[PATCH 1/2] sched/fair: reuse the ENQUEUE_DELAYED calculation in enqueue_task_fair()

[PATCH 1/2] sched/fair: reuse the ENQUEUE_DELAYED calculation in enqueue_task_fair()

[Kayra Cizmeci]

Currently flags & ENQUEUE_DELAYED checks spread throughout the
enqueue_task_fair(), connect these checks to a bool 'delayed' that
gets calculated at the start of the function.

No functional change intended.

Signed-off-by: Kayra Cizmeci <kayracizmeci@gmail.com>
---
 kernel/sched/fair.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6d881e530f89..b411384125ec 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7985,7 +7985,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	unsigned long weight;
-	bool curr;
+	bool curr, delayed = (flags & ENQUEUE_DELAYED);
 
 	if (task_is_throttled(p) && enqueue_throttled_task(p))
 		return;
@@ -7996,12 +7996,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * Let's add the task's estimated utilization to the cfs_rq's
 	 * estimated utilization, before we update schedutil.
 	 */
-	if (!p->se.sched_delayed || (flags & ENQUEUE_DELAYED))
+	if (!p->se.sched_delayed || delayed)
 		util_est_enqueue(cfs_rq, p);
 
 	update_curr_eevdf(cfs_rq);
 
-	if (flags & ENQUEUE_DELAYED) {
+	if (delayed) {
 		requeue_delayed_entity(cfs_rq, se);
 		return;
 	}
-- 
2.53.0

[PATCH 2/2] sched/fair: avoid recalculating curr status in place_entity() and requeue_delayed_entity()

[Kayra Cizmeci]

In enqueue_task_fair() a bool is calculated by cfs_rq->curr == se.
But this information gets recalculated on requeue_delayed_entity() and
requeue_delayed_entity() only gets called in enqueue_task_fair().
And on place_entity() if se == curr we call the avg_vruntime_weight()
twice with the same input. place_entity() only gets called in
enqueue_task_fair() and requeue_delayed_entity().

Use the information on enqueue_task_fair() in requeue_delayed_entity().
And place_entity() to avoid calling avg_vruntime_weight() twice.

Signed-off-by: Kayra Cizmeci <kayracizmeci@gmail.com>
---
The patch needs curr to be invariant so I added the same 
(cfs_rq->curr == se) to places in requeue_delayed_entity() and
and enqueue_task_fair(). Like after the place_entity() call in
requeue_delayed_entity(), or like before if (curr) the old place
of the calculation. And added WARN_ON_ONCE(curr != new_calc_curr)
or something like that I don't know how to say it normally.

Then I booted these changes on x86 (Zen 3)
called perf bench sched messaging with 200 groups and 5000 loops.
And then I make sure if the requeue_delayed_entity() was really working
with ftrace. The results were good but I left the computer on 2 more
hours and then checked the results again. It was still good, but
considering that I booted the kernel with busybox I don't think
much happened on that 2 hour window. 

 kernel/sched/fair.c | 36 ++++++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b411384125ec..304ef70685d2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6175,7 +6175,7 @@ void __setparam_fair(struct task_struct *p, const struct sched_attr *attr)
 }
 
 static void
-place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags, bool is_curr)
 {
 	u64 vslice, vruntime = avg_vruntime(cfs_rq);
 	unsigned int nr_queued = cfs_rq->h_nr_queued;
@@ -6199,7 +6199,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	if (sched_feat(PLACE_LAG) && nr_queued && se->vlag) {
 		struct sched_entity *curr = cfs_rq->curr;
-		long load, weight;
+		long load, weight, curr_weight;
 
 		lag = se->vlag;
 
