sched/fair: Fix PELT integrity for new tasks

Vincent and Yuyang found another few scenarios in which entity
tracking goes wobbly.

The scenarios are basically due to the fact that new tasks are not
immediately attached and thereby differ from the normal situation -- a
task is always attached to a cfs_rq load average (such that it
includes its blocked contribution) and are explicitly
detached/attached on migration to another cfs_rq.

Scenario 1: switch to fair class

  p->sched_class = fair_class;
  if (queued)
    enqueue_task(p);
      ...
        enqueue_entity()
	  enqueue_entity_load_avg()
	    migrated = !sa->last_update_time (true)
	    if (migrated)
	      attach_entity_load_avg()
  check_class_changed()
    switched_from() (!fair)
    switched_to()   (fair)
      switched_to_fair()
        attach_entity_load_avg()

If @p is a new task that hasn't been fair before, it will have
!last_update_time and, per the above, end up in
attach_entity_load_avg() _twice_.

Scenario 2: change between cgroups

  sched_move_group(p)
    if (queued)
      dequeue_task()
    task_move_group_fair()
      detach_task_cfs_rq()
        detach_entity_load_avg()
      set_task_rq()
      attach_task_cfs_rq()
        attach_entity_load_avg()
    if (queued)
      enqueue_task();
        ...
          enqueue_entity()
	    enqueue_entity_load_avg()
	      migrated = !sa->last_update_time (true)
	      if (migrated)
	        attach_entity_load_avg()

Similar as with scenario 1, if @p is a new task, it will have
!load_update_time and we'll end up in attach_entity_load_avg()
_twice_.

Furthermore, notice how we do a detach_entity_load_avg() on something
that wasn't attached to begin with.

As stated above; the problem is that the new task isn't yet attached
to the load tracking and thereby violates the invariant assumption.

This patch remedies this by ensuring a new task is indeed properly
attached to the load tracking on creation, through
post_init_entity_util_avg().

Of course, this isn't entirely as straightforward as one might think,
since the task is hashed before we call wake_up_new_task() and thus
can be poked at. We avoid this by adding TASK_NEW and teaching
cpu_cgroup_can_attach() to refuse such tasks.

Reported-by: Yuyang Du <yuyang.du@intel.com>
Reported-by: Vincent Guittot <vincent.guittot@linaro.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: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 37 insertions, 8 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 64f26bc436eb..0c21a12c0205 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -690,6 +690,10 @@ void init_entity_runnable_average(struct sched_entity *se)
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
 
+static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
+static int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq);
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
 /*
  * With new tasks being created, their initial util_avgs are extrapolated
  * based on the cfs_rq's current util_avg:
@@ -720,6 +724,7 @@ void post_init_entity_util_avg(struct sched_entity *se)
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	struct sched_avg *sa = &se->avg;
 	long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+	u64 now = cfs_rq_clock_task(cfs_rq);
 
 	if (cap > 0) {
 		if (cfs_rq->avg.util_avg != 0) {
@@ -733,16 +738,37 @@ void post_init_entity_util_avg(struct sched_entity *se)
 		}
 		sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
 	}
+
+	if (entity_is_task(se)) {
+		struct task_struct *p = task_of(se);
+		if (p->sched_class != &fair_sched_class) {
+			/*
+			 * For !fair tasks do:
+			 *
+			update_cfs_rq_load_avg(now, cfs_rq, false);
+			attach_entity_load_avg(cfs_rq, se);
+			switched_from_fair(rq, p);
+			 *
+			 * such that the next switched_to_fair() has the
+			 * expected state.
+			 */
+			se->avg.last_update_time = now;
+			return;
+		}
+	}
+
+	update_cfs_rq_load_avg(now, cfs_rq, false);
+	attach_entity_load_avg(cfs_rq, se);
 }
 
-#else
+#else /* !CONFIG_SMP */
 void init_entity_runnable_average(struct sched_entity *se)
 {
 }
 void post_init_entity_util_avg(struct sched_entity *se)
 {
 }
-#endif
+#endif /* CONFIG_SMP */
 
 /*
  * Update the current task's runtime statistics.
@@ -2840,8 +2866,6 @@ void set_task_rq_fair(struct sched_entity *se,
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
-
 static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
@@ -2951,6 +2975,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	/*
 	 * If we got migrated (either between CPUs or between cgroups) we'll
 	 * have aged the average right before clearing @last_update_time.
+	 *
+	 * Or we're fresh through post_init_entity_util_avg().
 	 */
 	if (se->avg.last_update_time) {
 		__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
@@ -3056,11 +3082,14 @@ void remove_entity_load_avg(struct sched_entity *se)
 	u64 last_update_time;
 
 	/*
-	 * Newly created task or never used group entity should not be removed
-	 * from its (source) cfs_rq
+	 * tasks cannot exit without having gone through wake_up_new_task() ->
+	 * post_init_entity_util_avg() which will have added things to the
+	 * cfs_rq, so we can remove unconditionally.
+	 *
+	 * Similarly for groups, they will have passed through
+	 * post_init_entity_util_avg() before unregister_sched_fair_group()
+	 * calls this.
 	 */
-	if (se->avg.last_update_time == 0)
-		return;
 
 	last_update_time = cfs_rq_last_update_time(cfs_rq);