From: Steve Sistare <steve.sistare@oracle.com>

Define and initialize a sparse bitmap of overloaded CPUs, per
last-level-cache scheduling domain, for use by the CFS scheduling class.
Save a pointer to cfs_overload_cpus in the rq for efficient access.

Signed-off-by: Steve Sistare <steve.sistare@oracle.com>
Signed-off-by: Chen Jinghuang <chenjinghuang2@huawei.com>
---
 include/linux/sched/topology.h |  1 +
 kernel/sched/sched.h           |  2 ++
 kernel/sched/topology.c        | 25 +++++++++++++++++++++++--
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 45c0022b91ce..472c3dcf5a34 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -67,6 +67,7 @@ struct sched_domain_shared {
 	atomic_t	ref;
 	atomic_t	nr_busy_cpus;
 	int		has_idle_cores;
+	struct sparsemask *cfs_overload_cpus;
 	int		nr_idle_scan;
 };
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b82fb70a9d54..4989a92eeb9b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -85,6 +85,7 @@ struct cfs_rq;
 struct rt_rq;
 struct sched_group;
 struct cpuidle_state;
+struct sparsemask;
 
 #if defined(CONFIG_PARAVIRT) && !defined(CONFIG_HAVE_PV_STEAL_CLOCK_GEN)
 # include <asm/paravirt.h>
@@ -1173,6 +1174,7 @@ struct rq {
 	struct cfs_rq		cfs;
 	struct rt_rq		rt;
 	struct dl_rq		dl;
+	struct sparsemask	*cfs_overload_cpus;
 #ifdef CONFIG_SCHED_CLASS_EXT
 	struct scx_rq		scx;
 	struct sched_dl_entity	ext_server;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index fac1b9155b6e..7bf1f68dac32 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -6,6 +6,7 @@
 #include <linux/sched/isolation.h>
 #include <linux/bsearch.h>
 #include "sched.h"
+#include "sparsemask.h"
 
 DEFINE_MUTEX(sched_domains_mutex);
 void sched_domains_mutex_lock(void)
@@ -683,7 +684,9 @@ DEFINE_STATIC_KEY_FALSE(sched_cluster_active);
 
 static void update_top_cache_domain(int cpu)
 {
+	struct sparsemask *cfs_overload_cpus = NULL;
 	struct sched_domain_shared *sds = NULL;
+	struct rq *rq = cpu_rq(cpu);
 	struct sched_domain *sd;
 	int id = cpu;
 	int size = 1;
@@ -693,8 +696,10 @@ static void update_top_cache_domain(int cpu)
 		id = cpumask_first(sched_domain_span(sd));
 		size = cpumask_weight(sched_domain_span(sd));
 		sds = sd->shared;
+		cfs_overload_cpus = sds->cfs_overload_cpus;
 	}
 
+	rcu_assign_pointer(rq->cfs_overload_cpus, cfs_overload_cpus);
 	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
 	per_cpu(sd_llc_size, cpu) = size;
 	per_cpu(sd_llc_id, cpu) = id;
@@ -2474,7 +2479,22 @@ static void __sdt_free(const struct cpumask *cpu_map)
 
 static int sd_llc_alloc(struct sched_domain *sd)
 {
-	/* Allocate sd->shared data here. Empty for now. */
+	struct sched_domain_shared *sds = sd->shared;
+	struct cpumask *span = sched_domain_span(sd);
+	int nid = cpu_to_node(cpumask_first(span));
+	int flags = __GFP_ZERO | GFP_KERNEL;
+	struct sparsemask *mask;
+
+	/*
+	 * Allocate the bitmap if not already allocated.  This is called for
+	 * every CPU in the LLC but only allocates once per sd_llc_shared.
+	 */
+	if (!sds->cfs_overload_cpus) {
+		mask = sparsemask_alloc_node(nr_cpu_ids, 3, flags, nid);
+		if (!mask)
+			return 1;
+		sds->cfs_overload_cpus = mask;
+	}
 
 	return 0;
 }
@@ -2486,7 +2506,8 @@ static void sd_llc_free(struct sched_domain *sd)
 	if (!sds)
 		return;
 
-	/* Free data here. Empty for now. */
+	sparsemask_free(sds->cfs_overload_cpus);
+	sds->cfs_overload_cpus = NULL;
 }
 
 static int sd_llc_alloc_all(const struct cpumask *cpu_map, struct s_data *d)
-- 
2.34.1