[PATCH 11/19] sched/fair: Identify busiest sched_group for LLC-aware load balancing

[Tim Chen]

The load balancer selects the busiest sched_group and migrates tasks
to less busy groups to distribute load across CPUs.

With cache-aware scheduling enabled, the busiest sched_group is
the one with most tasks preferring the destination LLC. If
the group has the llc_balance flag set, cache aware load balancing is
triggered.

Introduce the helper function update_llc_busiest() to identify the
sched_group with the most tasks preferring the destination LLC.

Co-developed-by: Chen Yu <yu.c.chen@xxxxxxxxx>
Signed-off-by: Chen Yu <yu.c.chen@xxxxxxxxx>
Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
---
 kernel/sched/fair.c | 39 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index af7b578eaa06..8469ec528cb1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10877,6 +10877,23 @@ static inline bool llc_balance(struct lb_env *env, struct sg_lb_stats *sgs,
 
 	return false;
 }
+
+static bool update_llc_busiest(struct lb_env *env,
+			       struct sg_lb_stats *busiest,
+			       struct sg_lb_stats *sgs)
+{
+	int idx;
+
+	/* Only the candidate with llc_balance needs to be taken care of */
+	if (!sgs->group_llc_balance)
+		return false;
+
+	/*
+	 * There are more tasks that want to run on dst_cpu's LLC.
+	 */
+	idx = llc_idx(env->dst_cpu);
+	return sgs->nr_pref_llc[idx] > busiest->nr_pref_llc[idx];
+}
 #else
 static inline void record_sg_llc_stats(struct lb_env *env, struct sg_lb_stats *sgs,
 				       struct sched_group *group)
@@ -10888,6 +10905,13 @@ static inline bool llc_balance(struct lb_env *env, struct sg_lb_stats *sgs,
 {
 	return false;
 }
+
+static bool update_llc_busiest(struct lb_env *env,
+			       struct sg_lb_stats *busiest,
+			       struct sg_lb_stats *sgs)
+{
+	return false;
+}
 #endif
 
 /**
@@ -11035,6 +11059,17 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	     sds->local_stat.group_type != group_has_spare))
 		return false;
 
+	/* deal with prefer LLC load balance, if failed, fall into normal load balance */
+	if (update_llc_busiest(env, busiest, sgs))
+		return true;
+
+	/*
+	 * If the busiest group has tasks with LLC preference,
+	 * skip normal load balance.
+	 */
+	if (busiest->group_llc_balance)
+		return false;
+
 	if (sgs->group_type > busiest->group_type)
 		return true;
 
@@ -11942,9 +11977,11 @@ static struct sched_group *sched_balance_find_src_group(struct lb_env *env)
 	/*
 	 * Try to move all excess tasks to a sibling domain of the busiest
 	 * group's child domain.
+	 * Also do so if we can move some tasks that prefer the local LLC.
 	 */
 	if (sds.prefer_sibling && local->group_type == group_has_spare &&
-	    sibling_imbalance(env, &sds, busiest, local) > 1)
+	    (busiest->group_llc_balance ||
+	    sibling_imbalance(env, &sds, busiest, local) > 1))
 		goto force_balance;
 
 	if (busiest->group_type != group_overloaded) {
-- 
2.32.0