[PATCH 2/4] time : set broadcast irq affinity

[Daniel Lezcano]

When a cpu goes to a deep idle state where its local timer is shutdown,
it notifies the time frame work to use the broadcast timer instead.

Unfortunately, the broadcast device could wake up any CPU, including an
idle one which is not concerned by the wake up at all.

This implies, in the worst case, an idle CPU will wake up to send an IPI
to another idle cpu.

This patch solves this by setting the irq affinity to the cpu concerned
by the nearest timer event, by this way, the CPU which is wake up is
guarantee to be the one concerned by the next event and we are safe with
unnecessary wakeup for another idle CPU.

As the irq affinity is not supported by all the archs, a flag is needed
to specify which clocksource can handle it.

Signed-off-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
---
 include/linux/clockchips.h   |    1 +
 kernel/time/tick-broadcast.c |   39 ++++++++++++++++++++++++++++++++-------
 2 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 6634652..c256cea 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -54,6 +54,7 @@ enum clock_event_nofitiers {
  */
 #define CLOCK_EVT_FEAT_C3STOP		0x000008
 #define CLOCK_EVT_FEAT_DUMMY		0x000010
+#define CLOCK_EVT_FEAT_DYNIRQ		0x000020
 
 /**
  * struct clock_event_device - clock event device descriptor
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 6197ac0..1f7b4f4 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -406,13 +406,36 @@ struct cpumask *tick_get_broadcast_oneshot_mask(void)
 	return to_cpumask(tick_broadcast_oneshot_mask);
 }
 
-static int tick_broadcast_set_event(struct clock_event_device *bc,
+/*
+ * Set broadcast interrupt affinity
+ */
+static void tick_broadcast_set_affinity(struct clock_event_device *bc, int cpu)
+{
+	if (!(bc->features & CLOCK_EVT_FEAT_DYNIRQ))
+		return;
+
+	if (cpumask_equal(bc->cpumask, cpumask_of(cpu)))
+		return;
+
+	bc->cpumask = cpumask_of(cpu);
+	irq_set_affinity(bc->irq, bc->cpumask);
+}
+
+static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
 				    ktime_t expires, int force)
 {
+	int ret;
+
 	if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
 		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
 
-	return clockevents_program_event(bc, expires, force);
+	ret = clockevents_program_event(bc, expires, force);
+	if (ret)
+		return ret;
+
+	tick_broadcast_set_affinity(bc, cpu);
+
+	return 0;
 }
 
 int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
@@ -441,7 +464,7 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 {
 	struct tick_device *td;
 	ktime_t now, next_event;
-	int cpu;
+	int cpu, next_cpu;
 
 	raw_spin_lock(&tick_broadcast_lock);
 again:
@@ -454,8 +477,10 @@ again:
 		td = &per_cpu(tick_cpu_device, cpu);
 		if (td->evtdev->next_event.tv64 <= now.tv64)
 			cpumask_set_cpu(cpu, to_cpumask(tmpmask));
-		else if (td->evtdev->next_event.tv64 < next_event.tv64)
+		else if (td->evtdev->next_event.tv64 < next_event.tv64) {
 			next_event.tv64 = td->evtdev->next_event.tv64;
+			next_cpu = cpu;
+		}
 	}
 
 	/*
@@ -478,7 +503,7 @@ again:
 		 * Rearm the broadcast device. If event expired,
 		 * repeat the above
 		 */
-		if (tick_broadcast_set_event(dev, next_event, 0))
+		if (tick_broadcast_set_event(dev, next_cpu, next_event, 0))
 			goto again;
 	}
 	raw_spin_unlock(&tick_broadcast_lock);
@@ -521,7 +546,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 			cpumask_set_cpu(cpu, tick_get_broadcast_oneshot_mask());
 			clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
 			if (dev->next_event.tv64 < bc->next_event.tv64)
-				tick_broadcast_set_event(bc, dev->next_event, 1);
+				tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
 		}
 	} else {
 		if (cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
@@ -590,7 +615,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 			clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
 			tick_broadcast_init_next_event(to_cpumask(tmpmask),
 						       tick_next_period);
-			tick_broadcast_set_event(bc, tick_next_period, 1);
+			tick_broadcast_set_event(bc, cpu, tick_next_period, 1);
 		} else
 			bc->next_event.tv64 = KTIME_MAX;
 	} else {
-- 
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/