2 files changed, 50 insertions, 0 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 50d04b92ceda..4f163a8ffabf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1034,6 +1034,9 @@ struct task_struct {
 #ifdef CONFIG_SMP
         struct llist_node wake_entry;
         int on_cpu;
+        struct task_struct *last_wakee;
+        unsigned long wakee_flips;
+        unsigned long wakee_flip_decay_ts;
 #endif
         int on_rq;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 765d87acdf05..860063a8c849 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3017,6 +3017,23 @@ static unsigned long cpu_avg_load_per_task(int cpu)
         return 0;
 }
 
+static void record_wakee(struct task_struct *p)
+{
+        /*
+         * Rough decay (wiping) for cost saving, don't worry
+         * about the boundary, really active task won't care
+         * about the loss.
+         */
+        if (jiffies > current->wakee_flip_decay_ts + HZ) {
+                current->wakee_flips = 0;
+                current->wakee_flip_decay_ts = jiffies;
+        }
+
+        if (current->last_wakee != p) {
+                current->last_wakee = p;
+                current->wakee_flips++;
+        }
+}
 
 static void task_waking_fair(struct task_struct *p)
 {
@@ -3037,6 +3054,7 @@ static void task_waking_fair(struct task_struct *p)
 #endif
 
         se->vruntime -= min_vruntime;
+        record_wakee(p);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -3155,6 +3173,28 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 
 #endif
 
+static int wake_wide(struct task_struct *p)
+{
+        int factor = nr_cpus_node(cpu_to_node(smp_processor_id()));
+
+        /*
+         * Yeah, it's the switching-frequency, could means many wakee or
+         * rapidly switch, use factor here will just help to automatically
+         * adjust the loose-degree, so bigger node will lead to more pull.
+         */
+        if (p->wakee_flips > factor) {
+                /*
+                 * wakee is somewhat hot, it needs certain amount of cpu
+                 * resource, so if waker is far more hot, prefer to leave
+                 * it alone.
+                 */
+                if (current->wakee_flips > (factor * p->wakee_flips))
+                        return 1;
+        }
+
+        return 0;
+}
+
 static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
         s64 this_load, load;
@@ -3164,6 +3204,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
         unsigned long weight;
         int balanced;
 
+        /*
+         * If we wake multiple tasks be careful to not bounce
+         * ourselves around too much.
+         */
+        if (wake_wide(p))
+                return 0;
+
         idx       = sd->wake_idx;
         this_cpu  = smp_processor_id();
         prev_cpu  = task_cpu(p);