4 files changed, 110 insertions, 18 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5662f58f0b69..58453b8272fd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -544,7 +544,7 @@ void resched_cpu(int cpu)
         raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 /*
  * In the semi idle case, use the nearest busy cpu for migrating timers
  * from an idle cpu.  This is good for power-savings.
@@ -582,7 +582,7 @@ unlock:
  * 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)
+static void wake_up_idle_cpu(int cpu)
 {
         struct rq *rq = cpu_rq(cpu);
 
@@ -612,20 +612,56 @@ void wake_up_idle_cpu(int cpu)
                 smp_send_reschedule(cpu);
 }
 
+static bool wake_up_full_nohz_cpu(int cpu)
+{
+        if (tick_nohz_full_cpu(cpu)) {
+                if (cpu != smp_processor_id() ||
+                    tick_nohz_tick_stopped())
+                        smp_send_reschedule(cpu);
+                return true;
+        }
+
+        return false;
+}
+
+void wake_up_nohz_cpu(int cpu)
+{
+        if (!wake_up_full_nohz_cpu(cpu))
+                wake_up_idle_cpu(cpu);
+}
+
 static inline bool got_nohz_idle_kick(void)
 {
         int cpu = smp_processor_id();
         return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu));
 }
 
-#else /* CONFIG_NO_HZ */
+#else /* CONFIG_NO_HZ_COMMON */
 
 static inline bool got_nohz_idle_kick(void)
 {
         return false;
 }
 
-#endif /* CONFIG_NO_HZ */
+#endif /* CONFIG_NO_HZ_COMMON */
+
+#ifdef CONFIG_NO_HZ_FULL
+bool sched_can_stop_tick(void)
+{
+       struct rq *rq;
+
+       rq = this_rq();
+
+       /* Make sure rq->nr_running update is visible after the IPI */
+       smp_rmb();
+
+       /* More than one running task need preemption */
+       if (rq->nr_running > 1)
+               return false;
+
+       return true;
+}
+#endif /* CONFIG_NO_HZ_FULL */
 
 void sched_avg_update(struct rq *rq)
 {
@@ -1357,7 +1393,8 @@ static void sched_ttwu_pending(void)
 
 void scheduler_ipi(void)
 {
-        if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
+        if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()
+            && !tick_nohz_full_cpu(smp_processor_id()))
                 return;
 
         /*
@@ -1374,6 +1411,7 @@ void scheduler_ipi(void)
          * somewhat pessimize the simple resched case.
          */
         irq_enter();
+        tick_nohz_full_check();
         sched_ttwu_pending();
 
         /*
@@ -1855,6 +1893,8 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
                 kprobe_flush_task(prev);
                 put_task_struct(prev);
         }
+
+        tick_nohz_task_switch(current);
 }
 
 #ifdef CONFIG_SMP
@@ -2118,7 +2158,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active)
         return load >> FSHIFT;
 }
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 /*
  * Handle NO_HZ for the global load-average.
  *
@@ -2344,12 +2384,12 @@ static void calc_global_nohz(void)
         smp_wmb();
         calc_load_idx++;
 }
-#else /* !CONFIG_NO_HZ */
+#else /* !CONFIG_NO_HZ_COMMON */
 
 static inline long calc_load_fold_idle(void) { return 0; }
 static inline void calc_global_nohz(void) { }
 
-#endif /* CONFIG_NO_HZ */
+#endif /* CONFIG_NO_HZ_COMMON */
 
 /*
  * calc_load - update the avenrun load estimates 10 ticks after the
@@ -2509,7 +2549,7 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
         sched_avg_update(this_rq);
 }
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 /*
  * There is no sane way to deal with nohz on smp when using jiffies because the
  * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
@@ -2569,7 +2609,7 @@ void update_cpu_load_nohz(void)
         }
         raw_spin_unlock(&this_rq->lock);
 }
-#endif /* CONFIG_NO_HZ */
+#endif /* CONFIG_NO_HZ_COMMON */
 
