[PATCH] perf: Add support to monitor idle time on cpu-clock

[Peter Zijlstra]

Adding support to use perf_event_attr::exclude_idle
(the :I modifierr in perf tools)to monitor idle time
on cpu-clock event.

Link: http://lkml.kernel.org/n/tip-jw45kl6ydrhzqx4uxws0qsqb@xxxxxxxxxxxxxx
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
---
 kernel/events/core.c     | 22 ++++++++++++++++++----
 kernel/sched/idle_task.c | 17 +++++++++++++++++
 2 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2989e3b0fe8b..62c0dc75ed11 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9391,19 +9391,33 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
  * Software event: cpu wall time clock
  */
 
+static u64 cpu_clock_count(struct perf_event *event)
+{
+	u64 now = local_clock();
+
+	if (event->attr.exclude_idle)
+		now -= idle_task(event->oncpu)->se.sum_exec_runtime;
+
+	return now;
+}
+
 static void cpu_clock_event_update(struct perf_event *event)
 {
-	s64 prev;
+	s64 prev, delta;
 	u64 now;
 
-	now = local_clock();
+	now = cpu_clock_count(event);
 	prev = local64_xchg(&event->hw.prev_count, now);
-	local64_add(now - prev, &event->count);
+	delta = now - prev;
+	if (delta > 0)
+		local64_add(delta, &event->count);
 }
 
 static void cpu_clock_event_start(struct perf_event *event, int flags)
 {
-	local64_set(&event->hw.prev_count, local_clock());
+	u64 now = cpu_clock_count(event);
+
+	local64_set(&event->hw.prev_count, now);
 	perf_swevent_start_hrtimer(event);
 }
 
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index d518664cce4f..e360ce5dd9a2 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -27,9 +27,14 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 static struct task_struct *
 pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
+	struct task_struct *idle = rq->idle;
+
 	put_prev_task(rq, prev);
 	update_idle_core(rq);
 	schedstat_inc(rq->sched_goidle);
+
+	idle->se.exec_start = rq_clock_task(rq);
+
 	return rq->idle;
 }
 
@@ -48,6 +53,15 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
+	struct task_struct *idle = rq->idle;
+	u64 delta, now;
+
+	now = rq_clock_task(rq);
+	delta = now - idle->se.exec_start;
+	if (likely((s64)delta > 0))
+		idle->se.sum_exec_runtime += delta;
+	idle->se.exec_start = now;
+
 	rq_last_tick_reset(rq);
 }
 
@@ -57,6 +71,9 @@ static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
 
 static void set_curr_task_idle(struct rq *rq)
 {
+	struct task_struct *idle = rq->idle;
+
+	idle->se.exec_start = rq_clock_task(rq);
 }
 
 static void switched_to_idle(struct rq *rq, struct task_struct *p)
-- 
2.13.6