,7 +25,7 @@ class TestSundryScripts(unittest.TestCase):
     # scripts that use windows-only modules
     windows_only = ['win_add2path']
     # denylisted for other reasons
-    other = ['analyze_dxp', '2to3']
+    other = ['2to3']
 
     skiplist = denylist + allowlist + windows_only + other
 
@@ -50,13 +50,6 @@ class TestSundryScripts(unittest.TestCase):
         for name in self.windows_only:
             import_tool(name)
 
-    def test_analyze_dxp_import(self):
-        if hasattr(sys, 'getdxp'):
-            import_tool('analyze_dxp')
-        else:
-            with self.assertRaises(RuntimeError):
-                import_tool('analyze_dxp')
-
 
 if __name__ == '__main__':
     unittest.main()
diff --git a/Misc/NEWS.d/next/Core and Builtins/2022-09-30-13-26-58.gh-issue-97670.n61vMR.rst b/Misc/NEWS.d/next/Core and Builtins/2022-09-30-13-26-58.gh-issue-97670.n61vMR.rst
new file mode 100644
index 0000000..50b4787
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2022-09-30-13-26-58.gh-issue-97670.n61vMR.rst
@@ -0,0 +1,6 @@
+Remove the :func:`sys.getdxp` function and the ``Tools/scripts/analyze_dxp.py``
+script. DXP stands for "dynamic execution pairs". They were related to
+``DYNAMIC_EXECUTION_PROFILE`` and ``DXPAIRS`` macros which have been removed in
+Python 3.11. Python can now be built with :option:`./configure --enable-pystats
+<--enable-pystats>` to gather statistics on Python opcodes.  Patch by Victor
+Stinner.
diff --git a/Python/ceval.c b/Python/ceval.c
index 9453770..82b5422 100644
--- a/Python/ceval.c
+++ b/Python/ceval.c
@@ -7207,61 +7207,6 @@ format_awaitable_error(PyThreadState *tstate, PyTypeObject *type, int oparg)
     }
 }
 
-#ifdef Py_STATS
-
-static PyObject *
-getarray(uint64_t a[256])
-{
-    int i;
-    PyObject *l = PyList_New(256);
-    if (l == NULL) return NULL;
-    for (i = 0; i < 256; i++) {
-        PyObject *x = PyLong_FromUnsignedLongLong(a[i]);
-        if (x == NULL) {
-            Py_DECREF(l);
-            return NULL;
-        }
-        PyList_SET_ITEM(l, i, x);
-    }
-    for (i = 0; i < 256; i++)
-        a[i] = 0;
-    return l;
-}
-
-PyObject *
-_Py_GetDXProfile(PyObject *self, PyObject *args)
-{
-    int i;
-    PyObject *l = PyList_New(257);
-    if (l == NULL) return NULL;
-    for (i = 0; i < 256; i++) {
-        PyObject *x = getarray(_py_stats_struct.opcode_stats[i].pair_count);
-        if (x == NULL) {
-            Py_DECREF(l);
-            return NULL;
-        }
-        PyList_SET_ITEM(l, i, x);
-    }
-    PyObject *counts = PyList_New(256);
-    if (counts == NULL) {
-        Py_DECREF(l);
-        return NULL;
-    }
-    for (i = 0; i < 256; i++) {
-        PyObject *x = PyLong_FromUnsignedLongLong(
-            _py_stats_struct.opcode_stats[i].execution_count);
-        if (x == NULL) {
-            Py_DECREF(counts);
-            Py_DECREF(l);
-            return NULL;
-        }
-        PyList_SET_ITEM(counts, i, x);
-    }
-    PyList_SET_ITEM(l, 256, counts);
-    return l;
-}
-
-#endif
 
 Py_ssize_t
 _PyEval_RequestCodeExtraIndex(freefunc free)
diff --git a/Python/sysmodule.c b/Python/sysmodule.c
index 584a8be..1ecf6a2 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -2014,11 +2014,6 @@ sys__debugmallocstats_impl(PyObject *module)
 extern PyObject *_Py_GetObjects(PyObject *, PyObject *);
 #endif
 
-#ifdef Py_STATS
-/* Defined in ceval.c because it uses static globals in that file */
-extern PyObject *_Py_GetDXProfile(PyObject *,  PyObject *);
-#endif
-
 #ifdef __cplusplus
 }
 #endif
@@ -2217,9 +2212,6 @@ static PyMethodDef sys_methods[] = {
     SYS_GETDEFAULTENCODING_METHODDEF
     SYS_GETDLOPENFLAGS_METHODDEF
     SYS_GETALLOCATEDBLOCKS_METHODDEF
-#ifdef Py_STATS
-    {"getdxp", _Py_GetDXProfile, METH_VARARGS},
-#endif
     SYS_GETFILESYSTEMENCODING_METHODDEF
     SYS_GETFILESYSTEMENCODEERRORS_METHODDEF
     SYS__GETQUICKENEDCOUNT_METHODDEF
diff --git a/Tools/scripts/README b/Tools/scripts/README
index 6affa67..b53b0f2 100644
--- a/Tools/scripts/README
+++ b/Tools/scripts/README
@@ -3,7 +3,6 @@ useful while building, extending or managing Python.
 
