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

[Steve Sistare <steven.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 <steven.sistare@oracle.com>
---
 include/linux/sched/topology.h |  1 +
 kernel/sched/sched.h           |  2 ++
 kernel/sched/topology.c        | 21 +++++++++++++++++++--
 3 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 2634774..8bac15d 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 455fa33..aadfe68 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
@@ -805,6 +806,7 @@ 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 a2363f6..f18c416 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -3,6 +3,7 @@
  * Scheduler topology setup/handling methods
  */
 #include "sched.h"
+#include <linux/sparsemask.h>
 
 DEFINE_MUTEX(sched_domains_mutex);
 
@@ -440,6 +441,7 @@ static void update_top_cache_domain(int cpu)
 static void
 cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 {
+	struct sparsemask *cfs_overload_cpus;
 	struct rq *rq = cpu_rq(cpu);
 	struct sched_domain *tmp;
 
@@ -481,6 +483,10 @@ static void update_top_cache_domain(int cpu)
 	dirty_sched_domain_sysctl(cpu);
 	destroy_sched_domains(tmp);
 
+	sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
+	cfs_overload_cpus = (sd ? sd->shared->cfs_overload_cpus : NULL);
+	rcu_assign_pointer(rq->cfs_overload_cpus, cfs_overload_cpus);
+
 	update_top_cache_domain(cpu);
 }
 
@@ -1611,9 +1617,19 @@ static void __sdt_free(const struct cpumask *cpu_map)
 	}
 }
 
+#define ZALLOC_MASK(maskp, nelems, node)				  \
+	(!*(maskp) && !zalloc_sparsemask_node(maskp, nelems,		  \
+					      SPARSEMASK_DENSITY_DEFAULT, \
+					      GFP_KERNEL, node))	  \
+
 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));
+
+	if (ZALLOC_MASK(&sds->cfs_overload_cpus, nr_cpu_ids, nid))
+		return 1;
 
 	return 0;
 }
@@ -1625,7 +1641,8 @@ static void sd_llc_free(struct sched_domain *sd)
 	if (!sds)
 		return;
 
-	/* Free data here. Empty for now. */
+	free_sparsemask(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