Re: [PATCH v12 14/25] fs/resctrl: Rebuild free RMID list on each mount

[Babu Moger <babu.moger@amd.com>]

Hi Tony,

On 9/16/26 18:13, Tony Luck wrote:
> Application Energy Telemetry (AET) event enumeration takes place
> asynchronously. Linux builds the pmt_telemetry module into the kernel to
> kick off enumeration early enough that it completes before first mount of
> the resctrl file system.
> 
> Allowing pmt_telemetry to be a loadable module means that it is possible
> for different numbers of RMIDs to be supported on each mount, depending
> on whether pmt_telemetry module is loaded.
> 
> Initialize rmid_free_lru based on the number of RMIDs available for the
> current mount cycle.
> 
> Signed-off-by: Tony Luck <tony.luck@intel.com>
> ---
> v12:
> 	New patch. Split from patch 12.
> ---
>   fs/resctrl/monitor.c | 64 +++++++++++++++++++++++++++++---------------
>   1 file changed, 42 insertions(+), 22 deletions(-)
> 
> diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
> index b8bd59c52c62..8dde2b81b72f 100644
> --- a/fs/resctrl/monitor.c
> +++ b/fs/resctrl/monitor.c
> @@ -75,6 +75,11 @@ static unsigned int rmid_limbo_count;
>    */
>   static struct rmid_entry	*rmid_ptrs;
>   
> +/*
> + * @num_rmid_ptrs - The number of elements in rmid_ptrs[].
> + */
> +static u32 num_rmid_ptrs;
> +
>   /*
>    * This is the threshold cache occupancy in bytes at which we will consider an
>    * RMID available for re-allocation.
> @@ -975,45 +980,60 @@ void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long del
>   
>   int setup_rmid_lru_list(void)
>   {
> -	struct rmid_entry *entry = NULL;
> -	u32 idx_limit;
> -	u32 idx;
> +	struct rmid_entry *entry;
> +	u32 cur_idx_limit;
> +	u32 rsvd_idx;
>   	int i;
>   
>   	if (!resctrl_mon_capable())
>   		return 0;
>   
>   	/*
> -	 * Called on every mount, but the number of RMIDs cannot change
> -	 * after the first mount, so keep using the same set of rmid_ptrs[]
> -	 * until resctrl_exit(). Note that the limbo handler continues to
> -	 * access rmid_ptrs[] after resctrl is unmounted.
> +	 * Allocate the largest number of RMIDs that this system will ever
> +	 * need. These cannot be freed until resctrl_exit() because the limbo
> +	 * handler continues to access rmid_ptrs[] after resctrl is unmounted.
>   	 */
> -	if (rmid_ptrs)
> -		return 0;
> +	if (!rmid_ptrs) {
> +		num_rmid_ptrs = resctrl_arch_system_max_rmid_idx();
> +		rmid_ptrs = kzalloc_objs(struct rmid_entry, num_rmid_ptrs);
> +		if (!rmid_ptrs) {
> +			num_rmid_ptrs = 0;
> +			return -ENOMEM;
> +		}
>   
> -	idx_limit = resctrl_arch_system_max_rmid_idx();
> -	rmid_ptrs = kzalloc_objs(struct rmid_entry, idx_limit);
> -	if (!rmid_ptrs)
> -		return -ENOMEM;
> +		for (i = 0; i < num_rmid_ptrs; i++) {
> +			entry = &rmid_ptrs[i];
> +			INIT_LIST_HEAD(&entry->list);
>   
> -	for (i = 0; i < idx_limit; i++) {
> -		entry = &rmid_ptrs[i];
> -		INIT_LIST_HEAD(&entry->list);
> +			resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid);
> +		}
> +	}
>   
> -		resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid);
> -		list_add_tail(&entry->list, &rmid_free_lru);
> +	/* Find how many RMIDs are available for this mount */
> +	cur_idx_limit = resctrl_arch_system_num_rmid_idx();
> +	if (cur_idx_limit > num_rmid_ptrs) {
> +		pr_warn_once("RMID count %u exceeds allocated %u; capping\n",
> +			     cur_idx_limit, num_rmid_ptrs);
> +		cur_idx_limit = num_rmid_ptrs;
>   	}
>   
> +	INIT_LIST_HEAD(&rmid_free_lru);

It is possible the list is not empty at this point with difference in 
numbers from one mount to another?  Should you check if the list is 
empty and clean it up?

Thanks
Babu