Introduce a new migration type, migrate_llc_task, to support
cache-aware load balancing.

After identifying the busiest sched_group (having the most tasks
preferring the destination LLC), mark migrations with this type.
During load balancing, each runqueue in the busiest sched_group is
examined, and the runqueue with the highest number of tasks preferring
the destination CPU is selected as the busiest runqueue.

Co-developed-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---

Notes:
    v3->v4:
       No change.

 kernel/sched/fair.c | 38 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c032eeebe191..e0e618cd4e15 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9768,7 +9768,8 @@ enum migration_type {
 	migrate_load = 0,
 	migrate_util,
 	migrate_task,
-	migrate_misfit
+	migrate_misfit,
+	migrate_llc_task
 };
 
 #define LBF_ALL_PINNED	0x01
@@ -10382,6 +10383,10 @@ static int detach_tasks(struct lb_env *env)
 
 			env->imbalance = 0;
 			break;
+
+		case migrate_llc_task:
+			env->imbalance--;
+			break;
 		}
 
 		detach_task(p, env);
@@ -12022,6 +12027,15 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		return;
 	}
 
+#ifdef CONFIG_SCHED_CACHE
+	if (busiest->group_type == group_llc_balance) {
+		/* Move a task that prefer local LLC */
+		env->migration_type = migrate_llc_task;
+		env->imbalance = 1;
+		return;
+	}
+#endif
+
 	if (busiest->group_type == group_imbalanced) {
 		/*
 		 * In the group_imb case we cannot rely on group-wide averages
@@ -12328,7 +12342,10 @@ static struct rq *sched_balance_find_src_rq(struct lb_env *env,
 {
 	struct rq *busiest = NULL, *rq;
 	unsigned long busiest_util = 0, busiest_load = 0, busiest_capacity = 1;
+	unsigned int __maybe_unused busiest_pref_llc = 0;
+	struct sched_domain __maybe_unused *sd_tmp;
 	unsigned int busiest_nr = 0;
+	int __maybe_unused dst_llc;
 	int i;
 
 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
@@ -12456,6 +12473,23 @@ static struct rq *sched_balance_find_src_rq(struct lb_env *env,
 
 			break;
 
+		case migrate_llc_task:
+#ifdef CONFIG_SCHED_CACHE
+			sd_tmp = rcu_dereference_all(rq->sd);
+			dst_llc = llc_id(env->dst_cpu);
+
+			if (valid_llc_buf(sd_tmp, dst_llc)) {
+				unsigned int this_pref_llc =
+					sd_tmp->llc_counts[dst_llc];
+
+				if (busiest_pref_llc < this_pref_llc) {
+					busiest_pref_llc = this_pref_llc;
+					busiest = rq;
+				}
+			}
+#endif
+			break;
+
 		}
 	}
 
@@ -12619,6 +12653,8 @@ static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd
 	case migrate_misfit:
 		__schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance);
 		break;
+	case migrate_llc_task:
+		break;
 	}
 }
 
-- 
2.32.0