gh-109587: Allow "precompiled" perf-trampolines to largely mitigate the cost of enabling perf-trampolines (#109666)

Lib/test/test_perf_profiler.py

@@ -353,6 +353,82 @@ class TestPerfProfiler(unittest.TestCase):
             self.assertNotIn(f"py::bar:{script}", stdout)
             self.assertNotIn(f"py::baz:{script}", stdout)
 
+    def test_pre_fork_compile(self):
+        code = """if 1:
+                import sys
+                import os
+                import sysconfig
+                from _testinternalcapi import (
+                    compile_perf_trampoline_entry,
+                    perf_trampoline_set_persist_after_fork,
+                )
+
+                def foo_fork():
+                    pass
+
+                def bar_fork():
+                    foo_fork()
+
+                def foo():
+                    pass
+
+                def bar():
+                    foo()
+
+                def compile_trampolines_for_all_functions():
+                    perf_trampoline_set_persist_after_fork(1)
+                    for _, obj in globals().items():
+                        if callable(obj) and hasattr(obj, '__code__'):
+                            compile_perf_trampoline_entry(obj.__code__)
+
+                if __name__ == "__main__":
+                    compile_trampolines_for_all_functions()
+                    pid = os.fork()
+                    if pid == 0:
+                        print(os.getpid())
+                        bar_fork()
+                    else:
+                        bar()
+                """
+
+        with temp_dir() as script_dir:
+            script = make_script(script_dir, "perftest", code)
+            with subprocess.Popen(
+                [sys.executable, "-Xperf", script],
+                universal_newlines=True,
+                stderr=subprocess.PIPE,
+                stdout=subprocess.PIPE,
+            ) as process:
+                stdout, stderr = process.communicate()
+
+        self.assertEqual(process.returncode, 0)
+        self.assertNotIn("Error:", stderr)
+        child_pid = int(stdout.strip())
+        perf_file = pathlib.Path(f"/tmp/perf-{process.pid}.map")
+        perf_child_file = pathlib.Path(f"/tmp/perf-{child_pid}.map")
+        self.assertTrue(perf_file.exists())
+        self.assertTrue(perf_child_file.exists())
+
+        perf_file_contents = perf_file.read_text()
+        self.assertIn(f"py::foo:{script}", perf_file_contents)
+        self.assertIn(f"py::bar:{script}", perf_file_contents)
+        self.assertIn(f"py::foo_fork:{script}", perf_file_contents)
+        self.assertIn(f"py::bar_fork:{script}", perf_file_contents)
+
+        child_perf_file_contents = perf_child_file.read_text()
+        self.assertIn(f"py::foo_fork:{script}", child_perf_file_contents)
+        self.assertIn(f"py::bar_fork:{script}", child_perf_file_contents)
+
+        # Pre-compiled perf-map entries of a forked process must be
+        # identical in both the parent and child perf-map files.
+        perf_file_lines = perf_file_contents.split("\n")
+        for line in perf_file_lines:
+            if (
+                f"py::foo_fork:{script}" in line
+                or f"py::bar_fork:{script}" in line
+            ):
+                self.assertIn(line, child_perf_file_contents)
+
 
 if __name__ == "__main__":
     unittest.main()