linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Frederic Weisbecker <fweisbec@gmail.com>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>,
	Alessio Igor Bogani <abogani@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Avi Kivity <avi@redhat.com>, Chris Metcalf <cmetcalf@tilera.com>,
	Christoph Lameter <cl@linux.com>,
	Geoff Levand <geoff@infradead.org>,
	Gilad Ben Yossef <gilad@benyossef.com>,
	Hakan Akkan <hakanakkan@gmail.com>,
	Ingo Molnar <mingo@kernel.org>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Paul Gortmaker <paul.gortmaker@windriver.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: [PATCH 20/24] nohz: Full dynticks mode
Date: Thu, 20 Dec 2012 19:33:07 +0100	[thread overview]
Message-ID: <1356028391-14427-21-git-send-email-fweisbec@gmail.com> (raw)
In-Reply-To: <1356028391-14427-1-git-send-email-fweisbec@gmail.com>

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 <fweisbec@gmail.com>
Cc: Alessio Igor Bogani <abogani@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
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>
---
 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


  parent reply	other threads:[~2012-12-20 18:34 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-12-20 18:32 [ANNOUNCE] 3.7-nohz1 Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 01/24] context_tracking: Add comments on interface and internals Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 02/24] cputime: Generic on-demand virtual cputime accounting Frederic Weisbecker
2012-12-21  5:11   ` Steven Rostedt
2012-12-26  8:19   ` Li Zhong
2012-12-29 13:15     ` Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 03/24] cputime: Allow dynamic switch between tick/virtual based " Frederic Weisbecker
2012-12-21 15:05   ` Steven Rostedt
2012-12-22 17:43     ` Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 04/24] cputime: Use accessors to read task cputime stats Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 05/24] cputime: Safely read cputime of full dynticks CPUs Frederic Weisbecker
2012-12-21 15:09   ` Steven Rostedt
2012-12-22 17:51     ` Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 06/24] nohz: Basic full dynticks interface Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 07/24] nohz: Assign timekeeping duty to a non-full-nohz CPU Frederic Weisbecker
2012-12-21 16:13   ` Steven Rostedt
2012-12-22 16:39     ` Frederic Weisbecker
2012-12-22 17:05       ` Steven Rostedt
2012-12-20 18:32 ` [PATCH 08/24] nohz: Trace timekeeping update Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 09/24] nohz: Wake up full dynticks CPUs when a timer gets enqueued Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 10/24] rcu: Restart the tick on non-responding full dynticks CPUs Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 11/24] sched: Comment on rq->clock correctness in ttwu_do_wakeup() in nohz Frederic Weisbecker
2012-12-20 18:32 ` [PATCH 12/24] sched: Update rq clock on nohz CPU before migrating tasks Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 13/24] sched: Update rq clock on nohz CPU before setting fair group shares Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 14/24] sched: Update rq clock on tickless CPUs before calling check_preempt_curr() Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 15/24] sched: Update rq clock earlier in unthrottle_cfs_rq Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 16/24] sched: Update clock of nohz busiest rq before balancing Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 17/24] sched: Update rq clock before idle balancing Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 18/24] sched: Update nohz rq clock before searching busiest group on load balancing Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 19/24] nohz: Move nohz load balancer selection into idle logic Frederic Weisbecker
2012-12-20 18:33 ` Frederic Weisbecker [this message]
2012-12-26  6:12   ` [PATCH 20/24] nohz: Full dynticks mode Namhyung Kim
2012-12-26  7:02     ` Namhyung Kim
2012-12-29 13:21     ` Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 21/24] nohz: Only stop the tick on RCU nocb CPUs Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 22/24] nohz: Don't turn off the tick if rcu needs it Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 23/24] nohz: Don't stop the tick if posix cpu timers are running Frederic Weisbecker
2012-12-20 18:33 ` [PATCH 24/24] nohz: Add some tracing Frederic Weisbecker
2012-12-21  2:35 ` [ANNOUNCE] 3.7-nohz1 Steven Rostedt
2012-12-23 23:43   ` Frederic Weisbecker
2012-12-30  3:56     ` Paul E. McKenney
2013-01-04 23:42       ` Frederic Weisbecker
2013-01-07 13:06         ` Paul E. McKenney
2012-12-21  5:20 ` Hakan Akkan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1356028391-14427-21-git-send-email-fweisbec@gmail.com \
    --to=fweisbec@gmail.com \
    --cc=abogani@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=avi@redhat.com \
    --cc=cl@linux.com \
    --cc=cmetcalf@tilera.com \
    --cc=geoff@infradead.org \
    --cc=gilad@benyossef.com \
    --cc=hakanakkan@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=paul.gortmaker@windriver.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).