1 files changed, 42 insertions, 0 deletions
diff --git a/compiler-rt/lib/builtins/trampoline_setup.c b/compiler-rt/lib/builtins/trampoline_setup.c
index 844eb2794414..830e25e4c030 100644
--- a/compiler-rt/lib/builtins/trampoline_setup.c
+++ b/compiler-rt/lib/builtins/trampoline_setup.c
@@ -41,3 +41,45 @@ COMPILER_RT_ABI void __trampoline_setup(uint32_t *trampOnStack,
   __clear_cache(trampOnStack, &trampOnStack[10]);
 }
 #endif // __powerpc__ && !defined(__powerpc64__)
+
+// The AArch64 compiler generates calls to __trampoline_setup() when creating
+// trampoline functions on the stack for use with nested functions.
+// This function creates a custom 36-byte trampoline function on the stack
+// which loads x18 with a pointer to the outer function's locals
+// and then jumps to the target nested function.
+// Note: x18 is a reserved platform register on Windows and macOS.
+
+#if defined(__aarch64__) && defined(__ELF__)
+COMPILER_RT_ABI void __trampoline_setup(uint32_t *trampOnStack,
+                                        int trampSizeAllocated,
+                                        const void *realFunc, void *localsPtr) {
+  // This should never happen, but if compiler did not allocate
+  // enough space on stack for the trampoline, abort.
+  if (trampSizeAllocated < 36)
+    compilerrt_abort();
+
+  // create trampoline
+  // Load realFunc into x17. mov/movk 16 bits at a time.
+  trampOnStack[0] =
+      0xd2800000u | ((((uint64_t)realFunc >> 0) & 0xffffu) << 5) | 0x11;
+  trampOnStack[1] =
+      0xf2a00000u | ((((uint64_t)realFunc >> 16) & 0xffffu) << 5) | 0x11;
+  trampOnStack[2] =
+      0xf2c00000u | ((((uint64_t)realFunc >> 32) & 0xffffu) << 5) | 0x11;
+  trampOnStack[3] =
+      0xf2e00000u | ((((uint64_t)realFunc >> 48) & 0xffffu) << 5) | 0x11;
+  // Load localsPtr into x18
+  trampOnStack[4] =
+      0xd2800000u | ((((uint64_t)localsPtr >> 0) & 0xffffu) << 5) | 0x12;
+  trampOnStack[5] =
+      0xf2a00000u | ((((uint64_t)localsPtr >> 16) & 0xffffu) << 5) | 0x12;
+  trampOnStack[6] =
+      0xf2c00000u | ((((uint64_t)localsPtr >> 32) & 0xffffu) << 5) | 0x12;
+  trampOnStack[7] =
+      0xf2e00000u | ((((uint64_t)localsPtr >> 48) & 0xffffu) << 5) | 0x12;
+  trampOnStack[8] = 0xd61f0220; // br x17
+
+  // Clear instruction cache.
+  __clear_cache(trampOnStack, &trampOnStack[9]);
+}
+#endif // defined(__aarch64__) && !defined(__APPLE__) && !defined(_WIN64)