tick: Introduce hrtimer based broadcast

On some architectures, in certain CPU deep idle states the local timers stop.
An external clock device is used to wakeup these CPUs. The kernel support for the
wakeup of these CPUs is provided by the tick broadcast framework by using the
external clock device as the wakeup source.

However not all implementations of architectures provide such an external
clock device. This patch includes support in the broadcast framework to handle
the wakeup of the CPUs in deep idle states on such systems by queuing a hrtimer
on one of the CPUs, which is meant to handle the wakeup of CPUs in deep idle states.

This patchset introduces a pseudo clock device which can be registered by the
archs as tick_broadcast_device in the absence of a real external clock
device. Once registered, the broadcast framework will work as is for these
architectures as long as the archs take care of the BROADCAST_ENTER
notification failing for one of the CPUs. This CPU is made the stand by CPU to
handle wakeup of the CPUs in deep idle and it *must not enter deep idle states*.

The CPU with the earliest wakeup is chosen to be this CPU. Hence this way the
stand by CPU dynamically moves around and so does the hrtimer which is queued
to trigger at the next earliest wakeup time. This is consistent with the case where
an external clock device is present. The smp affinity of this clock device is
set to the CPU with the earliest wakeup. This patchset handles the hotplug of
the stand by CPU as well by moving the hrtimer on to the CPU handling the CPU_DEAD
notification.

Originally-from: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: deepthi@linux.vnet.ibm.com
Cc: paulmck@linux.vnet.ibm.com
Cc: fweisbec@gmail.com
Cc: paulus@samba.org
Cc: srivatsa.bhat@linux.vnet.ibm.com
Cc: svaidy@linux.vnet.ibm.com
Cc: peterz@infradead.org
Cc: benh@kernel.crashing.org
Cc: rafael.j.wysocki@intel.com
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/20140207080632.17187.80532.stgit@preeti.in.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 51 insertions, 3 deletions

diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 84c8fd91d744..63c7b2d9ed8e 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -643,6 +643,42 @@ again:
 	raw_spin_unlock(&tick_broadcast_lock);
 }
 
+static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
+{
+	if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+		return 0;
+	if (bc->next_event.tv64 == KTIME_MAX)
+		return 0;
+	return bc->bound_on == cpu ? -EBUSY : 0;
+}
+
+static void broadcast_shutdown_local(struct clock_event_device *bc,
+				     struct clock_event_device *dev)
+{
+	/*
+	 * For hrtimer based broadcasting we cannot shutdown the cpu
+	 * local device if our own event is the first one to expire or
+	 * if we own the broadcast timer.
+	 */
+	if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
+		if (broadcast_needs_cpu(bc, smp_processor_id()))
+			return;
+		if (dev->next_event.tv64 < bc->next_event.tv64)
+			return;
+	}
+	clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+}
+
+static void broadcast_move_bc(int deadcpu)
+{
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+	if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+		return;
+	/* This moves the broadcast assignment to this cpu */
+	clockevents_program_event(bc, bc->next_event, 1);
+}
+
 /*
  * Powerstate information: The system enters/leaves a state, where
  * affected devices might stop
@@ -661,7 +697,7 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 	 * states
 	 */
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-		return;
+		return 0;
 
 	/*
 	 * We are called with preemtion disabled from the depth of the
@@ -672,7 +708,7 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 	dev = td->evtdev;
 
 	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return;
+		return 0;
 
 	bc = tick_broadcast_device.evtdev;
 
@@ -680,7 +716,7 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 	if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
-			clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+			broadcast_shutdown_local(bc, dev);
 			/*
 			 * We only reprogram the broadcast timer if we
 			 * did not mark ourself in the force mask and
@@ -693,6 +729,16 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 			    dev->next_event.tv64 < bc->next_event.tv64)
 				tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
 		}
+		/*
+		 * If the current CPU owns the hrtimer broadcast
+		 * mechanism, it cannot go deep idle and we remove the
+		 * CPU from the broadcast mask. We don't have to go
+		 * through the EXIT path as the local timer is not
+		 * shutdown.
+		 */
+		ret = broadcast_needs_cpu(bc, cpu);
+		if (ret)
+			cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	} else {
 		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
@@ -866,6 +912,8 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
 	cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
 
+	broadcast_move_bc(cpu);
+
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }