sched: Keep at least 1 tick per second for active dynticks tasks

The scheduler doesn't yet fully support environments
with a single task running without a periodic tick.

In order to ensure we still maintain the duties of scheduler_tick(),
keep at least 1 tick per second.

This makes sure that we keep the progression of various scheduler
accounting and background maintainance even with a very low granularity.
Examples include cpu load, sched average, CFS entity vruntime,
avenrun and events such as load balancing, amongst other details
handled in sched_class::task_tick().

This limitation will be removed in the future once we get
these individual items to work in full dynticks CPUs.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@linaro.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>

4 files changed, 48 insertions, 0 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e94842d..3bdf986 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2736,8 +2736,35 @@ 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)
 {
 	if (in_lock_functions(addr)) {
@@ -6993,6 +7020,9 @@ void __init sched_init(void)
 #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/idle_task.c b/kernel/sched/idle_task.c
index b8ce773..d8da010 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 24dc298..ce39224d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -410,6 +410,9 @@ struct rq {
 	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: */
@@ -1090,6 +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);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1c9f53b..07929c6 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -600,6 +600,13 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 			time_delta = KTIME_MAX;
 		}
 
+#ifdef CONFIG_NO_HZ_FULL
+		if (!ts->inidle) {
+			time_delta = min(time_delta,
+					 scheduler_tick_max_deferment());
+		}
+#endif
+
 		/*
 		 * calculate the expiry time for the next timer wheel
 		 * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals