From aa9b16306e3243229580ff889cc59fd66bf77973 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paul.mckenney@linaro.org>
Date: Thu, 10 May 2012 16:41:44 -0700
Subject: rcu: Precompute RCU_FAST_NO_HZ timer offsets

When a CPU is entering dyntick-idle mode, tick_nohz_stop_sched_tick()
calls rcu_needs_cpu() see if RCU needs that CPU, and, if not, computes the
next wakeup time based on the timer wheels.  Only later, when actually
entering the idle loop, rcu_prepare_for_idle() will be invoked.  In some
cases, rcu_prepare_for_idle() will post timers to wake the CPU back up.
But all for naught: The next wakeup time for the CPU has already been
computed, and posting a timer afterwards does not force that wakeup
time to be recomputed.  This means that rcu_prepare_for_idle()'s have
no effect.

This is not a problem on a busy system because something else will wake
up the CPU soon enough.  However, on lightly loaded systems, the CPU
might stay asleep for a considerable length of time.  If that CPU has
a callback that the rest of the system is waiting on, the system might
run very slowly or (in theory) even hang.

This commit avoids this problem by having rcu_needs_cpu() give
tick_nohz_stop_sched_tick() an estimate of when RCU will need the CPU
to wake back up, which tick_nohz_stop_sched_tick() takes into account
when programming the CPU's wakeup time.  An alternative approach is
for rcu_prepare_for_idle() to use hrtimers instead of normal timers,
but timers are much more efficient than are hrtimers for frequently
and repeatedly posting and cancelling a given timer, which is exactly
what RCU_FAST_NO_HZ does.

Reported-by: Pascal Chapperon <pascal.chapperon@wanadoo.fr>
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Tested-by: Pascal Chapperon <pascal.chapperon@wanadoo.fr>
---
 kernel/time/tick-sched.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'kernel/time')

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6a3a5b9ff561..52f5ebbd443b 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -274,6 +274,7 @@ EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 {
 	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
+	unsigned long rcu_delta_jiffies;
 	ktime_t last_update, expires, now;
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 	u64 time_delta;
@@ -322,7 +323,7 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 		time_delta = timekeeping_max_deferment();
 	} while (read_seqretry(&xtime_lock, seq));
 
-	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
+	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
 	    arch_needs_cpu(cpu)) {
 		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
@@ -330,6 +331,10 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 		/* Get the next timer wheel timer */
 		next_jiffies = get_next_timer_interrupt(last_jiffies);
 		delta_jiffies = next_jiffies - last_jiffies;
+		if (rcu_delta_jiffies < delta_jiffies) {
+			next_jiffies = last_jiffies + rcu_delta_jiffies;
+			delta_jiffies = rcu_delta_jiffies;
+		}
 	}
 	/*
 	 * Do not stop the tick, if we are only one off
-- 
cgit v1.2.3