function-graph: add option to calculate graph time or not

graph time is the time that a function is executing another function.
Thus if function A calls B, if graph-time is set, then the time for
A includes B. This is the default behavior. But if graph-time is off,
then the time spent executing B is subtracted from A.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>

4 files changed, 28 insertions, 6 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ed1fc5021d44..71e5faef12ab 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -604,6 +604,7 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace)
 static void profile_graph_return(struct ftrace_graph_ret *trace)
 {
 	struct ftrace_profile_stat *stat;
+	unsigned long long calltime;
 	struct ftrace_profile *rec;
 	unsigned long flags;
 
@@ -612,9 +613,27 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
 	if (!stat->hash)
 		goto out;
 
+	calltime = trace->rettime - trace->calltime;
+
+	if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
+		int index;
+
+		index = trace->depth;
+
+		/* Append this call time to the parent time to subtract */
+		if (index)
+			current->ret_stack[index - 1].subtime += calltime;
+
+		if (current->ret_stack[index].subtime < calltime)
+			calltime -= current->ret_stack[index].subtime;
+		else
+			calltime = 0;
+	}
+
 	rec = ftrace_find_profiled_func(stat, trace->func);
 	if (rec)
-		rec->time += trace->rettime - trace->calltime;
+		rec->time += calltime;
+
  out:
 	local_irq_restore(flags);
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 821bf49771d4..5d1a16cae376 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -255,7 +255,8 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
-	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME;
+	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
+	TRACE_ITER_GRAPH_TIME;
 
 /**
  * trace_wake_up - wake up tasks waiting for trace input
@@ -317,6 +318,7 @@ static const char *trace_options[] = {
 	"latency-format",
 	"global-clock",
 	"sleep-time",
+	"graph-time",
 	NULL
 };
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c66ca3b66050..e3429a8ab059 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -685,6 +685,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_LATENCY_FMT		= 0x40000,
 	TRACE_ITER_GLOBAL_CLK		= 0x80000,
 	TRACE_ITER_SLEEP_TIME		= 0x100000,
+	TRACE_ITER_GRAPH_TIME		= 0x200000,
 };
 
 /*
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 85bba0f018b0..10f6ad7d85f6 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -78,13 +78,14 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 	current->ret_stack[index].ret = ret;
 	current->ret_stack[index].func = func;
 	current->ret_stack[index].calltime = calltime;
+	current->ret_stack[index].subtime = 0;
 	*depth = index;
 
 	return 0;
 }
 
 /* Retrieve a function return address to the trace stack on thread info.*/
-void
+static void
 ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 {
 	int index;
@@ -104,9 +105,6 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 	trace->calltime = current->ret_stack[index].calltime;
 	trace->overrun = atomic_read(&current->trace_overrun);
 	trace->depth = index;
-	barrier();
-	current->curr_ret_stack--;
-
 }
 
 /*
@@ -121,6 +119,8 @@ unsigned long ftrace_return_to_handler(void)
 	ftrace_pop_return_trace(&trace, &ret);
 	trace.rettime = trace_clock_local();
 	ftrace_graph_return(&trace);
+	barrier();
+	current->curr_ret_stack--;
 
 	if (unlikely(!ret)) {
 		ftrace_graph_stop();