x86: align alloca to 16-byte boundary

Align the stack allocation to a 16-byte boundary.  This ensures that the
stack parameters are 16-byte aligned which is needed for some
instructions.
diff --git a/src/x86/ffi.c b/src/x86/ffi.c
index 3b4e25e..897498f 100644
--- a/src/x86/ffi.c
+++ b/src/x86/ffi.c
@@ -32,6 +32,7 @@
 #ifndef __x86_64__
 #include <ffi.h>
 #include <ffi_common.h>
+#include <stdint.h>
 #include <stdlib.h>
 #include "internal.h"
 
@@ -674,7 +675,8 @@
     }
 
   bytes = cif->bytes;
-  argp = stack = alloca(bytes + sizeof(*frame) + rsize);
+  argp = stack =
+      (void *)((uintptr_t)alloca(bytes + sizeof(*frame) + rsize + 15) & ~16);
   frame = (struct call_frame *)(stack + bytes);
   if (rsize)
     rvalue = frame + 1;