[newlib-cygwin] Cygwin: implement spinlock pause for AArch64

https://sourceware.org/git/gitweb.cgi?p=newlib-cygwin.git;h=557e7cf22612e3a9e2d8abe032c0c57a39029ad3

commit 557e7cf22612e3a9e2d8abe032c0c57a39029ad3
Author: Radek Bartoň <[email protected]>
Date:   Thu Jun 5 12:41:37 2025 +0200

    Cygwin: implement spinlock pause for AArch64
    
    Signed-off-by: Radek Bartoň <[email protected]>

Diff:
---
 winsup/cygwin/local_includes/cygtls.h           | 5 ++++-
 winsup/cygwin/thread.cc                         | 5 +++++
 winsup/testsuite/winsup.api/pthread/cpu_relax.h | 3 ++-
 3 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/winsup/cygwin/local_includes/cygtls.h b/winsup/cygwin/local_includes/cygtls.h
index 29a539d83..44bd44e72 100644
--- a/winsup/cygwin/local_includes/cygtls.h
+++ b/winsup/cygwin/local_includes/cygtls.h
@@ -243,8 +243,11 @@ public: /* Do NOT remove this public: line, it's a marker for gentls_offsets. */
   {
     while (InterlockedExchange (&stacklock, 1))
       {
-#ifdef __x86_64__
+#if defined(__x86_64__)
 	__asm__ ("pause");
+#elif defined(__aarch64__)
+	__asm__ ("dmb ishst\n"
+                 "yield");
 #else
 #error unimplemented for this target
 #endif
diff --git a/winsup/cygwin/thread.cc b/winsup/cygwin/thread.cc
index fea6079b8..510e2be93 100644
--- a/winsup/cygwin/thread.cc
+++ b/winsup/cygwin/thread.cc
@@ -1968,7 +1968,12 @@ pthread_spinlock::lock ()
       else if (spins < FAST_SPINS_LIMIT)
         {
           ++spins;
+#if defined(__x86_64__)
           __asm__ volatile ("pause":::);
+#elif defined(__aarch64__)
+          __asm__ volatile ("dmb ishst\n"
+                            "yield":::);
+#endif
         }
       else
 	{
diff --git a/winsup/testsuite/winsup.api/pthread/cpu_relax.h b/winsup/testsuite/winsup.api/pthread/cpu_relax.h
index 1936dc5f4..71cec0b2b 100644
--- a/winsup/testsuite/winsup.api/pthread/cpu_relax.h
+++ b/winsup/testsuite/winsup.api/pthread/cpu_relax.h
@@ -4,7 +4,8 @@
 #if defined(__x86_64__) || defined(__i386__)  // Check for x86 architectures
    #define CPU_RELAX() __asm__ volatile ("pause" :::)
 #elif defined(__aarch64__) || defined(__arm__)  // Check for ARM architectures
-   #define CPU_RELAX() __asm__ volatile ("yield" :::)
+   #define CPU_RELAX() __asm__ volatile ("dmb ishst \
+                                          yield" :::)
 #else
    #error unimplemented for this target
 #endif