[GIT PULL] scheduler fixes

[Ingo Molnar]

Linus,

Please pull the latest sched/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-2021-07-11

   # HEAD: 3e1493f46390618ea78607cb30c58fc19e2a5035 sched/uclamp: Ignore max aggregation if rq is idle

Three fixes:

 - Fix load tracking bug/inconsistency
 - Fix a sporadic CFS bandwidth constraints enforcement bug
 - Fix a uclamp utilization tracking bug for newly woken tasks

 Thanks,

	Ingo

------------------>
Odin Ugedal (1):
      sched/fair: Fix CFS bandwidth hrtimer expiry type

Vincent Guittot (1):
      sched/fair: Sync load_sum with load_avg after dequeue

Xuewen Yan (1):
      sched/uclamp: Ignore max aggregation if rq is idle


 kernel/sched/fair.c  |  7 ++++---
 kernel/sched/sched.h | 21 ++++++++++++++-------
 2 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 45edf61eed73..1b15a19910a3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3037,8 +3037,9 @@ enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	u32 divider = get_pelt_divider(&se->avg);
 	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
-	sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum);
+	cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider;
 }
 #else
 static inline void
@@ -5053,7 +5054,7 @@ static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
 static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
 {
 	struct hrtimer *refresh_timer = &cfs_b->period_timer;
-	u64 remaining;
+	s64 remaining;
 
 	/* if the call-back is running a quota refresh is already occurring */
 	if (hrtimer_callback_running(refresh_timer))
@@ -5061,7 +5062,7 @@ static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
 
 	/* is a quota refresh about to occur? */
 	remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer));
-	if (remaining < min_expire)
+	if (remaining < (s64)min_expire)
 		return 1;
 
 	return 0;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c80d42e9589b..14a41a243f7b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2818,20 +2818,27 @@ static __always_inline
 unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 				  struct task_struct *p)
 {
-	unsigned long min_util;
-	unsigned long max_util;
+	unsigned long min_util = 0;
+	unsigned long max_util = 0;
 
 	if (!static_branch_likely(&sched_uclamp_used))
 		return util;
 
-	min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
-	max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
-
 	if (p) {
-		min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN));
-		max_util = max(max_util, uclamp_eff_value(p, UCLAMP_MAX));
+		min_util = uclamp_eff_value(p, UCLAMP_MIN);
+		max_util = uclamp_eff_value(p, UCLAMP_MAX);
+
+		/*
+		 * Ignore last runnable task's max clamp, as this task will
+		 * reset it. Similarly, no need to read the rq's min clamp.
+		 */
+		if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+			goto out;
 	}
 
+	min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
+	max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
+out:
 	/*
 	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
 	 * RUNNABLE tasks with _different_ clamps, we can end up with an