Merge branch 'smp/threadalloc' into smp/hotplug

Reason: Pull in the separate branch which was created so arch/tile can
base further work on it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 27 insertions, 14 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6a63cde23d03..7b77e3b84b4f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6406,16 +6406,26 @@ static void __sdt_free(const struct cpumask *cpu_map)
                 struct sd_data *sdd = &tl->data;
 
                 for_each_cpu(j, cpu_map) {
-                        struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
-                        if (sd && (sd->flags & SD_OVERLAP))
-                                free_sched_groups(sd->groups, 0);
-                        kfree(*per_cpu_ptr(sdd->sd, j));
-                        kfree(*per_cpu_ptr(sdd->sg, j));
-                        kfree(*per_cpu_ptr(sdd->sgp, j));
+                        struct sched_domain *sd;
+
+                        if (sdd->sd) {
+                                sd = *per_cpu_ptr(sdd->sd, j);
+                                if (sd && (sd->flags & SD_OVERLAP))
+                                        free_sched_groups(sd->groups, 0);
+                                kfree(*per_cpu_ptr(sdd->sd, j));
+                        }
+
+                        if (sdd->sg)
+                                kfree(*per_cpu_ptr(sdd->sg, j));
+                        if (sdd->sgp)
+                                kfree(*per_cpu_ptr(sdd->sgp, j));
                 }
                 free_percpu(sdd->sd);
+                sdd->sd = NULL;
                 free_percpu(sdd->sg);
+                sdd->sg = NULL;
                 free_percpu(sdd->sgp);
+                sdd->sgp = NULL;
         }
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0d97ebdc58f0..e9553640c1c3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -784,7 +784,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
                 update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
 #ifdef CONFIG_SMP
         if (entity_is_task(se))
-                list_add_tail(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
+                list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
 #endif
         cfs_rq->nr_running++;
 }
@@ -3215,6 +3215,8 @@ static int move_one_task(struct lb_env *env)
 
 static unsigned long task_h_load(struct task_struct *p);
 
+static const unsigned int sched_nr_migrate_break = 32;
+
 /*
  * move_tasks tries to move up to load_move weighted load from busiest to
  * this_rq, as part of a balancing operation within domain "sd".
@@ -3242,7 +3244,7 @@ static int move_tasks(struct lb_env *env)
 
                 /* take a breather every nr_migrate tasks */
                 if (env->loop > env->loop_break) {
-                        env->loop_break += sysctl_sched_nr_migrate;
+                        env->loop_break += sched_nr_migrate_break;
                         env->flags |= LBF_NEED_BREAK;
                         break;
                 }
@@ -3252,7 +3254,7 @@ static int move_tasks(struct lb_env *env)
 
                 load = task_h_load(p);
 
-                if (load < 16 && !env->sd->nr_balance_failed)
+                if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
                         goto next;
 
                 if ((load / 2) > env->load_move)
@@ -4407,7 +4409,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
                 .dst_cpu        = this_cpu,
                 .dst_rq         = this_rq,
                 .idle           = idle,
-                .loop_break     = sysctl_sched_nr_migrate,
+                .loop_break     = sched_nr_migrate_break,
         };
 
         cpumask_copy(cpus, cpu_active_mask);
@@ -4445,10 +4447,10 @@ redo:
                  * correctly treated as an imbalance.
                  */
                 env.flags |= LBF_ALL_PINNED;
-                env.load_move = imbalance;
-                env.src_cpu = busiest->cpu;
-                env.src_rq = busiest;
-                env.loop_max = busiest->nr_running;
+                env.load_move   = imbalance;
+                env.src_cpu     = busiest->cpu;
+                env.src_rq      = busiest;
+                env.loop_max    = min_t(unsigned long, sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
                 local_irq_save(flags);
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index e61fd73913d0..de00a486c5c6 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -68,3 +68,4 @@ SCHED_FEAT(TTWU_QUEUE, true)
 
 SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
+SCHED_FEAT(LB_MIN, false)