Re: [PATCH v8 28/32] fs/resctrl: Move RMID initialization to first mount

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

Hi Tony,

On 8/11/25 11:17 AM, Tony Luck wrote:
> resctrl assumesthat the number of supported RMIDs is enumerated during

"assumesthat" -> "assumes that"

> early initialization.

The context can be made a more specific though. For example, 
	L3 monitor features are enumerated during resctrl initialization
	and rmid_ptrs[] that tracks all RMIDs and depends on the
	number of supported RMIDs is allocated during this time.

	Telemetry monitor features are enumerated during resctrl mount and may
	support a different number of RMIDs compared to L3 monitor features.

> 
> Telemetry monitor events break that assumption because they are not
> enumerated in early initialization and may support a different number
> of RMIDs compared to L3 monitor features.
> 
> Delay allocation and initialization of rmid_ptrs[] until first mount.
> 
> Rename routines to match what they now do:
> dom_data_init() -> setup_rmid_lru_list()
> dom_data_exit() -> free_rmid_lru_list()
> 
> Signed-off-by: Tony Luck <tony.luck@intel.com>
> ---

...

> diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
> index 0d9c8d4e0e9c..4c13b55db995 100644
> --- a/fs/resctrl/monitor.c
> +++ b/fs/resctrl/monitor.c
> @@ -802,20 +802,19 @@ void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long del
>  		schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
>  }
>  
> -static int dom_data_init(struct rdt_resource *r)
> +int setup_rmid_lru_list(void)
>  {
>  	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
>  	struct rmid_entry *entry = NULL;
> -	int err = 0, i;
>  	u32 idx;
> +	int i;
>  
> -	mutex_lock(&rdtgroup_mutex);
> +	if (rmid_ptrs)
> +		return 0;
>  
>  	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
> -	if (!rmid_ptrs) {
> -		err = -ENOMEM;
> -		goto out_unlock;
> -	}
> +	if (!rmid_ptrs)
> +		return -ENOMEM;
>  
>  	for (i = 0; i < idx_limit; i++) {
>  		entry = &rmid_ptrs[i];
> @@ -828,31 +827,20 @@ static int dom_data_init(struct rdt_resource *r)
>  	/*
>  	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
>  	 * are always allocated. These are used for the rdtgroup_default
> -	 * control group, which will be setup later in resctrl_init().
> +	 * control group, which was setup earlier in rdtgroup_setup_default().
>  	 */
>  	idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
>  					   RESCTRL_RESERVED_RMID);
>  	entry = __rmid_entry(idx);
>  	list_del(&entry->list);
>  
> -out_unlock:
> -	mutex_unlock(&rdtgroup_mutex);
> -
> -	return err;
> +	return 0;
>  }
>  

Removing the mutex lock/unlock from setup_rmid_lru_list() is correct since
setup_rmid_lru_list() is called with mutex held.
free_rmid_lru_list() is not called with mutex held so it is not clear why
it is ok to remove mutex lock/unlock below?

> -static void dom_data_exit(struct rdt_resource *r)
> +void free_rmid_lru_list(void)
>  {
> -	mutex_lock(&rdtgroup_mutex);
> -
> -	if (!r->mon_capable)
> -		goto out_unlock;
> -
>  	kfree(rmid_ptrs);
>  	rmid_ptrs = NULL;
> -
> -out_unlock:
> -	mutex_unlock(&rdtgroup_mutex);
>  }
>  
>  #define MON_EVENT(_eventid, _name, _res, _fp)	\
> @@ -914,7 +902,8 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid)
>   * resctrl_mon_l3_resource_init() - Initialise global monitoring structures.
>   *
>   * Allocate and initialise global monitor resources that do not belong to a
> - * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists.
> + * specific domain. i.e. the closid_num_dirty_rmid[] used to find the CLOSID
> + * with the cleanest set of RMIDs.
>   * Called once during boot after the struct rdt_resource's have been configured
>   * but before the filesystem is mounted.
>   * Resctrl's cpuhp callbacks may be called before this point to bring a domain
> @@ -925,7 +914,6 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid)
>  int resctrl_mon_l3_resource_init(void)
>  {
>  	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
> -	int ret;
>  
>  	if (!r->mon_capable)
>  		return 0;
> @@ -947,15 +935,6 @@ int resctrl_mon_l3_resource_init(void)
>  		closid_num_dirty_rmid = tmp;
>  	}
>  
> -	ret = dom_data_init(r);
> -	if (ret) {
> -		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
> -			kfree(closid_num_dirty_rmid);
> -			closid_num_dirty_rmid = NULL;
> -		}
> -		return ret;
> -	}
> -
>  	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
>  		mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].configurable = true;
>  		resctrl_file_fflags_init("mbm_total_bytes_config",
> @@ -977,12 +956,8 @@ int resctrl_mon_l3_resource_init(void)
>  
>  void resctrl_mon_l3_resource_exit(void)
>  {
> -	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
> -
>  	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
>  		kfree(closid_num_dirty_rmid);
>  		closid_num_dirty_rmid = NULL;
>  	}
> -
> -	dom_data_exit(r);
>  }
> diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
> index 5352480eb55c..d1ecc5cd3089 100644
> --- a/fs/resctrl/rdtgroup.c
> +++ b/fs/resctrl/rdtgroup.c
> @@ -2599,6 +2599,12 @@ static int rdt_get_tree(struct fs_context *fc)
>  		goto out;
>  	}
>  
> +	if (resctrl_arch_mon_capable()) {
> +		ret = setup_rmid_lru_list();
> +		if (ret)
> +			goto out;
> +	}
> +
>  	ret = rdtgroup_setup_root(ctx);
>  	if (ret)
>  		goto out;

Shouldn't this be cleaned up on failure? I expected to see free_rmid_lru_list()
in rdt_get_tree()'s failure paths.

> @@ -4408,4 +4414,5 @@ void resctrl_exit(void)
>  	 */
>  
>  	resctrl_mon_l3_resource_exit();
> +	free_rmid_lru_list();
>  }

Reinette