1 files changed, 278 insertions, 71 deletions

diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 64522ecdfe0e..7e33d3f2e889 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -1,24 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * 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/compiler.h>
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/hrtimer.h>
 #include <linux/interrupt.h>
+#include <linux/nmi.h>
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/module.h>
+#include <trace/events/power.h>
 
 #include <asm/irq_regs.h>
 
@@ -29,11 +28,35 @@
  */
 DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
 /*
- * Tick next event: keeps track of the tick time
+ * Tick next event: keeps track of the tick time. It's updated by the
+ * CPU which handles the tick and protected by jiffies_lock. There is
+ * no requirement to write hold the jiffies seqcount for it.
  */
 ktime_t tick_next_period;
-ktime_t tick_period;
+
+/*
+ * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
+ * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
+ * variable has two functions:
+ *
+ * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
+ *    timekeeping lock all at once. Only the CPU which is assigned to do the
+ *    update is handling it.
+ *
+ * 2) Hand off the duty in the NOHZ idle case by setting the value to
+ *    TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
+ *    at it will take over and keep the time keeping alive.  The handover
+ *    procedure also covers cpu hotplug.
+ */
 int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
+#ifdef CONFIG_NO_HZ_FULL
+/*
+ * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns
+ * tick_do_timer_cpu and it should be taken over by an eligible secondary
+ * when one comes online.
+ */
+static int tick_do_timer_boot_cpu __read_mostly = -1;
+#endif
 
 /*
  * Debugging: see timer_list.c
@@ -62,14 +85,17 @@ int tick_is_oneshot_available(void)
  */
 static void tick_periodic(int cpu)
 {
-	if (tick_do_timer_cpu == cpu) {
-		write_seqlock(&jiffies_lock);
+	if (READ_ONCE(tick_do_timer_cpu) == cpu) {
+		raw_spin_lock(&jiffies_lock);
+		write_seqcount_begin(&jiffies_seq);
 
 		/* Keep track of the next tick event */
-		tick_next_period = ktime_add(tick_next_period, tick_period);
+		tick_next_period = ktime_add_ns(tick_next_period, TICK_NSEC);
 
 		do_timer(1);
-		write_sequnlock(&jiffies_lock);
+		write_seqcount_end(&jiffies_seq);
+		raw_spin_unlock(&jiffies_lock);
+		update_wall_time();
 	}
 
 	update_process_times(user_mode(get_irq_regs()));
@@ -82,18 +108,27 @@ static void tick_periodic(int cpu)
 void tick_handle_periodic(struct clock_event_device *dev)
 {
 	int cpu = smp_processor_id();
-	ktime_t next;
+	ktime_t next = dev->next_event;
 
 	tick_periodic(cpu);
 
-	if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
-		return;
 	/*
-	 * Setup the next period for devices, which do not have
-	 * periodic mode:
+	 * The cpu might have transitioned to HIGHRES or NOHZ mode via
+	 * update_process_times() -> run_local_timers() ->
+	 * hrtimer_run_queues().
 	 */
-	next = ktime_add(dev->next_event, tick_period);
+	if (IS_ENABLED(CONFIG_TICK_ONESHOT) && dev->event_handler != tick_handle_periodic)
+		return;
+
+	if (!clockevent_state_oneshot(dev))
+		return;
 	for (;;) {
+		/*
+		 * Setup the next period for devices, which do not have
+		 * periodic mode:
+		 */
+		next = ktime_add_ns(next, TICK_NSEC);
+
 		if (!clockevents_program_event(dev, next, false))
 			return;
 		/*
@@ -102,12 +137,11 @@ void tick_handle_periodic(struct clock_event_device *dev)
 		 * to be sure we're using a real hardware clocksource.
 		 * Otherwise we could get trapped in an infinite
 		 * loop, as the tick_periodic() increments jiffies,
-		 * when then will increment time, posibly causing
+		 * which then will increment time, possibly causing
 		 * the loop to trigger again and again.
 		 */
 		if (timekeeping_valid_for_hres())
 			tick_periodic(cpu);
-		next = ktime_add(next, tick_period);
 	}
 }
 
@@ -124,22 +158,22 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 
 	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
 	    !tick_broadcast_oneshot_active()) {
-		clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
 	} else {
-		unsigned long seq;
+		unsigned int seq;
 		ktime_t next;
 
 		do {
-			seq = read_seqbegin(&jiffies_lock);
+			seq = read_seqcount_begin(&jiffies_seq);
 			next = tick_next_period;
-		} while (read_seqretry(&jiffies_lock, seq));
+		} while (read_seqcount_retry(&jiffies_seq, seq));
 
