1 files changed, 62 insertions, 9 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index d1ad69b270ca..8dcdec6fe0fe 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -594,18 +594,14 @@ enum {
         SCHED_FEAT_NEW_FAIR_SLEEPERS    = 1,
         SCHED_FEAT_WAKEUP_PREEMPT       = 2,
         SCHED_FEAT_START_DEBIT          = 4,
-        SCHED_FEAT_TREE_AVG             = 8,
-        SCHED_FEAT_APPROX_AVG           = 16,
-        SCHED_FEAT_HRTICK               = 32,
-        SCHED_FEAT_DOUBLE_TICK          = 64,
+        SCHED_FEAT_HRTICK               = 8,
+        SCHED_FEAT_DOUBLE_TICK          = 16,
 };
 
 const_debug unsigned int sysctl_sched_features =
                 SCHED_FEAT_NEW_FAIR_SLEEPERS    * 1 |
                 SCHED_FEAT_WAKEUP_PREEMPT       * 1 |
                 SCHED_FEAT_START_DEBIT          * 1 |
-                SCHED_FEAT_TREE_AVG             * 0 |
-                SCHED_FEAT_APPROX_AVG           * 0 |
                 SCHED_FEAT_HRTICK               * 1 |
                 SCHED_FEAT_DOUBLE_TICK          * 0;
 
@@ -1056,6 +1052,49 @@ static void resched_cpu(int cpu)
         resched_task(cpu_curr(cpu));
         spin_unlock_irqrestore(&rq->lock, flags);
 }
+
+#ifdef CONFIG_NO_HZ
+/*
+ * When add_timer_on() enqueues a timer into the timer wheel of an
+ * idle CPU then this timer might expire before the next timer event
+ * which is scheduled to wake up that CPU. In case of a completely
+ * idle system the next event might even be infinite time into the
+ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
+ * leaves the inner idle loop so the newly added timer is taken into
+ * account when the CPU goes back to idle and evaluates the timer
+ * wheel for the next timer event.
+ */
+void wake_up_idle_cpu(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+
+        if (cpu == smp_processor_id())
+                return;
+
+        /*
+         * This is safe, as this function is called with the timer
+         * wheel base lock of (cpu) held. When the CPU is on the way
+         * to idle and has not yet set rq->curr to idle then it will
+         * be serialized on the timer wheel base lock and take the new
+         * timer into account automatically.
+         */
+        if (rq->curr != rq->idle)
+                return;
+
+        /*
+         * We can set TIF_RESCHED on the idle task of the other CPU
+         * lockless. The worst case is that the other CPU runs the
+         * idle task through an additional NOOP schedule()
+         */
+        set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED);
+
+        /* NEED_RESCHED must be visible before we test polling */
+        smp_mb();
+        if (!tsk_is_polling(rq->idle))
+                smp_send_reschedule(cpu);
+}
+#endif
+
 #else
 static void __resched_task(struct task_struct *p, int tif_bit)
 {
@@ -1396,6 +1435,12 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 {
         s64 delta;
 
+        /*
+         * Buddy candidates are cache hot:
+         */
+        if (&p->se == cfs_rq_of(&p->se)->next)
+                return 1;
+
         if (p->sched_class != &fair_sched_class)
                 return 0;
 
@@ -1855,10 +1900,11 @@ out_activate:
                 schedstat_inc(p, se.nr_wakeups_remote);
         update_rq_clock(rq);
         activate_task(rq, p, 1);
-        check_preempt_curr(rq, p);
         success = 1;
 
 out_running:
+        check_preempt_curr(rq, p);
+
         p->state = TASK_RUNNING;
 #ifdef CONFIG_SMP
         if (p->sched_class->task_wake_up)
@@ -1892,6 +1938,8 @@ static void __sched_fork(struct task_struct *p)
         p->se.exec_start                = 0;
         p->se.sum_exec_runtime          = 0;
         p->se.prev_sum_exec_runtime     = 0;
+        p->se.last_wakeup               = 0;
+        p->se.avg_overlap               = 0;
 
 #ifdef CONFIG_SCHEDSTATS
         p->se.wait_start                = 0;
@@ -3877,7 +3925,7 @@ need_resched_nonpreemptible:
 
         if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
                 if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
-                                unlikely(signal_pending(prev)))) {
+                                signal_pending(prev))) {
                         prev->state = TASK_RUNNING;
                 } else {
                         deactivate_task(rq, prev, 1);
@@ -6802,6 +6850,10 @@ static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
  */
 static cpumask_t fallback_doms;
 
+void __attribute__((weak)) arch_update_cpu_topology(void)
+{
+}
+
 /*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
@@ -6811,6 +6863,7 @@ static int arch_init_sched_domains(const cpumask_t *cpu_map)
 {
         int err;
 
+        arch_update_cpu_topology();
         ndoms_cur = 1;
         doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
         if (!doms_cur)
@@ -6915,7 +6968,7 @@ match2:
 }
 
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-static int arch_reinit_sched_domains(void)
+int arch_reinit_sched_domains(void)
 {
         int err;