linux-kernel - Re: [PATCH v3] sched/fair: Sync se's load_avg with cfs_rq in reweight

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: <Zp_QzS-DUiE934X2@linux.ibm.com>
Date: Tue, 23 Jul 2024 21:18:54 +0530
From: Vishal Chourasia <vishalc@...ux.ibm.com>
To: Chuyi Zhou <zhouchuyi@...edance.com>
Cc: mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
        vincent.guittot@...aro.org, dietmar.eggemann@....com,
        rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
        vschneid@...hat.com, chengming.zhou@...ux.dev,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3] sched/fair: Sync se's load_avg with cfs_rq in
 reweight_task

On Tue, Jul 23, 2024 at 07:42:47PM +0800, Chuyi Zhou wrote:
> In reweight_task(), there are two situations:
> 
> 1. The task was on_rq, then the task's load_avg is accurate because we
> synchronized it with cfs_rq through update_load_avg() in dequeue_task().
> 
> 2. The task is sleeping, its load_avg might not have been updated for some
> time, which can result in inaccurate dequeue_load_avg() in
> reweight_entity().
> 
> This patch solves this by using sync_entity_load_avg() to synchronize the
> load_avg of se with cfs_rq before dequeue_load_avg() in reweight_entity().
> For tasks were on_rq, since we already update load_avg to accurate values
> in dequeue_task(), this change will not have other effects due to the short
> time interval between the two updates.
> 
> Suggested-by: Dietmar Eggemann <dietmar.eggemann@....com>
> Signed-off-by: Chuyi Zhou <zhouchuyi@...edance.com>
> ---
> Changes in v3:
> - use sync_entity_load_avg() rather than update_load_avg() to sync the
> sleeping task with its cfs_rq suggested by Dietmar.
> - Link t0 v2: https://lore.kernel.org/lkml/20240720051248.59608-1-zhouchuyi@bytedance.com/
> Changes in v2:
> - change the description in commit log.
> - use update_load_avg() in reweight_task() rather than in reweight_entity
> suggested by chengming.
> - Link to v1: https://lore.kernel.org/lkml/20240716150840.23061-1-zhouchuyi@bytedance.com/
> ---
>  kernel/sched/fair.c | 43 ++++++++++++++++++++++++-------------------
>  1 file changed, 24 insertions(+), 19 deletions(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 9057584ec06d..da3cdd86ab2e 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -3669,11 +3669,32 @@ dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
>  	cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum,
>  					  cfs_rq->avg.load_avg * PELT_MIN_DIVIDER);
>  }
> +
> +static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
> +{
> +	return u64_u32_load_copy(cfs_rq->avg.last_update_time,
> +				 cfs_rq->last_update_time_copy);
> +}
> +
> +/*
> + * Synchronize entity load avg of dequeued entity without locking
> + * the previous rq.
> + */
> +static void sync_entity_load_avg(struct sched_entity *se)
> +{
> +	struct cfs_rq *cfs_rq = cfs_rq_of(se);
> +	u64 last_update_time;
> +
> +	last_update_time = cfs_rq_last_update_time(cfs_rq);
> +	__update_load_avg_blocked_se(last_update_time, se);
> +}
> +
The difference between using update_load_avg() and
sync_entity_load_avg() is:
1. update_load_avg() uses the updated PELT clock value from the rq
   structure.  
2. sync_entity_load_avg() uses the last updated time of
   the cfs_rq where the scheduling entity (se) is attached.

Won't this affect the entity load sync?

-- vishal.c

>  #else
>  static inline void
>  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) { }
> +static void sync_entity_load_avg(struct sched_entity *se) { }
>  #endif
	>  
>  static void reweight_eevdf(struct sched_entity *se, u64 avruntime,
		> @@ -3795,7 +3816,9 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
			>  		if (!curr)
			>  			__dequeue_entity(cfs_rq, se);
			>  		update_load_sub(&cfs_rq->load, se->load.weight);
			> -	}
			> +	} else if (entity_is_task(se))
			> +		sync_entity_load_avg(se);
			> +
			>  	dequeue_load_avg(cfs_rq, se);
			>  
			>  	if (se->on_rq) {
			> @@ -4034,11 +4057,6 @@ static inline bool load_avg_is_decayed(struct sched_avg *sa)
			>  	return true;
			>  }
			>  
			> -static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
			> -{
			> -	return u64_u32_load_copy(cfs_rq->avg.last_update_time,
					> -				 cfs_rq->last_update_time_copy);
			> -}
			>  #ifdef CONFIG_FAIR_GROUP_SCHED
		>  /*
					>   * Because list_add_leaf_cfs_rq always places a child cfs_rq on the list
					> @@ -4773,19 +4791,6 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
					>  	}
					>  }
					>  
					> -/*
					> - * Synchronize entity load avg of dequeued entity without locking
					> - * the previous rq.
					> - */
> -static void sync_entity_load_avg(struct sched_entity *se)
	> -{
		> -	struct cfs_rq *cfs_rq = cfs_rq_of(se);
		> -	u64 last_update_time;
		> -
			> -	last_update_time = cfs_rq_last_update_time(cfs_rq);
		> -	__update_load_avg_blocked_se(last_update_time, se);
		> -}
		> -
		>  /*
					>   * Task first catches up with cfs_rq, and then subtract
					>   * itself from the cfs_rq (task must be off the queue now).
					> -- 
					> 2.20.1
					>