[PATCH 14/41] nohz/cpuset: Restart tick when nohz flag is cleared on cpuset

[Frederic Weisbecker]

Issue an IPI to restart the tick on a CPU that belongs
to a cpuset when its nohz flag gets cleared.

Signed-off-by: Frederic Weisbecker <fweisbec at gmail.com>
Cc: Alessio Igor Bogani <abogani at kernel.org>
Cc: Andrew Morton <akpm at linux-foundation.org>
Cc: Avi Kivity <avi at redhat.com>
Cc: Chris Metcalf <cmetcalf at tilera.com>
Cc: Christoph Lameter <cl at linux.com>
Cc: Daniel Lezcano <daniel.lezcano at linaro.org>
Cc: Geoff Levand <geoff at infradead.org>
Cc: Gilad Ben Yossef <gilad at benyossef.com>
Cc: Hakan Akkan <hakanakkan at gmail.com>
Cc: Ingo Molnar <mingo at kernel.org>
Cc: Kevin Hilman <khilman at ti.com>
Cc: Max Krasnyansky <maxk at qualcomm.com>
Cc: Paul E. McKenney <paulmck at linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz at infradead.org>
Cc: Stephen Hemminger <shemminger at vyatta.com>
Cc: Steven Rostedt <rostedt at goodmis.org>
Cc: Sven-Thorsten Dietrich <thebigcorporation at gmail.com>
Cc: Thomas Gleixner <tglx at linutronix.de>
---
 include/linux/cpuset.h   |    2 ++
 kernel/cpuset.c          |   23 +++++++++++++++++++++++
 kernel/time/tick-sched.c |    8 ++++++++
 3 files changed, 33 insertions(+), 0 deletions(-)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 5510708..89ef5f3 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -263,6 +263,8 @@ static inline bool cpuset_adaptive_nohz(void)
 
 	return false;
 }
+
+extern void cpuset_exit_nohz_interrupt(void *unused);
 #else
 static inline bool cpuset_cpu_adaptive_nohz(int cpu) { return false; }
 static inline bool cpuset_adaptive_nohz(void) { return false; }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 5a28cf8..00864a0 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1221,6 +1221,14 @@ static void cpuset_change_flag(struct task_struct *tsk,
 
 DEFINE_PER_CPU(int, cpu_adaptive_nohz_ref);
 
+static void cpu_exit_nohz(int cpu)
+{
+	preempt_disable();
+	smp_call_function_single(cpu, cpuset_exit_nohz_interrupt,
+				 NULL, true);
+	preempt_enable();
+}
+
 static void update_nohz_cpus(struct cpuset *old_cs, struct cpuset *cs)
 {
 	int cpu;
@@ -1234,6 +1242,21 @@ static void update_nohz_cpus(struct cpuset *old_cs, struct cpuset *cs)
 			per_cpu(cpu_adaptive_nohz_ref, cpu) += 1;
 		else
 			per_cpu(cpu_adaptive_nohz_ref, cpu) -= 1;
+
+		val = per_cpu(cpu_adaptive_nohz_ref, cpu);
+
+		if (!val) {
+			/*
+			 * The update to cpu_adaptive_nohz_ref must be
+			 * visible right away. So that once we restart the tick
+			 * from the IPI, it won't be stopped again due to cache
+			 * update lag.
+			 * FIXME: We probably need more to ensure this value is really
+			 * visible right away.
+			 */
+			smp_mb();
+			cpu_exit_nohz(cpu);
+		}
 	}
 }
 #else
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index fc35d41..fe31add 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -875,6 +875,14 @@ void tick_nohz_check_adaptive(void)
 	}
 }
 
+void cpuset_exit_nohz_interrupt(void *unused)
+{
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+	if (ts->tick_stopped && !is_idle_task(current))
+		tick_nohz_restart_adaptive();
+}
+
 void tick_nohz_post_schedule(void)
 {
 	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
-- 
1.7.5.4