-		clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 
 		for (;;) {
 			if (!clockevents_program_event(dev, next, false))
 				return;
-			next = ktime_add(next, tick_period);
+			next = ktime_add_ns(next, TICK_NSEC);
 		}
 	}
 }
@@ -151,8 +185,8 @@ static void tick_setup_device(struct tick_device *td,
 			      struct clock_event_device *newdev, int cpu,
 			      const struct cpumask *cpumask)
 {
-	ktime_t next_event;
 	void (*handler)(struct clock_event_device *) = NULL;
+	ktime_t next_event = 0;
 
 	/*
 	 * First device setup ?
@@ -162,13 +196,31 @@ static void tick_setup_device(struct tick_device *td,
 		 * If no cpu took the do_timer update, assign it to
 		 * this cpu:
 		 */
-		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
-			if (!tick_nohz_full_cpu(cpu))
-				tick_do_timer_cpu = cpu;
-			else
-				tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+		if (READ_ONCE(tick_do_timer_cpu) == TICK_DO_TIMER_BOOT) {
+			WRITE_ONCE(tick_do_timer_cpu, cpu);
 			tick_next_period = ktime_get();
-			tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
+#ifdef CONFIG_NO_HZ_FULL
+			/*
+			 * The boot CPU may be nohz_full, in which case the
+			 * first housekeeping secondary will take do_timer()
+			 * from it.
+			 */
+			if (tick_nohz_full_cpu(cpu))
+				tick_do_timer_boot_cpu = cpu;
+
+		} else if (tick_do_timer_boot_cpu != -1 && !tick_nohz_full_cpu(cpu)) {
+			tick_do_timer_boot_cpu = -1;
+			/*
+			 * The boot CPU will stay in periodic (NOHZ disabled)
+			 * mode until clocksource_done_booting() called after
+			 * smp_init() selects a high resolution clocksource and
+			 * timekeeping_notify() kicks the NOHZ stuff alive.
+			 *
+			 * So this WRITE_ONCE can only race with the READ_ONCE
+			 * check in tick_periodic() but this race is harmless.
+			 */
+			WRITE_ONCE(tick_do_timer_cpu, cpu);
+#endif
 		}
 
 		/*
@@ -208,7 +260,7 @@ static void tick_setup_device(struct tick_device *td,
 
 void tick_install_replacement(struct clock_event_device *newdev)
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	int cpu = smp_processor_id();
 
 	clockevents_exchange_device(td->evtdev, newdev);
@@ -260,7 +312,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
 bool tick_check_replacement(struct clock_event_device *curdev,
 			    struct clock_event_device *newdev)
 {
-	if (tick_check_percpu(curdev, newdev, smp_processor_id()))
+	if (!tick_check_percpu(curdev, newdev, smp_processor_id()))
 		return false;
 
 	return tick_check_preferred(curdev, newdev);
@@ -277,18 +329,10 @@ void tick_check_new_device(struct clock_event_device *newdev)
 	int cpu;
 
 	cpu = smp_processor_id();
-	if (!cpumask_test_cpu(cpu, newdev->cpumask))
-		goto out_bc;
-
 	td = &per_cpu(tick_cpu_device, cpu);
 	curdev = td->evtdev;
 
-	/* cpu local device ? */
-	if (!tick_check_percpu(curdev, newdev, cpu))
-		goto out_bc;
-
-	/* Preference decision */
-	if (!tick_check_preferred(curdev, newdev))
+	if (!tick_check_replacement(curdev, newdev))
 		goto out_bc;
 
 	if (!try_module_get(newdev->owner))
@@ -313,70 +357,232 @@ out_bc:
 	/*
 	 * Can the new device be used as a broadcast device ?
 	 */
-	tick_install_broadcast_device(newdev);
+	tick_install_broadcast_device(newdev, cpu);
 }
 
-/*
- * Transfer the do_timer job away from a dying cpu.
+/**
+ * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
+ * @state:	The target state (enter/exit)
+ *
+ * The system enters/leaves a state, where affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
  *
- * Called with interrupts disabled.
+ * Called with interrupts disabled, so clockevents_lock is not
+ * required here because the local clock event device cannot go away
+ * under us.
  */
-void tick_handover_do_timer(int *cpup)
+int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 {
-	if (*cpup == tick_do_timer_cpu) {
-		int cpu = cpumask_first(cpu_online_mask);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 
-		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
-			TICK_DO_TIMER_NONE;
-	}
+	if (!(td->evtdev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 0;
+
+	return __tick_broadcast_oneshot_control(state);
 }
+EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
 
