On Sat, Jun 22, 2024 at 03:50:21PM -1000, Tejun Heo wrote:
> For flexibility, sched_ext allows the BPF scheduler to select the CPU to
> execute a task on at dispatch time so that e.g. a queue can be shared across
> multiple CPUs. To enable this, the dispatch path is executed from balance()
> so that a dispatched task can be hot-migrated to its target CPU. This means
> that sched_ext needs its balance() method invoked before every
> pick_next_task() even when the CPU is waking up from SCHED_IDLE.
> 
> for_balance_class_range() defined in kernel/sched/ext.h implements this
> selective iteration promotion. However, the indirection obfuscates more than
> helps. Open code the iteration promotion in put_prev_task_balance() and
> remove for_balance_class_range().
> 
> No functional changes intended.
> 
> Signed-off-by: Tejun Heo <tj@kernel.org>
> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
> Cc: David Vernet <void@manifault.com>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Thomas Gleixner <tglx@linutronix.de>

Acked-by: David Vernet <void@manifault.com>

> ---
>  kernel/sched/core.c | 14 +++++++++++++-
>  kernel/sched/ext.h  |  9 ---------
>  2 files changed, 13 insertions(+), 10 deletions(-)
> 
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 1092955a7d6e..827e0dc78ea0 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -5834,7 +5834,19 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
>  				  struct rq_flags *rf)
>  {
>  #ifdef CONFIG_SMP
> +	const struct sched_class *start_class = prev->sched_class;
>  	const struct sched_class *class;
> +
> +#ifdef CONFIG_SCHED_CLASS_EXT
> +	/*
> +	 * SCX requires a balance() call before every pick_next_task() including
> +	 * when waking up from SCHED_IDLE. If @start_class is below SCX, start
> +	 * from SCX instead.
> +	 */
> +	if (sched_class_above(&ext_sched_class, start_class))
> +		start_class = &ext_sched_class;
> +#endif
> +
>  	/*
>  	 * We must do the balancing pass before put_prev_task(), such
>  	 * that when we release the rq->lock the task is in the same
> @@ -5843,7 +5855,7 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
>  	 * We can terminate the balance pass as soon as we know there is
>  	 * a runnable task of @class priority or higher.
>  	 */
> -	for_balance_class_range(class, prev->sched_class, &idle_sched_class) {
> +	for_active_class_range(class, start_class, &idle_sched_class) {
>  		if (class->balance(rq, prev, rf))
>  			break;
>  	}
> diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
> index 229007693504..1d7837bdfaba 100644
> --- a/kernel/sched/ext.h
> +++ b/kernel/sched/ext.h
> @@ -68,14 +68,6 @@ static inline const struct sched_class *next_active_class(const struct sched_cla
>  #define for_each_active_class(class)						\
>  	for_active_class_range(class, __sched_class_highest, __sched_class_lowest)
>  
> -/*
> - * SCX requires a balance() call before every pick_next_task() call including
> - * when waking up from idle.
> - */
> -#define for_balance_class_range(class, prev_class, end_class)			\
> -	for_active_class_range(class, (prev_class) > &ext_sched_class ?		\
> -			       &ext_sched_class : (prev_class), (end_class))
> -
>  #ifdef CONFIG_SCHED_CORE
>  bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
>  		   bool in_fi);
> @@ -100,7 +92,6 @@ static inline bool task_on_scx(const struct task_struct *p) { return false; }
>  static inline void init_sched_ext_class(void) {}
>  
>  #define for_each_active_class		for_each_class
> -#define for_balance_class_range		for_class_range
>  
>  #endif	/* CONFIG_SCHED_CLASS_EXT */
>  
> -- 
> 2.45.2
>