clockevents: Cleanup dead cpu explicitely

clockevents_notify() is a leftover from the early design of the
clockevents facility. It's really not a notification mechanism,
it's a multiplex call. We are way better off to have explicit
calls instead of this monstrosity.

Split out the cleanup function for a dead cpu and invoke it
directly from the cpu down code. Make it conditional on
CPU_HOTPLUG as well.

Temporary change, will be refined in the future.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[ Rebased, added clockevents_notify() removal ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1735025.raBZdQHM3m@vostro.rjw.lan
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/clockchips.h

@@ -8,12 +8,6 @@
 #ifndef _LINUX_CLOCKCHIPS_H
 #define _LINUX_CLOCKCHIPS_H
 
-/* Clock event notification values */
-enum clock_event_nofitiers {
-	CLOCK_EVT_NOTIFY_ADD,
-	CLOCK_EVT_NOTIFY_CPU_DEAD,
-};
-
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
 # include <linux/clocksource.h>

include/linux/tick.h

@@ -20,6 +20,7 @@ extern void tick_suspend_local(void);
 /* Should be core only, but XEN resume magic and ARM BL switcher require it */
 extern void tick_resume_local(void);
 extern void tick_handover_do_timer(void);
+extern void tick_cleanup_dead_cpu(int cpu);
 #else /* CONFIG_GENERIC_CLOCKEVENTS */
 static inline void tick_init(void) { }
 static inline void tick_freeze(void) { }
@@ -27,6 +28,7 @@ static inline void tick_unfreeze(void) { }
 static inline void tick_suspend_local(void) { }
 static inline void tick_resume_local(void) { }
 static inline void tick_handover_do_timer(void) { }
+static inline void tick_cleanup_dead_cpu(int cpu) { }
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
 #ifdef CONFIG_TICK_ONESHOT

kernel/cpu.c

@@ -419,6 +419,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	__cpu_die(cpu);
 
 	/* CPU is completely dead: tell everyone.  Too late to complain. */
+	tick_cleanup_dead_cpu(cpu);
 	cpu_notify_nofail(CPU_DEAD | mod, hcpu);
 
 	check_for_tasks(cpu);

kernel/time/clockevents.c

@@ -642,23 +642,20 @@ void clockevents_resume(void)
 			dev->resume(dev);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /**
- * clockevents_notify - notification about relevant events
+ * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu
- * Returns 0 on success, any other value on error
  */
-int clockevents_notify(unsigned long reason, void *arg)
+void tick_cleanup_dead_cpu(int cpu)
 {
 	struct clock_event_device *dev, *tmp;
 	unsigned long flags;
-	int cpu, ret = 0;
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
-	switch (reason) {
+	tick_shutdown_broadcast_oneshot(cpu);
-	case CLOCK_EVT_NOTIFY_CPU_DEAD:
+	tick_shutdown_broadcast(cpu);
-		tick_shutdown_broadcast_oneshot(arg);
+	tick_shutdown(cpu);
-		tick_shutdown_broadcast(arg);
-		tick_shutdown(arg);
 	/*
 	 * Unregister the clock event devices which were
 	 * released from the users in the notify chain.
@@ -668,7 +665,6 @@ int clockevents_notify(unsigned long reason, void *arg)
 	/*
 	 * Now check whether the CPU has left unused per cpu devices
 	 */
-		cpu = *((int *)arg);
 	list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) {
 		if (cpumask_test_cpu(cpu, dev->cpumask) &&
 		    cpumask_weight(dev->cpumask) == 1 &&
@@ -677,14 +673,9 @@ int clockevents_notify(unsigned long reason, void *arg)
 			list_del(&dev->list);
 		}
 	}
-		break;
-	default:
-		break;
-	}
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
-	return ret;
 }
-EXPORT_SYMBOL_GPL(clockevents_notify);
+#endif
 
 #ifdef CONFIG_SYSFS
 struct bus_type clockevents_subsys = {

kernel/time/hrtimer.c

@@ -1709,11 +1709,8 @@ static int hrtimer_cpu_notify(struct notifier_block *self,
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-	{
-		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
 		migrate_hrtimers(scpu);
 		break;
-	}
 #endif
 
 	default:

kernel/time/tick-broadcast.c

@@ -410,14 +410,14 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
 		dev->event_handler = tick_handle_periodic_broadcast;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * Remove a CPU from broadcasting
  */
-void tick_shutdown_broadcast(unsigned int *cpup)
+void tick_shutdown_broadcast(unsigned int cpu)
 {
 	struct clock_event_device *bc;
 	unsigned long flags;
-	unsigned int cpu = *cpup;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -432,6 +432,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
+#endif
 
 void tick_suspend_broadcast(void)
 {
@@ -672,21 +673,6 @@ static void broadcast_shutdown_local(struct clock_event_device *bc,
 	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 }
 
