Re: [PATCH] sched/uclamp: Let each sched_class handle uclamp

[Dietmar Eggemann]

On 10/03/2025 03:41, Xuewen Yan wrote:
> On Sat, Mar 8, 2025 at 2:32 AM Dietmar Eggemann
> <dietmar.eggemann@xxxxxxx> wrote:
>>
>> On 06/03/2025 13:01, Xuewen Yan wrote:
>>> On Thu, Mar 6, 2025 at 2:24 AM Dietmar Eggemann
>>> <dietmar.eggemann@xxxxxxx> wrote:
>>>>
>>>> On 27/02/2025 14:54, Hongyan Xia wrote:
>>>>
>>>> [...]
>>>>
>>>>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>>>>> index 857808da23d8..7e5a653811ad 100644
>>>>> --- a/kernel/sched/fair.c
>>>>> +++ b/kernel/sched/fair.c
>>>>> @@ -6941,8 +6941,10 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>>>>>        * Let's add the task's estimated utilization to the cfs_rq's
>>>>>        * estimated utilization, before we update schedutil.
>>>>>        */
>>>>> -     if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & ENQUEUE_RESTORE))))
>>>>> +     if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & ENQUEUE_RESTORE)))) {
>>>>> +             uclamp_rq_inc(rq, p);
>>>>>               util_est_enqueue(&rq->cfs, p);
>>>>> +     }
>>>>
>>>> So you want to have p uclamp-enqueued so that its uclamp_min value
>>>> counts for the cpufreq_update_util()/cfs_rq_util_change() calls later in
>>>> enqueue_task_fair?
>>>>
>>>>   if (p->in_iowait)
>>>>     cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
>>>>
>>>>   enqueue_entity() -> update_load_avg() -> cfs_rq_util_change() ->
>>>>   cpufreq_update_util()
>>>>
>>>> But if you do this before requeue_delayed_entity() (1) you will not
>>>> uclamp-enqueue p which got his ->sched_delayed just cleared in (1)?
>>>>
>>>
>>> Could we change to the following:
>>>
>>> when enqueue:
>>>
>>> -     if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags
>>> & ENQUEUE_RESTORE))))
>>> +     if (!(p->se.sched_delayed && !(flags & ENQUEUE_DELAYED)))
>>
>> Why you want to check ENQUEUE_DELAYED as well here? Isn't
>> !p->se.sched_delayed implying !ENQUEUE_DELAYED).
> 
> Indeed, the (!(p->se.sched_delayed && !(flags & ENQUEUE_DELAYED))) is equal to
> the  (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags &
> ENQUEUE_RESTORE)))).
> I just think it might be easier to read using the ENQUEUE_DELAYED flag.
> Because we only allow enq the uclamp and util_est when wake up the delayed-task.

OK, I see.

So that means we would not have to move the uclamp handling into the sched
classes necessarily, we could use flags in enqueue_task() as well:

-->8--

Subject: [PATCH] Align uclamp and util_est and call before freq update

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
---
 kernel/sched/core.c | 14 ++++++++------
 kernel/sched/fair.c |  4 ++--
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b60916d77482..f833108a3b2d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1747,7 +1747,8 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	}
 }
 
-static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
+static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p,
+				 int flags)
 {
 	enum uclamp_id clamp_id;
 
@@ -1763,7 +1764,7 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
-	if (p->se.sched_delayed)
+	if (p->se.sched_delayed && !(flags & ENQUEUE_DELAYED))
 		return;
 
 	for_each_clamp_id(clamp_id)
@@ -2067,12 +2068,13 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	if (!(flags & ENQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
-	p->sched_class->enqueue_task(rq, p, flags);
 	/*
-	 * Must be after ->enqueue_task() because ENQUEUE_DELAYED can clear
-	 * ->sched_delayed.
+	 * Can be before ->enqueue_task() because uclamp considers the
+	 * ENQUEUE_DELAYED task before its ->sched_delayed gets cleared
+	 * in ->enqueue_task().
 	 */
-	uclamp_rq_inc(rq, p);
+	uclamp_rq_inc(rq, p, flags);
+	p->sched_class->enqueue_task(rq, p, flags);
 
 	psi_enqueue(p, flags);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 061a29e88ee2..e26d1dfea601 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6951,7 +6951,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * Let's add the task's estimated utilization to the cfs_rq's
 	 * estimated utilization, before we update schedutil.
 	 */
-	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & ENQUEUE_RESTORE))))
+	if (!p->se.sched_delayed || (flags & ENQUEUE_DELAYED))
 		util_est_enqueue(&rq->cfs, p);
 
 	if (flags & ENQUEUE_DELAYED) {
@@ -7193,7 +7193,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
  */
 static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & DEQUEUE_SAVE))))
+	if (!p->se.sched_delayed)
 		util_est_dequeue(&rq->cfs, p);
 
 	util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP);
-- 
2.34.1