sched/core: Fix incorrect wait time and wait count statistics

At present scheduler resets task's wait start timestamp when the task
migrates to another rq.  This misleads scheduler itself into reporting
less wait time than actual by omitting time spent for waiting prior to
migration and also more wait count than actual by counting migration as
wait end event which can be seen by trace or /proc/<pid>/sched with
CONFIG_SCHEDSTATS=y.

Carry forward migrating task's wait time prior to migration and
don't count migration as a wait end event to fix such statistics error.

In order to determine whether task is migrating mark task->on_rq with
TASK_ON_RQ_MIGRATING while dequeuing and enqueuing due to migration.

Signed-off-by: Joonwoo Park <joonwoop@codeaurora.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: ohaugan@codeaurora.org
Link: http://lkml.kernel.org/r/20151113033854.GA4247@codeaurora.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/core.c

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4d568ac9..1b7cb5e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1071,8 +1071,8 @@
 {
 	lockdep_assert_held(&rq->lock);
 
-	dequeue_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_MIGRATING;
+	dequeue_task(rq, p, 0);
 	set_task_cpu(p, new_cpu);
 	raw_spin_unlock(&rq->lock);
 
@@ -1080,8 +1080,8 @@
 
 	raw_spin_lock(&rq->lock);
 	BUG_ON(task_cpu(p) != new_cpu);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	enqueue_task(rq, p, 0);
+	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 
 	return rq;
@@ -1274,6 +1274,15 @@
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
 			!p->on_rq);
 
+	/*
+	 * Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING,
+	 * because schedstat_wait_{start,end} rebase migrating task's wait_start
+	 * time relying on p->on_rq.
+	 */
+	WARN_ON_ONCE(p->state == TASK_RUNNING &&
+		     p->sched_class == &fair_sched_class &&
+		     (p->on_rq && !task_on_rq_migrating(p)));
+
 #ifdef CONFIG_LOCKDEP
 	/*
 	 * The caller should hold either p->pi_lock or rq->lock, when changing
@@ -1310,9 +1319,11 @@
 		src_rq = task_rq(p);
 		dst_rq = cpu_rq(cpu);
 
+		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
+		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
 	} else {
 		/*

kernel/sched/fair.c

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 95b944e..f7017ad 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -738,12 +738,56 @@
 	update_curr(cfs_rq_of(&rq->curr->se));
 }
 
+#ifdef CONFIG_SCHEDSTATS
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq)));
+	u64 wait_start = rq_clock(rq_of(cfs_rq));
+
+	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
+	    likely(wait_start > se->statistics.wait_start))
+		wait_start -= se->statistics.wait_start;
+
+	se->statistics.wait_start = wait_start;
 }
 
+static void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct task_struct *p;
+	u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start;
+
+	if (entity_is_task(se)) {
+		p = task_of(se);
+		if (task_on_rq_migrating(p)) {
+			/*
+			 * Preserve migrating task's wait time so wait_start
+			 * time stamp can be adjusted to accumulate wait time
+			 * prior to migration.
+			 */
+			se->statistics.wait_start = delta;
+			return;
+		}
+		trace_sched_stat_wait(p, delta);
+	}
+
+	se->statistics.wait_max = max(se->statistics.wait_max, delta);
+	se->statistics.wait_count++;
+	se->statistics.wait_sum += delta;
+	se->statistics.wait_start = 0;
+}
+#else
+static inline void
+update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+
+static inline void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+#endif
+
 /*
  * Task is being enqueued - update stats:
  */
@@ -757,23 +801,6 @@
 		update_stats_wait_start(cfs_rq, se);
 }
 
-static void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start));
-	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
-	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
-#ifdef CONFIG_SCHEDSTATS
-	if (entity_is_task(se)) {
-		trace_sched_stat_wait(task_of(se),
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
-	}
-#endif
-	schedstat_set(se->statistics.wait_start, 0);
-}
-
 static inline void
 update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -5745,8 +5772,8 @@
 {
 	lockdep_assert_held(&env->src_rq->lock);
 
-	deactivate_task(env->src_rq, p, 0);
 	p->on_rq = TASK_ON_RQ_MIGRATING;
+	deactivate_task(env->src_rq, p, 0);
 	set_task_cpu(p, env->dst_cpu);
 }
 
@@ -5879,8 +5906,8 @@
 	lockdep_assert_held(&rq->lock);
 
 	BUG_ON(task_rq(p) != rq);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	activate_task(rq, p, 0);
+	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 }