linux-kernel - Re: [PATCH v2 2/5] sched/fair: Implement throttle task work and related helpers

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: <1221e872-c4db-4db4-b68f-8c395fc07119@linux.dev>
Date: Wed, 18 Jun 2025 17:03:41 +0800
From: Chengming Zhou <chengming.zhou@...ux.dev>
To: Aaron Lu <ziqianlu@...edance.com>,
 Valentin Schneider <vschneid@...hat.com>, Ben Segall <bsegall@...gle.com>,
 K Prateek Nayak <kprateek.nayak@....com>,
 Peter Zijlstra <peterz@...radead.org>, Josh Don <joshdon@...gle.com>,
 Ingo Molnar <mingo@...hat.com>, Vincent Guittot
 <vincent.guittot@...aro.org>, Xi Wang <xii@...gle.com>
Cc: linux-kernel@...r.kernel.org, Juri Lelli <juri.lelli@...hat.com>,
 Dietmar Eggemann <dietmar.eggemann@....com>,
 Steven Rostedt <rostedt@...dmis.org>, Mel Gorman <mgorman@...e.de>,
 Chuyi Zhou <zhouchuyi@...edance.com>, Jan Kiszka <jan.kiszka@...mens.com>,
 Florian Bezdeka <florian.bezdeka@...mens.com>
Subject: Re: [PATCH v2 2/5] sched/fair: Implement throttle task work and
 related helpers

On 2025/6/18 16:19, Aaron Lu wrote:
> From: Valentin Schneider <vschneid@...hat.com>
> 
> Implement throttle_cfs_rq_work() task work which gets executed on task's
> ret2user path where the task is dequeued and marked as throttled.
> 
> Signed-off-by: Valentin Schneider <vschneid@...hat.com>
> Signed-off-by: Aaron Lu <ziqianlu@...edance.com>

LGTM,

Reviewed-by: Chengming Zhou <chengming.zhou@...ux.dev>

Thanks!

> ---
>   kernel/sched/fair.c | 65 +++++++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 65 insertions(+)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index f7b8597bc95ac..8226120b8771a 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -5757,8 +5757,51 @@ static inline int throttled_lb_pair(struct task_group *tg,
>   	       throttled_hierarchy(dest_cfs_rq);
>   }
>   
> +static inline bool task_is_throttled(struct task_struct *p)
> +{
> +	return p->throttled;
> +}
> +
> +static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags);
>   static void throttle_cfs_rq_work(struct callback_head *work)
>   {
> +	struct task_struct *p = container_of(work, struct task_struct, sched_throttle_work);
> +	struct sched_entity *se;
> +	struct cfs_rq *cfs_rq;
> +	struct rq *rq;
> +
> +	WARN_ON_ONCE(p != current);
> +	p->sched_throttle_work.next = &p->sched_throttle_work;
> +
> +	/*
> +	 * If task is exiting, then there won't be a return to userspace, so we
> +	 * don't have to bother with any of this.
> +	 */
> +	if ((p->flags & PF_EXITING))
> +		return;
> +
> +	scoped_guard(task_rq_lock, p) {
> +		se = &p->se;
> +		cfs_rq = cfs_rq_of(se);
> +
> +		/* Raced, forget */
> +		if (p->sched_class != &fair_sched_class)
> +			return;
> +
> +		/*
> +		 * If not in limbo, then either replenish has happened or this
> +		 * task got migrated out of the throttled cfs_rq, move along.
> +		 */
> +		if (!cfs_rq->throttle_count)
> +			return;
> +		rq = scope.rq;
> +		update_rq_clock(rq);
> +		WARN_ON_ONCE(p->throttled || !list_empty(&p->throttle_node));
> +		dequeue_task_fair(rq, p, DEQUEUE_SLEEP | DEQUEUE_SPECIAL);
> +		list_add(&p->throttle_node, &cfs_rq->throttled_limbo_list);
> +		p->throttled = true;
> +		resched_curr(rq);
> +	}
>   }
>   
>   void init_cfs_throttle_work(struct task_struct *p)
> @@ -5798,6 +5841,26 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
>   	return 0;
>   }
>   
> +static inline bool task_has_throttle_work(struct task_struct *p)
> +{
> +	return p->sched_throttle_work.next != &p->sched_throttle_work;
> +}
> +
> +static inline void task_throttle_setup_work(struct task_struct *p)
> +{
> +	if (task_has_throttle_work(p))
> +		return;
> +
> +	/*
> +	 * Kthreads and exiting tasks don't return to userspace, so adding the
> +	 * work is pointless
> +	 */
> +	if ((p->flags & (PF_EXITING | PF_KTHREAD)))
> +		return;
> +
> +	task_work_add(p, &p->sched_throttle_work, TWA_RESUME);
> +}
> +
>   static int tg_throttle_down(struct task_group *tg, void *data)
>   {
>   	struct rq *rq = data;
> @@ -6668,6 +6731,8 @@ static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
>   static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
>   static inline void sync_throttle(struct task_group *tg, int cpu) {}
>   static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
> +static void task_throttle_setup_work(struct task_struct *p) {}
> +static bool task_is_throttled(struct task_struct *p) { return false; }
>   
>   static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
>   {