From 7a14ce1d8c1d3a6118d406e64eaf9aa70375e085 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 12 May 2008 15:43:53 +0200
Subject: nohz: reduce jiffies polling overhead
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/time/tick-sched.c | 7 +++++++
1 file changed, 7 insertions(+)
(limited to 'kernel/time')
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b854a89..cb75394 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -48,6 +48,13 @@ static void tick_do_update_jiffies64(ktime_t now)
unsigned long ticks = 0;
ktime_t delta;
+ /*
+ * Do a quick check without holding xtime_lock:
+ */
+ delta = ktime_sub(now, last_jiffies_update);
+ if (delta.tv64 < tick_period.tv64)
+ return;
+
/* Reevalute with xtime_lock held */
write_seqlock(&xtime_lock);
--
cgit v1.1
From 8691e5a8f691cc2a4fda0651e8d307aaba0e7d68 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Fri, 6 Jun 2008 11:18:06 +0200
Subject: smp_call_function: get rid of the unused nonatomic/retry argument
It's never used and the comments refer to nonatomic and retry
interchangably. So get rid of it.
Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
kernel/time/tick-broadcast.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'kernel/time')
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 57a1f02..75e7185 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -266,7 +266,7 @@ void tick_broadcast_on_off(unsigned long reason, int *oncpu)
"offline CPU #%d\n", *oncpu);
else
smp_call_function_single(*oncpu, tick_do_broadcast_on_off,
- &reason, 1, 1);
+ &reason, 1);
}
/*
--
cgit v1.1
From aa276e1cafb3ce9d01d1e837bcd67e92616013ac Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 Jun 2008 19:15:00 +0200
Subject: x86, clockevents: add C1E aware idle function
C1E on AMD machines is like C3 but without control from the OS. Up to
now we disabled the local apic timer for those machines as it stops
when the CPU goes into C1E. This excludes those machines from high
resolution timers / dynamic ticks, which hurts especially X2 based
laptops.
The current boot time C1E detection has another, more serious flaw
as well: some BIOSes do not enable C1E until the ACPI processor module
is loaded. This causes systems to stop working after that point.
To work nicely with C1E enabled machines we use a separate idle
function, which checks on idle entry whether C1E was enabled in the
Interrupt Pending Message MSR. This allows us to do timer broadcasting
for C1E and covers the late enablement of C1E as well.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/time/tick-broadcast.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
(limited to 'kernel/time')
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 57a1f02..67f80c2 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -30,6 +30,7 @@
struct tick_device tick_broadcast_device;
static cpumask_t tick_broadcast_mask;
static DEFINE_SPINLOCK(tick_broadcast_lock);
+static int tick_broadcast_force;
#ifdef CONFIG_TICK_ONESHOT
static void tick_broadcast_clear_oneshot(int cpu);
@@ -232,10 +233,11 @@ static void tick_do_broadcast_on_off(void *why)
CLOCK_EVT_MODE_SHUTDOWN);
}
if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
- dev->features |= CLOCK_EVT_FEAT_DUMMY;
+ tick_broadcast_force = 1;
break;
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
- if (cpu_isset(cpu, tick_broadcast_mask)) {
+ if (!tick_broadcast_force &&
+ cpu_isset(cpu, tick_broadcast_mask)) {
cpu_clear(cpu, tick_broadcast_mask);
if (td->mode == TICKDEV_MODE_PERIODIC)
tick_setup_periodic(dev, 0);
--
cgit v1.1
From 857f3fd7a496ddf4329345af65a4a2b16dd25fe8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 11 Jul 2008 11:09:22 +0200
Subject: nohz: don't stop idle tick if softirqs are pending.
In case a cpu goes idle but softirqs are pending only an error message is
printed to the console. It may take a very long time until the pending
softirqs will finally be executed. Worst case would be a hanging system.
With this patch the timer tick just continues and the softirqs will be
executed after the next interrupt. Still a delay but better than a
hanging system.
Currently we have at least two device drivers on s390 which under certain
circumstances schedule a tasklet from process context. This is a reason
why we can end up with pending softirqs when going idle. Fixing these
drivers seems to be non-trivial.
However there is no question that the drivers should be fixed.
This patch shouldn't be considered as a bug fix. It just is intended to
keep a system running even if device drivers are buggy.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jan Glauber <jan.glauber@de.ibm.com>
Cc: Stefan Weinhuber <wein@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/time/tick-sched.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'kernel/time')
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index cb75394..86baa4f 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -235,6 +235,7 @@ void tick_nohz_stop_sched_tick(void)
local_softirq_pending());
ratelimit++;
}
+ goto end;
}
ts->idle_calls++;
--
cgit v1.1
From af52a90a14cdaa54ecbfb6e6982abb13466a4b56 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 7 Jul 2008 14:16:52 -0400
Subject: sched_clock: stop maximum check on NO HZ
Working with ftrace I would get large jumps of 11 millisecs or more with
the clock tracer. This killed the latencing timings of ftrace and also
caused the irqoff self tests to fail.
What was happening is with NO_HZ the idle would stop the jiffy counter and
before the jiffy counter was updated the sched_clock would have a bad
delta jiffies to compare with the gtod with the maximum.
The jiffies would stop and the last sched_tick would record the last gtod.
On wakeup, the sched clock update would compare the gtod + delta jiffies
(which would be zero) and compare it to the TSC. The TSC would have
correctly (with a stable TSC) moved forward several jiffies. But because the
jiffies has not been updated yet the clock would be prevented from moving
forward because it would appear that the TSC jumped too far ahead.
The clock would then virtually stop, until the jiffies are updated. Then
the next sched clock update would see that the clock was very much behind
since the delta jiffies is now correct. This would then jump the clock
forward by several jiffies.
This caused ftrace to report several milliseconds of interrupts off
latency at every resume from NO_HZ idle.
This patch adds hooks into the nohz code to disable the checking of the
maximum clock update when nohz is in effect. It resumes the max check
when nohz has updated the jiffies again.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/time/tick-sched.c | 2 ++
1 file changed, 2 insertions(+)
(limited to 'kernel/time')
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b854a89..d63008b 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -276,6 +276,7 @@ void tick_nohz_stop_sched_tick(void)
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
rcu_enter_nohz();
+ sched_clock_tick_stop(cpu);
}
/*
@@ -375,6 +376,7 @@ void tick_nohz_restart_sched_tick(void)
select_nohz_load_balancer(0);
now = ktime_get();
tick_do_update_jiffies64(now);
+ sched_clock_tick_start(cpu);
cpu_clear(cpu, nohz_cpu_mask);
/*
--
cgit v1.1