[PATCH v2] sched/eevdf: Fix sched idle task group preemption

[PATCH v2] sched/eevdf: Fix sched idle task group preemption

[Vincent Guittot]

Even with flat hierarchy which puts all runnable tasks in the same cfs rq,
we need to parse the hierarchy to check for sched_idle task group.

Reported-by: Jakub Okoński <jakub@okonski.org>
Link: https://lore.kernel.org/all/58dc8e8a-7260-43ce-aebb-8d9c29a6afc9@okonski.org/
Fixes: 85570f10a4c6 ("sched/eevdf: Move to a single runqueue")
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---

Changes since v1:
- fix prototype and cleanup unsued variable

 kernel/sched/fair.c | 82 ++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 69 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0f2364479f9d..27ce3eb467a0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -433,6 +433,38 @@ static inline struct sched_entity *parent_entity(const struct sched_entity *se)
 	return se->parent;
 }
 
+static void
+find_matching_se(struct sched_entity **se, struct sched_entity **pse)
+{
+	int se_depth, pse_depth;
+
+	/*
+	 * preemption test can be made between sibling entities who are in the
+	 * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
+	 * both tasks until we find their ancestors who are siblings of common
+	 * parent.
+	 */
+
+	/* First walk up until both entities are at same depth */
+	se_depth = (*se)->depth;
+	pse_depth = (*pse)->depth;
+
+	while (se_depth > pse_depth) {
+		se_depth--;
+		*se = parent_entity(*se);
+	}
+
+	while (pse_depth > se_depth) {
+		pse_depth--;
+		*pse = parent_entity(*pse);
+	}
+
+	while (!is_same_group(*se, *pse)) {
+		*se = parent_entity(*se);
+		*pse = parent_entity(*pse);
+	}
+}
+
 static int tg_is_idle(struct task_group *tg)
 {
 	return tg->idle > 0;
@@ -476,6 +508,11 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
 	return NULL;
 }
 
+static inline void
+find_matching_se(struct sched_entity **se, struct sched_entity **pse)
+{
+}
+
 static inline int tg_is_idle(struct task_group *tg)
 {
 	return 0;
@@ -10129,7 +10166,35 @@ preempt_sync(struct rq *rq, int wake_flags,
 }
 
 /*
- * Preempt the current task with a newly woken task if needed:
+ * Preempt an idle entity in favor of a non-idle entity (and don't preempt
+ * in the inverse case).
+ */
+static inline enum preempt_wakeup_action
+wakeup_preempt_sched_idle(struct sched_entity *cse, struct sched_entity *pse)
+{
+	int cse_is_idle, pse_is_idle;
+
+	find_matching_se(&cse, &pse);
+	WARN_ON_ONCE(!pse);
+
+	cse_is_idle = se_is_idle(cse);
+	pse_is_idle = se_is_idle(pse);
+
+	/*
+	 * Preempt an idle entity in favor of a non-idle entity (and don't preempt
+	 * in the inverse case).
+	 */
+	if (cse_is_idle && !pse_is_idle)
+		return PREEMPT_WAKEUP_RESCHED;
+
+	if (cse_is_idle != pse_is_idle)
+		return PREEMPT_WAKEUP_NONE;
+
+	return PREEMPT_WAKEUP_PICK;
+}
+
+/*
+ * Preempt the current task with a newly woken task if needed.
  */
 static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_flags)
 {
@@ -10137,7 +10202,6 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
 	struct task_struct *donor = rq->donor;
 	struct sched_entity *nse, *se = &donor->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = &rq->cfs;
-	int cse_is_idle, pse_is_idle;
 
 	/*
 	 * XXX Getting preempted by higher class, try and find idle CPU?
@@ -10174,22 +10238,14 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
 	if (!sched_feat(WAKEUP_PREEMPTION))
 		return;
 
-	WARN_ON_ONCE(!pse);
-
-	cse_is_idle = se_is_idle(se);
-	pse_is_idle = se_is_idle(pse);
+	preempt_action = wakeup_preempt_sched_idle(se, pse);
 
-	nse = se;
-	/*
-	 * Preempt an idle entity in favor of a non-idle entity (and don't preempt
-	 * in the inverse case).
-	 */
-	if (cse_is_idle && !pse_is_idle)
+	if (preempt_action == PREEMPT_WAKEUP_RESCHED)
 		goto preempt;
 
 	update_curr_fair(rq);
 
-	if (cse_is_idle != pse_is_idle)
+	if (preempt_action == PREEMPT_WAKEUP_NONE)
 		goto update;
 
 	/*
-- 
2.53.0

Re: [PATCH v2] sched/eevdf: Fix sched idle task group preemption

[Kayra Cizmeci]

On Mon, Oct 19, 2026 at 08:26:22PM +0200, Vincent Guittot wrote:
> Even with flat hierarchy which puts all runnable tasks in the same cfs rq,
> we need to parse the hierarchy to check for sched_idle task group.
> 
> Reported-by: Jakub Okoński <jakub@okonski.org>
> Link: https://lore.kernel.org/all/58dc8e8a-7260-43ce-aebb-8d9c29a6afc9@okonski.org/
> Fixes: 85570f10a4c6 ("sched/eevdf: Move to a single runqueue")
> Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
> ---
> 
> Changes since v1:
> - fix prototype and cleanup unsued variable
> 
>  kernel/sched/fair.c | 82 ++++++++++++++++++++++++++++++++++++++-------
>  1 file changed, 69 insertions(+), 13 deletions(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 0f2364479f9d..27ce3eb467a0 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -433,6 +433,38 @@ static inline struct sched_entity *parent_entity(const struct sched_entity *se)
>  	return se->parent;
>  }
>  
> +static void
> +find_matching_se(struct sched_entity **se, struct sched_entity **pse)
> +{
> +	int se_depth, pse_depth;
> +
> +	/*
> +	 * preemption test can be made between sibling entities who are in the
> +	 * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
> +	 * both tasks until we find their ancestors who are siblings of common
> +	 * parent.
> +	 */
> +
> +	/* First walk up until both entities are at same depth */
> +	se_depth = (*se)->depth;
> +	pse_depth = (*pse)->depth;
> +
> +	while (se_depth > pse_depth) {
> +		se_depth--;
> +		*se = parent_entity(*se);
> +	}
> +
> +	while (pse_depth > se_depth) {
> +		pse_depth--;
> +		*pse = parent_entity(*pse);
> +	}
> +
> +	while (!is_same_group(*se, *pse)) {
> +		*se = parent_entity(*se);
> +		*pse = parent_entity(*pse);
> +	}
> +}
> +

So in a hierarchy like:

    ROOT
     /\
    /  \
   /    \
  GA    GB
   |    /\
   V   /  \
  TA  GC   GD
      |    |
      V    V
      TB   TC

Where GA is idle, GB is not, GC is idle and GD is not.

1. TA == se & TB == pse:
pse_depth > se_depth is true, so we goto GC. Now pse = GC.
Then we enter !is_same_group() block where we go up one more
time, so now se is GA, and pse is GB.


>  static int tg_is_idle(struct task_group *tg)
>  {
>  	return tg->idle > 0;
> @@ -476,6 +508,11 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
>  	return NULL;
>  }
>  
> +static inline void
> +find_matching_se(struct sched_entity **se, struct sched_entity **pse)
> +{
> +}
> +
>  static inline int tg_is_idle(struct task_group *tg)
>  {
>  	return 0;
> @@ -10129,7 +10166,35 @@ preempt_sync(struct rq *rq, int wake_flags,
>  }
>  
>  /*
> - * Preempt the current task with a newly woken task if needed:
> + * Preempt an idle entity in favor of a non-idle entity (and don't preempt
> + * in the inverse case).
> + */
> +static inline enum preempt_wakeup_action
> +wakeup_preempt_sched_idle(struct sched_entity *cse, struct sched_entity *pse)
> +{
> +	int cse_is_idle, pse_is_idle;
> +
> +	find_matching_se(&cse, &pse);
> +	WARN_ON_ONCE(!pse);
> +
> +	cse_is_idle = se_is_idle(cse);
> +	pse_is_idle = se_is_idle(pse);
> +
> +	/*
> +	 * Preempt an idle entity in favor of a non-idle entity (and don't preempt
> +	 * in the inverse case).
> +	 */
> +	if (cse_is_idle && !pse_is_idle)
> +		return PREEMPT_WAKEUP_RESCHED;
> +
> +	if (cse_is_idle != pse_is_idle)
> +		return PREEMPT_WAKEUP_NONE;
> +
> +	return PREEMPT_WAKEUP_PICK;
> +}
> +
> +/*


2. In here, cse_is_idle is true, while pse_is_idle is false.
So we return PREEMPT_WAKEUP_RESCHED. If these are inversed,
we return PREEMPT_WAKEUP_NONE. If they are equal, we return
PREEMPT_WAKEUP_PICK.


> + * Preempt the current task with a newly woken task if needed.
>   */
>  static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_flags)
>  {
> @@ -10137,7 +10202,6 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
>  	struct task_struct *donor = rq->donor;
>  	struct sched_entity *nse, *se = &donor->se, *pse = &p->se;
>  	struct cfs_rq *cfs_rq = &rq->cfs;
> -	int cse_is_idle, pse_is_idle;
>  
>  	/*
>  	 * XXX Getting preempted by higher class, try and find idle CPU?
> @@ -10174,22 +10238,14 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
>  	if (!sched_feat(WAKEUP_PREEMPTION))
>  		return;
>  
> -	WARN_ON_ONCE(!pse);
> -
> -	cse_is_idle = se_is_idle(se);
> -	pse_is_idle = se_is_idle(pse);
> +	preempt_action = wakeup_preempt_sched_idle(se, pse);
>  
> -	nse = se;
> -	/*
> -	 * Preempt an idle entity in favor of a non-idle entity (and don't preempt
> -	 * in the inverse case).
> -	 */
> -	if (cse_is_idle && !pse_is_idle)
> +	if (preempt_action == PREEMPT_WAKEUP_RESCHED)
>  		goto preempt;
>  
>  	update_curr_fair(rq);
>  
> -	if (cse_is_idle != pse_is_idle)
> +	if (preempt_action == PREEMPT_WAKEUP_NONE)
>  		goto update;
>  
>  	/*
> -- 
> 2.53.0
> 

This only changes where we look, not what we do
with the results. AFAICT. I added my review notes too. They are not
essential but I still did wanted to add them IDK why tho.

Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>

Thanks,

Kayra