 2to3                      Main script for running the 2to3 conversion tool
 abitype.py                Converts a C file to use the PEP 384 type definition API
-analyze_dxp.py            Analyzes the result of sys.getdxp()
 combinerefs.py            A helper for analyzing PYTHONDUMPREFS output
 diff.py                   Print file diffs in context, unified, or ndiff formats
 eptags.py                 Create Emacs TAGS file for Python modules
diff --git a/Tools/scripts/analyze_dxp.py b/Tools/scripts/analyze_dxp.py
deleted file mode 100644
index bde931e..0000000
--- a/Tools/scripts/analyze_dxp.py
+++ /dev/null
@@ -1,129 +0,0 @@
-"""
-Some helper functions to analyze the output of sys.getdxp() (which is
-only available if Python was built with -DDYNAMIC_EXECUTION_PROFILE).
-These will tell you which opcodes have been executed most frequently
-in the current process, and, if Python was also built with -DDXPAIRS,
-will tell you which instruction _pairs_ were executed most frequently,
-which may help in choosing new instructions.
-
-If Python was built without -DDYNAMIC_EXECUTION_PROFILE, importing
-this module will raise a RuntimeError.
-
-If you're running a script you want to profile, a simple way to get
-the common pairs is:
-
-$ PYTHONPATH=$PYTHONPATH:<python_srcdir>/Tools/scripts \
-./python -i -O the_script.py --args
-...
-> from analyze_dxp import *
-> s = render_common_pairs()
-> open('/tmp/some_file', 'w').write(s)
-"""
-
-import copy
-import opcode
-import operator
-import sys
-import threading
-
-if not hasattr(sys, "getdxp"):
-    raise RuntimeError("Can't import analyze_dxp: Python built without"
-                       " -DDYNAMIC_EXECUTION_PROFILE.")
-
-
-_profile_lock = threading.RLock()
-_cumulative_profile = sys.getdxp()
-
-# If Python was built with -DDXPAIRS, sys.getdxp() returns a list of
-# lists of ints.  Otherwise it returns just a list of ints.
-def has_pairs(profile):
-    """Returns True if the Python that produced the argument profile
-    was built with -DDXPAIRS."""
-
-    return len(profile) > 0 and isinstance(profile[0], list)
-
-
-def reset_profile():
-    """Forgets any execution profile that has been gathered so far."""
-    with _profile_lock:
-        sys.getdxp()  # Resets the internal profile
-        global _cumulative_profile
-        _cumulative_profile = sys.getdxp()  # 0s out our copy.
-
-
-def merge_profile():
-    """Reads sys.getdxp() and merges it into this module's cached copy.
-
-    We need this because sys.getdxp() 0s itself every time it's called."""
-
-    with _profile_lock:
-        new_profile = sys.getdxp()
-        if has_pairs(new_profile):
-            for first_inst in range(len(_cumulative_profile)):
-                for second_inst in range(len(_cumulative_profile[first_inst])):
-                    _cumulative_profile[first_inst][second_inst] += (
-                        new_profile[first_inst][second_inst])
-        else:
-            for inst in range(len(_cumulative_profile)):
-                _cumulative_profile[inst] += new_profile[inst]
-
-
-def snapshot_profile():
-    """Returns the cumulative execution profile until this call."""
-    with _profile_lock:
-        merge_profile()
-        return copy.deepcopy(_cumulative_profile)
-
-
-def common_instructions(profile):
-    """Returns the most common opcodes in order of descending frequency.
-
-    The result is a list of tuples of the form
-      (opcode, opname, # of occurrences)
-
-    """
-    if has_pairs(profile) and profile:
-        inst_list = profile[-1]
-    else:
-        inst_list = profile
-    result = [(op, opcode.opname[op], count)
-              for op, count in enumerate(inst_list)
-              if count > 0]
-    result.sort(key=operator.itemgetter(2), reverse=True)
-    return result
-
-
-def common_pairs(profile):
-    """Returns the most common opcode pairs in order of descending frequency.
-
-    The result is a list of tuples of the form
-      ((1st opcode, 2nd opcode),
-       (1st opname, 2nd opname),
-       # of occurrences of the pair)
-
-    """
-    if not has_pairs(profile):
-        return []
-    result = [((op1, op2), (opcode.opname[op1], opcode.opname[op2]), count)
-              # Drop the row of single-op profiles with [:-1]
-              for op1, op1profile in enumerate(profile[:-1])
-              for op2, count in enumerate(op1profile)
-              if count > 0]
-    result.sort(key=operator.itemgetter(2), reverse=True)
-    return result
-
-
-def render_common_pairs(profile=None):
-    """Renders the most common opcode pairs to a string in order of
-    descending frequency.
-
-    The result is a series of lines of the form:
-      # of occurrences: ('1st opname', '2nd opname')
-
-    """
-    if profile is None:
-        profile = snapshot_profile()
-    def seq():
-        for _, ops, count in common_pairs(profile):
-            yield "%s: %s\n" % (count, ops)
-    return ''.join(seq())