Received-SPF: pass (google.com: domain of linux-kernel+bounces-208488-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Message-ID: <da0b9016-379b-4e4f-9741-5f69189661b9@arm.com>
Date: Mon, 10 Jun 2024 16:29:08 +0100
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [RFC PATCH v3 2/6] sched/uclamp: Track a new util_avg_bias signal
From: Hongyan Xia <hongyan.xia2@arm.com>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>,
 Ingo Molnar <mingo@redhat.com>, Peter Zijlstra <peterz@infradead.org>,
 Vincent Guittot <vincent.guittot@linaro.org>,
 Juri Lelli <juri.lelli@redhat.com>, Steven Rostedt <rostedt@goodmis.org>,
 Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
 Daniel Bristot de Oliveira <bristot@redhat.com>,
 Valentin Schneider <vschneid@redhat.com>
Cc: Qais Yousef <qyousef@layalina.io>,
 Morten Rasmussen <morten.rasmussen@arm.com>,
 Lukasz Luba <lukasz.luba@arm.com>,
 Christian Loehle <christian.loehle@arm.com>, pierre.gondois@arm.com,
 linux-kernel@vger.kernel.org
References: <cover.1715082714.git.hongyan.xia2@arm.com>
 <2e43dc6b376ea6d785976a398b5d9ffe823cf35d.1715082714.git.hongyan.xia2@arm.com>
 <fdde3285-6d40-458d-84bd-3d7badc1e592@arm.com>
 <1b36141c-1ad7-4c34-b293-92003f473465@arm.com>
Content-Language: en-US
In-Reply-To: <1b36141c-1ad7-4c34-b293-92003f473465@arm.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit

On 28/05/2024 12:09, Hongyan Xia wrote:
> On 26/05/2024 23:52, Dietmar Eggemann wrote:
>[...]
>>> +    old = READ_ONCE(p->se.avg.util_avg_bias);
>>> +    new = (int)clamp(util, uclamp_min, uclamp_max) - (int)util;
>>> +
>>> +    WRITE_ONCE(p->se.avg.util_avg_bias, new);
>>> +    if (!p->se.on_rq)
>>> +        return;
>>> +    WRITE_ONCE(avg->util_avg_bias, READ_ONCE(avg->util_avg_bias) + 
>>> new - old);
>>> +}
>>> +#else /* !CONFIG_UCLAMP_TASK */
>>> +static void update_util_bias(struct sched_avg *avg, struct 
>>> task_struct *p)
>>> +{
>>> +}
>>> +#endif
>>> +
>>>   /*
>>>    * sched_entity:
>>>    *
>>> @@ -296,6 +330,8 @@ int __update_load_avg_blocked_se(u64 now, struct 
>>> sched_entity *se)
>>>   {
>>>       if (___update_load_sum(now, &se->avg, 0, 0, 0)) {
>>>           ___update_load_avg(&se->avg, se_weight(se));
>>> +        if (entity_is_task(se))
>>> +            update_util_bias(NULL, task_of(se));
>>
>> IMHO,
>>
>> update_util_bias(struct sched_avg *avg, struct sched_entity *se)
>>
>>      if (!entity_is_task(se))
>>          return;
>>
>>      ...
>>
>> would be easier to read.
> 
> Yeah, that would work, and might be a good way to prepare for group 
> clamping if it ever becomes a thing.
> 

Sadly it's not as easy as I hoped. The problem is that we need to fetch 
task uclamp values here so we need to get p anyway. Also, even if one 
day we implement group uclamp, we need to fetch the cfs_rq this se is on 
instead of the whole rq, so the function signature needs to change 
anyway. Keeping it the current way might be the better thing to do here.

> [...]