linux-kernel - Re: [PATCH 17/24] sched/fair: Implement delayed dequeue

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: <20241106135346.GL24862@noisy.programming.kicks-ass.net>
Date: Wed, 6 Nov 2024 14:53:46 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Mike Galbraith <efault@....de>
Cc: Phil Auld <pauld@...hat.com>, mingo@...hat.com, juri.lelli@...hat.com,
	vincent.guittot@...aro.org, dietmar.eggemann@....com,
	rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
	vschneid@...hat.com, linux-kernel@...r.kernel.org,
	kprateek.nayak@....com, wuyun.abel@...edance.com,
	youssefesmat@...omium.org, tglx@...utronix.de
Subject: Re: [PATCH 17/24] sched/fair: Implement delayed dequeue

On Tue, Nov 05, 2024 at 05:05:12AM +0100, Mike Galbraith wrote:

> After one minute of lightly loaded box browsing, trace_printk() said:
> 
>   645   - racy peek says there is a room available
>    11   - cool, reserved room is free
>   206   - no vacancy or wakee pinned
> 38807   - SIS accommodates room seeker
> 
> The below should improve the odds, but high return seems unlikely.
> 
> ---
>  kernel/sched/core.c |    9 ++++++++-
>  1 file changed, 8 insertions(+), 1 deletion(-)
> 
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -3790,7 +3790,13 @@ static int ttwu_runnable(struct task_str
>  	rq = __task_rq_lock(p, &rf);
>  	if (task_on_rq_queued(p)) {
>  		update_rq_clock(rq);
> -		if (p->se.sched_delayed)
> +		/*
> +		 * If wakee is mobile and the room it reserved is occupied, let it try to migrate.
> +		 */
> +		if (p->se.sched_delayed && rq->nr_running > 1 && cpumask_weight(p->cpus_ptr) > 1) {
> +			dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
> +			goto out_unlock;
> +		} else if (p->se.sched_delayed)
>  			enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED);
>  		if (!task_on_cpu(rq, p)) {
>  			/*
> @@ -3802,6 +3808,7 @@ static int ttwu_runnable(struct task_str
>  		ttwu_do_wakeup(p);
>  		ret = 1;
>  	}
> +out_unlock:
>  	__task_rq_unlock(rq, &rf);
> 
>  	return ret;

So... I was trying to make that prettier and ended up with something
like this:

---
 kernel/sched/core.c  | 46 ++++++++++++++++++++++++++++------------------
 kernel/sched/sched.h |  5 +++++
 2 files changed, 33 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 54d82c21fc8e..b083c6385e88 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3774,28 +3774,38 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
  */
 static int ttwu_runnable(struct task_struct *p, int wake_flags)
 {
-	struct rq_flags rf;
-	struct rq *rq;
-	int ret = 0;
+	CLASS(__task_rq_lock, rq_guard)(p);
+	struct rq *rq = rq_guard.rq;
 
-	rq = __task_rq_lock(p, &rf);
-	if (task_on_rq_queued(p)) {
-		update_rq_clock(rq);
-		if (p->se.sched_delayed)
-			enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED);
-		if (!task_on_cpu(rq, p)) {
-			/*
-			 * When on_rq && !on_cpu the task is preempted, see if
-			 * it should preempt the task that is current now.
-			 */
-			wakeup_preempt(rq, p, wake_flags);
+	if (!task_on_rq_queued(p))
+		return 0;
+
+	update_rq_clock(rq);
+	if (p->se.sched_delayed) {
+		int queue_flags = ENQUEUE_DELAYED | ENQUEUE_NOCLOCK;
+
+		/*
+		 * Since sched_delayed means we cannot be current anywhere,
+		 * dequeue it here and have it fall through to the
+		 * select_task_rq() case further along the ttwu() path.
+		 */
+		if (rq->nr_running > 1 && p->nr_cpus_allowed > 1) {
+			dequeue_task(rq, p, DEQUEUE_SLEEP | queue_flags);
+			return 0;
 		}
-		ttwu_do_wakeup(p);
-		ret = 1;
+
+		enqueue_task(rq, p, queue_flags);
 	}
-	__task_rq_unlock(rq, &rf);
+	if (!task_on_cpu(rq, p)) {
+		/*
+		 * When on_rq && !on_cpu the task is preempted, see if
+		 * it should preempt the task that is current now.
+		 */
+		wakeup_preempt(rq, p, wake_flags);
+	}
+	ttwu_do_wakeup(p);
 
-	return ret;
+	return 1;
 }
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 21b1780c6695..1714ac38500f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1787,6 +1787,11 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
 
+DEFINE_LOCK_GUARD_1(__task_rq_lock, struct task_struct,
+		    _T->rq = __task_rq_lock(_T->lock, &_T->rf),
+		    __task_rq_unlock(_T->rq, &_T->rf),
+		    struct rq *rq; struct rq_flags rf)
+
 DEFINE_LOCK_GUARD_1(task_rq_lock, struct task_struct,
 		    _T->rq = task_rq_lock(_T->lock, &_T->rf),
 		    task_rq_unlock(_T->rq, _T->lock, &_T->rf),