workqueue: Clarify that schedule_on_each_cpu is synchronous

[karo-tx-linux.git] / kernel / sched_fair.c

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index e44a591531a13dca3aae7b75af4570079cc97818..a171138a94026c4a52879b74f297916ac4afd497 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -54,13 +54,13 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling
  * Minimal preemption granularity for CPU-bound tasks:
  * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity = 2000000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 2000000ULL;
+unsigned int sysctl_sched_min_granularity = 750000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
  */
-static unsigned int sched_nr_latency = 3;
+static unsigned int sched_nr_latency = 8;
 
 /*
  * After fork, child runs first. If set to 0 (default) then
@@ -1240,6 +1240,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
         * effect of the currently running task from the load
         * of the current CPU:
         */
+       rcu_read_lock();
        if (sync) {
                tg = task_group(current);
                weight = current->se.load.weight;
@@ -1275,6 +1276,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
                balanced = this_eff_load <= prev_eff_load;
        } else
                balanced = true;
+       rcu_read_unlock();
 
        /*
         * If the currently running task will sleep within
@@ -1311,7 +1313,7 @@ static struct sched_group *
 find_idlest_group(struct sched_domain *sd, struct task_struct *p,
                  int this_cpu, int load_idx)
 {
-       struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
+       struct sched_group *idlest = NULL, *group = sd->groups;
        unsigned long min_load = ULONG_MAX, this_load = 0;
        int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
@@ -1346,7 +1348,6 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 
                if (local_group) {
                        this_load = avg_load;
-                       this = group;
                } else if (avg_load < min_load) {
                        min_load = avg_load;
                        idlest = group;
@@ -2266,8 +2267,6 @@ unsigned long scale_rt_power(int cpu)
        struct rq *rq = cpu_rq(cpu);
        u64 total, available;
 
-       sched_avg_update(rq);
-
        total = sched_avg_period() + (rq->clock - rq->age_stamp);
        available = total - rq->rt_avg;
 
@@ -2425,14 +2424,14 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         * domains. In the newly idle case, we will allow all the cpu's
         * to do the newly idle load balance.
         */
-       if (idle != CPU_NEWLY_IDLE && local_group &&
-           balance_cpu != this_cpu) {
-               *balance = 0;
-               return;
+       if (idle != CPU_NEWLY_IDLE && local_group) {
+               if (balance_cpu != this_cpu) {
+                       *balance = 0;
+                       return;
+               }
+               update_group_power(sd, this_cpu);
        }
 
-       update_group_power(sd, this_cpu);
-
        /* Adjust by relative CPU power of the group */
        sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
@@ -3750,6 +3749,8 @@ static void task_fork_fair(struct task_struct *p)
 
        raw_spin_lock_irqsave(&rq->lock, flags);
 
+       update_rq_clock(rq);
+
        if (unlikely(task_cpu(p) != this_cpu))
                __set_task_cpu(p, this_cpu);