[newlib-cygwin] Aarch64: Add inline assembly pthread wrapper

https://sourceware.org/git/gitweb.cgi?p=newlib-cygwin.git;h=f4ba145056dbe99adf4dbe632bec035e006539f8

commit f4ba145056dbe99adf4dbe632bec035e006539f8
Author: Thirumalai Nagalingam <thirumalai.nagalingam-ftNtnR/FhrXEC4y91aVriVaTQe2KTcn/@public.gmane.org>
Date:   Fri Jun 20 02:12:51 2025 +0530

    Aarch64: Add inline assembly pthread wrapper
    
    This patch adds AArch64-specific inline assembly block for the pthread
    wrapper used to bootstrap new threads. It sets up the thread stack,
    adjusts for __CYGTLS_PADSIZE__, releases the original stack via
    VirtualFree, and invokes the target thread function.
    
    Signed-off-by: Thirumalai Nagalingam <[email protected]>

Diff:
---
 winsup/cygwin/create_posix_thread.cc | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/winsup/cygwin/create_posix_thread.cc b/winsup/cygwin/create_posix_thread.cc
index 3fcd61707..592aaf1a5 100644
--- a/winsup/cygwin/create_posix_thread.cc
+++ b/winsup/cygwin/create_posix_thread.cc
@@ -75,7 +75,7 @@ pthread_wrapper (PVOID arg)
   /* Initialize new _cygtls. */
   _my_tls.init_thread (wrapper_arg.stackbase - __CYGTLS_PADSIZE__,
 		       (DWORD (*)(void*, void*)) wrapper_arg.func);
-#ifdef __x86_64__
+#if defined(__x86_64__)
   __asm__ ("\n\
 	   leaq  %[WRAPPER_ARG], %%rbx	# Load &wrapper_arg into rbx	\n\
 	   movq  (%%rbx), %%r12		# Load thread func into r12	\n\
@@ -99,6 +99,22 @@ pthread_wrapper (PVOID arg)
 	   call  *%%r12			# Call thread func		\n"
 	   : : [WRAPPER_ARG] "o" (wrapper_arg),
 	       [CYGTLS] "i" (__CYGTLS_PADSIZE__));
+#elif defined(__aarch64__)
+  /* Sets up a new thread stack, frees the original OS stack,
+   * and calls the thread function with its arg using AArch64 ABI. */
+  __asm__ __volatile__ ("\n\
+	   mov     x19, %[WRAPPER_ARG]  // x19 = &wrapper_arg              \n\
+	   ldp     x0, x10, [x19, #16]  // x0 = stackaddr, x10 = stackbase \n\
+	   sub     sp, x10, %[CYGTLS]   // sp = stackbase - (CYGTLS)       \n\
+	   mov     fp, xzr              // clear frame pointer (x29)       \n\
+	   mov     x1, xzr              // x1 = 0 (dwSize)                 \n\
+	   mov     x2, #0x8000          // x2 = MEM_RELEASE                \n\
+	   bl      VirtualFree          // free original stack             \n\
+	   ldp     x19, x0, [x19]       // x19 = func, x0 = arg            \n\
+	   blr     x19                  // call thread function            \n"
+	   : : [WRAPPER_ARG] "r" (&wrapper_arg),
+	       [CYGTLS] "r" (__CYGTLS_PADSIZE__)
+	   : "x0", "x1", "x2", "x10", "x19", "x29", "memory");
 #else
 #error unimplemented for this target
 #endif