gh-103323: Get the "Current" Thread State from a Thread-Local Variable (gh-103324)

We replace _PyRuntime.tstate_current with a thread-local variable. As part of this change, we add a _Py_thread_local macro in pyport.h (only for the core runtime) to smooth out the compiler differences. The main motivation here is in support of a per-interpreter GIL, but this change also provides some performance improvement opportunities.

Note that we do not provide a fallback to the thread-local, either falling back to the old tstate_current or to thread-specific storage (PyThread_tss_*()). If that proves problematic then we can circle back. I consider it unlikely, but will run the buildbots to double-check.

Also note that this does not change any of the code related to the GILState API, where it uses a thread state stored in thread-specific storage. I suspect we can combine that with _Py_tss_tstate (from here). However, that can be addressed separately and is not urgent (nor critical).

(While this change was mostly done independently, I did take some inspiration from earlier (~2020) work by @markshannon (main...markshannon:threadstate_in_tls) and @vstinner (#23976).)

3 files changed, 38 insertions, 12 deletions

diff --git a/Include/internal/pycore_pystate.h b/Include/internal/pycore_pystate.h
index 6e5f228..c40f9e7 100644
--- a/Include/internal/pycore_pystate.h
+++ b/Include/internal/pycore_pystate.h
@@ -64,17 +64,14 @@ _Py_ThreadCanHandlePendingCalls(void)
 /* Variable and macro for in-line access to current thread
    and interpreter state */
 
-static inline PyThreadState*
-_PyRuntimeState_GetThreadState(_PyRuntimeState *runtime)
-{
-    return (PyThreadState*)_Py_atomic_load_relaxed(&runtime->tstate_current);
-}
+#if defined(HAVE_THREAD_LOCAL) && !defined(Py_BUILD_CORE_MODULE)
+extern _Py_thread_local PyThreadState *_Py_tss_tstate;
+#endif
+PyAPI_DATA(PyThreadState *) _PyThreadState_GetCurrent(void);
 
 /* Get the current Python thread state.
 
-   Efficient macro reading directly the 'tstate_current' atomic
-   variable. The macro is unsafe: it does not check for error and it can
-   return NULL.
+   This function is unsafe: it does not check for error and it can return NULL.
 
    The caller must hold the GIL.
 
@@ -82,9 +79,20 @@ _PyRuntimeState_GetThreadState(_PyRuntimeState *runtime)
 static inline PyThreadState*
 _PyThreadState_GET(void)
 {
-    return _PyRuntimeState_GetThreadState(&_PyRuntime);
+#if defined(HAVE_THREAD_LOCAL) && !defined(Py_BUILD_CORE_MODULE)
+    return _Py_tss_tstate;
+#else
+    return _PyThreadState_GetCurrent();
+#endif
+}
+
+static inline PyThreadState*
+_PyRuntimeState_GetThreadState(_PyRuntimeState *Py_UNUSED(runtime))
+{
+    return _PyThreadState_GET();
 }
 
+
 static inline void
 _Py_EnsureFuncTstateNotNULL(const char *func, PyThreadState *tstate)
 {
diff --git a/Include/internal/pycore_runtime.h b/Include/internal/pycore_runtime.h
index 3ebe499..2a3fd8a 100644
--- a/Include/internal/pycore_runtime.h
+++ b/Include/internal/pycore_runtime.h
@@ -119,9 +119,6 @@ typedef struct pyruntimestate {
 
     unsigned long main_thread;
 
-    /* Assuming the current thread holds the GIL, this is the
-       PyThreadState for the current thread. */
-    _Py_atomic_address tstate_current;
     /* Used for the thread state bound to the current thread. */
     Py_tss_t autoTSSkey;
 
diff --git a/Include/pyport.h b/Include/pyport.h
index 5e226f5..bd0ba6d 100644
--- a/Include/pyport.h
+++ b/Include/pyport.h
@@ -662,6 +662,27 @@ extern char * _getpty(int *, int, mode_t, int);
 #  define WITH_THREAD
 #endif
 
+#ifdef WITH_THREAD
+#  ifdef Py_BUILD_CORE
+#    ifdef HAVE_THREAD_LOCAL
+#      error "HAVE_THREAD_LOCAL is already defined"
+#    endif
+#    define HAVE_THREAD_LOCAL 1
+#    ifdef thread_local
+#      define _Py_thread_local thread_local
+#    elif __STDC_VERSION__ >= 201112L && !defined(__STDC_NO_THREADS__)
+#      define _Py_thread_local _Thread_local
+#    elif defined(_MSC_VER)  /* AKA NT_THREADS */
+#      define _Py_thread_local __declspec(thread)
+#    elif defined(__GNUC__)  /* includes clang */
+#      define _Py_thread_local __thread
+#    else
+       // fall back to the PyThread_tss_*() API, or ignore.
+#      undef HAVE_THREAD_LOCAL
+#    endif
+#  endif
+#endif
+
 /* Check that ALT_SOABI is consistent with Py_TRACE_REFS:
    ./configure --with-trace-refs should must be used to define Py_TRACE_REFS */
 #if defined(ALT_SOABI) && defined(Py_TRACE_REFS)