[PATCH v2 21/23] -- DO NOT APPLY!!! -- sched/cache/stats: Add schedstat for cache aware load balancing

[Tim Chen <tim.c.chen@linux.intel.com>]

From: Chen Yu <yu.c.chen@intel.com>

Debug patch only.

With cache-aware load balancing enabled, statistics related to its activity
are exposed via /proc/schedstat and debugfs. For instance, if users want to
verify metrics like the number of exceeding RSS and nr_running limits, they
can filter the output of /sys/kernel/debug/sched/debug and compute the required
statistics manually:

llc_exceed_cap SUM: 6
llc_exceed_nr SUM: 4531

Furthermore, these statistics exposed in /proc/schedstats can be queried manually
or via perf sched stats[1] with minor modifications.

Link: https://lore.kernel.org/all/20250909114227.58802-1-swapnil.sapkal@amd.com #1

Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 include/linux/sched/topology.h | 1 +
 kernel/sched/fair.c            | 1 +
 kernel/sched/stats.c           | 5 +++--
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 0ba4697d74ba..8702c1e731a0 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -108,6 +108,7 @@ struct sched_domain {
 	unsigned int lb_imbalance_util[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_imbalance_task[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_imbalance_misfit[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_llc[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a2e2d6742481..742e455b093e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12684,6 +12684,7 @@ static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd
 		__schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance);
 		break;
 	case migrate_llc_task:
+		__schedstat_add(sd->lb_imbalance_llc[idle], env->imbalance);
 		break;
 	}
 }
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index d1c9429a4ac5..3736f6102261 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -104,7 +104,7 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
  * Bump this up when changing the output format or the meaning of an existing
  * format, so that tools can adapt (or abort)
  */
-#define SCHEDSTAT_VERSION 17
+#define SCHEDSTAT_VERSION 18
 
 static int show_schedstat(struct seq_file *seq, void *v)
 {
@@ -139,7 +139,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 			seq_printf(seq, "domain%d %s %*pb", dcount++, sd->name,
 				   cpumask_pr_args(sched_domain_span(sd)));
 			for (itype = 0; itype < CPU_MAX_IDLE_TYPES; itype++) {
-				seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u",
+				seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u %u",
 				    sd->lb_count[itype],
 				    sd->lb_balanced[itype],
 				    sd->lb_failed[itype],
@@ -147,6 +147,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 				    sd->lb_imbalance_util[itype],
 				    sd->lb_imbalance_task[itype],
 				    sd->lb_imbalance_misfit[itype],
+				    sd->lb_imbalance_llc[itype],
 				    sd->lb_gained[itype],
 				    sd->lb_hot_gained[itype],
 				    sd->lb_nobusyq[itype],
-- 
2.32.0