1 files changed, 43 insertions, 33 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ff7692ccda89..3e1fd96c6cf9 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2097,6 +2097,7 @@ struct sd_lb_stats {
         unsigned long max_load;
         unsigned long busiest_load_per_task;
         unsigned long busiest_nr_running;
+        unsigned long busiest_group_capacity;
 
         int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2416,14 +2417,12 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         unsigned long load, max_cpu_load, min_cpu_load;
         int i;
         unsigned int balance_cpu = -1, first_idle_cpu = 0;
-        unsigned long sum_avg_load_per_task;
-        unsigned long avg_load_per_task;
+        unsigned long avg_load_per_task = 0;
 
         if (local_group)
                 balance_cpu = group_first_cpu(group);
 
         /* Tally up the load of all CPUs in the group */
-        sum_avg_load_per_task = avg_load_per_task = 0;
         max_cpu_load = 0;
         min_cpu_load = ~0UL;
 
@@ -2453,7 +2452,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
                 sgs->sum_nr_running += rq->nr_running;
                 sgs->sum_weighted_load += weighted_cpuload(i);
 
-                sum_avg_load_per_task += cpu_avg_load_per_task(i);
         }
 
         /*
@@ -2473,7 +2471,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         /* Adjust by relative CPU power of the group */
         sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
-
         /*
          * Consider the group unbalanced when the imbalance is larger
          * than the average weight of two tasks.
@@ -2483,8 +2480,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
          *      normalized nr_running number somewhere that negates
          *      the hierarchy?
          */
-        avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
-                group->cpu_power;
+        if (sgs->sum_nr_running)
+                avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
         if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
                 sgs->group_imb = 1;
@@ -2553,6 +2550,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                         sds->max_load = sgs.avg_load;
                         sds->busiest = group;
                         sds->busiest_nr_running = sgs.sum_nr_running;
+                        sds->busiest_group_capacity = sgs.group_capacity;
                         sds->busiest_load_per_task = sgs.sum_weighted_load;
                         sds->group_imb = sgs.group_imb;
                 }
@@ -2575,6 +2573,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 {
         unsigned long tmp, pwr_now = 0, pwr_move = 0;
         unsigned int imbn = 2;
+        unsigned long scaled_busy_load_per_task;
 
         if (sds->this_nr_running) {
                 sds->this_load_per_task /= sds->this_nr_running;
@@ -2585,8 +2584,12 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
                 sds->this_load_per_task =
                         cpu_avg_load_per_task(this_cpu);
 
-        if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
-                        sds->busiest_load_per_task * imbn) {
+        scaled_busy_load_per_task = sds->busiest_load_per_task
+                                                 * SCHED_LOAD_SCALE;
+        scaled_busy_load_per_task /= sds->busiest->cpu_power;
+
+        if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
+                        (scaled_busy_load_per_task * imbn)) {
                 *imbalance = sds->busiest_load_per_task;
                 return;
         }
@@ -2637,7 +2640,14 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
                 unsigned long *imbalance)
 {
-        unsigned long max_pull;
+        unsigned long max_pull, load_above_capacity = ~0UL;
+
+        sds->busiest_load_per_task /= sds->busiest_nr_running;
+        if (sds->group_imb) {
+                sds->busiest_load_per_task =
+                        min(sds->busiest_load_per_task, sds->avg_load);
+        }
+
         /*
          * In the presence of smp nice balancing, certain scenarios can have
          * max load less than avg load(as we skip the groups at or below
@@ -2648,9 +2658,29 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
                 return fix_small_imbalance(sds, this_cpu, imbalance);
         }
 
-        /* Don't want to pull so many tasks that a group would go idle */
-        max_pull = min(sds->max_load - sds->avg_load,
-                        sds->max_load - sds->busiest_load_per_task);
+        if (!sds->group_imb) {
+                /*
+                 * Don't want to pull so many tasks that a group would go idle.
+                 */
+                load_above_capacity = (sds->busiest_nr_running -
+                                                sds->busiest_group_capacity);
+
+                load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_LOAD_SCALE);
+
+                load_above_capacity /= sds->busiest->cpu_power;
+        }
+
+        /*
+         * We're trying to get all the cpus to the average_load, so we don't
+         * want to push ourselves above the average load, nor do we wish to
+         * reduce the max loaded cpu below the average load. At the same time,
+         * we also don't want to reduce the group load below the group capacity
+         * (so that we can implement power-savings policies etc). Thus we look
+         * for the minimum possible imbalance.
+         * Be careful of negative numbers as they'll appear as very large values
+         * with unsigned longs.
+         */
+        max_pull = min(sds->max_load - sds->avg_load, load_above_capacity);
 
         /* How much load to actually move to equalise the imbalance */
         *imbalance = min(max_pull * sds->busiest->cpu_power,
@@ -2718,7 +2748,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
          * 4) This group is more busy than the avg busieness at this
          *    sched_domain.
          * 5) The imbalance is within the specified limit.
-         * 6) Any rebalance would lead to ping-pong
          */
         if (!(*balance))
                 goto ret;
@@ -2737,25 +2766,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
                 goto out_balanced;
 
-        sds.busiest_load_per_task /= sds.busiest_nr_running;
-        if (sds.group_imb)
-                sds.busiest_load_per_task =
-                        min(sds.busiest_load_per_task, sds.avg_load);
-
-        /*
-         * We're trying to get all the cpus to the average_load, so we don't
-         * want to push ourselves above the average load, nor do we wish to
-         * reduce the max loaded cpu below the average load, as either of these
-         * actions would just result in more rebalancing later, and ping-pong
-         * tasks around. Thus we look for the minimum possible imbalance.
-         * Negative imbalances (*we* are more loaded than anyone else) will
-         * be counted as no imbalance for these purposes -- we can't fix that
-         * by pulling tasks to us. Be careful of negative numbers as they'll
-         * appear as very large values with unsigned longs.
-         */
-        if (sds.max_load <= sds.busiest_load_per_task)
-                goto out_balanced;
-
         /* Looks like there is an imbalance. Compute it */
         calculate_imbalance(&sds, this_cpu, imbalance);
         return sds.busiest;