Re: [PATCH v19 12/20] x86/resctrl: Create Sub-NUMA Cluster (SNC) monitor files

[Reinette Chatre]

Hi Tony,

On 5/28/24 3:19 PM, Tony Luck wrote:
> When SNC mode is enabled, create subdirectories and files to monitor
> at the SNC node granularity. Monitor files at the L3 granularity are
> tagged with a "sum" attribute to indicate that all SNC nodes sharing
> an L3 cache should be read and summed to provide the result to the
> user.

What does "all SNC nodes sharing an L3 cache should be read and summed" mean?

> Note that the "domid" field for files that must sum across SNC domains
> has the L3 cache instance id, while non-summing files use the domain id.
>
> Also the "sum" files do not need to make a call to mon_event_read() to

Drop "Also" - it is a red flag that a new patch is needed.

> initialize the MBM counters. This will be handled by initializing the
> individual SNC nodes that share the L3.
>
> Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
> ---
>   arch/x86/kernel/cpu/resctrl/rdtgroup.c | 53 ++++++++++++++++++--------
>   1 file changed, 38 insertions(+), 15 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> index dd386ad9458a..6a5c35a176d5 100644
> --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> @@ -3026,7 +3026,8 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
>   }
>   
>   static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
> -			     struct rdt_resource *r, struct rdtgroup *prgrp)
> +			     struct rdt_resource *r, struct rdtgroup *prgrp,
> +			     bool do_sum)
>   {
>   	union mon_data_bits priv;
>   	struct mon_evt *mevt;
> @@ -3037,15 +3038,18 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
>   		return -EPERM;
>   
>   	priv.u.rid = r->rid;
> -	priv.u.domid = d->hdr.id;
> +	priv.u.domid = do_sum ? d->ci->id : d->hdr.id;
> +	priv.u.sum = do_sum;
>   	list_for_each_entry(mevt, &r->evt_list, list) {
>   		priv.u.evtid = mevt->evtid;
>   		ret = mon_addfile(kn, mevt->name, priv.priv);
>   		if (ret)
>   			return ret;
>   
> -		if (is_mbm_event(mevt->evtid))
> +		if (!do_sum && is_mbm_event(mevt->evtid)) {
> +			rr.sumdomains = 0;
>   			mon_event_read(&rr, r, d, prgrp, mevt->evtid, true);
> +		}
>   	}
>   
>   	return 0;
> @@ -3055,23 +3059,42 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
>   				struct rdt_mon_domain *d,
>   				struct rdt_resource *r, struct rdtgroup *prgrp)
>   {
> -	struct kernfs_node *kn;
> +	struct kernfs_node *kn, *ckn;
>   	char name[32];
> +	bool snc_mode;
>   	int ret;
>   
> -	sprintf(name, "mon_%s_%02d", r->name, d->hdr.id);
> -	/* create the directory */
> -	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
> -	if (IS_ERR(kn))
> -		return PTR_ERR(kn);
> +	snc_mode = r->mon_scope != RESCTRL_L3_CACHE;
> +	sprintf(name, "mon_%s_%02d", r->name, d->ci->id);
> +	kn = kernfs_find_and_get_ns(parent_kn, name, NULL);

This new kernfs_find_and_get_ns() call takes a reference on the
kernfs_node before it is returned. Where is that new reference
released or why is it ok not to release the reference?

> +	if (!kn) {
> +		/* create the directory */

At this point this comment is not useful.

> +		kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
> +		if (IS_ERR(kn))
> +			return PTR_ERR(kn);
>   
> -	ret = rdtgroup_kn_set_ugid(kn);
> -	if (ret)
> -		goto out_destroy;
> +		ret = rdtgroup_kn_set_ugid(kn);
> +		if (ret)
> +			goto out_destroy;
> +		ret = mon_add_all_files(kn, d, r, prgrp, snc_mode);
> +		if (ret)
> +			goto out_destroy;
> +	}
>   
> -	ret = mon_add_all_files(kn, d, r, prgrp);
> -	if (ret)
> -		goto out_destroy;
> +	if (snc_mode) {
> +		sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id);
> +		ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp);
> +		if (IS_ERR(ckn))
> +			goto out_destroy;
> +
> +		ret = rdtgroup_kn_set_ugid(ckn);
> +		if (ret)
> +			goto out_destroy;
> +
> +		ret = mon_add_all_files(ckn, d, r, prgrp, false);
> +		if (ret)
> +			goto out_destroy;
> +	}
>   
>   	kernfs_activate(kn);
>   	return 0;

Reinette