[PATCH v4 03/10] sched/topology: Provide cfs_overload_cpus bitmap

[Steve Sistare]

From: Steve Sistare <steve.sistare@xxxxxxxxxx>

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 <steven.sistare@xxxxxxxxxx>
---
 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 6b99761..b173a77 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -72,6 +72,7 @@ struct sched_domain_shared {
 	atomic_t	ref;
 	atomic_t	nr_busy_cpus;
 	int		has_idle_cores;
+	struct sparsemask *cfs_overload_cpus;
 };
 
 struct sched_domain {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 618577f..eacf5db 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -81,6 +81,7 @@
 
 struct rq;
 struct cpuidle_state;
+struct sparsemask;
 
 /* task_struct::on_rq states: */
 #define TASK_ON_RQ_QUEUED	1
@@ -812,6 +813,7 @@ struct rq {
 	struct cfs_rq		cfs;
 	struct rt_rq		rt;
 	struct dl_rq		dl;
+	struct sparsemask	*cfs_overload_cpus;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this CPU: */
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 3e72ce0..89a78ce 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -3,6 +3,7 @@
  * Scheduler topology setup/handling methods
  */
 #include "sched.h"
+#include "sparsemask.h"
 
 DEFINE_MUTEX(sched_domains_mutex);
 
@@ -410,7 +411,9 @@ static void destroy_sched_domains(struct sched_domain *sd)
 
 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;
@@ -420,8 +423,10 @@ 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;
@@ -1621,7 +1626,22 @@ 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;
 }
@@ -1633,7 +1653,8 @@ 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)
-- 
1.8.3.1