@@ -6256,10 +6256,17 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		 *   vl_i = (W + w_i)*vl'_i / W
 		 */
 		load = cfs_rq->sum_weight;
-		if (curr && curr->on_rq)
-			load += avg_vruntime_weight(cfs_rq, curr->h_load.weight);
+		if (curr) {
+			curr_weight = avg_vruntime_weight(cfs_rq, curr->h_load.weight);
+			if (curr->on_rq)
+				load += curr_weight;
+		}
+
+		if (is_curr)
+			weight = curr_weight;
+		else
+			weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);
 
-		weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);
 		lag *= load + weight;
 		if (WARN_ON_ONCE(!load))
 			load = 1;
@@ -7900,7 +7907,7 @@ static int choose_idle_cpu(int cpu, struct task_struct *p)
 }
 
 static void
-requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
+requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool curr)
 {
 	/*
 	 * se->sched_delayed should imply: se->on_rq == 1.
@@ -7912,10 +7919,10 @@ requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 	if (update_entity_lag(cfs_rq, se)) {
 		cfs_rq->h_nr_queued--;
-		if (se != cfs_rq->curr)
+		if (!curr)
 			__dequeue_entity(cfs_rq, se);
-		place_entity(cfs_rq, se, 0);
-		if (se != cfs_rq->curr)
+		place_entity(cfs_rq, se, 0, curr);
+		if (!curr)
 			__enqueue_entity(cfs_rq, se);
 		cfs_rq->h_nr_queued++;
 	}
@@ -8000,9 +8007,10 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		util_est_enqueue(cfs_rq, p);
 
 	update_curr_eevdf(cfs_rq);
+	curr = (cfs_rq->curr == se);
 
 	if (delayed) {
-		requeue_delayed_entity(cfs_rq, se);
+		requeue_delayed_entity(cfs_rq, se, curr);
 		return;
 	}
 
@@ -8017,18 +8025,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	/*
 	 * XXX comment on the curr thing
 	 */
-	curr = (cfs_rq->curr == se);
+
 	if (curr)
-		place_entity(cfs_rq, se, flags);
+		place_entity(cfs_rq, se, flags, curr);
 
 	if (se->on_rq && se->sched_delayed)
-		requeue_delayed_entity(cfs_rq, se);
+		requeue_delayed_entity(cfs_rq, se, curr);
 
 	weight = enqueue_hierarchy(p, flags);
 
 	if (!curr) {
 		reweight_eevdf(cfs_rq, se, weight, false);
-		place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
+		place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED, curr);
 		__enqueue_entity(cfs_rq, se);
 	}
 
-- 
2.53.0

[PATCH v2 0/2] sched/fair: reduce repeated work in enqueue path

[Kayra Cizmeci]

1/2: Gather the flags & DELAYED_QUEUE controls in one place.

2/2: give the calculated curr == se onto requeue_delayed_entity()
and place_entity()

Changelog:

1/2: No changes.

2/2: add (is_curr || curr->on_rq) condition to the 
check for calculating curr_weight so when both of them are false the 
curr_weight won't go to waste.

v1: https://lore.kernel.org/lkml/20260824125223.508178-1-kayracizmeci@gmail.com/

Kayra Cizmeci (2):
  sched/fair: reuse the ENQUEUE_DELAYED calculation in
    enqueue_task_fair()
  sched/fair: avoid recalculating curr status in place_entity() and
    requeue_delayed_entity()

 kernel/sched/fair.c | 42 +++++++++++++++++++++++++-----------------
 1 file changed, 25 insertions(+), 17 deletions(-)

-- 
2.53.0

[PATCH v2 1/2] sched/fair: reuse the ENQUEUE_DELAYED calculation in enqueue_task_fair()

[Kayra Cizmeci]

Currently flags & ENQUEUE_DELAYED checks spread throughout the
enqueue_task_fair(), connect these checks to a bool 'delayed' that
gets calculated at the start of the function.

No functional change intended.