 /*
  * Called from scheduler_tick()
@@ -2696,7 +2736,34 @@ void scheduler_tick(void)
         rq->idle_balance = idle_cpu(cpu);
         trigger_load_balance(rq, cpu);
 #endif
+        rq_last_tick_reset(rq);
+}
+
+#ifdef CONFIG_NO_HZ_FULL
+/**
+ * scheduler_tick_max_deferment
+ *
+ * Keep at least one tick per second when a single
+ * active task is running because the scheduler doesn't
+ * yet completely support full dynticks environment.
+ *
+ * This makes sure that uptime, CFS vruntime, load
+ * balancing, etc... continue to move forward, even
+ * with a very low granularity.
+ */
+u64 scheduler_tick_max_deferment(void)
+{
+        struct rq *rq = this_rq();
+        unsigned long next, now = ACCESS_ONCE(jiffies);
+
+        next = rq->last_sched_tick + HZ;
+
+        if (time_before_eq(next, now))
+                return 0;
+
+        return jiffies_to_usecs(next - now) * NSEC_PER_USEC;
 }
+#endif
 
 notrace unsigned long get_parent_ip(unsigned long addr)
 {
@@ -6951,9 +7018,12 @@ void __init sched_init(void)
                 INIT_LIST_HEAD(&rq->cfs_tasks);
 
                 rq_attach_root(rq, &def_root_domain);
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
                 rq->nohz_flags = 0;
 #endif
+#ifdef CONFIG_NO_HZ_FULL
+                rq->last_sched_tick = 0;
+#endif
 #endif
                 init_rq_hrtick(rq);
                 atomic_set(&rq->nr_iowait, 0);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8bf7081b1ec5..c61a614465c8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5355,7 +5355,7 @@ out_unlock:
         return 0;
 }
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 /*
  * idle load balancing details
  * - When one of the busy CPUs notice that there may be an idle rebalancing
@@ -5572,9 +5572,9 @@ out:
                 rq->next_balance = next_balance;
 }
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 /*
- * In CONFIG_NO_HZ case, the idle balance kickee will do the
+ * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
  * rebalancing for all the cpus for whom scheduler ticks are stopped.
  */
 static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
@@ -5717,7 +5717,7 @@ void trigger_load_balance(struct rq *rq, int cpu)
         if (time_after_eq(jiffies, rq->next_balance) &&
             likely(!on_null_domain(cpu)))
                 raise_softirq(SCHED_SOFTIRQ);
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
         if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
                 nohz_balancer_kick(cpu);
 #endif
@@ -6187,7 +6187,7 @@ __init void init_sched_fair_class(void)
 #ifdef CONFIG_SMP
         open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
         nohz.next_balance = jiffies;
         zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
         cpu_notifier(sched_ilb_notifier, 0);
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index b8ce77328341..d8da01008d39 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -17,6 +17,7 @@ select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
 static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
 {
         idle_exit_fair(rq);
+        rq_last_tick_reset(rq);
 }
 
 static void post_schedule_idle(struct rq *rq)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4c225c4c7111..ce39224d6155 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -5,6 +5,7 @@
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
+#include <linux/tick.h>
 
 #include "cpupri.h"
 #include "cpuacct.h"
@@ -405,10 +406,13 @@ struct rq {
         #define CPU_LOAD_IDX_MAX 5
         unsigned long cpu_load[CPU_LOAD_IDX_MAX];
         unsigned long last_load_update_tick;
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
         u64 nohz_stamp;
         unsigned long nohz_flags;
 #endif
+#ifdef CONFIG_NO_HZ_FULL
+        unsigned long last_sched_tick;
+#endif
         int skip_clock_update;
 
         /* capture load from *all* tasks on this cpu: */
@@ -1072,6 +1076,16 @@ static inline u64 steal_ticks(u64 steal)
 static inline void inc_nr_running(struct rq *rq)
 {
         rq->nr_running++;
+
+#ifdef CONFIG_NO_HZ_FULL
+        if (rq->nr_running == 2) {
+                if (tick_nohz_full_cpu(rq->cpu)) {
+                        /* Order rq->nr_running write against the IPI */
+                        smp_wmb();
+                        smp_send_reschedule(rq->cpu);
+                }
+       }
+#endif
 }
 
 static inline void dec_nr_running(struct rq *rq)
@@ -1079,6 +1093,13 @@ static inline void dec_nr_running(struct rq *rq)
         rq->nr_running--;
 }
 
+static inline void rq_last_tick_reset(struct rq *rq)
+{
+#ifdef CONFIG_NO_HZ_FULL
+        rq->last_sched_tick = jiffies;
+#endif
+}
+
 extern void update_rq_clock(struct rq *rq);
 
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
@@ -1299,7 +1320,7 @@ extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
 
 extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 enum rq_nohz_flag_bits {
         NOHZ_TICK_STOPPED,
         NOHZ_BALANCE_KICK,