[PATCH 4/5] sched/isolation: Residual 1Hz scheduler tick offload

[Frederic Weisbecker <frederic@kernel.org>]

When a CPU runs in full dynticks mode, a 1Hz tick remains in order to
keep the scheduler stats alive. However this residual tick is a burden
for bare metal tasks that can't stand any interruption at all, or want
to minimize them.

Adding the boot parameter "isolcpus=nohz_offload" will now outsource
these scheduler ticks to the global workqueue so that a housekeeping CPU
handles that tick remotely.

Note it's still up to the user to affine the global workqueues to the
housekeeping CPUs through /sys/devices/virtual/workqueue/cpumask or
domains isolation.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <kernellwp@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c      | 88 ++++++++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/isolation.c |  4 +++
 kernel/sched/sched.h     |  2 ++
 3 files changed, 91 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d72d0e9..b964890 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3052,9 +3052,14 @@ void scheduler_tick(void)
  */
 u64 scheduler_tick_max_deferment(void)
 {
-	struct rq *rq = this_rq();
-	unsigned long next, now = READ_ONCE(jiffies);
+	struct rq *rq;
+	unsigned long next, now;
 
+	if (!housekeeping_cpu(smp_processor_id(), HK_FLAG_TICK_SCHED))
+		return ktime_to_ns(KTIME_MAX);
+
+	rq = this_rq();
+	now = READ_ONCE(jiffies);
 	next = rq->last_sched_tick + HZ;
 
 	if (time_before_eq(next, now))
@@ -3062,7 +3067,82 @@ u64 scheduler_tick_max_deferment(void)
 
 	return jiffies_to_nsecs(next - now);
 }
-#endif
+
+struct tick_work {
+	int			cpu;
+	struct delayed_work	work;
+};
+
+static struct tick_work __percpu *tick_work_cpu;
+
+static void sched_tick_remote(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct tick_work *twork = container_of(dwork, struct tick_work, work);
+	int cpu = twork->cpu;
+	struct rq *rq = cpu_rq(cpu);
+	struct rq_flags rf;
+
+	/*
+	 * Handle the tick only if it appears the remote CPU is running
+	 * in full dynticks mode. The check is racy by nature, but
+	 * missing a tick or having one too much is no big deal.
+	 */
+	if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) {
+		rq_lock_irq(rq, &rf);
+		update_rq_clock(rq);
+		rq->curr->sched_class->task_tick(rq, rq->curr, 0);
+		rq_unlock_irq(rq, &rf);
+	}
+
+	queue_delayed_work(system_unbound_wq, dwork, HZ);
+}
+
+static void sched_tick_start(int cpu)
+{
+	struct tick_work *twork;
+
+	if (housekeeping_cpu(cpu, HK_FLAG_TICK_SCHED))
+		return;
+
+	WARN_ON_ONCE(!tick_work_cpu);
+
+	twork = per_cpu_ptr(tick_work_cpu, cpu);
+	twork->cpu = cpu;
+	INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
+	queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void sched_tick_stop(int cpu)
+{
+	struct tick_work *twork;
+
+	if (housekeeping_cpu(cpu, HK_FLAG_TICK_SCHED))
+		return;
+
+	WARN_ON_ONCE(!tick_work_cpu);
+
+	twork = per_cpu_ptr(tick_work_cpu, cpu);
+	cancel_delayed_work_sync(&twork->work);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+int __init sched_tick_offload_init(void)
+{
+	tick_work_cpu = alloc_percpu(struct tick_work);
+	if (!tick_work_cpu) {
+		pr_err("Can't allocate remote tick struct\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+#else
+static void sched_tick_start(int cpu) { }
+static void sched_tick_stop(int cpu) { }
+#endif /* CONFIG_NO_HZ_FULL */
 
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
 				defined(CONFIG_PREEMPT_TRACER))
@@ -5713,6 +5793,7 @@ int sched_cpu_starting(unsigned int cpu)
 {
 	set_cpu_rq_start_time(cpu);
 	sched_rq_cpu_starting(cpu);
+	sched_tick_start(cpu);
 	return 0;
 }
 
@@ -5724,6 +5805,7 @@ int sched_cpu_dying(unsigned int cpu)
 
 	/* Handle pending wakeups and then migrate everything off */
 	sched_ttwu_pending();
+	sched_tick_stop(cpu);
 
 	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 264ddcd..c5e7e90a 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/static_key.h>
 #include <linux/ctype.h>
+#include "sched.h"
 
 DEFINE_STATIC_KEY_FALSE(housekeeping_overriden);
 EXPORT_SYMBOL_GPL(housekeeping_overriden);
@@ -60,6 +61,9 @@ void __init housekeeping_init(void)
 
 	static_branch_enable(&housekeeping_overriden);
 
+	if (housekeeping_flags & HK_FLAG_TICK_SCHED)
+		sched_tick_offload_init();
+
 	/* We need at least one CPU to handle housekeeping work */
 	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b19552a2..5a3b82c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1587,6 +1587,7 @@ extern void post_init_entity_util_avg(struct sched_entity *se);
 
 #ifdef CONFIG_NO_HZ_FULL
 extern bool sched_can_stop_tick(struct rq *rq);
+extern int __init sched_tick_offload_init(void);
 
 /*
  * Tick may be needed by tasks in the runqueue depending on their policy and
@@ -1611,6 +1612,7 @@ static inline void sched_update_tick_dependency(struct rq *rq)
 		tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
 }
 #else
+static inline int sched_tick_offload_init(void) { return 0; }
 static inline void sched_update_tick_dependency(struct rq *rq) { }
 #endif
 
-- 
2.7.4