1 files changed, 63 insertions, 18 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index db3f674ca49d..933f3d1b62ea 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -25,7 +25,7 @@
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
- * (default: 5ms * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
  * 'timeslice length' - timeslices in CFS are of variable length
@@ -52,7 +52,7 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
- * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
 unsigned int sysctl_sched_min_granularity = 750000ULL;
 unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
@@ -519,7 +519,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 static void update_curr(struct cfs_rq *cfs_rq)
 {
         struct sched_entity *curr = cfs_rq->curr;
-        u64 now = rq_of(cfs_rq)->clock;
+        u64 now = rq_of(cfs_rq)->clock_task;
         unsigned long delta_exec;
 
         if (unlikely(!curr))
@@ -602,7 +602,7 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
         /*
          * We are starting a new run period:
          */
-        se->exec_start = rq_of(cfs_rq)->clock;
+        se->exec_start = rq_of(cfs_rq)->clock_task;
 }
 
 /**************************************************
@@ -1764,6 +1764,10 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
         set_task_cpu(p, this_cpu);
         activate_task(this_rq, p, 0);
         check_preempt_curr(this_rq, p, 0);
+
+        /* re-arm NEWIDLE balancing when moving tasks */
+        src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
+        this_rq->idle_stamp = 0;
 }
 
 /*
@@ -1798,7 +1802,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
          * 2) too many balance attempts have failed.
          */
 
-        tsk_cache_hot = task_hot(p, rq->clock, sd);
+        tsk_cache_hot = task_hot(p, rq->clock_task, sd);
         if (!tsk_cache_hot ||
                 sd->nr_balance_failed > sd->cache_nice_tries) {
 #ifdef CONFIG_SCHEDSTATS
@@ -2030,12 +2034,14 @@ struct sd_lb_stats {
         unsigned long this_load;
         unsigned long this_load_per_task;
         unsigned long this_nr_running;
+        unsigned long this_has_capacity;
 
         /* Statistics of the busiest group */
         unsigned long max_load;
         unsigned long busiest_load_per_task;
         unsigned long busiest_nr_running;
         unsigned long busiest_group_capacity;
+        unsigned long busiest_has_capacity;
 
         int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2058,6 +2064,7 @@ struct sg_lb_stats {
         unsigned long sum_weighted_load; /* Weighted load of group's tasks */
         unsigned long group_capacity;
         int group_imb; /* Is there an imbalance in the group ? */
+        int group_has_capacity; /* Is there extra capacity in the group? */
 };
 
 /**
@@ -2268,7 +2275,13 @@ unsigned long scale_rt_power(int cpu)
         u64 total, available;
 
         total = sched_avg_period() + (rq->clock - rq->age_stamp);
-        available = total - rq->rt_avg;
+
+        if (unlikely(total < rq->rt_avg)) {
+                /* Ensures that power won't end up being negative */
+                available = 0;
+        } else {
+                available = total - rq->rt_avg;
+        }
 
         if (unlikely((s64)total < SCHED_LOAD_SCALE))
                 total = SCHED_LOAD_SCALE;
@@ -2378,7 +2391,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
                         int local_group, const struct cpumask *cpus,
                         int *balance, struct sg_lb_stats *sgs)
 {
-        unsigned long load, max_cpu_load, min_cpu_load;
+        unsigned long load, max_cpu_load, min_cpu_load, max_nr_running;
         int i;
         unsigned int balance_cpu = -1, first_idle_cpu = 0;
         unsigned long avg_load_per_task = 0;
@@ -2389,6 +2402,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         /* Tally up the load of all CPUs in the group */
         max_cpu_load = 0;
         min_cpu_load = ~0UL;
+        max_nr_running = 0;
 
         for_each_cpu_and(i, sched_group_cpus(group), cpus) {
                 struct rq *rq = cpu_rq(i);
@@ -2406,8 +2420,10 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
                         load = target_load(i, load_idx);
                 } else {
                         load = source_load(i, load_idx);
-                        if (load > max_cpu_load)
+                        if (load > max_cpu_load) {
                                 max_cpu_load = load;
+                                max_nr_running = rq->nr_running;
+                        }
                         if (min_cpu_load > load)
                                 min_cpu_load = load;
                 }
@@ -2447,13 +2463,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         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)
+        if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
                 sgs->group_imb = 1;
 
