ftrace: Reduce size of function graph entries

Currently ftrace_graph_ent{,_entry} and ftrace_graph_ret{,_entry} struct
can have padding bytes at the end due to alignment in 64-bit data type.
As these data are recorded so frequently, those paddings waste
non-negligible space.  As the ring buffer maintains alignment properly
for each architecture, just to remove the extra padding using 'packed'
attribute.

  ftrace_graph_ent_entry:  24 -> 20
  ftrace_graph_ret_entry:  48 -> 44

Also I moved the 'overrun' field in struct ftrace_graph_ret to minimize
the padding in the middle.

Tested on x86_64 only.

Link: http://lkml.kernel.org/r/1467197808-13578-1-git-send-email-namhyung@kernel.org

Cc: Ingo Molnar <mingo@kernel.org>
Cc: linux-arch@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 66a36a8..7d565af 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -754,23 +754,27 @@
 
 /*
  * Structure that defines an entry function trace.
+ * It's already packed but the attribute "packed" is needed
+ * to remove extra padding at the end.
  */
 struct ftrace_graph_ent {
 	unsigned long func; /* Current function */
 	int depth;
-};
+} __packed;
 
 /*
  * Structure that defines a return function trace.
+ * It's already packed but the attribute "packed" is needed
+ * to remove extra padding at the end.
  */
 struct ftrace_graph_ret {
 	unsigned long func; /* Current function */
-	unsigned long long calltime;
-	unsigned long long rettime;
 	/* Number of functions that overran the depth limit for current task */
 	unsigned long overrun;
+	unsigned long long calltime;
+	unsigned long long rettime;
 	int depth;
-};
+} __packed;
 
 /* Type of the callback handlers for tracing function graph*/
 typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */