1 files changed, 45 insertions, 1 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 89431248d33d..8b15e9e1d1b8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -886,6 +886,31 @@ static unsigned int task_scan_max(struct task_struct *p)
  */
 unsigned int sysctl_numa_balancing_settle_count __read_mostly = 3;
 
+static unsigned long weighted_cpuload(const int cpu);
+
+
+static int
+find_idlest_cpu_node(int this_cpu, int nid)
+{
+	unsigned long load, min_load = ULONG_MAX;
+	int i, idlest_cpu = this_cpu;
+
+	BUG_ON(cpu_to_node(this_cpu) == nid);
+
+	rcu_read_lock();
+	for_each_cpu(i, cpumask_of_node(nid)) {
+		load = weighted_cpuload(i);
+
+		if (load < min_load) {
+			min_load = load;
+			idlest_cpu = i;
+		}
+	}
+	rcu_read_unlock();
+
+	return idlest_cpu;
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq, nid, max_nid = -1;
@@ -916,10 +941,29 @@ static void task_numa_placement(struct task_struct *p)
 		}
 	}
 
-	/* Update the tasks preferred node if necessary */
+	/*
+	 * Record the preferred node as the node with the most faults,
+	 * requeue the task to be running on the idlest CPU on the
+	 * preferred node and reset the scanning rate to recheck
+	 * the working set placement.
+	 */
 	if (max_faults && max_nid != p->numa_preferred_nid) {
+		int preferred_cpu;
+
+		/*
+		 * If the task is not on the preferred node then find the most
+		 * idle CPU to migrate to.
+		 */
+		preferred_cpu = task_cpu(p);
+		if (cpu_to_node(preferred_cpu) != max_nid) {
+			preferred_cpu = find_idlest_cpu_node(preferred_cpu,
+							     max_nid);
+		}
+
+		/* Update the preferred nid and migrate task if possible */
 		p->numa_preferred_nid = max_nid;
 		p->numa_migrate_seq = 0;
+		migrate_task_to(p, preferred_cpu);
 	}
 }