Re: [PATCH v4 11/24] x86/resctrl: Add cpumask_any_housekeeping() for limbo/overflow

[Reinette Chatre <reinette.chatre@intel.com>]

Hi James,

On 5/25/2023 11:01 AM, James Morse wrote:

...

> @@ -55,6 +56,28 @@
>  /* Max event bits supported */
>  #define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
>  
> +/**
> + * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
> + *			        aren't marked nohz_full
> + * @mask:	The mask to pick a CPU from.
> + *
> + * Returns a CPU in @mask. If there are housekeeping CPUs that don't use
> + * nohz_full, these are preferred.
> + */
> +static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask)
> +{
> +	int cpu, hk_cpu;

Should both of these be unsigned int?

> +
> +	cpu = cpumask_any(mask);
> +	if (tick_nohz_full_cpu(cpu)) {
> +		hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
> +		if (hk_cpu < nr_cpu_ids)
> +			cpu = hk_cpu;
> +	}
> +
> +	return cpu;
> +}
> +
>  struct rdt_fs_context {
>  	struct kernfs_fs_context	kfc;
>  	bool				enable_cdpl2;
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index 128d4c7206e4..e267869d60d5 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -770,9 +770,9 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
>  void cqm_handle_limbo(struct work_struct *work)
>  {
>  	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
> -	int cpu = smp_processor_id();
>  	struct rdt_resource *r;
>  	struct rdt_domain *d;
> +	int cpu;
>  
>  	mutex_lock(&rdtgroup_mutex);
>  
> @@ -781,8 +781,10 @@ void cqm_handle_limbo(struct work_struct *work)
>  
>  	__check_limbo(d, false);
>  
> -	if (has_busy_rmid(r, d))
> +	if (has_busy_rmid(r, d)) {
> +		cpu = cpumask_any_housekeeping(&d->cpu_mask);
>  		schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);

I expected cqm_work_cpu to also change when the worker moves to a different CPU.

> +	}
>  
>  	mutex_unlock(&rdtgroup_mutex);
>  }
> @@ -792,7 +794,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
>  	unsigned long delay = msecs_to_jiffies(delay_ms);
>  	int cpu;
>  
> -	cpu = cpumask_any(&dom->cpu_mask);
> +	cpu = cpumask_any_housekeeping(&dom->cpu_mask);
>  	dom->cqm_work_cpu = cpu;
>  
>  	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
> @@ -802,10 +804,10 @@ void mbm_handle_overflow(struct work_struct *work)
>  {
>  	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
>  	struct rdtgroup *prgrp, *crgrp;
> -	int cpu = smp_processor_id();
>  	struct list_head *head;
>  	struct rdt_resource *r;
>  	struct rdt_domain *d;
> +	int cpu;
>  
>  	mutex_lock(&rdtgroup_mutex);
>  
> @@ -826,6 +828,11 @@ void mbm_handle_overflow(struct work_struct *work)
>  			update_mba_bw(prgrp, d);
>  	}
>  
> +	/*
> +	 * Re-check for housekeeping CPUs. This allows the overflow handler to
> +	 * move off a nohz_full CPU quickly.
> +	 */
> +	cpu = cpumask_any_housekeeping(&d->cpu_mask);
>  	schedule_delayed_work_on(cpu, &d->mbm_over, delay);

Here I expected mbm_work_cpu to change if the worker moves to a different CPU. 

>  
>  out_unlock:
> @@ -839,7 +846,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
>  
>  	if (!static_branch_likely(&rdt_mon_enable_key))
>  		return;
> -	cpu = cpumask_any(&dom->cpu_mask);
> +	cpu = cpumask_any_housekeeping(&dom->cpu_mask);
>  	dom->mbm_work_cpu = cpu;
>  	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
>  }

Reinette