[PATCH 04/19] sched/fair: Introduce a static key to enable cache aware only for multi LLCs

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

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

Enable cache-aware load balancing only if at least 1 NUMA node has
more than one LLC.

Suggested-by: Libo Chen <libo.chen@oracle.com>
Suggested-by: Adam Li <adamli@os.amperecomputing.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 kernel/sched/fair.c     | 15 ++++++++++++---
 kernel/sched/sched.h    |  1 +
 kernel/sched/topology.c | 14 ++++++++++++--
 3 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cd080468ddc9..3d643449c48c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1208,6 +1208,14 @@ static s64 update_se(struct rq *rq, struct sched_entity *se)
 __read_mostly unsigned int llc_overload_pct       = 50;
 __read_mostly unsigned int llc_imb_pct            = 20;
 
+DEFINE_STATIC_KEY_FALSE(sched_cache_allowed);
+
+static inline bool sched_cache_enabled(void)
+{
+	return sched_feat(SCHED_CACHE) &&
+		static_branch_likely(&sched_cache_allowed);
+}
+
 static int llc_id(int cpu)
 {
 	if (cpu < 0)
@@ -1294,7 +1302,7 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
 	struct mm_sched *pcpu_sched;
 	unsigned long epoch;
 
-	if (!sched_feat(SCHED_CACHE))
+	if (!sched_cache_enabled())
 		return;
 
 	if (p->sched_class != &fair_sched_class)
@@ -1330,7 +1338,7 @@ static void task_tick_cache(struct rq *rq, struct task_struct *p)
 	struct callback_head *work = &p->cache_work;
 	struct mm_struct *mm = p->mm;
 
-	if (!sched_feat(SCHED_CACHE))
+	if (!sched_cache_enabled())
 		return;
 
 	if (!mm || !mm->pcpu_sched)
@@ -10716,7 +10724,8 @@ static void record_sg_llc_stats(struct lb_env *env,
 	struct sched_domain *sd = env->sd->child;
 	struct sched_domain_shared *sd_share;
 
-	if (!sched_feat(SCHED_CACHE) || env->idle == CPU_NEWLY_IDLE)
+	if (!sched_cache_enabled() ||
+	    env->idle == CPU_NEWLY_IDLE)
 		return;
 
 	/* only care about sched domains spanning a LLC */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a52c96064b36..60f1e51685ec 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2800,6 +2800,7 @@ extern unsigned int sysctl_numa_balancing_hot_threshold;
 #ifdef CONFIG_SCHED_CACHE
 extern unsigned int llc_overload_pct;
 extern unsigned int llc_imb_pct;
+extern struct static_key_false sched_cache_allowed;
 #endif
 
 #ifdef CONFIG_SCHED_HRTICK
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 6e2f54169e66..2675db980f70 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2444,6 +2444,7 @@ static int
 build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr)
 {
 	enum s_alloc alloc_state = sa_none;
+	bool has_multi_llcs = false;
 	struct sched_domain *sd;
 	struct s_data d;
 	struct rq *rq = NULL;
@@ -2530,10 +2531,12 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 				 * between LLCs and memory channels.
 				 */
 				nr_llcs = sd->span_weight / child->span_weight;
-				if (nr_llcs == 1)
+				if (nr_llcs == 1) {
 					imb = sd->span_weight >> 3;
-				else
+				} else {
 					imb = nr_llcs;
+					has_multi_llcs = true;
+				}
 				imb = max(1U, imb);
 				sd->imb_numa_nr = imb;
 
@@ -2581,6 +2584,13 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	if (has_cluster)
 		static_branch_inc_cpuslocked(&sched_cluster_active);
 
+#ifdef CONFIG_SCHED_CACHE
+	if (has_multi_llcs) {
+		static_branch_enable_cpuslocked(&sched_cache_allowed);
+		pr_info("Cache aware load balance enabled.\n");
+	}
+#endif
+
 	if (rq && sched_debug_verbose)
 		pr_info("root domain span: %*pbl\n", cpumask_pr_args(cpu_map));
 
-- 
2.32.0