1 files changed, 20 insertions, 13 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 3f7ec9e27ee1..6fa833ab2cb8 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -22,6 +22,7 @@
 
 #include <linux/latencytop.h>
 #include <linux/sched.h>
+#include <linux/cpumask.h>
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
@@ -2103,21 +2104,20 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
               enum cpu_idle_type idle, int *all_pinned,
               int *this_best_prio, struct cfs_rq *busiest_cfs_rq)
 {
-        int loops = 0, pulled = 0, pinned = 0;
+        int loops = 0, pulled = 0;
         long rem_load_move = max_load_move;
         struct task_struct *p, *n;
 
         if (max_load_move == 0)
                 goto out;
 
-        pinned = 1;
-
         list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) {
                 if (loops++ > sysctl_sched_nr_migrate)
                         break;
 
                 if ((p->se.load.weight >> 1) > rem_load_move ||
-                    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned))
+                    !can_migrate_task(p, busiest, this_cpu, sd, idle,
+                                      all_pinned))
                         continue;
 
                 pull_task(busiest, p, this_rq, this_cpu);
@@ -2152,9 +2152,6 @@ out:
          */
         schedstat_add(sd, lb_gained[idle], pulled);
 
-        if (all_pinned)
-                *all_pinned = pinned;
-
         return max_load_move - rem_load_move;
 }
 
@@ -3061,7 +3058,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 
         /*
          * if *imbalance is less than the average load per runnable task
-         * there is no gaurantee that any tasks will be moved so we'll have
+         * there is no guarantee that any tasks will be moved so we'll have
          * a think about bumping its value to force at least one task to be
          * moved
          */
@@ -3126,6 +3123,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (!sds.busiest || sds.busiest_nr_running == 0)
                 goto out_balanced;
 
+        sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
+
         /*
          * If the busiest group is imbalanced the below checks don't
          * work because they assumes all things are equal, which typically
@@ -3150,7 +3149,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
          * Don't pull any tasks if this group is already above the domain
          * average load.
          */
-        sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
         if (sds.this_load >= sds.avg_load)
                 goto out_balanced;
 
@@ -3339,6 +3337,7 @@ redo:
                  * still unbalanced. ld_moved simply stays zero, so it is
                  * correctly treated as an imbalance.
                  */
+                all_pinned = 1;
                 local_irq_save(flags);
                 double_rq_lock(this_rq, busiest);
                 ld_moved = move_tasks(this_rq, this_cpu, busiest,
@@ -3819,6 +3818,17 @@ void select_nohz_load_balancer(int stop_tick)
 
 static DEFINE_SPINLOCK(balancing);
 
+static unsigned long __read_mostly max_load_balance_interval = HZ/10;
+
+/*
+ * Scale the max load_balance interval with the number of CPUs in the system.
+ * This trades load-balance latency on larger machines for less cross talk.
+ */
+static void update_max_interval(void)
+{
+        max_load_balance_interval = HZ*num_online_cpus()/10;
+}
+
 /*
  * It checks each scheduling domain to see if it is due to be balanced,
  * and initiates a balancing operation if so.
@@ -3848,10 +3858,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 
                 /* scale ms to jiffies */
                 interval = msecs_to_jiffies(interval);
-                if (unlikely(!interval))
-                        interval = 1;
-                if (interval > HZ*NR_CPUS/10)
-                        interval = HZ*NR_CPUS/10;
+                interval = clamp(interval, 1UL, max_load_balance_interval);
 
                 need_serialize = sd->flags & SD_SERIALIZE;