Signed-off-by: Kayra Cizmeci <kayracizmeci@gmail.com>
---
 kernel/sched/fair.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6d881e530f89..b411384125ec 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7985,7 +7985,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	unsigned long weight;
-	bool curr;
+	bool curr, delayed = (flags & ENQUEUE_DELAYED);
 
 	if (task_is_throttled(p) && enqueue_throttled_task(p))
 		return;
@@ -7996,12 +7996,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * Let's add the task's estimated utilization to the cfs_rq's
 	 * estimated utilization, before we update schedutil.
 	 */
-	if (!p->se.sched_delayed || (flags & ENQUEUE_DELAYED))
+	if (!p->se.sched_delayed || delayed)
 		util_est_enqueue(cfs_rq, p);
 
 	update_curr_eevdf(cfs_rq);
 
-	if (flags & ENQUEUE_DELAYED) {
+	if (delayed) {
 		requeue_delayed_entity(cfs_rq, se);
 		return;
 	}
-- 
2.53.0

[PATCH v2 2/2] sched/fair: avoid recalculating curr status in place_entity() and requeue_delayed_entity()

[Kayra Cizmeci]

In enqueue_task_fair() a bool is calculated by cfs_rq->curr == se.
But this information gets recalculated on requeue_delayed_entity() and
requeue_delayed_entity() only gets called in enqueue_task_fair().
And on place_entity() if se == curr we call the avg_vruntime_weight()
twice with the same input. place_entity() only gets called in
enqueue_task_fair() and requeue_delayed_entity().

Use the information on enqueue_task_fair() in requeue_delayed_entity().
And place_entity() to avoid calling avg_vruntime_weight() twice.

Signed-off-by: Kayra Cizmeci <kayracizmeci@gmail.com>
---
The patch needs curr to be invariant so I added the same 
(cfs_rq->curr == se) to places in requeue_delayed_entity() and
and enqueue_task_fair(). Like after the place_entity() call in
requeue_delayed_entity(), or like before if (curr) the old place
of the calculation. And added WARN_ON_ONCE(curr != new_calc_curr)
or something like that I don't know how to say it normally.

Then I booted these changes on x86 (Zen 3)
called perf bench sched messaging with 200 groups and 5000 loops.
And then I make sure if the requeue_delayed_entity() was really working
with ftrace. The results were good but I left the computer on 2 more
hours and then checked the results again. It was still good, but
considering that I booted the kernel with busybox I don't think
much happened on that 2 hour window.

 kernel/sched/fair.c | 36 ++++++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b411384125ec..f1b46fe26d12 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6175,7 +6175,7 @@ void __setparam_fair(struct task_struct *p, const struct sched_attr *attr)
 }
 
 static void
-place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags, bool is_curr)
 {
 	u64 vslice, vruntime = avg_vruntime(cfs_rq);
 	unsigned int nr_queued = cfs_rq->h_nr_queued;
@@ -6199,7 +6199,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	if (sched_feat(PLACE_LAG) && nr_queued && se->vlag) {
 		struct sched_entity *curr = cfs_rq->curr;
-		long load, weight;
+		long load, weight, curr_weight;
 
 		lag = se->vlag;
 
@@ -6256,10 +6256,17 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		 *   vl_i = (W + w_i)*vl'_i / W
 		 */
 		load = cfs_rq->sum_weight;
-		if (curr && curr->on_rq)
-			load += avg_vruntime_weight(cfs_rq, curr->h_load.weight);
+		if (curr && (curr->on_rq || is_curr)) {
+			curr_weight = avg_vruntime_weight(cfs_rq, curr->h_load.weight);
+			if (curr->on_rq)
+				load += curr_weight;
+		}
+
+		if (is_curr)
+			weight = curr_weight;
+		else
+			weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);
 
-		weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);
 		lag *= load + weight;
 		if (WARN_ON_ONCE(!load))
 			load = 1;
@@ -7900,7 +7907,7 @@ static int choose_idle_cpu(int cpu, struct task_struct *p)
 }
 
 static void
-requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
+requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool curr)
 {
 	/*
 	 * se->sched_delayed should imply: se->on_rq == 1.
@@ -7912,10 +7919,10 @@ requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 	if (update_entity_lag(cfs_rq, se)) {
 		cfs_rq->h_nr_queued--;
-		if (se != cfs_rq->curr)
+		if (!curr)
 			__dequeue_entity(cfs_rq, se);
-		place_entity(cfs_rq, se, 0);
-		if (se != cfs_rq->curr)
+		place_entity(cfs_rq, se, 0, curr);
+		if (!curr)
 			__enqueue_entity(cfs_rq, se);
 		cfs_rq->h_nr_queued++;
 	}
@@ -8000,9 +8007,10 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		util_est_enqueue(cfs_rq, p);
 
 	update_curr_eevdf(cfs_rq);
+	curr = (cfs_rq->curr == se);
 
 	if (delayed) {
-		requeue_delayed_entity(cfs_rq, se);
+		requeue_delayed_entity(cfs_rq, se, curr);
 		return;
 	}
 
@@ -8017,18 +8025,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	/*
 	 * XXX comment on the curr thing
 	 */
-	curr = (cfs_rq->curr == se);
+
 	if (curr)
-		place_entity(cfs_rq, se, flags);
+		place_entity(cfs_rq, se, flags, curr);
 
 	if (se->on_rq && se->sched_delayed)
-		requeue_delayed_entity(cfs_rq, se);
+		requeue_delayed_entity(cfs_rq, se, curr);
 
 	weight = enqueue_hierarchy(p, flags);
 
 	if (!curr) {
 		reweight_eevdf(cfs_rq, se, weight, false);
-		place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
+		place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED, curr);
 		__enqueue_entity(cfs_rq, se);
 	}
 
-- 
2.53.0

Re: [PATCH v2 1/2] sched/fair: reuse the ENQUEUE_DELAYED calculation in enqueue_task_fair()

[K Prateek Nayak]

On 8/26/2026 3:45 PM, Kayra Cizmeci wrote:
> @@ -7996,12 +7996,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>  	 * Let's add the task's estimated utilization to the cfs_rq's
>  	 * estimated utilization, before we update schedutil.
>  	 */
> -	if (!p->se.sched_delayed || (flags & ENQUEUE_DELAYED))
> +	if (!p->se.sched_delayed || delayed)

nit. This reads funny now - not delayed or delayed?

Maybe wakeup_delayed but all of this should be optimized by compiler
at the end and a big ENQUEUE_DELAYED is better for humans who are
reading the code no?

>  		util_est_enqueue(cfs_rq, p);
>  
>  	update_curr_eevdf(cfs_rq);
>  
> -	if (flags & ENQUEUE_DELAYED) {
> +	if (delayed) {
>  		requeue_delayed_entity(cfs_rq, se);
>  		return;
>  	}

-- 
Thanks and Regards,
Prateek

Re: [PATCH v2 1/2] sched/fair: reuse the ENQUEUE_DELAYED calculation in enqueue_task_fair()

[Kayra Cizmeci]

> Maybe wakeup_delayed but all of this should be optimized by compiler
> at the end and a big ENQUEUE_DELAYED is better for humans who are
> reading the code no?

Can't we rename it and use it in both places? If not then using ENQUEUE_DELAYED 
is better since the approach remains the same in both places, no?

Thanks,
Kayra

Re: [PATCH] sched/fair: Remove unused autogroup.h include

[Kayra Cizmeci]

Gentle ping on this patch.

Re: [PATCH v2 1/2] sched/fair: reuse the ENQUEUE_DELAYED calculation in enqueue_task_fair()

[Kayra Cizmeci]

Hello Prateek,

>> @@ -7996,12 +7996,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>>  	 * Let's add the task's estimated utilization to the cfs_rq's
>>  	 * estimated utilization, before we update schedutil.
>>  	 */
>> -	if (!p->se.sched_delayed || (flags & ENQUEUE_DELAYED))
>> +	if (!p->se.sched_delayed || delayed)

> nit. This reads funny now - not delayed or delayed?

> Maybe wakeup_delayed but all of this should be optimized by compiler
> at the end and a big ENQUEUE_DELAYED is better for humans who are
> reading the code no?

In my first message I was thinking that renaming and using it in both places would be 
the better approach. But I thought about this the meantime and I changed my mind.
flags & ENQUEUE_DELAYED reads better and more clear than a bool. And I can't really
see a big advantage of renaming it over this version.

Patch subject is a bit confusing since it says reuse the bla bla
calculation in the enqueue_task_fair(). And this subject
makes it seem like there is a performance claim.

I knew It was getting optimized by the compiler, I thought at the time that
gathering this flags & ENQUEUE_DELAYED in one place would be better.

I'm dropping this patch (1/2) but I'll continue with 2/2 :->.

NOTE: I send the wrong file that was with the same
name with my correct file that I supposed to send. Sorry for this autogroup.h
ping thing. Ah..

Thanks, 
Kayra

Re: [PATCH v2 2/2] sched/fair: avoid recalculating curr status in place_entity() and requeue_delayed_entity()

[Kayra Cizmeci]

Gentle Ping on this patch, :_:

Re: [PATCH v2 2/2] sched/fair: avoid recalculating curr status in place_entity() and requeue_delayed_entity()

[Vincent Guittot]

On Wed, 26 Aug 2026 at 12:18, Kayra Cizmeci <kayracizmeci@gmail.com> wrote:
>
> In enqueue_task_fair() a bool is calculated by cfs_rq->curr == se.
> But this information gets recalculated on requeue_delayed_entity() and
> requeue_delayed_entity() only gets called in enqueue_task_fair().
> And on place_entity() if se == curr we call the avg_vruntime_weight()
> twice with the same input. place_entity() only gets called in
> enqueue_task_fair() and requeue_delayed_entity().
>
> Use the information on enqueue_task_fair() in requeue_delayed_entity().
> And place_entity() to avoid calling avg_vruntime_weight() twice.
>
> Signed-off-by: Kayra Cizmeci <kayracizmeci@gmail.com>
> ---
> The patch needs curr to be invariant so I added the same
> (cfs_rq->curr == se) to places in requeue_delayed_entity() and
> and enqueue_task_fair(). Like after the place_entity() call in
> requeue_delayed_entity(), or like before if (curr) the old place
> of the calculation. And added WARN_ON_ONCE(curr != new_calc_curr)
> or something like that I don't know how to say it normally.
>
> Then I booted these changes on x86 (Zen 3)
> called perf bench sched messaging with 200 groups and 5000 loops.
> And then I make sure if the requeue_delayed_entity() was really working
> with ftrace. The results were good but I left the computer on 2 more
> hours and then checked the results again. It was still good, but
> considering that I booted the kernel with busybox I don't think
> much happened on that 2 hour window.
>
>  kernel/sched/fair.c | 36 ++++++++++++++++++++++--------------
>  1 file changed, 22 insertions(+), 14 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index b411384125ec..f1b46fe26d12 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6175,7 +6175,7 @@ void __setparam_fair(struct task_struct *p, const struct sched_attr *attr)
>  }
>
>  static void
> -place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
> +place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags, bool is_curr)
>  {
>         u64 vslice, vruntime = avg_vruntime(cfs_rq);
>         unsigned int nr_queued = cfs_rq->h_nr_queued;
> @@ -6199,7 +6199,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
>          */
>         if (sched_feat(PLACE_LAG) && nr_queued && se->vlag) {
>                 struct sched_entity *curr = cfs_rq->curr;
> -               long load, weight;
> +               long load, weight, curr_weight;
>
>                 lag = se->vlag;
>
> @@ -6256,10 +6256,17 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
>                  *   vl_i = (W + w_i)*vl'_i / W
>                  */
>                 load = cfs_rq->sum_weight;
> -               if (curr && curr->on_rq)
> -                       load += avg_vruntime_weight(cfs_rq, curr->h_load.weight);
> +               if (curr && (curr->on_rq || is_curr)) {
> +                       curr_weight = avg_vruntime_weight(cfs_rq, curr->h_load.weight);
> +                       if (curr->on_rq)
> +                               load += curr_weight;
> +               }
> +
> +               if (is_curr)
> +                       weight = curr_weight;
> +               else
> +                       weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);

This makes the code less readable and I don't think it gives any
measurable benefit.

