nds32: switch to copy_thread_tls()

Use the copy_thread_tls() calling convention which passes tls through a
register. This is required so we can remove the copy_thread{_tls}() split
and remove the HAVE_COPY_THREAD_TLS macro.

Cc: Greentime Hu <green.hu@gmail.com>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

arch/nds32/Kconfig

@@ -48,6 +48,7 @@ config NDS32
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_COPY_THREAD_TLS
 	help
 	  Andes(nds32) Linux support.
 

arch/nds32/kernel/process.c

@@ -149,8 +149,9 @@ void flush_thread(void)
 DEFINE_PER_CPU(struct task_struct *, __entry_task);
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
-int copy_thread(unsigned long clone_flags, unsigned long stack_start,
-		unsigned long stk_sz, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
+		    unsigned long stk_sz, struct task_struct *p,
+		    unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
@@ -170,7 +171,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		childregs->uregs[0] = 0;
 		childregs->osp = 0;
 		if (clone_flags & CLONE_SETTLS)
-			childregs->uregs[25] = childregs->uregs[3];
+			childregs->uregs[25] = tls;
 	}
 	/* cpu context switching  */
 	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;