1 files changed, 55 insertions, 5 deletions

diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 19ee339a1d0d..16f4830a5498 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -626,24 +626,61 @@ 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
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
  */
-void tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(unsigned long reason)
 {
 	struct clock_event_device *bc, *dev;
 	struct tick_device *td;
 	unsigned long flags;
 	ktime_t now;
-	int cpu;
+	int cpu, ret = 0;
 
 	/*
 	 * Periodic mode does not care about the enter/exit of power
 	 * states
 	 */
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-		return;
+		return 0;
 
 	/*
 	 * We are called with preemtion disabled from the depth of the
@@ -654,7 +691,7 @@ void 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;
 
@@ -662,7 +699,7 @@ void 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
@@ -675,6 +712,16 @@ void 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);
@@ -742,6 +789,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 	}
 out:
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	return ret;
 }
 
 /*
@@ -848,6 +896,8 @@ 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);
 }