>
> -               weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);
>                 lag *= load + weight;
>                 if (WARN_ON_ONCE(!load))
>                         load = 1;
> @@ -7900,7 +7907,7 @@ static int choose_idle_cpu(int cpu, struct task_struct *p)
>  }
>
>  static void
> -requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
> +requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool curr)
>  {
>         /*
>          * se->sched_delayed should imply: se->on_rq == 1.
> @@ -7912,10 +7919,10 @@ requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
>
>         if (update_entity_lag(cfs_rq, se)) {
>                 cfs_rq->h_nr_queued--;
> -               if (se != cfs_rq->curr)
> +               if (!curr)
>                         __dequeue_entity(cfs_rq, se);
> -               place_entity(cfs_rq, se, 0);
> -               if (se != cfs_rq->curr)
> +               place_entity(cfs_rq, se, 0, curr);
> +               if (!curr)
>                         __enqueue_entity(cfs_rq, se);
>                 cfs_rq->h_nr_queued++;
>         }
> @@ -8000,9 +8007,10 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>                 util_est_enqueue(cfs_rq, p);
>
>         update_curr_eevdf(cfs_rq);
> +       curr = (cfs_rq->curr == se);
>
>         if (delayed) {
> -               requeue_delayed_entity(cfs_rq, se);
> +               requeue_delayed_entity(cfs_rq, se, curr);
>                 return;
>         }
>
> @@ -8017,18 +8025,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>         /*
>          * XXX comment on the curr thing
>          */
> -       curr = (cfs_rq->curr == se);
> +
>         if (curr)
> -               place_entity(cfs_rq, se, flags);
> +               place_entity(cfs_rq, se, flags, curr);
>
>         if (se->on_rq && se->sched_delayed)
> -               requeue_delayed_entity(cfs_rq, se);
> +               requeue_delayed_entity(cfs_rq, se, curr);
>
>         weight = enqueue_hierarchy(p, flags);
>
>         if (!curr) {
>                 reweight_eevdf(cfs_rq, se, weight, false);
> -               place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
> +               place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED, curr);
>                 __enqueue_entity(cfs_rq, se);
>         }
>
> --
> 2.53.0
>

Re: [PATCH v2 2/2] sched/fair: avoid recalculating curr status in place_entity() and requeue_delayed_entity()

[Peter Zijlstra]

On Wed, Aug 26, 2026 at 01:15:42PM +0300, Kayra Cizmeci wrote:
> In enqueue_task_fair() a bool is calculated by cfs_rq->curr == se.
> But this information gets recalculated on requeue_delayed_entity() and
> requeue_delayed_entity() only gets called in enqueue_task_fair().
> And on place_entity() if se == curr we call the avg_vruntime_weight()
> twice with the same input. place_entity() only gets called in
> enqueue_task_fair() and requeue_delayed_entity().

I found it very hard to follow your Changelog. Could be my Friday brain.
Sorry if I misunderstood.