-void hotplug_cpu__broadcast_tick_pull(int deadcpu)
-{
-	struct clock_event_device *bc;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-	bc = tick_broadcast_device.evtdev;
-
-	if (bc && broadcast_needs_cpu(bc, deadcpu)) {
-		/* This moves the broadcast assignment to this CPU: */
-		clockevents_program_event(bc, bc->next_event, 1);
-	}
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
-}
-
 /**
  * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
  * @state:	The target state (enter/exit)
@@ -908,14 +894,28 @@ void tick_broadcast_switch_to_oneshot(void)
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+void hotplug_cpu__broadcast_tick_pull(int deadcpu)
+{
+	struct clock_event_device *bc;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+	bc = tick_broadcast_device.evtdev;
+
+	if (bc && broadcast_needs_cpu(bc, deadcpu)) {
+		/* This moves the broadcast assignment to this CPU: */
+		clockevents_program_event(bc, bc->next_event, 1);
+	}
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
 
 /*
  * Remove a dead CPU from broadcasting
  */
-void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
+void tick_shutdown_broadcast_oneshot(unsigned int cpu)
 {
 	unsigned long flags;
-	unsigned int cpu = *cpup;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -929,6 +929,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
+#endif
 
 /*
  * Check, whether the broadcast device is in one shot mode

kernel/time/tick-common.c

@@ -348,7 +348,6 @@ void tick_handover_do_timer(void)
 			TICK_DO_TIMER_NONE;
 	}
 }
-#endif
 
 /*
  * Shutdown an event device on a given cpu:
@@ -357,9 +356,9 @@ void tick_handover_do_timer(void)
  * access the hardware device itself.
  * We just set the mode and remove it from the lists.
  */
-void tick_shutdown(unsigned int *cpup)
+void tick_shutdown(unsigned int cpu)
 {
-	struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
+	struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
 	struct clock_event_device *dev = td->evtdev;
 
 	td->mode = TICKDEV_MODE_PERIODIC;
@@ -375,6 +374,7 @@ void tick_shutdown(unsigned int *cpup)
 		td->evtdev = NULL;
 	}
 }
+#endif
 
 /**
  * tick_suspend_local - Suspend the local tick device

kernel/time/tick-internal.h

@@ -20,7 +20,7 @@ extern int tick_do_timer_cpu __read_mostly;
 extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
 extern void tick_handle_periodic(struct clock_event_device *dev);
 extern void tick_check_new_device(struct clock_event_device *dev);
-extern void tick_shutdown(unsigned int *cpup);
+extern void tick_shutdown(unsigned int cpu);
 extern void tick_suspend(void);
 extern void tick_resume(void);
 extern bool tick_check_replacement(struct clock_event_device *curdev,
@@ -52,7 +52,7 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
 extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
 extern void tick_install_broadcast_device(struct clock_event_device *dev);
 extern int tick_is_broadcast_device(struct clock_event_device *dev);
-extern void tick_shutdown_broadcast(unsigned int *cpup);
+extern void tick_shutdown_broadcast(unsigned int cpu);
 extern void tick_suspend_broadcast(void);
 extern void tick_resume_broadcast(void);
 extern bool tick_resume_check_broadcast(void);
@@ -66,7 +66,7 @@ static inline void tick_install_broadcast_device(struct clock_event_device *dev)
 static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; }
 static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; }
 static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
-static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
+static inline void tick_shutdown_broadcast(unsigned int cpu) { }
 static inline void tick_suspend_broadcast(void) { }
 static inline void tick_resume_broadcast(void) { }
 static inline bool tick_resume_check_broadcast(void) { return false; }
@@ -117,7 +117,7 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
 #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
 extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
 extern void tick_broadcast_switch_to_oneshot(void);
-extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
+extern void tick_shutdown_broadcast_oneshot(unsigned int cpu);
 extern int tick_broadcast_oneshot_active(void);
 extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
@@ -125,7 +125,7 @@ extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
 #else /* !(BROADCAST && ONESHOT): */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
-static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
 static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }