Re: [PATCH] sched/deadline: Fix server stopping with runnable tasks

[Peter Zijlstra <peterz@infradead.org>]

On Tue, Jan 13, 2026 at 09:52:01AM +0100, Gabriele Monaco wrote:
> The deadline server can currently stop due to idle although fair tasks
> are runnable. This happens essentially when:
> 
> * the server is set to idle, a task wakes up, the server stops
> * a task wakes up, the server sets itself to idle and stops right away
> 
> Address both cases by clearing the server idle flag whenever a fair task
> wakes up and accounting also for pending tasks in the definition of idle.
> 
> Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
> ---
> 
> This is really quick and dirty but seems to fix it according to the
> models. I also updated the chart to show what is happening here.
> I added the same event (server_resume) to the model.
> 
>  kernel/sched/deadline.c | 12 ++++++++----
>  1 file changed, 8 insertions(+), 4 deletions(-)
> 
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 138136742871..1070e93350df 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -1376,7 +1376,7 @@ update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se, int
>  
>  static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
>  {
> -	bool idle = rq->curr == rq->idle;
> +	bool idle = rq->curr == rq->idle && !rq->nr_running && !rq->ttwu_pending;

This is idle_cpu(), perhaps we can lift that thing into sched.h or so.

>  	s64 scaled_delta_exec;
>  
>  	if (unlikely(delta_exec <= 0)) {
> @@ -1560,8 +1560,8 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
>   * | 8 |       B:zero_laxity-wait       |     |    |
>   * |   |                                | <---+    |
>   * |   +--------------------------------+          |
> - * |     |              ^     ^           2        |
> - * |     | 7            | 2   +--------------------+
> + * |     |              ^         ^       2        |
> + * |     | 7            | 2, 1    +----------------+
>   * |     v              |
>   * |   +-------------+  |
>   * +-- | C:idle-wait | -+
> @@ -1606,8 +1606,11 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
>   *   dl_defer_idle = 0
>   *
>   *
> - * [1] A->B, A->D
> + * [1] A->B, A->D, C->B
>   * dl_server_start()
> + *   dl_defer_idle = 0;
> + *   if (dl_server_active)
> + *     return; // [B]
>   *   dl_server_active = 1;
>   *   enqueue_dl_entity()
>   *     update_dl_entity(WAKEUP)
> @@ -1741,6 +1744,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
>  {
>  	struct rq *rq = dl_se->rq;
>  
> +	dl_se->dl_defer_idle = 0;
>  	if (!dl_server(dl_se) || dl_se->dl_server_active)
>  		return;

Yeah, this seems sensible.

Let me pick it up and do that idle_cpu() thing.