[PATCH 4/4] sched/topology: the group balance cpu must be a cpu where the group is installed

[Lauro Ramos Venancio]

An overlap sched group may not be installed in all cpus that compose the
group. Currently, the group balance cpu may be a cpu where the group is
not installed, causing two problems:

1) Two groups may have the same group balance cpu and, as consequence,
share the sched_group_capacity.
2) should_we_balance() in fair.c may never return true.

This patch changes the group mask meaning to mark all the cpus where a
group is installed.

Signed-off-by: Lauro Ramos Venancio <lvenanci@xxxxxxxxxx>
---
 kernel/sched/topology.c | 40 ++++++++++++++++++++++++++++++++++------
 1 file changed, 34 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index e77c93a..694e799 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -493,8 +493,10 @@ enum s_alloc {
 };
 
 /*
- * Build an iteration mask that can exclude certain CPUs from the upwards
- * domain traversal.
+ * An overlap sched group may not be installed in all CPUs that compose the
+ * group. So build the mask, marking all the CPUs where the group is installed.
+ *
+ * This function can only be used when all the groups are already built.
  */
 static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
 {
@@ -505,7 +507,11 @@ static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
 
 	for_each_cpu(i, sg_span) {
 		sibling = *per_cpu_ptr(sdd->sd, i);
-		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+		if (!sibling->groups)
+			continue;
+
+		if (!cpumask_equal(sg_span, sched_group_cpus(sibling->groups)))
 			continue;
 
 		cpumask_set_cpu(i, sched_group_mask(sg));
@@ -523,6 +529,7 @@ int group_balance_cpu(struct sched_group *sg)
 
 /*
  * Find the group balance cpu when the group mask is not available yet.
+ * This function can only be used when all the groups are already built.
  */
 static int find_group_balance_cpu(struct sched_domain *sd,
 				  struct sched_group *sg)
@@ -534,7 +541,11 @@ static int find_group_balance_cpu(struct sched_domain *sd,
 
 	for_each_cpu(i, sg_span) {
 		sibling = *per_cpu_ptr(sdd->sd, i);
-		if (cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+		if (!sibling->groups)
+			continue;
+
+		if (cpumask_equal(sg_span, sched_group_cpus(sibling->groups)))
 			return i;
 	}
 
@@ -584,6 +595,17 @@ static void init_overlap_sched_group(struct sched_domain *sd,
 	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
 }
 
+static void init_overlap_sched_groups(struct sched_domain *sd)
+{
+	struct sched_group *sg = sd->groups;
+
+	do {
+		init_overlap_sched_group(sd, sg);
+
+		sg = sg->next;
+	} while (sg != sd->groups);
+}
+
 static int
 build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 {
@@ -624,8 +646,6 @@ static void init_overlap_sched_group(struct sched_domain *sd,
 		sg_span = sched_group_cpus(sg);
 		cpumask_or(covered, covered, sg_span);
 
-		init_overlap_sched_group(sd, sg);
-
 		if (!first)
 			first = sg;
 		if (last)
@@ -1482,6 +1502,14 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		}
 	}
 
+	/* Init overlap groups */
+	for_each_cpu(i, cpu_map) {
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			if (sd->flags & SD_OVERLAP)
+				init_overlap_sched_groups(sd);
+		}
+	}
+
 	/* Calculate CPU capacity for physical packages and nodes */
 	for (i = nr_cpumask_bits-1; i >= 0; i--) {
 		if (!cpumask_test_cpu(i, cpu_map))
-- 
1.8.3.1