x86/resctrl: Track the number of dirty RMID a CLOSID has

MPAM's PMG bits extend its PARTID space, meaning the same PMG value can be
used for different control groups.

This means once a CLOSID is allocated, all its monitoring ids may still be
dirty, and held in limbo.

Keep track of the number of RMID held in limbo each CLOSID has. This will
allow a future helper to find the 'cleanest' CLOSID when allocating.

The array is only needed when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is
defined. This will never be the case on x86.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Link: https://lore.kernel.org/r/20240213184438.16675-9-james.morse@arm.com
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>

Author: James Morse

arch/x86/kernel/cpu/resctrl/monitor.c

@@ -50,6 +50,13 @@ struct rmid_entry {
  */
 static LIST_HEAD(rmid_free_lru);
 
+/*
+ * @closid_num_dirty_rmid    The number of dirty RMID each CLOSID has.
+ *     Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined.
+ *     Indexed by CLOSID. Protected by rdtgroup_mutex.
+ */
+static u32 *closid_num_dirty_rmid;
+
 /*
  * @rmid_limbo_count - count of currently unused but (potentially)
  *     dirty RMIDs.
@@ -292,6 +299,17 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	return 0;
 }
 
+static void limbo_release_entry(struct rmid_entry *entry)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	rmid_limbo_count--;
+	list_add_tail(&entry->list, &rmid_free_lru);
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		closid_num_dirty_rmid[entry->closid]--;
+}
+
 /*
  * Check the RMIDs that are marked as busy for this domain. If the
  * reported LLC occupancy is below the threshold clear the busy bit and
@@ -328,10 +346,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 
 		if (force_free || !rmid_dirty) {
 			clear_bit(idx, d->rmid_busy_llc);
-			if (!--entry->busy) {
-				rmid_limbo_count--;
-				list_add_tail(&entry->list, &rmid_free_lru);
-			}
+			if (!--entry->busy)
+				limbo_release_entry(entry);
 		}
 		cur_idx = idx + 1;
 	}
@@ -398,6 +414,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 	u64 val = 0;
 	u32 idx;
 
+	lockdep_assert_held(&rdtgroup_mutex);
+
 	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
 
 	entry->busy = 0;
@@ -423,10 +441,13 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 	}
 	put_cpu();
 
-	if (entry->busy)
+	if (entry->busy) {
 		rmid_limbo_count++;
-	else
+		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+			closid_num_dirty_rmid[entry->closid]++;
+	} else {
 		list_add_tail(&entry->list, &rmid_free_lru);
+	}
 }
 
 void free_rmid(u32 closid, u32 rmid)
@@ -770,13 +791,39 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
 static int dom_data_init(struct rdt_resource *r)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+	u32 num_closid = resctrl_arch_get_num_closid(r);
 	struct rmid_entry *entry = NULL;
+	int err = 0, i;
 	u32 idx;
-	int i;
+
+	mutex_lock(&rdtgroup_mutex);
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		u32 *tmp;
+
+		/*
+		 * If the architecture hasn't provided a sanitised value here,
+		 * this may result in larger arrays than necessary. Resctrl will
+		 * use a smaller system wide value based on the resources in
+		 * use.
+		 */
+		tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL);
+		if (!tmp) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
+
+		closid_num_dirty_rmid = tmp;
+	}
 
 	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
-	if (!rmid_ptrs)
-		return -ENOMEM;
+	if (!rmid_ptrs) {
+		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+			kfree(closid_num_dirty_rmid);
+			closid_num_dirty_rmid = NULL;
+		}
+		err = -ENOMEM;
+		goto out_unlock;
+	}
 
 	for (i = 0; i < idx_limit; i++) {
 		entry = &rmid_ptrs[i];
@@ -796,13 +843,21 @@ static int dom_data_init(struct rdt_resource *r)
 	entry = __rmid_entry(idx);
 	list_del(&entry->list);
 
-	return 0;
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return err;
 }
 
 static void __exit dom_data_exit(void)
 {
 	mutex_lock(&rdtgroup_mutex);
 
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		kfree(closid_num_dirty_rmid);
+		closid_num_dirty_rmid = NULL;
+	}
+
 	kfree(rmid_ptrs);
 	rmid_ptrs = NULL;