[PATCH 2/2] nohz: Move full nohz kick to its own IPI

[Frederic Weisbecker]

Now that we have smp_queue_function_single() which can be used to
safely queue IPIs when interrupts are disabled and without worrying
about concurrent callers, lets use it for the full dynticks kick to
notify a CPU that it's exiting single task mode.

This unbloats a bit the scheduler IPI that the nohz code was abusing
for its cool "callable anywhere/anytime" properties.

Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Jens Axboe <jens.axboe@xxxxxxxxxx>
Cc: Kevin Hilman <khilman@xxxxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
---
 include/linux/tick.h     |  2 ++
 kernel/sched/core.c      |  5 +----
 kernel/sched/sched.h     |  2 +-
 kernel/time/tick-sched.c | 20 ++++++++++++++++++++
 4 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/include/linux/tick.h b/include/linux/tick.h
index b84773c..9d3fcc2 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -182,6 +182,7 @@ static inline bool tick_nohz_full_cpu(int cpu)
 extern void tick_nohz_init(void);
 extern void __tick_nohz_full_check(void);
 extern void tick_nohz_full_kick(void);
+extern void tick_nohz_full_kick_cpu(int cpu);
 extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(struct task_struct *tsk);
 #else
@@ -190,6 +191,7 @@ static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void __tick_nohz_full_check(void) { }
 static inline void tick_nohz_full_kick(void) { }
+static inline void tick_nohz_full_kick_cpu(int cpu) { }
 static inline void tick_nohz_full_kick_all(void) { }
 static inline void __tick_nohz_task_switch(struct task_struct *tsk) { }
 #endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9cae286..e4b344e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1499,9 +1499,7 @@ void scheduler_ipi(void)
 	 */
 	preempt_fold_need_resched();
 
-	if (llist_empty(&this_rq()->wake_list)
-			&& !tick_nohz_full_cpu(smp_processor_id())
-			&& !got_nohz_idle_kick())
+	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
 		return;
 
 	/*
@@ -1518,7 +1516,6 @@ void scheduler_ipi(void)
 	 * somewhat pessimize the simple resched case.
 	 */
 	irq_enter();
-	tick_nohz_full_check();
 	sched_ttwu_pending();
 
 	/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c9007f2..4771063 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1225,7 +1225,7 @@ static inline void inc_nr_running(struct rq *rq)
 		if (tick_nohz_full_cpu(rq->cpu)) {
 			/* Order rq->nr_running write against the IPI */
 			smp_wmb();
-			smp_send_reschedule(rq->cpu);
+			tick_nohz_full_kick_cpu(rq->cpu);
 		}
        }
 #endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 9f8af69..33a0043 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -230,6 +230,26 @@ void tick_nohz_full_kick(void)
 		irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
 }
 
+static DEFINE_PER_CPU(struct queue_single_data, nohz_full_kick_qsd);
+
+static void nohz_full_kick_queue(struct queue_single_data *qsd)
+{
+	__tick_nohz_full_check();
+}
+
+void tick_nohz_full_kick_cpu(int cpu)
+{
+	if (!tick_nohz_full_cpu(cpu))
+		return;
+
+	if (cpu == smp_processor_id()) {
+		irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
+	} else {
+		smp_queue_function_single(cpu, nohz_full_kick_queue,
+					  &per_cpu(nohz_full_kick_qsd, cpu));
+	}
+}
+
 static void nohz_full_kick_ipi(void *info)
 {
 	__tick_nohz_full_check();
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/