> @@ -8000,9 +8007,10 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>  		util_est_enqueue(cfs_rq, p);
>  
>  	update_curr_eevdf(cfs_rq);
> +	curr = (cfs_rq->curr == se);
>  
>  	if (delayed) {
> -		requeue_delayed_entity(cfs_rq, se);
> +		requeue_delayed_entity(cfs_rq, se, curr);
>  		return;
>  	}
>  
> @@ -8017,18 +8025,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>  	/*
>  	 * XXX comment on the curr thing
>  	 */
> -	curr = (cfs_rq->curr == se);
> +
>  	if (curr)
> -		place_entity(cfs_rq, se, flags);
> +		place_entity(cfs_rq, se, flags, curr);

As I argued here:
  
  https://patch.msgid.link/20260813103155.GC1246887%40noisy.programming.kicks-ass.net

I suspect that case is impossible. Which AFAICT renders your whole patch
one big no-op, no?

That is, I think we want to do the below.

---
 kernel/sched/fair.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4d0b94465d19..3c7fb0684a76 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7996,7 +7996,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	unsigned long weight;
-	bool curr;
 
 	if (task_is_throttled(p) && enqueue_throttled_task(p))
 		return;
@@ -8025,23 +8024,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (p->in_iowait)
 		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
 
-	/*
-	 * XXX comment on the curr thing
-	 */
-	curr = (cfs_rq->curr == se);
-	if (curr)
-		place_entity(cfs_rq, se, flags);
 
 	if (se->on_rq && se->sched_delayed)
 		requeue_delayed_entity(cfs_rq, se);
 
 	weight = enqueue_hierarchy(p, flags);
-
-	if (!curr) {
-		reweight_eevdf(cfs_rq, se, weight, false);
-		place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
-		__enqueue_entity(cfs_rq, se);
-	}
+	reweight_eevdf(cfs_rq, se, weight, false);
+	place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
+	__enqueue_entity(cfs_rq, se);
 
 	if (!rq_h_nr_queued && rq->cfs.h_nr_queued)
 		dl_server_start(&rq->fair_server);

Re: [PATCH v2 2/2] sched/fair: avoid recalculating curr status in place_entity() and requeue_delayed_entity()

[Kayra Cizmeci]

Hello Vincent,

>> @@ -6256,10 +6256,17 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
>>                  *   vl_i = (W + w_i)*vl'_i / W
>>                  */
>>                 load = cfs_rq->sum_weight;
>> -               if (curr && curr->on_rq)
>> -                       load += avg_vruntime_weight(cfs_rq, curr->h_load.weight);
>> +               if (curr && (curr->on_rq || is_curr)) {
>> +                       curr_weight = avg_vruntime_weight(cfs_rq, curr->h_load.weight);
>> +                       if (curr->on_rq)
>> +                               load += curr_weight;
>> +               }
>> +
>> +               if (is_curr)
>> +                       weight = curr_weight;
>> +               else
>> +                       weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);

> This makes the code less readable and I don't think it gives any
> measurable benefit.

Well, yeah. 1 avg_vruntime_weight() less or much is not measurable
in any means. 

The main thing I wanted was to handle curr == se case
on here.

Maybe we could remove this is_curr bool and look se == curr
in function, and remove this curr weight and let the curr use weight
instead. So, the curr_weightnbecomes weight, we could be done
with the if (is_curr) block since we don't need to set weight to curr_weight.

Well if you think handling curr == se separately is wrong, then I'll drop the patch.

Please let me know what you're thinking :-).

Thanks,
Kayra :_:

Re: [PATCH v2 2/2] sched/fair: avoid recalculating curr status in place_entity() and requeue_delayed_entity()

[Kayra Cizmeci]

Hello Peter :>,

>> In enqueue_task_fair() a bool is calculated by cfs_rq->curr == se.
>> But this information gets recalculated on requeue_delayed_entity() and
>> requeue_delayed_entity() only gets called in enqueue_task_fair().
>> And on place_entity() if se == curr we call the avg_vruntime_weight()
>> twice with the same input. place_entity() only gets called in
>> enqueue_task_fair() and requeue_delayed_entity().

> I found it very hard to follow your Changelog. Could be my Friday brain.
> Sorry if I misunderstood.

It's not your Friday brain, it's my talking skills ;>.

