Re: [PATCH v5 06/24] x86/resctrl: Track the number of dirty RMID a CLOSID has

[Reinette Chatre]

Hi James,

On 7/28/2023 9:42 AM, James Morse wrote:
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index de91ca781d9f..44addc0126fc 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -43,6 +43,13 @@ struct rmid_entry {
>   */
>  static LIST_HEAD(rmid_free_lru);
>  
> +/**
> + * @closid_num_dirty_rmid    The number of dirty RMID each CLOSID has.
> + * Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined.
> + * Indexed by CLOSID. Protected by rdtgroup_mutex.
> + */
> +static int *closid_num_dirty_rmid;
> +

Will the values ever be negative?

>  /**
>   * @rmid_limbo_count     count of currently unused but (potentially)
>   *     dirty RMIDs.
> @@ -285,6 +292,17 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
>  	return 0;
>  }
>  
> +static void limbo_release_entry(struct rmid_entry *entry)
> +{
> +	lockdep_assert_held(&rdtgroup_mutex);
> +
> +	rmid_limbo_count--;
> +	list_add_tail(&entry->list, &rmid_free_lru);
> +
> +	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
> +		closid_num_dirty_rmid[entry->closid]--;
> +}
> +
>  /*
>   * Check the RMIDs that are marked as busy for this domain. If the
>   * reported LLC occupancy is below the threshold clear the busy bit and
> @@ -321,10 +339,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
>  
>  		if (force_free || !rmid_dirty) {
>  			clear_bit(idx, d->rmid_busy_llc);
> -			if (!--entry->busy) {
> -				rmid_limbo_count--;
> -				list_add_tail(&entry->list, &rmid_free_lru);
> -			}
> +			if (!--entry->busy)
> +				limbo_release_entry(entry);
>  		}
>  		cur_idx = idx + 1;
>  	}
> @@ -391,6 +407,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
>  	u64 val = 0;
>  	u32 idx;
>  
> +	lockdep_assert_held(&rdtgroup_mutex);
> +
>  	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
>  
>  	entry->busy = 0;
> @@ -416,9 +434,11 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
>  	}
>  	put_cpu();
>  
> -	if (entry->busy)
> +	if (entry->busy) {
>  		rmid_limbo_count++;
> -	else
> +		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
> +			closid_num_dirty_rmid[entry->closid]++;
> +	} else
>  		list_add_tail(&entry->list, &rmid_free_lru);
>  }

This new addition breaks the coding style with the last statement
now also needing a brace.

>  
> @@ -782,13 +802,28 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
>  static int dom_data_init(struct rdt_resource *r)
>  {
>  	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
> +	u32 num_closid = resctrl_arch_get_num_closid(r);
>  	struct rmid_entry *entry = NULL;
>  	u32 idx;
>  	int i;
>  
> +	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
> +		int *tmp;
> +
> +		tmp = kcalloc(num_closid, sizeof(int), GFP_KERNEL);
> +		if (!tmp)
> +			return -ENOMEM;
> +
> +		mutex_lock(&rdtgroup_mutex);
> +		closid_num_dirty_rmid = tmp;
> +		mutex_unlock(&rdtgroup_mutex);
> +	}
> +

It does no harm but I cannot see why the mutex is needed here. 

>  	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
> -	if (!rmid_ptrs)
> +	if (!rmid_ptrs) {
> +		kfree(closid_num_dirty_rmid);
>  		return -ENOMEM;
> +	}
>  
>  	for (i = 0; i < idx_limit; i++) {
>  		entry = &rmid_ptrs[i];

How will this new memory be freed? Actually I cannot find where
rmid_ptrs is freed either .... is a "dom_data_free()" needed?

Reinette