s390/ftrace: prepare_ftrace_return() function call order

Steven Rostedt noted that s390 is the only architecture which calls
ftrace_push_return_trace() before ftrace_graph_entry() and therefore has
the small advantage that trace.depth gets initialized automatically.

However this small advantage isn't worth the difference and possible subtle
breakage that may result from this.
So change s390 to have the same function call order like all other
architectures: first ftrace_graph_entry(), then ftrace_push_return_trace()

Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

arch/s390/kernel/ftrace.c

@@ -151,14 +151,13 @@ unsigned long __kprobes prepare_ftrace_return(unsigned long parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
 	ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE;
-	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
-		goto out;
 	trace.func = ip;
+	trace.depth = current->curr_ret_stack + 1;
 	/* Only trace if the calling function expects to. */
-	if (!ftrace_graph_entry(&trace)) {
-		current->curr_ret_stack--;
+	if (!ftrace_graph_entry(&trace))
+		goto out;
+	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
 		goto out;
-	}
 	parent = (unsigned long) return_to_handler;
 out:
 	return parent;