Address code review

Author: corona10

Include/internal/pycore_lock.h

@@ -13,6 +13,10 @@ extern "C" {
 #  error "this header requires Py_BUILD_CORE define"
 #endif
 
+#if defined(MS_WINDOWS)
+#  include <emmintrin.h>  // _mm_pause()
+#endif
+
 //_Py_UNLOCKED is defined as 0 and _Py_LOCKED as 1 in Include/cpython/pylock.h
 #define _Py_HAS_PARKED  2
 #define _Py_ONCE_INITIALIZED 4
@@ -70,10 +74,25 @@ PyMutex_LockFlags(PyMutex *m, _PyLockFlags flags)
 // error messages) otherwise returns 0.
 extern int _PyMutex_TryUnlock(PyMutex *m);
 
-// Yield the processor using a lightweight CPU pause hint (e.g., x86 PAUSE,
-// AArch64 WFE). Falls back to sched_yield()/SwitchToThread() on platforms
-// without a known pause instruction.
-extern void _Py_yield(void);
+// Lightweight CPU pause hint for spin-wait loops (e.g., x86 PAUSE, AArch64 WFE).
+// Falls back to sched_yield() on platforms without a known pause instruction.
+static inline void
+_Py_yield(void)
+{
+#if defined(__x86_64__) || defined(__i386__)
+    __asm__ volatile ("pause" ::: "memory");
+#elif defined(__aarch64__)
+    __asm__ volatile ("wfe");
+#elif defined(__arm__) && __ARM_ARCH >= 7
+    __asm__ volatile ("yield" ::: "memory");
+#elif defined(__powerpc__) || defined(__ppc__) || defined(__PPC__)
+    __asm__ volatile ("or 27,27,27" ::: "memory");
+#elif defined(MS_WINDOWS)
+    _mm_pause();
+#elif defined(HAVE_SCHED_H)
+    sched_yield();
+#endif
+}
 
 
 // PyEvent is a one-time event notification

Python/lock.c

@@ -8,14 +8,6 @@
 #include "pycore_time.h"          // _PyTime_Add()
 #include "pycore_stats.h"         // FT_STAT_MUTEX_SLEEP_INC()
 
-#ifdef MS_WINDOWS
-#  ifndef WIN32_LEAN_AND_MEAN
-#    define WIN32_LEAN_AND_MEAN
-#  endif
-#  include <windows.h>            // SwitchToThread()
-#elif defined(HAVE_SCHED_H)
-#  include <sched.h>              // sched_yield()
-#endif
 
 // If a thread waits on a lock for longer than TIME_TO_BE_FAIR_NS (1 ms), then
 // the unlocking thread directly hands off ownership of the lock. This avoids
@@ -40,28 +32,6 @@ struct mutex_entry {
     int handed_off;
 };
 
-void
-_Py_yield(void)
-{
-#if defined(__GNUC__) || defined(__clang__)
-#  if defined(__x86_64__) || defined(__i386__)
-    __asm__ volatile ("pause" ::: "memory");
-#  elif defined(__aarch64__)
-    __asm__ volatile ("wfe");
-#  elif defined(__arm__) && __ARM_ARCH >= 7
-    __asm__ volatile ("yield" ::: "memory");
-#  elif defined(__powerpc__) || defined(__ppc__) || defined(__PPC__)
-    __asm__ volatile ("or 27,27,27" ::: "memory");
-#  else
-    sched_yield();
-#  endif
-#elif defined(MS_WINDOWS)
-    SwitchToThread();
-#elif defined(HAVE_SCHED_H)
-    sched_yield();
-#endif
-}
-
 PyLockStatus
 _PyMutex_LockTimed(PyMutex *m, PyTime_t timeout, _PyLockFlags flags)
 {