[Patch v4 03/22] sched/cache: Record per LLC utilization to guide cache aware scheduling decisions

[Tim Chen]

From: Chen Yu <yu.c.chen@xxxxxxxxx>

When a system becomes busy and a process's preferred LLC is
saturated with too many threads, tasks within that LLC migrate
frequently. These in LLC migrations introduce latency and degrade
performance. To avoid this, task aggregation should be suppressed
when the preferred LLC is overloaded, which requires a metric to
indicate LLC utilization.

Record per LLC utilization/cpu capacity during periodic load
balancing. These statistics will be used in later patches to decide
whether tasks should be aggregated into their preferred LLC.

Signed-off-by: Chen Yu <yu.c.chen@xxxxxxxxx>
Co-developed-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
---

Notes:
    v3->v4:
       No change.

 include/linux/sched/topology.h |  4 ++
 kernel/sched/fair.c            | 70 ++++++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 45c0022b91ce..a4e2fb31f2fd 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -68,6 +68,10 @@ struct sched_domain_shared {
 	atomic_t	nr_busy_cpus;
 	int		has_idle_cores;
 	int		nr_idle_scan;
+#ifdef CONFIG_SCHED_CACHE
+	unsigned long	util_avg;
+	unsigned long	capacity;
+#endif
 };
 
 struct sched_domain {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 20a33900f4ea..f6692d9de017 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9789,6 +9789,28 @@ static inline int task_is_ineligible_on_dst_cpu(struct task_struct *p, int dest_
 	return 0;
 }
 
+#ifdef CONFIG_SCHED_CACHE
+static __maybe_unused bool get_llc_stats(int cpu, unsigned long *util,
+					 unsigned long *cap)
+{
+	struct sched_domain_shared *sd_share;
+
+	sd_share = rcu_dereference_all(per_cpu(sd_llc_shared, cpu));
+	if (!sd_share)
+		return false;
+
+	*util = READ_ONCE(sd_share->util_avg);
+	*cap = READ_ONCE(sd_share->capacity);
+
+	return true;
+}
+#else
+static inline bool get_llc_stats(int cpu, unsigned long *util,
+				 unsigned long *cap)
+{
+	return false;
+}
+#endif
 /*
  * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
  */
@@ -10763,6 +10785,53 @@ sched_reduced_capacity(struct rq *rq, struct sched_domain *sd)
 	return check_cpu_capacity(rq, sd);
 }
 
+#ifdef CONFIG_SCHED_CACHE
+/*
+ * Record the statistics for this scheduler group for later
+ * use. These values guide load balancing on aggregating tasks
+ * to a LLC.
+ */
+static void record_sg_llc_stats(struct lb_env *env,
+				struct sg_lb_stats *sgs,
+				struct sched_group *group)
+{
+	struct sched_domain_shared *sd_share;
+	int cpu;
+
+	if (!sched_cache_enabled() || env->idle == CPU_NEWLY_IDLE)
+		return;
+
+	/* Only care about sched domain spanning multiple LLCs */
+	if (env->sd->child != rcu_dereference_all(per_cpu(sd_llc, env->dst_cpu)))
+		return;
+
+	/*
+	 * At this point we know this group spans a LLC domain.
+	 * Record the statistic of this group in its corresponding
+	 * shared LLC domain.
+	 * Note: sd_share cannot be obtained via sd->child->shared,
+	 * because the latter refers to the domain that covers the
+	 * local group. Instead, sd_share should be located using
+	 * the first CPU of the LLC group.
+	 */
+	cpu = cpumask_first(sched_group_span(group));
+	sd_share = rcu_dereference_all(per_cpu(sd_llc_shared, cpu));
+	if (!sd_share)
+		return;
+
+	if (READ_ONCE(sd_share->util_avg) != sgs->group_util)
+		WRITE_ONCE(sd_share->util_avg, sgs->group_util);
+
+	if (unlikely(READ_ONCE(sd_share->capacity) != sgs->group_capacity))
+		WRITE_ONCE(sd_share->capacity, sgs->group_capacity);
+}
+#else
+static inline void record_sg_llc_stats(struct lb_env *env, struct sg_lb_stats *sgs,
+				       struct sched_group *group)
+{
+}
+#endif
+
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
  * @env: The load balancing environment.
@@ -10852,6 +10921,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 	sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs);
 
+	record_sg_llc_stats(env, sgs, group);
 	/* Computing avg_load makes sense only when group is overloaded */
 	if (sgs->group_type == group_overloaded)
 		sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) /
-- 
2.32.0