arm64 torture test hotplug failures (offlining causes -EBUSY)

[Frederic Weisbecker]

On Wed, Jan 18, 2023 at 10:37:08PM +0000, Joel Fernandes wrote:
> 
> That's a great idea. I found a way to do that without having to do the
> EXPORT_SYMBOL (like in Zhouyi's patch).
> 
> Would the following be acceptable (only build-tested)?
> 
> I can run more tests and submit a patch:
> 
> diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
> index 55405ebf23ab..f73bc520b70e 100644
> --- a/drivers/base/cpu.c
> +++ b/drivers/base/cpu.c
> @@ -487,7 +487,8 @@ static const struct attribute_group *cpu_root_attr_groups[] = {
>  bool cpu_is_hotpluggable(unsigned int cpu)
>  {
>  	struct device *dev = get_cpu_device(cpu);
> -	return dev && container_of(dev, struct cpu, dev)->hotpluggable;
> +	return dev && container_of(dev, struct cpu, dev)->hotpluggable
> +		&& !tick_nohz_cpu_hotpluggable(cpu);
>  }
>  EXPORT_SYMBOL_GPL(cpu_is_hotpluggable);
>  
> diff --git a/include/linux/tick.h b/include/linux/tick.h
> index bfd571f18cfd..9459fef5b857 100644
> --- a/include/linux/tick.h
> +++ b/include/linux/tick.h
> @@ -216,6 +216,7 @@ extern void tick_nohz_dep_set_signal(struct task_struct *tsk,
>  				     enum tick_dep_bits bit);
>  extern void tick_nohz_dep_clear_signal(struct signal_struct *signal,
>  				       enum tick_dep_bits bit);
> +extern bool tick_nohz_cpu_hotpluggable(unsigned int cpu);
>  
>  /*
>   * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases
> @@ -280,6 +281,7 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { }
>  
>  static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { }
>  static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { }
> +static inline bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { return true; }
>  
>  static inline void tick_dep_set(enum tick_dep_bits bit) { }
>  static inline void tick_dep_clear(enum tick_dep_bits bit) { }
> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> index 9c6f661fb436..d1cc7525240e 100644
> --- a/kernel/time/tick-sched.c
> +++ b/kernel/time/tick-sched.c
> @@ -522,6 +522,11 @@ static int tick_nohz_cpu_down(unsigned int cpu)
>  	return 0;
>  }
>  
> +bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
> +{
> +	return tick_nohz_cpu_down(cpu) == 0;
> +}
> +

Can you make it the opposite? Have tick_nohz_cpu_down() call
tick_nohz_cpu_hotpluggable()? To avoid future accidents.

Thanks.


>  void __init tick_nohz_init(void)
>  {
>  	int cpu, ret;
> -- 
> 2.39.0.246.g2a6d74b583-goog
>