Re: [RFC PATCH v2 12/25] sched/rt: Add {alloc/free}_rt_sched_group and dl_server specific functions

[Juri Lelli <juri.lelli@redhat.com>]

Hi!

On 31/07/25 12:55, Yuri Andriaccio wrote:
> From: luca abeni <luca.abeni@santannapisa.it>
> 
> Add allocation and deallocation code for rt-cgroups. Add rt dl_server's specific
> functions that pick the next eligible task to run.
> 
> Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
> Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
> Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
> Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
> Co-developed-by: Yuri Andriaccio <yurand2000@gmail.com>
> Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
> Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
> ---
>  kernel/sched/rt.c | 107 ++++++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 104 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index 38178003184..9c4ac6875a2 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -93,8 +93,39 @@ void unregister_rt_sched_group(struct task_group *tg)
>  
>  void free_rt_sched_group(struct task_group *tg)
>  {
> +	int i;
> +
>  	if (!rt_group_sched_enabled())
>  		return;
> +
> +	for_each_possible_cpu(i) {
> +		if (tg->dl_se) {
> +			unsigned long flags;
> +
> +			/*
> +			 * Since the dl timer is going to be cancelled,
> +			 * we risk to never decrease the running bw...
> +			 * Fix this issue by changing the group runtime
> +			 * to 0 immediately before freeing it.
> +			 */
> +			dl_init_tg(tg->dl_se[i], 0, tg->dl_se[i]->dl_period);
> +			raw_spin_rq_lock_irqsave(cpu_rq(i), flags);
> +			BUG_ON(tg->rt_rq[i]->rt_nr_running);
> +			raw_spin_rq_unlock_irqrestore(cpu_rq(i), flags);

So here we always call dl_init_tg for cpu 0, is it correct?

Also I wonder if the lock shouldn't cover both init and subsequent
check.

> +
> +			hrtimer_cancel(&tg->dl_se[i]->dl_timer);
> +			kfree(tg->dl_se[i]);
> +		}
> +		if (tg->rt_rq) {
> +			struct rq *served_rq;
> +
> +			served_rq = container_of(tg->rt_rq[i], struct rq, rt);
> +			kfree(served_rq);
> +		}
> +	}
> +
> +	kfree(tg->rt_rq);
> +	kfree(tg->dl_se);
>  }
>  
>  void init_tg_rt_entry(struct task_group *tg, struct rq *served_rq,
> @@ -109,12 +140,77 @@ void init_tg_rt_entry(struct task_group *tg, struct rq *served_rq,
>  	tg->dl_se[cpu] = dl_se;
>  }
>  
> +static bool rt_server_has_tasks(struct sched_dl_entity *dl_se)
> +{
> +	return !!dl_se->my_q->rt.rt_nr_running;
> +}
> +
> +static struct task_struct *_pick_next_task_rt(struct rt_rq *rt_rq);
> +static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool first);
> +static struct task_struct *rt_server_pick(struct sched_dl_entity *dl_se)
> +{
> +	struct rt_rq *rt_rq = &dl_se->my_q->rt;
> +	struct rq *rq = rq_of_rt_rq(rt_rq);
> +	struct task_struct *p;
> +
> +	if (dl_se->my_q->rt.rt_nr_running == 0)
> +		return NULL;
> +
> +	p = _pick_next_task_rt(rt_rq);
> +	set_next_task_rt(rq, p, true);
> +
> +	return p;
> +}
> +
>  int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
>  {
> +	struct rq *s_rq;
> +	struct sched_dl_entity *dl_se;
> +	int i;
> +
>  	if (!rt_group_sched_enabled())
>  		return 1;
>  
> +	tg->rt_rq = kcalloc(nr_cpu_ids, sizeof(struct rt_rq *), GFP_KERNEL);
> +	if (!tg->rt_rq)
> +		goto err;
> +	tg->dl_se = kcalloc(nr_cpu_ids, sizeof(dl_se), GFP_KERNEL);
> +	if (!tg->dl_se)
> +		goto err;

Don't we need to free the array allocated above if we fail here?

Thanks,
Juri