-        sgs->group_capacity =
-                DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
+        sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
         if (!sgs->group_capacity)
                 sgs->group_capacity = fix_small_capacity(sd, group);
+
+        if (sgs->group_capacity > sgs->sum_nr_running)
+                sgs->group_has_capacity = 1;
 }
 
 /**
@@ -2542,9 +2560,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                 /*
                  * In case the child domain prefers tasks go to siblings
                  * first, lower the sg capacity to one so that we'll try
-                 * and move all the excess tasks away.
+                 * and move all the excess tasks away. We lower the capacity
+                 * of a group only if the local group has the capacity to fit
+                 * these excess tasks, i.e. nr_running < group_capacity. The
+                 * extra check prevents the case where you always pull from the
+                 * heaviest group when it is already under-utilized (possible
+                 * with a large weight task outweighs the tasks on the system).
                  */
-                if (prefer_sibling)
+                if (prefer_sibling && !local_group && sds->this_has_capacity)
                         sgs.group_capacity = min(sgs.group_capacity, 1UL);
 
                 if (local_group) {
@@ -2552,12 +2575,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                         sds->this = sg;
                         sds->this_nr_running = sgs.sum_nr_running;
                         sds->this_load_per_task = sgs.sum_weighted_load;
+                        sds->this_has_capacity = sgs.group_has_capacity;
                 } else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
                         sds->max_load = sgs.avg_load;
                         sds->busiest = sg;
                         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->busiest_has_capacity = sgs.group_has_capacity;
                         sds->group_imb = sgs.group_imb;
                 }
 
@@ -2754,6 +2779,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
                 return fix_small_imbalance(sds, this_cpu, imbalance);
 
 }
+
 /******* find_busiest_group() helpers end here *********************/
 
 /**
@@ -2805,6 +2831,11 @@ 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.
+         *
+         * Note: when doing newidle balance, if the local group has excess
+         * capacity (i.e. nr_running < group_capacity) and the busiest group
+         * does not have any capacity, we force a load balance to pull tasks
+         * to the local group. In this case, we skip past checks 3, 4 and 5.
          */
         if (!(*balance))
                 goto ret;
@@ -2816,6 +2847,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (!sds.busiest || sds.busiest_nr_running == 0)
                 goto out_balanced;
 
+        /*  SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+        if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
+                        !sds.busiest_has_capacity)
+                goto force_balance;
+
         if (sds.this_load >= sds.max_load)
                 goto out_balanced;
 
@@ -2827,6 +2863,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
                 goto out_balanced;
 
+force_balance:
         /* Looks like there is an imbalance. Compute it */
         calculate_imbalance(&sds, this_cpu, imbalance);
         return sds.busiest;
@@ -3031,7 +3068,14 @@ redo:
 
         if (!ld_moved) {
                 schedstat_inc(sd, lb_failed[idle]);
-                sd->nr_balance_failed++;
+                /*
+                 * Increment the failure counter only on periodic balance.
+                 * We do not want newidle balance, which can be very
+                 * frequent, pollute the failure counter causing
+                 * excessive cache_hot migrations and active balances.
+                 */
+                if (idle != CPU_NEWLY_IDLE)
+                        sd->nr_balance_failed++;
 
                 if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
                                         this_cpu)) {
@@ -3153,10 +3197,8 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
                 interval = msecs_to_jiffies(sd->balance_interval);
                 if (time_after(next_balance, sd->last_balance + interval))
                         next_balance = sd->last_balance + interval;
-                if (pulled_task) {
-                        this_rq->idle_stamp = 0;
+                if (pulled_task)
                         break;
-                }
         }
 
         raw_spin_lock(&this_rq->lock);
@@ -3751,8 +3793,11 @@ static void task_fork_fair(struct task_struct *p)
 
         update_rq_clock(rq);
 
-        if (unlikely(task_cpu(p) != this_cpu))
+        if (unlikely(task_cpu(p) != this_cpu)) {
+                rcu_read_lock();
                 __set_task_cpu(p, this_cpu);
+                rcu_read_unlock();
+        }
 
         update_curr(cfs_rq);