[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <40d9ebed-1090-4772-a83a-18a12f35ecc0@kylinos.cn>
Date: Wed, 2 Jul 2025 08:48:41 +0800
From: Zihuan Zhang <zhangzihuan@...inos.cn>
To: Xuewen Yan <xuewen.yan94@...il.com>
Cc: xuewen.yan@...soc.com, vincent.guittot@...aro.org, mingo@...hat.com,
peterz@...radead.org, juri.lelli@...hat.com, rostedt@...dmis.org,
bsegall@...gle.com, mgorman@...e.de, vschneid@...hat.com,
hongyan.xia2@....com, linux-kernel@...r.kernel.org, ke.wang@...soc.com,
di.shen@...soc.com, kprateek.nayak@....com, kuyo.chang@...iatek.com,
juju.sung@...iatek.com, qyousef@...alina.io
Subject: Re: [PATCH v1] sched/uclamp: Skip uclamp_rq_dec() for non-final
dequeue of delayed tasks
Hi Xuewen,
在 2025/7/1 18:49, Xuewen Yan 写道:
> Hi zihuan,
>
> On Tue, Jul 1, 2025 at 5:34 PM Zihuan Zhang <zhangzihuan@...inos.cn> wrote:
>> Currently, uclamp_rq_inc() skips updating the clamp aggregation for
>> delayed tasks unless ENQUEUE_DELAYED is set, to ensure we only track the
>> real enqueue of a task that was previously marked as sched_delayed.
>>
>> However, the corresponding uclamp_rq_dec() path only checks
>> sched_delayed, and misses the DEQUEUE_DELAYED flag. As a result, we may
>> skip dec for a delayed task that is now being truly dequeued, leading to
>> uclamp aggregation mismatch.
>>
>> This patch makes uclamp_rq_dec() consistent with uclamp_rq_inc() by
>> checking both sched_delayed and DEQUEUE_DELAYED, ensuring correct
>> accounting symmetry.
>>
>> Fixes: 90ca9410dab2 ("sched/uclamp: Align uclamp and util_est and call before freq update")
>> Signed-off-by: Zihuan Zhang <zhangzihuan@...inos.cn>
>> ---
>> kernel/sched/core.c | 9 +++++----
>> 1 file changed, 5 insertions(+), 4 deletions(-)
>>
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index 8988d38d46a3..99f1542cff7d 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -1781,7 +1781,7 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p, int flags
>> rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE;
>> }
>>
>> -static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
>> +static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p, int flags)
>> {
>> enum uclamp_id clamp_id;
>>
>> @@ -1797,7 +1797,8 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
>> if (unlikely(!p->sched_class->uclamp_enabled))
>> return;
>>
>> - if (p->se.sched_delayed)
>> + /* Skip dec if this is a delayed task not being truly dequeued */
>> + if (p->se.sched_delayed && !(flags & DEQUEUE_DELAYED))
>> return;
> Consider the __sched_setscheduler(),when changing the delayed-task's
> sched-class,your patch would dec the uclamp twice.
Thanks for your clarification. I’ve understood that the kernel
unconditionally decrements the uclamp counter when dequeuing a task,
regardless of whether it’s currently enqueued. That makes sense.
Appreciate your time and explanation!
> BR
> ---
> xuewen
>
>> for_each_clamp_id(clamp_id)
>> @@ -2039,7 +2040,7 @@ static void __init init_uclamp(void)
>>
>> #else /* !CONFIG_UCLAMP_TASK */
>> static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p, int flags) { }
>> -static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { }
>> +static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p, int flags) { }
>> static inline void uclamp_fork(struct task_struct *p) { }
>> static inline void uclamp_post_fork(struct task_struct *p) { }
>> static inline void init_uclamp(void) { }
>> @@ -2112,7 +2113,7 @@ inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags)
>> * Must be before ->dequeue_task() because ->dequeue_task() can 'fail'
>> * and mark the task ->sched_delayed.
>> */
>> - uclamp_rq_dec(rq, p);
>> + uclamp_rq_dec(rq, p, flags);
>> return p->sched_class->dequeue_task(rq, p, flags);
>> }
>>
>> --
>> 2.25.1
>>
Best regards,
Zihuan
Powered by blists - more mailing lists