[PATCH v5 27/41] arm_mpam: resctrl: Add support for csu counters

[Ben Horgan]

From: James Morse <james.morse at arm.com>

resctrl exposes a counter via a file named llc_occupancy. This isn't really
a counter as its value goes up and down, this is a snapshot of the cache
storage usage monitor.

Add some picking code which will only find an L3. The resctrl counter
file is called llc_occupancy but we don't check it is the last one as
it is already identified as L3.

Tested-by: Shaopeng Tan <tan.shaopeng at jp.fujitsu.com>
Tested-by: Zeng Heng <zengheng4 at huawei.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng at jp.fujitsu.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron at huawei.com>
Signed-off-by: James Morse <james.morse at arm.com>
Co-developed-by: Dave Martin <dave.martin at arm.com>
Signed-off-by: Dave Martin <dave.martin at arm.com>
Signed-off-by: Ben Horgan <ben.horgan at arm.com>
---
Changes since rfc:
Allow csu counters however many partid or pmg there are
else if -> if
reduce scope of local variables
drop has_csu

Changes since v2:
return -> break so works for mbwu in later patch
add for_each_mpam_resctrl_mon
return error from mpam_resctrl_monitor_init(). It may fail when is abmc
allocation introduced in a later patch.
Squashed in patch from Dave Martin:
https://lore.kernel.org/lkml/20250820131621.54983-1-Dave.Martin@arm.com/

Changes since v3:
resctrl_enable_mon_event() signature update
Restrict the events considered
num-rmid update
Use raw_smp_processor_id()
Tighten heuristics:
 Make sure it is the L3
 Please shout if this means the counters aren't exposed on any platforms
Drop tags due to change in policy/rework

Changes since v4:
Move generic monitor boilerplate to separate patch
---
 drivers/resctrl/mpam_resctrl.c | 83 ++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)

diff --git a/drivers/resctrl/mpam_resctrl.c b/drivers/resctrl/mpam_resctrl.c
index c14e59e8586d..a570cdf06feb 100644
--- a/drivers/resctrl/mpam_resctrl.c
+++ b/drivers/resctrl/mpam_resctrl.c
@@ -289,6 +289,28 @@ static bool class_has_usable_mba(struct mpam_props *cprops)
 	return mba_class_use_mbw_max(cprops);
 }
 
+static bool cache_has_usable_csu(struct mpam_class *class)
+{
+	struct mpam_props *cprops;
+
+	if (!class)
+		return false;
+
+	cprops = &class->props;
+
+	if (!mpam_has_feature(mpam_feat_msmon_csu, cprops))
+		return false;
+
+	/*
+	 * CSU counters settle on the value, so we can get away with
+	 * having only one.
+	 */
+	if (!cprops->num_csu_mon)
+		return false;
+
+	return true;
+}
+
 /*
  * Calculate the worst-case percentage change from each implemented step
  * in the control.
@@ -602,6 +624,64 @@ static void mpam_resctrl_pick_mba(void)
 	}
 }
 
+static void counter_update_class(enum resctrl_event_id evt_id,
+				 struct mpam_class *class)
+{
+	struct mpam_class *existing_class = mpam_resctrl_counters[evt_id].class;
+
+	if (existing_class) {
+		if (class->level == 3) {
+			pr_debug("Existing class is L3 - L3 wins\n");
+			return;
+		}
+
+		if (existing_class->level < class->level) {
+			pr_debug("Existing class is closer to L3, %u versus %u - closer is better\n",
+				 existing_class->level, class->level);
+			return;
+		}
+	}
+
+	mpam_resctrl_counters[evt_id].class = class;
+}
+
+static void mpam_resctrl_pick_counters(void)
+{
+	struct mpam_class *class;
+
+	lockdep_assert_cpus_held();
+
+	guard(srcu)(&mpam_srcu);
+	list_for_each_entry_srcu(class, &mpam_classes, classes_list,
+				 srcu_read_lock_held(&mpam_srcu)) {
+		/* The name of the resource is L3... */
+		if (class->type == MPAM_CLASS_CACHE && class->level != 3) {
+			pr_debug("class %u is a cache but not the L3", class->level);
+			continue;
+		}
+
+		if (!cpumask_equal(&class->affinity, cpu_possible_mask)) {
+			pr_debug("class %u does not cover all CPUs",
+				 class->level);
+			continue;
+		}
+
+		if (cache_has_usable_csu(class)) {
+			pr_debug("class %u has usable CSU",
+				 class->level);
+
+			/* CSU counters only make sense on a cache. */
+			switch (class->type) {
+			case MPAM_CLASS_CACHE:
+				counter_update_class(QOS_L3_OCCUP_EVENT_ID, class);
+				break;
+			default:
+				break;
+			}
+		}
+	}
+}
+
 static int mpam_resctrl_control_init(struct mpam_resctrl_res *res)
 {
 	struct mpam_class *class = res->class;
@@ -1157,6 +1237,9 @@ int mpam_resctrl_setup(void)
 		}
 	}
 
+	/* Find some classes to use for monitors */
+	mpam_resctrl_pick_counters();
+
 	for_each_mpam_resctrl_mon(mon, eventid) {
 		if (!mon->class)
 			continue;	// dummy resource
-- 
2.43.0