1 files changed, 45 insertions, 13 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fe4e0d775375..c1217bfe5e81 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3516,7 +3516,6 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
  * attach_entity_load_avg - attach this entity to its cfs_rq load avg
  * @cfs_rq: cfs_rq to attach to
  * @se: sched_entity to attach
- * @flags: migration hints
  *
  * Must call update_cfs_rq_load_avg() before this, since we rely on
  * cfs_rq->avg.last_update_time being current.
@@ -5912,6 +5911,20 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    (available_idle_cpu(prev) || sched_idle_cpu(prev)))
 		return prev;
 
+	/*
+	 * Allow a per-cpu kthread to stack with the wakee if the
+	 * kworker thread and the tasks previous CPUs are the same.
+	 * The assumption is that the wakee queued work for the
+	 * per-cpu kthread that is now complete and the wakeup is
+	 * essentially a sync wakeup. An obvious example of this
+	 * pattern is IO completions.
+	 */
+	if (is_per_cpu_kthread(current) &&
+	    prev == smp_processor_id() &&
+	    this_rq()->nr_running <= 1) {
+		return prev;
+	}
+
 	/* Check a recently used CPU as a potential idle candidate: */
 	recent_used_cpu = p->recent_used_cpu;
 	if (recent_used_cpu != prev &&
@@ -8324,6 +8337,8 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 
 	sgs->group_capacity = group->sgc->capacity;
 
+	sgs->group_weight = group->group_weight;
+
 	sgs->group_type = group_classify(sd->imbalance_pct, group, sgs);
 
 	/*
@@ -8658,10 +8673,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	/*
 	 * Try to use spare capacity of local group without overloading it or
 	 * emptying busiest.
-	 * XXX Spreading tasks across NUMA nodes is not always the best policy
-	 * and special care should be taken for SD_NUMA domain level before
-	 * spreading the tasks. For now, load_balance() fully relies on
-	 * NUMA_BALANCING and fbq_classify_group/rq to override the decision.
 	 */
 	if (local->group_type == group_has_spare) {
 		if (busiest->group_type > group_fully_busy) {
@@ -8701,16 +8712,37 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 			env->migration_type = migrate_task;
 			lsub_positive(&nr_diff, local->sum_nr_running);
 			env->imbalance = nr_diff >> 1;
-			return;
-		}
+		} else {
 
-		/*
-		 * If there is no overload, we just want to even the number of
-		 * idle cpus.
-		 */
-		env->migration_type = migrate_task;
-		env->imbalance = max_t(long, 0, (local->idle_cpus -
+			/*
+			 * If there is no overload, we just want to even the number of
+			 * idle cpus.
+			 */
+			env->migration_type = migrate_task;
+			env->imbalance = max_t(long, 0, (local->idle_cpus -
 						 busiest->idle_cpus) >> 1);
+		}
+
+		/* Consider allowing a small imbalance between NUMA groups */
+		if (env->sd->flags & SD_NUMA) {
+			unsigned int imbalance_min;
+
+			/*
+			 * Compute an allowed imbalance based on a simple
+			 * pair of communicating tasks that should remain
+			 * local and ignore them.
+			 *
+			 * NOTE: Generally this would have been based on
+			 * the domain size and this was evaluated. However,
+			 * the benefit is similar across a range of workloads
+			 * and machines but scaling by the domain size adds
+			 * the risk that lower domains have to be rebalanced.
+			 */
+			imbalance_min = 2;
+			if (busiest->sum_nr_running <= imbalance_min)
+				env->imbalance = 0;
+		}
+
 		return;
 	}