fs/resctrl: Move RMID initialization to first mount

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(). This is required because the limbo handler
keeps running after resctrl is unmounted and needs 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>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com

Author: aegl

fs/resctrl/internal.h

@@ -369,6 +369,10 @@ 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);

fs/resctrl/monitor.c

@@ -903,20 +903,29 @@ 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_limit;
 	u32 idx;
+	int i;
 
-	mutex_lock(&rdtgroup_mutex);
+	if (!resctrl_arch_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.
+	 */
+	if (rmid_ptrs)
+		return 0;
+
+	idx_limit = resctrl_arch_system_num_rmid_idx();
 	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];
@@ -929,30 +938,24 @@ 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;
+	if (!resctrl_arch_mon_capable())
+		return;
 
+	mutex_lock(&rdtgroup_mutex);
 	kfree(rmid_ptrs);
 	rmid_ptrs = NULL;
-
-out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
 }
 
@@ -1830,7 +1833,8 @@ static void closid_num_dirty_rmid_free(void)
  * 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
@@ -1850,12 +1854,6 @@ int resctrl_l3_mon_resource_init(void)
 	if (ret)
 		return ret;
 
-	ret = dom_data_init(r);
-	if (ret) {
-		closid_num_dirty_rmid_free();
-		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",
@@ -1902,6 +1900,4 @@ void resctrl_l3_mon_resource_exit(void)
 		return;
 
 	closid_num_dirty_rmid_free();
-
-	dom_data_exit(r);
 }

fs/resctrl/rdtgroup.c

@@ -2800,6 +2800,10 @@ static int rdt_get_tree(struct fs_context *fc)
 		goto out;
 	}
 
+	ret = setup_rmid_lru_list();
+	if (ret)
+		goto out;
+
 	ret = rdtgroup_setup_root(ctx);
 	if (ret)
 		goto out;
@@ -4655,4 +4659,5 @@ void resctrl_exit(void)
 	 */
 
 	resctrl_l3_mon_resource_exit();
+	free_rmid_lru_list();
 }