linux-kernel - Re: [PATCH v7 22/23] sched: Refactor dl/rt find_lowest/latest

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]
Date: Fri, 22 Dec 2023 13:52:47 +0000
From: Metin Kaya <metin.kaya@....com>
To: John Stultz <jstultz@...gle.com>, LKML <linux-kernel@...r.kernel.org>
Cc: Joel Fernandes <joelaf@...gle.com>, Qais Yousef <qyousef@...gle.com>,
 Ingo Molnar <mingo@...hat.com>, Peter Zijlstra <peterz@...radead.org>,
 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>, Youssef Esmat
 <youssefesmat@...gle.com>, Mel Gorman <mgorman@...e.de>,
 Daniel Bristot de Oliveira <bristot@...hat.com>,
 Will Deacon <will@...nel.org>, Waiman Long <longman@...hat.com>,
 Boqun Feng <boqun.feng@...il.com>, "Paul E. McKenney" <paulmck@...nel.org>,
 Xuewen Yan <xuewen.yan94@...il.com>, K Prateek Nayak
 <kprateek.nayak@....com>, Thomas Gleixner <tglx@...utronix.de>,
 kernel-team@...roid.com
Subject: Re: [PATCH v7 22/23] sched: Refactor dl/rt find_lowest/latest_rq
 logic

On 20/12/2023 12:18 am, John Stultz wrote:
> This pulls re-validation logic done in find_lowest_rq
> and find_latest_rq after re-acquiring the rq locks out into its
> own function.
> 
> This allows us to later use a more complicated validation
> check for chain-migration when using proxy-exectuion.

                                              execution

> 
> TODO: It seems likely we could consolidate this two functions
> further and leave the task_is_rt()/task_is_dl() checks externally?

Agreed.

> 
> Cc: Joel Fernandes <joelaf@...gle.com>
> Cc: Qais Yousef <qyousef@...gle.com>
> Cc: Ingo Molnar <mingo@...hat.com>
> Cc: Peter Zijlstra <peterz@...radead.org>
> Cc: Juri Lelli <juri.lelli@...hat.com>
> Cc: Vincent Guittot <vincent.guittot@...aro.org>
> Cc: Dietmar Eggemann <dietmar.eggemann@....com>
> Cc: Valentin Schneider <vschneid@...hat.com>
> Cc: Steven Rostedt <rostedt@...dmis.org>
> Cc: Ben Segall <bsegall@...gle.com>
> Cc: Zimuzo Ezeozue <zezeozue@...gle.com>
> Cc: Youssef Esmat <youssefesmat@...gle.com>
> Cc: Mel Gorman <mgorman@...e.de>
> Cc: Daniel Bristot de Oliveira <bristot@...hat.com>
> Cc: Will Deacon <will@...nel.org>
> Cc: Waiman Long <longman@...hat.com>
> Cc: Boqun Feng <boqun.feng@...il.com>
> Cc: "Paul E. McKenney" <paulmck@...nel.org>
> Cc: Metin Kaya <Metin.Kaya@....com>
> Cc: Xuewen Yan <xuewen.yan94@...il.com>
> Cc: K Prateek Nayak <kprateek.nayak@....com>
> Cc: Thomas Gleixner <tglx@...utronix.de>
> Cc: kernel-team@...roid.com
> Signed-off-by: John Stultz <jstultz@...gle.com>
> ---
>   kernel/sched/deadline.c | 31 ++++++++++++++++++++-----
>   kernel/sched/rt.c       | 50 ++++++++++++++++++++++++++++-------------
>   2 files changed, 59 insertions(+), 22 deletions(-)
> 
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 21e56ac58e32..8b5701727342 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -2172,6 +2172,30 @@ static int find_later_rq(struct task_struct *sched_ctx, struct task_struct *exec
>   	return -1;
>   }
>   
> +static inline bool dl_revalidate_rq_state(struct task_struct *task, struct rq *rq,
> +					  struct rq *later)
> +{
> +	if (task_rq(task) != rq)
> +		return false;
> +
> +	if (!cpumask_test_cpu(later->cpu, &task->cpus_mask))
> +		return false;
> +
> +	if (task_on_cpu(rq, task))
> +		return false;
> +
> +	if (!dl_task(task))
> +		return false;
> +
> +	if (is_migration_disabled(task))
> +		return false;
> +
> +	if (!task_on_rq_queued(task))
> +		return false;
> +
> +	return true;
> +}
> +
>   /* Locks the rq it finds */
>   static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
>   {
> @@ -2204,12 +2228,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
>   
>   		/* Retry if something changed. */
>   		if (double_lock_balance(rq, later_rq)) {
> -			if (unlikely(task_rq(task) != rq ||
> -				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) ||
> -				     task_on_cpu(rq, task) ||
> -				     !dl_task(task) ||
> -				     is_migration_disabled(task) ||
> -				     !task_on_rq_queued(task))) {
> +			if (unlikely(!dl_revalidate_rq_state(task, rq, later_rq))) {
>   				double_unlock_balance(rq, later_rq);
>   				later_rq = NULL;
>   				break;
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index f8134d062fa3..fabb19891e95 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -1935,6 +1935,39 @@ static int find_lowest_rq(struct task_struct *sched_ctx, struct task_struct *exe
>   	return -1;
>   }
>   
> +static inline bool rt_revalidate_rq_state(struct task_struct *task, struct rq *rq,
> +					  struct rq *lowest)
> +{
> +	/*
> +	 * We had to unlock the run queue. In
> +	 * the mean time, task could have
> +	 * migrated already or had its affinity changed.
> +	 * Also make sure that it wasn't scheduled on its rq.
> +	 * It is possible the task was scheduled, set
> +	 * "migrate_disabled" and then got preempted, so we must
> +	 * check the task migration disable flag here too.
> +	 */
> +	if (task_rq(task) != rq)
> +		return false;
> +
> +	if (!cpumask_test_cpu(lowest->cpu, &task->cpus_mask))
> +		return false;
> +
> +	if (task_on_cpu(rq, task))
> +		return false;
> +
> +	if (!rt_task(task))
> +		return false;
> +
> +	if (is_migration_disabled(task))
> +		return false;
> +
> +	if (!task_on_rq_queued(task))
> +		return false;
> +
> +	return true;
> +}
> +
>   /* Will lock the rq it finds */
>   static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
>   {
> @@ -1964,22 +1997,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
>   
>   		/* if the prio of this runqueue changed, try again */
>   		if (double_lock_balance(rq, lowest_rq)) {
> -			/*
> -			 * We had to unlock the run queue. In
> -			 * the mean time, task could have
> -			 * migrated already or had its affinity changed.
> -			 * Also make sure that it wasn't scheduled on its rq.
> -			 * It is possible the task was scheduled, set
> -			 * "migrate_disabled" and then got preempted, so we must
> -			 * check the task migration disable flag here too.
> -			 */
> -			if (unlikely(task_rq(task) != rq ||
> -				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
> -				     task_on_cpu(rq, task) ||
> -				     !rt_task(task) ||
> -				     is_migration_disabled(task) ||
> -				     !task_on_rq_queued(task))) {
> -
> +			if (unlikely(!rt_revalidate_rq_state(task, rq, lowest_rq))) {
>   				double_unlock_balance(rq, lowest_rq);
>   				lowest_rq = NULL;
>   				break;