sched/fair: Make it possible to account fair load avg consistently

The current code accounts for the time a task was absent from the fair
class (per ATTACH_AGE_LOAD). However it does not work correctly when a
task got migrated or moved to another cgroup while outside of the fair
class.

This patch tries to address that by aging on migration. We locklessly
read the 'last_update_time' stamp from both the old and new cfs_rq,
ages the load upto the old time, and sets it to the new time.

These timestamps should in general not be more than 1 tick apart from
one another, so there is a definite bound on things.

Signed-off-by: Byungchul Park <byungchul.park@lge.com>
[ Changelog, a few edits and !SMP build fix ]
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>
Link: http://lkml.kernel.org/r/1445616981-29904-2-git-send-email-byungchul.park@lge.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/core.c

@@ -2120,6 +2120,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	p->se.cfs_rq			= NULL;
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif

kernel/sched/fair.c

@@ -2715,6 +2715,52 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 	}
 }
 
+/*
+ * Called within set_task_rq() right before setting a task's cpu. The
+ * caller only guarantees p->pi_lock is held; no other assumptions,
+ * including the state of rq->lock, should be made.
+ */
+void set_task_rq_fair(struct sched_entity *se,
+		      struct cfs_rq *prev, struct cfs_rq *next)
+{
+	if (!sched_feat(ATTACH_AGE_LOAD))
+		return;
+
+	/*
+	 * We are supposed to update the task to "current" time, then its up to
+	 * date and ready to go to new CPU/cfs_rq. But we have difficulty in
+	 * getting what current time is, so simply throw away the out-of-date
+	 * time. This will result in the wakee task is less decayed, but giving
+	 * the wakee more load sounds not bad.
+	 */
+	if (se->avg.last_update_time && prev) {
+		u64 p_last_update_time;
+		u64 n_last_update_time;
+
+#ifndef CONFIG_64BIT
+		u64 p_last_update_time_copy;
+		u64 n_last_update_time_copy;
+
+		do {
+			p_last_update_time_copy = prev->load_last_update_time_copy;
+			n_last_update_time_copy = next->load_last_update_time_copy;
+
+			smp_rmb();
+
+			p_last_update_time = prev->avg.last_update_time;
+			n_last_update_time = next->avg.last_update_time;
+
+		} while (p_last_update_time != p_last_update_time_copy ||
+			 n_last_update_time != n_last_update_time_copy);
+#else
+		p_last_update_time = prev->avg.last_update_time;
+		n_last_update_time = next->avg.last_update_time;
+#endif
+		__update_load_avg(p_last_update_time, cpu_of(rq_of(prev)),
+				  &se->avg, 0, 0, NULL);
+		se->avg.last_update_time = n_last_update_time;
+	}
+}
 #else /* CONFIG_FAIR_GROUP_SCHED */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 #endif /* CONFIG_FAIR_GROUP_SCHED */

kernel/sched/sched.h

@@ -335,7 +335,15 @@ extern void sched_move_task(struct task_struct *tsk);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
-#endif
+
+#ifdef CONFIG_SMP
+extern void set_task_rq_fair(struct sched_entity *se,
+			     struct cfs_rq *prev, struct cfs_rq *next);
+#else /* !CONFIG_SMP */
+static inline void set_task_rq_fair(struct sched_entity *se,
+			     struct cfs_rq *prev, struct cfs_rq *next) { }
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #else /* CONFIG_CGROUP_SCHED */
 
@@ -933,6 +941,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]);
 	p->se.cfs_rq = tg->cfs_rq[cpu];
 	p->se.parent = tg->se[cpu];
 #endif