[PATCH] tick-management: core functionality

With Ingo Molnar <mingo@elte.hu>

The tick-management code is the first user of the clockevents layer.  It takes
clock event devices from the clock events core and uses them to provide the
periodic tick.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 279 insertions, 1 deletions

diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 2bf1805914d..337daef7275 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,3 +1,4 @@
 obj-y += ntp.o clocksource.o jiffies.o
 
-obj-$(CONFIG_GENERIC_CLOCKEVENTS) += clockevents.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS)	+= clockevents.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS)	+= tick-common.o
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
new file mode 100644
index 00000000000..46e4381c26e
--- /dev/null
+++ b/kernel/time/tick-common.c
@@ -0,0 +1,277 @@
+/*
+ * linux/kernel/time/tick-common.c
+ *
+ * This file contains the base functions to manage periodic tick
+ * related events.
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/irq.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+
+/*
+ * Tick devices
+ */
+static DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
+/*
+ * Tick next event: keeps track of the tick time
+ */
+static ktime_t tick_next_period;
+static ktime_t tick_period;
+static int tick_do_timer_cpu = -1;
+static DEFINE_SPINLOCK(tick_device_lock);
+
+/*
+ * Periodic tick
+ */
+static void tick_periodic(int cpu)
+{
+	if (tick_do_timer_cpu == cpu) {
+		write_seqlock(&xtime_lock);
+
+		/* Keep track of the next tick event */
+		tick_next_period = ktime_add(tick_next_period, tick_period);
+
+		do_timer(1);
+		write_sequnlock(&xtime_lock);
+	}
+
+	update_process_times(user_mode(get_irq_regs()));
+	profile_tick(CPU_PROFILING);
+}
+
+/*
+ * Event handler for periodic ticks
+ */
+void tick_handle_periodic(struct clock_event_device *dev)
+{
+	int cpu = smp_processor_id();
+
+	tick_periodic(cpu);
+
+	if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
+		return;
+	/*
+	 * Setup the next period for devices, which do not have
+	 * periodic mode:
+	 */
+	for (;;) {
+		ktime_t next = ktime_add(dev->next_event, tick_period);
+
+		if (!clockevents_program_event(dev, next, ktime_get()))
+			return;
+		tick_periodic(cpu);
+	}
+}
+
+/*
+ * Setup the device for a periodic tick
+ */
+void tick_setup_periodic(struct clock_event_device *dev)
+{
+	dev->event_handler = tick_handle_periodic;
+
+	if (dev->features & CLOCK_EVT_FEAT_PERIODIC) {
+		clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
+	} else {
+		unsigned long seq;
+		ktime_t next;
+
+		do {
+			seq = read_seqbegin(&xtime_lock);
+			next = tick_next_period;
+		} while (read_seqretry(&xtime_lock, seq));
+
+		clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+
+		for (;;) {
+			if (!clockevents_program_event(dev, next, ktime_get()))
+				return;
+			next = ktime_add(next, tick_period);
+		}
+	}
+}
+
+/*
+ * Setup the tick device
+ */
+static void tick_setup_device(struct tick_device *td,
+			      struct clock_event_device *newdev, int cpu,
+			      cpumask_t cpumask)
+{
+	ktime_t next_event;
+	void (*handler)(struct clock_event_device *) = NULL;
+
+	/*
+	 * First device setup ?
+	 */
+	if (!td->evtdev) {
+		/*
+		 * If no cpu took the do_timer update, assign it to
+		 * this cpu:
+		 */
+		if (tick_do_timer_cpu == -1) {
+			tick_do_timer_cpu = cpu;
+			tick_next_period = ktime_get();
+			tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
+		}
+
+		/*
+		 * Startup in periodic mode first.
+		 */
+		td->mode = TICKDEV_MODE_PERIODIC;
+	} else {
+		handler = td->evtdev->event_handler;
+		next_event = td->evtdev->next_event;
+	}
+
+	td->evtdev = newdev;
+
+	/*
+	 * When the device is not per cpu, pin the interrupt to the
+	 * current cpu:
+	 */
+	if (!cpus_equal(newdev->cpumask, cpumask))
+		irq_set_affinity(newdev->irq, cpumask);
+
+	if (td->mode == TICKDEV_MODE_PERIODIC)
+		tick_setup_periodic(newdev, 0);
+}
+
+/*
+ * Check, if the new registered device should be used.
+ */
+static int tick_check_new_device(struct clock_event_device *newdev)
+{
+	struct clock_event_device *curdev;
+	struct tick_device *td;
+	int cpu, ret = NOTIFY_OK;
+	unsigned long flags;
+	cpumask_t cpumask;
+
+	spin_lock_irqsave(&tick_device_lock, flags);
+
+	cpu = smp_processor_id();
+	if (!cpu_isset(cpu, newdev->cpumask))
+		goto out;
+
+	td = &per_cpu(tick_cpu_device, cpu);
+	curdev = td->evtdev;
+	cpumask = cpumask_of_cpu(cpu);
+
+	/* cpu local device ? */
+	if (!cpus_equal(newdev->cpumask, cpumask)) {
+
+		/*
+		 * If the cpu affinity of the device interrupt can not
+		 * be set, ignore it.
+		 */
+		if (!irq_can_set_affinity(newdev->irq))
+			goto out_bc;
+
+		/*
+		 * If we have a cpu local device already, do not replace it
+		 * by a non cpu local device
+		 */
+		if (curdev && cpus_equal(curdev->cpumask, cpumask))
+			goto out_bc;
+	}
+
+	/*
+	 * If we have an active device, then check the rating and the oneshot
+	 * feature.
+	 */
+	if (curdev) {
+		/*
+		 * Check the rating
+		 */
+		if (curdev->rating >= newdev->rating)
+			goto out;
+	}
+
+	/*
+	 * Replace the eventually existing device by the new
+	 * device.
+	 */
+	clockevents_exchange_device(curdev, newdev);
+	tick_setup_device(td, newdev, cpu, cpumask);
+	ret = NOTIFY_STOP;
+
+out:
+	spin_unlock_irqrestore(&tick_device_lock, flags);
+	return ret;
+}
+
+/*
+ * Shutdown an event device on a given cpu:
+ *
+ * This is called on a life CPU, when a CPU is dead. So we cannot
+ * access the hardware device itself.
+ * We just set the mode and remove it from the lists.
+ */
+static void tick_shutdown(unsigned int *cpup)
+{
+	struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
+	struct clock_event_device *dev = td->evtdev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tick_device_lock, flags);
+	td->mode = TICKDEV_MODE_PERIODIC;
+	if (dev) {
+		/*
+		 * Prevent that the clock events layer tries to call
+		 * the set mode function!
+		 */
+		dev->mode = CLOCK_EVT_MODE_UNUSED;
+		clockevents_exchange_device(dev, NULL);
+		td->evtdev = NULL;
+	}
+	spin_unlock_irqrestore(&tick_device_lock, flags);
+}
+
+/*
+ * Notification about clock event devices
+ */
+static int tick_notify(struct notifier_block *nb, unsigned long reason,
+			       void *dev)
+{
+	switch (reason) {
+
+	case CLOCK_EVT_NOTIFY_ADD:
+		return tick_check_new_device(dev);
+
+	case CLOCK_EVT_NOTIFY_CPU_DEAD:
+		tick_shutdown(dev);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block tick_notifier = {
+	.notifier_call = tick_notify,
+};
+
+/**
+ * tick_init - initialize the tick control
+ *
+ * Register the notifier with the clockevents framework
+ */
+void __init tick_init(void)
+{
+	clockevents_register_notifier(&tick_notifier);
+}