> As I argued here:

>  https://patch.msgid.link/20260813103155.GC1246887%40noisy.programming.kicks-ass.net

Oh, I remembered that patch. 1 month ago. But I didn't look into it in detail at the time.

> I suspect that case is impossible. Which AFAICT renders your whole patch
> one big no-op, no?

Well, I run some tests with WARN_ON_ONCE and that case never worked. Atleast on my tests and on my machine. I didn't done so many tests tho.

I remember doing some WARN_ON_ONCE tests on v1 too. But I don't think I did
a test about curr == se, since I thought there was no way that it does not work. Well... :P.



> That is, I think we want to do the below.

> ---
>  kernel/sched/fair.c | 16 +++-------------
>  1 file changed, 3 insertions(+), 13 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 4d0b94465d19..3c7fb0684a76 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -7996,7 +7996,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>         struct sched_entity *se = &p->se;
>         struct cfs_rq *cfs_rq = &rq->cfs;
>         unsigned long weight;
> -       bool curr;
> 
>         if (task_is_throttled(p) && enqueue_throttled_task(p))
>                 return;
> @@ -8025,23 +8024,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>         if (p->in_iowait)
>                 cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
> 
> -       /*
> -        * XXX comment on the curr thing
> -        */
> -       curr = (cfs_rq->curr == se);
> -       if (curr)
> -               place_entity(cfs_rq, se, flags);
>
>         if (se->on_rq && se->sched_delayed)
>                 requeue_delayed_entity(cfs_rq, se);
> 
>         weight = enqueue_hierarchy(p, flags);
> -
> -       if (!curr) {
> -               reweight_eevdf(cfs_rq, se, weight, false);
> -               place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
> -               __enqueue_entity(cfs_rq, se);
> -       }
> +       reweight_eevdf(cfs_rq, se, weight, false);
> +       place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
> +       __enqueue_entity(cfs_rq, se);

        if (!rq_h_nr_queued && rq->cfs.h_nr_queued)
                dl_server_start(&rq->fair_server);

So, you say remove all of this curr crap and get everything in one place since the
curr = (cfs_rq->curr == se) returns false all the time? That way we wouldn't need to
worry about the place_entity() parts neither. I'm OK. I'll send the v3 today or tommorow
latest.

[PATCH v3] sched/fair: remove dead code on enqueue_task_fair()

[Kayra Cizmeci]

cfs_rq->curr == se path on enqueue_task_fair() seems to be unachievable.

Remove the code that depends on this cfs_rq->curr == se case on
enqueue_task_fair() and bool curr too since there are two possibilities
and one has been removed, we can proceed directly with the other.

Signed-off-by: Kayra Cizmeci <kayracizmeci@gmail.com>
---
Ah.. 

I forgot to add v3. Sorry of the other one.

 kernel/sched/fair.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ade1eceb39b8..440e4fdebe2f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7985,7 +7985,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	unsigned long weight;
-	bool curr;
 
 	if (task_is_throttled(p) && enqueue_throttled_task(p))
 		return;
@@ -8014,23 +8013,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (p->in_iowait)
 		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
 
-	/*
-	 * XXX comment on the curr thing
-	 */
-	curr = (cfs_rq->curr == se);
-	if (curr)
-		place_entity(cfs_rq, se, flags);
 
 	if (se->on_rq && se->sched_delayed)
 		requeue_delayed_entity(cfs_rq, se);
 
 	weight = enqueue_hierarchy(p, flags);
-
-	if (!curr) {
-		reweight_eevdf(cfs_rq, se, weight, false);
-		place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
-		__enqueue_entity(cfs_rq, se);
-	}
+	reweight_eevdf(cfs_rq, se, weight, false);
+	place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
+	__enqueue_entity(cfs_rq, se);
 
 	if (!rq_h_nr_queued && rq->cfs.h_nr_queued)
 		dl_server_start(&rq->fair_server);
-- 
2.53.0