- Fix a corner case where vruntime of a task is not being sanitized

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmQgQeEACgkQEsHwGGHe
 VUpJ+w//c01JpzBXQvGGlNSTTuUzSxLAQz0n8lQmixpYHOUgVL3CQlOF+OfnkYPp
 mz8m3nDh1FB9o70Sd2J4/OjY2Gh1qENrBLmj509LTnZE9hADRI0T5Mn93Jo7m7HY
 QoXrYWEwJYwsLzJ66mR8A0xts5jWgkJsAWKXF9gfxf/ieeycdJ1GdOdzC1tp4Nfe
 /4SEjSbUhx/bsBbAdJ38Z/iQGT0HuyQLOBGBuBcFE0JnP/aYEanAQsxxP2LObeVw
 Za7ATxdJ9I1TErVfRsG0GDSiVKCYzSG2GME5TXibgPJ2g1+m0I7gZgpGO9Q8Wzo4
 7y0X+vqsykY/Me3xEDBVaeCiHmFTambkxOR2xVJ2TISN8b390yePy4vgY1QQDidd
 eNh9S2x1dsKp8i4NdYyeW7xwaTfIDp9Yp4XNP8cw02VzW0FSCnsmCzwGHIXsF4K/
 Sib+bhKUo+Qmck5nJlV6R5Xr9cvGgyPpBvD8/XqqwF5lHJ7xg4qkPwPKjoKL1HRj
 YT1t+l0kzcg/onyDAuPe1mIRFf7Q8x5G8zkUGMG401h2tazv19rjK4+V1UemhBqA
 h5Cf1BBy6+6kn4DDb/zD+0IgpDFKJDaClxNwfPzaplAoMC/8+0nxxnu7f32eT59k
 /JtMisERhr6lG0Q+TfURhB3yyCiBjBR2EKcKzHz+KARtxs7a4T0=
 =Z8oJ
 -----END PGP SIGNATURE-----

Merge tag 'sched_urgent_for_v6.3_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fix from Borislav Petkov:

 - Fix a corner case where vruntime of a task is not being sanitized

* tag 'sched_urgent_for_v6.3_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Sanitize vruntime of entity being migrated

kernel/sched/core.c

@@ -2084,6 +2084,9 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	if (task_on_rq_migrating(p))
+		flags |= ENQUEUE_MIGRATED;
+
 	enqueue_task(rq, p, flags);
 
 	p->on_rq = TASK_ON_RQ_QUEUED;

kernel/sched/fair.c

@@ -4648,11 +4648,33 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
 #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,
@@ -4684,13 +4706,24 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	/*
 	 * 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);
@@ -4770,6 +4803,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	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_fair(cfs_rq, se, flags);
@@ -7657,9 +7693,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 	/* Tell new CPU we are migrated */
 	se->avg.last_update_time = 0;
 
-	/* We have migrated, no longer consider this task hot */
-	se->exec_start = 0;
-
 	update_scan_period(p, new_cpu);
 }