When a CPU is in full dynticks mode, try to switch
it to nohz mode from the interrupt exit path if it is
running a single non-idle task.
Then restart the tick if necessary if we are enqueuing a
second task while the timer is stopped, so that the scheduler
tick is rearmed.
[TODO: Check remaining things to be done from scheduler_tick()]
[ Included build fix from Geoff Levand ]
Signed-off-by: Frederic Weisbecker <fweis...@gmail.com>
Cc: Alessio Igor Bogani <abog...@kernel.org>
Cc: Andrew Morton <a...@linux-foundation.org>
Cc: Avi Kivity <a...@redhat.com>
Cc: Chris Metcalf <cmetc...@tilera.com>
Cc: Christoph Lameter <c...@linux.com>
Cc: Geoff Levand <ge...@infradead.org>
Cc: Gilad Ben Yossef <gi...@benyossef.com>
Cc: Hakan Akkan <hakanak...@gmail.com>
Cc: Ingo Molnar <mi...@kernel.org>
Cc: Paul E. McKenney <paul...@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortma...@windriver.com>
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Steven Rostedt <rost...@goodmis.org>
Cc: Thomas Gleixner <t...@linutronix.de>
---
include/linux/sched.h | 6 +++++
include/linux/tick.h | 2 +
kernel/sched/core.c | 22 ++++++++++++++++++++-
kernel/sched/sched.h | 8 +++++++
kernel/softirq.c | 5 ++-
kernel/time/tick-sched.c | 47 ++++++++++++++++++++++++++++++++++++++++-----
6 files changed, 81 insertions(+), 9 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8a89dc6..4ffac78 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2818,6 +2818,12 @@ static inline void inc_syscw(struct task_struct *tsk)
#define TASK_SIZE_OF(tsk) TASK_SIZE
#endif
+#ifdef CONFIG_NO_HZ_FULL
+extern bool sched_can_stop_tick(void);
+#else
+static inline bool sched_can_stop_tick(void) { return false; }
+#endif
+
#ifdef CONFIG_MM_OWNER
extern void mm_update_next_owner(struct mm_struct *mm);
extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 2d4f6f0..dfb90ea 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -159,8 +159,10 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64
*unused) { return -1; }
#ifdef CONFIG_NO_HZ_FULL
int tick_nohz_full_cpu(int cpu);
+extern void tick_nohz_full_check(void);
#else
static inline int tick_nohz_full_cpu(int cpu) { return 0; }
+static inline void tick_nohz_full_check(void) { }
#endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9cbace7..9d821a3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1215,6 +1215,24 @@ static void update_avg(u64 *avg, u64 sample)
}
#endif
+#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
+
static void
ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
{
@@ -1357,7 +1375,8 @@ 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 +1393,7 @@ 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 db3d4df..f3d8f4a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -943,6 +943,14 @@ static inline u64 steal_ticks(u64 steal)
static inline void inc_nr_running(struct rq *rq)
{
rq->nr_running++;
+
+ 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);
+ }
+ }
}
static inline void dec_nr_running(struct rq *rq)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index f5cc25f..6342078 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -307,7 +307,8 @@ void irq_enter(void)
int cpu = smp_processor_id();
rcu_irq_enter();
- if (is_idle_task(current) && !in_interrupt()) {
+
+ if ((is_idle_task(current) || tick_nohz_full_cpu(cpu)) &&
!in_interrupt()) {
/*
* Prevent raise_softirq from needlessly waking up ksoftirqd
* here, as softirq will be serviced on return from interrupt.
@@ -349,7 +350,7 @@ void irq_exit(void)
#ifdef CONFIG_NO_HZ
/* Make sure that timer wheel updates are propagated */
- if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
+ if (!in_interrupt())
tick_nohz_irq_exit();
#endif
rcu_irq_exit();
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1b607bce..c057a7e 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -585,6 +585,24 @@ void tick_nohz_idle_enter(void)
local_irq_enable();
}
+static void tick_nohz_full_stop_tick(struct tick_sched *ts)
+{
+#ifdef CONFIG_NO_HZ_FULL
+ int cpu = smp_processor_id();
+
+ if (!tick_nohz_full_cpu(cpu) || is_idle_task(current))
+ return;
+
+ if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
+ return;
+
+ if (!sched_can_stop_tick())
+ return;
+
+ tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
+#endif
+}
+
/**
* tick_nohz_irq_exit - update next tick event from interrupt exit
*
@@ -597,12 +615,15 @@ void tick_nohz_irq_exit(void)
{
struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
- if (!ts->inidle)
- return;
-
- /* Cancel the timer because CPU already waken up from the C-states*/
- menu_hrtimer_cancel();
- __tick_nohz_idle_enter(ts);
+ if (ts->inidle) {
+ if (!need_resched()) {
+ /* Cancel the timer because CPU already waken up from
the C-states*/
+ menu_hrtimer_cancel();
+ __tick_nohz_idle_enter(ts);
+ }
+ } else {
+ tick_nohz_full_stop_tick(ts);
+ }
}
/**
@@ -833,6 +854,20 @@ static inline void tick_check_nohz(int cpu) { }
#endif /* NO_HZ */
+#ifdef CONFIG_NO_HZ_FULL
+void tick_nohz_full_check(void)
+{
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+ if (tick_nohz_full_cpu(smp_processor_id())) {
+ if (ts->tick_stopped && !is_idle_task(current)) {
+ if (!sched_can_stop_tick())
+ tick_nohz_restart_sched_tick(ts, ktime_get());
+ }
+ }
+}
+#endif /* CONFIG_NO_HZ_FULL */
+
/*
* Called from irq_enter to notify about the possible interruption of idle()
*/
--
1.7.5.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
