gh-96143: Allow Linux perf profiler to see Python calls (GH-96123)

:warning:  :warning: Note for reviewers, hackers and fellow systems/low-level/compiler engineers :warning: :warning: 

If you have a lot of experience with this kind of shenanigans and want to improve the **first** version, **please make a PR against my branch** or **reach out by email** or **suggest code changes directly on GitHub**. 

If you have any **refinements or optimizations** please, wait until the first version is merged before starting hacking or proposing those so we can keep this PR productive.

2 files changed, 22 insertions, 0 deletions

diff --git a/Include/cpython/initconfig.h b/Include/cpython/initconfig.h
index 3b6d593..c6057a4 100644
--- a/Include/cpython/initconfig.h
+++ b/Include/cpython/initconfig.h
@@ -142,6 +142,7 @@ typedef struct PyConfig {
     unsigned long hash_seed;
     int faulthandler;
     int tracemalloc;
+    int perf_profiling;
     int import_time;
     int code_debug_ranges;
     int show_ref_count;
diff --git a/Include/internal/pycore_ceval.h b/Include/internal/pycore_ceval.h
index 2fcdaad..4914948c 100644
--- a/Include/internal/pycore_ceval.h
+++ b/Include/internal/pycore_ceval.h
@@ -65,6 +65,27 @@ extern PyObject* _PyEval_BuiltinsFromGlobals(
     PyThreadState *tstate,
     PyObject *globals);
 
+// Trampoline API
+
+typedef struct {
+    // Callback to initialize the trampoline state
+    void* (*init_state)(void);
+    // Callback to register every trampoline being created
+    void (*write_state)(void* state, const void *code_addr,
+                        unsigned int code_size, PyCodeObject* code);
+    // Callback to free the trampoline state
+    int (*free_state)(void* state);
+} _PyPerf_Callbacks;
+
+extern int _PyPerfTrampoline_SetCallbacks(_PyPerf_Callbacks *);
+extern void _PyPerfTrampoline_GetCallbacks(_PyPerf_Callbacks *);
+extern int _PyPerfTrampoline_Init(int activate);
+extern int _PyPerfTrampoline_Fini(void);
+extern int _PyIsPerfTrampolineActive(void);
+extern PyStatus _PyPerfTrampoline_AfterFork_Child(void);
+#ifdef PY_HAVE_PERF_TRAMPOLINE
+extern _PyPerf_Callbacks _Py_perfmap_callbacks;
+#endif
 
 static inline PyObject*
 _PyEval_EvalFrame(PyThreadState *tstate, struct _PyInterpreterFrame *frame, int throwflag)