[PATCH 4.14 41/66] sched/fair: Sanitize vruntime of entity being migrated

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

From: Vincent Guittot <vincent.guittot@linaro.org>

commit a53ce18cacb477dd0513c607f187d16f0fa96f71 upstream.

Commit 829c1651e9c4 ("sched/fair: sanitize vruntime of entity being placed")
fixes an overflowing bug, but ignore a case that se->exec_start is reset
after a migration.

For fixing this case, we delay the reset of se->exec_start after
placing the entity which se->exec_start to detect long sleeping task.

In order to take into account a possible divergence between the clock_task
of 2 rqs, we increase the threshold to around 104 days.

Fixes: 829c1651e9c4 ("sched/fair: sanitize vruntime of entity being placed")
Originally-by: Zhang Qiao <zhangqiao22@huawei.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Zhang Qiao <zhangqiao22@huawei.com>
Link: https://lore.kernel.org/r/20230317160810.107988-1-vincent.guittot@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 kernel/sched/core.c |    3 ++
 kernel/sched/fair.c |   53 ++++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 46 insertions(+), 10 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -776,6 +776,9 @@ static inline void dequeue_task(struct r
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	if (task_on_rq_migrating(p))
+		flags |= ENQUEUE_MIGRATED;
+
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible--;
 
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3611,11 +3611,33 @@ static void check_spread(struct cfs_rq *
 #endif
 }
 
+static inline bool entity_is_long_sleeper(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq;
+	u64 sleep_time;
+
+	if (se->exec_start == 0)
+		return false;
+
+	cfs_rq = cfs_rq_of(se);
+
+	sleep_time = rq_clock_task(rq_of(cfs_rq));
+
+	/* Happen while migrating because of clock task divergence */
+	if (sleep_time <= se->exec_start)
+		return false;
+
+	sleep_time -= se->exec_start;
+	if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD)))
+		return true;
+
+	return false;
+}
+
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
 	u64 vruntime = cfs_rq->min_vruntime;
-	u64 sleep_time;
 
 	/*
 	 * The 'current' period is already promised to the current tasks,
@@ -3642,13 +3664,24 @@ place_entity(struct cfs_rq *cfs_rq, stru
 
 	/*
 	 * Pull vruntime of the entity being placed to the base level of
-	 * cfs_rq, to prevent boosting it if placed backwards.  If the entity
-	 * slept for a long time, don't even try to compare its vruntime with
-	 * the base as it may be too far off and the comparison may get
-	 * inversed due to s64 overflow.
+	 * cfs_rq, to prevent boosting it if placed backwards.
+	 * However, min_vruntime can advance much faster than real time, with
+	 * the extreme being when an entity with the minimal weight always runs
+	 * on the cfs_rq. If the waking entity slept for a long time, its
+	 * vruntime difference from min_vruntime may overflow s64 and their
+	 * comparison may get inversed, so ignore the entity's original
+	 * vruntime in that case.
+	 * The maximal vruntime speedup is given by the ratio of normal to
+	 * minimal weight: scale_load_down(NICE_0_LOAD) / MIN_SHARES.
+	 * When placing a migrated waking entity, its exec_start has been set
+	 * from a different rq. In order to take into account a possible
+	 * divergence between new and prev rq's clocks task because of irq and
+	 * stolen time, we take an additional margin.
+	 * So, cutting off on the sleep time of
+	 *     2^63 / scale_load_down(NICE_0_LOAD) ~ 104 days
+	 * should be safe.
 	 */
-	sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
-	if ((s64)sleep_time > 60LL * NSEC_PER_SEC)
+	if (entity_is_long_sleeper(se))
 		se->vruntime = vruntime;
 	else
 		se->vruntime = max_vruntime(se->vruntime, vruntime);
@@ -3746,6 +3779,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, st
 
 	if (flags & ENQUEUE_WAKEUP)
 		place_entity(cfs_rq, se, 0);
+	/* Entity has migrated, no longer consider this task hot */
+	if (flags & ENQUEUE_MIGRATED)
+		se->exec_start = 0;
 
 	check_schedstat_required();
 	update_stats_enqueue(cfs_rq, se, flags);
@@ -6100,9 +6136,6 @@ static void migrate_task_rq_fair(struct
 
 	/* Tell new CPU we are migrated */
 	p->se.avg.last_update_time = 0;
-
-	/* We have migrated, no longer consider this task hot */
-	p->se.exec_start = 0;
 }
 
 static void task_dead_fair(struct task_struct *p)