linux-kernel - Re: [RESEND][PATCH v18 5/8] sched: Fix runtime accounting w/ split exec & sched contexts

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250710094506.GH1613376@noisy.programming.kicks-ass.net>
Date: Thu, 10 Jul 2025 11:45:06 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: John Stultz <jstultz@...gle.com>
Cc: LKML <linux-kernel@...r.kernel.org>,
	K Prateek Nayak <kprateek.nayak@....com>,
	Joel Fernandes <joelagnelf@...dia.com>,
	Qais Yousef <qyousef@...alina.io>, Ingo Molnar <mingo@...hat.com>,
	Juri Lelli <juri.lelli@...hat.com>,
	Vincent Guittot <vincent.guittot@...aro.org>,
	Dietmar Eggemann <dietmar.eggemann@....com>,
	Valentin Schneider <vschneid@...hat.com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Ben Segall <bsegall@...gle.com>,
	Zimuzo Ezeozue <zezeozue@...gle.com>, Mel Gorman <mgorman@...e.de>,
	Will Deacon <will@...nel.org>, Waiman Long <longman@...hat.com>,
	Boqun Feng <boqun.feng@...il.com>,
	"Paul E. McKenney" <paulmck@...nel.org>,
	Metin Kaya <Metin.Kaya@....com>,
	Xuewen Yan <xuewen.yan94@...il.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	Daniel Lezcano <daniel.lezcano@...aro.org>,
	Suleiman Souhlal <suleiman@...gle.com>,
	kuyo chang <kuyo.chang@...iatek.com>, hupu <hupu.gm@...il.com>,
	kernel-team@...roid.com
Subject: Re: [RESEND][PATCH v18 5/8] sched: Fix runtime accounting w/ split
 exec & sched contexts

On Mon, Jul 07, 2025 at 08:43:52PM +0000, John Stultz wrote:

> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index edcc7d59ecc3b..c34e0891193a7 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1143,30 +1143,40 @@ static void update_tg_load_avg(struct cfs_rq *cfs_rq)
>  }
>  #endif /* CONFIG_SMP */
>  
> +static s64 update_se(struct rq *rq, struct sched_entity *se)
>  {
>  	u64 now = rq_clock_task(rq);
>  	s64 delta_exec;
>  
> +	delta_exec = now - se->exec_start;
>  	if (unlikely(delta_exec <= 0))
>  		return delta_exec;
>  
> +	se->exec_start = now;
> +	if (entity_is_task(se)) {
> +		struct task_struct *donor = task_of(se);
> +		struct task_struct *running = rq->curr;
> +		/*
> +		 * If se is a task, we account the time against the running
> +		 * task, as w/ proxy-exec they may not be the same.
> +		 */
> +		running->se.exec_start = now;
> +		running->se.sum_exec_runtime += delta_exec;
>  
> +		trace_sched_stat_runtime(running, delta_exec);
> +		account_group_exec_runtime(running, delta_exec);
>  
> +		/* cgroup time is always accounted against the donor */
> +		cgroup_account_cputime(donor, delta_exec);
> +	} else {
> +		/* If not task, account the time against donor se  */
> +		se->sum_exec_runtime += delta_exec;
>  	}

Bah.. this is all terrible :-) But yeah, I suppose this wil do.

>  
>  	if (schedstat_enabled()) {
>  		struct sched_statistics *stats;
>  
> +		stats = __schedstats_from_se(se);
>  		__schedstat_set(stats->exec_max,
>  				max(delta_exec, stats->exec_max));
>  	}
> @@ -1213,7 +1223,7 @@ s64 update_curr_common(struct rq *rq)
>  {
>  	struct task_struct *donor = rq->donor;
>  
> +	return update_se(rq, &donor->se);
>  }

At this point this might as well read:

	return update_se(rq, &rq->donor->se);