Hi Tony,
On 8/29/25 12:33 PM, Tony Luck wrote:
> 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 first resctrl mount and
> may support a different number of RMIDs compared to L3 monitor features.
>
> Delay allocation and initialization of rmid_ptrs[] until first mount.
> Since the number of RMIDs cannot change on later mounts, keep the same
> set of rmid_ptrs[] until resctrl_exit().
Another strong reason is that the limbo handler keeps running after resctrl is
unmounted and may likely need to access rmid_ptrs[] as it keeps tracking
busy RMIDs after unmount.
>
> 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>
> ---
> fs/resctrl/internal.h | 4 ++++
> fs/resctrl/monitor.c | 50 ++++++++++++++-----------------------------
> fs/resctrl/rdtgroup.c | 7 ++++++
> 3 files changed, 27 insertions(+), 34 deletions(-)
>
> diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
> index 7c37142df1cc..6dde28d9cfac 100644
> --- a/fs/resctrl/internal.h
> +++ b/fs/resctrl/internal.h
> @@ -357,6 +357,10 @@ int closids_supported(void);
>
> void closid_free(int closid);
>
> +int setup_rmid_lru_list(void);
> +
> +void free_rmid_lru_list(void);
> +
> int alloc_rmid(u32 closid);
>
> void free_rmid(u32 closid, u32 rmid);
> diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
> index d5b96aca5d03..636342fad5a4 100644
> --- a/fs/resctrl/monitor.c
> +++ b/fs/resctrl/monitor.c
> @@ -802,20 +802,24 @@ 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);
> + /*
> + * 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().
> + */
> + 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];
> @@ -828,30 +832,21 @@ 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;
> }
>
> -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;
> -
Can use resctrl_arch_mon_capable() instead to keep this check while maintaining
symmetry with setup_rmid_lru_list() that will make this easier to follow?
Having the resctrl_arch_mon_capable() check within setup_rmid_lru_list() will
also help.
> kfree(rmid_ptrs);
> rmid_ptrs = NULL;
> -
> -out_unlock:
> mutex_unlock(&rdtgroup_mutex);
> }
>
> @@ -914,7 +909,8 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid)
> * resctrl_l3_mon_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 +921,6 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid)
> int resctrl_l3_mon_resource_init(void)
> {
> struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
> - int ret;
>
> if (!r->mon_capable)
> return 0;
> @@ -947,15 +942,6 @@ int resctrl_l3_mon_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 +963,8 @@ int resctrl_l3_mon_resource_init(void)
>
> void resctrl_l3_mon_resource_exit(void)
> {
> - struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
> -
As mentioned earlier, please try to maintain symmetry with resctrl_l3_mon_resource_init().
> 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 3201e9cad8da..886de0e01e8a 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;
> + }
As mentioned earlier, please try to make code symmetrical to make this
easier to understand. As this is written the reader sees that
setup_rmid_lru_list() needs to be protected by resctrl_arch_mon_capable()
while free_rmid_lru_list() can always be called whether system is
monitoring capable or not. This creates confusion that symmetrical code
can help with.
> +
> ret = rdtgroup_setup_root(ctx);
> if (ret)
> goto out;
> @@ -4408,4 +4414,5 @@ void resctrl_exit(void)
> */
>
> resctrl_l3_mon_resource_exit();
> + free_rmid_lru_list();
> }
Reinette