Revert "sched: Improve scalability via 'CPU buddies', which withstand random perturba...

[firefly-linux-kernel-4.4.55.git] / kernel / sched / fair.c

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d0cc03b3e70b9d2d2bfbbd418e6dfc858a7f6387..96e2b18b628312dd69e8ad2ee6e3a6e08f33cce7 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2052,7 +2052,7 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
        hrtimer_cancel(&cfs_b->slack_timer);
 }
 
-void unthrottle_offline_cfs_rqs(struct rq *rq)
+static void unthrottle_offline_cfs_rqs(struct rq *rq)
 {
        struct cfs_rq *cfs_rq;
 
@@ -2106,7 +2106,7 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
        return NULL;
 }
 static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
-void unthrottle_offline_cfs_rqs(struct rq *rq) {}
+static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
 
 #endif /* CONFIG_CFS_BANDWIDTH */
 
@@ -2637,6 +2637,8 @@ static int select_idle_sibling(struct task_struct *p, int target)
        int cpu = smp_processor_id();
        int prev_cpu = task_cpu(p);
        struct sched_domain *sd;
+       struct sched_group *sg;
+       int i;
 
        /*
         * If the task is going to be woken-up on this cpu and if it is
@@ -2653,17 +2655,29 @@ static int select_idle_sibling(struct task_struct *p, int target)
                return prev_cpu;
 
        /*
-        * Otherwise, check assigned siblings to find an elegible idle cpu.
+        * Otherwise, iterate the domains and find an elegible idle cpu.
         */
        sd = rcu_dereference(per_cpu(sd_llc, target));
-
        for_each_lower_domain(sd) {
-               if (!cpumask_test_cpu(sd->idle_buddy, tsk_cpus_allowed(p)))
-                       continue;
-               if (idle_cpu(sd->idle_buddy))
-                       return sd->idle_buddy;
-       }
+               sg = sd->groups;
+               do {
+                       if (!cpumask_intersects(sched_group_cpus(sg),
+                                               tsk_cpus_allowed(p)))
+                               goto next;
 
+                       for_each_cpu(i, sched_group_cpus(sg)) {
+                               if (!idle_cpu(i))
+                                       goto next;
+                       }
+
+                       target = cpumask_first_and(sched_group_cpus(sg),
+                                       tsk_cpus_allowed(p));
+                       goto done;
+next:
+                       sg = sg->next;
+               } while (sg != sd->groups);
+       }
+done:
        return target;
 }
 
@@ -3387,6 +3401,14 @@ static int tg_load_down(struct task_group *tg, void *data)
 
 static void update_h_load(long cpu)
 {
+       struct rq *rq = cpu_rq(cpu);
+       unsigned long now = jiffies;
+
+       if (rq->h_load_throttle == now)
+               return;
+
+       rq->h_load_throttle = now;
+
        rcu_read_lock();
        walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
        rcu_read_unlock();
@@ -3650,7 +3672,6 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  * @group: sched_group whose statistics are to be updated.
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
  * @local_group: Does group contain this_cpu.
- * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
  * @sgs: variable to hold the statistics for this group.
  */
@@ -3797,7 +3818,6 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 /**
  * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
  * @env: The load balancing environment.
- * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
  * @sds: variable to hold the statistics for this sched_domain.
  */
@@ -4293,11 +4313,10 @@ redo:
                env.src_rq    = busiest;
                env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
+               update_h_load(env.src_cpu);
 more_balance:
                local_irq_save(flags);
                double_rq_lock(this_rq, busiest);
-               if (!env.loop)
-                       update_h_load(env.src_cpu);
 
                /*
                 * cur_ld_moved - load moved in current iteration
@@ -4949,6 +4968,9 @@ static void rq_online_fair(struct rq *rq)
 static void rq_offline_fair(struct rq *rq)
 {
        update_sysctl();
+
+       /* Ensure any throttled groups are reachable by pick_next_task */
+       unthrottle_offline_cfs_rqs(rq);
 }
 
 #endif /* CONFIG_SMP */