+#ifdef CONFIG_HOTPLUG_CPU
+void tick_assert_timekeeping_handover(void)
+{
+	WARN_ON_ONCE(tick_do_timer_cpu == smp_processor_id());
+}
 /*
- * Shutdown an event device on a given cpu:
+ * Stop the tick and transfer the timekeeping job away from a dying cpu.
+ */
+int tick_cpu_dying(unsigned int dying_cpu)
+{
+	/*
+	 * If the current CPU is the timekeeper, it's the only one that can
+	 * safely hand over its duty. Also all online CPUs are in stop
+	 * machine, guaranteed not to be idle, therefore there is no
+	 * concurrency and it's safe to pick any online successor.
+	 */
+	if (tick_do_timer_cpu == dying_cpu)
+		tick_do_timer_cpu = cpumask_first(cpu_online_mask);
+
+	/* Make sure the CPU won't try to retake the timekeeping duty */
+	tick_sched_timer_dying(dying_cpu);
+
+	/* Remove CPU from timer broadcasting */
+	tick_offline_cpu(dying_cpu);
+
+	return 0;
+}
+
+/*
+ * Shutdown an event device on the outgoing 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.
+ * Called by the dying CPU during teardown, with clockevents_lock held
+ * and interrupts disabled.
  */
-void tick_shutdown(unsigned int *cpup)
+void tick_shutdown(void)
 {
-	struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	struct clock_event_device *dev = td->evtdev;
 
 	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);
 		dev->event_handler = clockevents_handle_noop;
 		td->evtdev = NULL;
 	}
 }
+#endif
 
-void tick_suspend(void)
+/**
+ * tick_suspend_local - Suspend the local tick device
+ *
+ * Called from the local cpu for freeze with interrupts disabled.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_suspend_local(void)
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 
 	clockevents_shutdown(td->evtdev);
 }
 
-void tick_resume(void)
+/**
+ * tick_resume_local - Resume the local tick device
+ *
+ * Called from the local CPU for unfreeze or XEN resume magic.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_resume_local(void)
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
-	int broadcast = tick_resume_broadcast();
-
-	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+	bool broadcast = tick_resume_check_broadcast();
 
+	clockevents_tick_resume(td->evtdev);
 	if (!broadcast) {
 		if (td->mode == TICKDEV_MODE_PERIODIC)
 			tick_setup_periodic(td->evtdev, 0);
 		else
 			tick_resume_oneshot();
 	}
+
+	/*
+	 * Ensure that hrtimers are up to date and the clockevents device
+	 * is reprogrammed correctly when high resolution timers are
+	 * enabled.
+	 */
+	hrtimers_resume_local();
+}
+
+/**
+ * tick_suspend - Suspend the tick and the broadcast device
+ *
+ * Called from syscore_suspend() via timekeeping_suspend with only one
+ * CPU online and interrupts disabled or from tick_unfreeze() under
+ * tick_freeze_lock.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_suspend(void)
+{
+	tick_suspend_local();
+	tick_suspend_broadcast();
+}
+
+/**
+ * tick_resume - Resume the tick and the broadcast device
+ *
+ * Called from syscore_resume() via timekeeping_resume with only one
+ * CPU online and interrupts disabled.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_resume(void)
+{
+	tick_resume_broadcast();
+	tick_resume_local();
+}
+
+#ifdef CONFIG_SUSPEND
+static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
+static DEFINE_WAIT_OVERRIDE_MAP(tick_freeze_map, LD_WAIT_SLEEP);
+static unsigned int tick_freeze_depth;
+
+/**
+ * tick_freeze - Suspend the local tick and (possibly) timekeeping.
+ *
+ * Check if this is the last online CPU executing the function and if so,
+ * suspend timekeeping.  Otherwise suspend the local tick.
+ *
+ * Call with interrupts disabled.  Must be balanced with %tick_unfreeze().
+ * Interrupts must not be enabled before the subsequent %tick_unfreeze().
+ */
+void tick_freeze(void)
+{
+	raw_spin_lock(&tick_freeze_lock);
+
+	tick_freeze_depth++;
+	if (tick_freeze_depth == num_online_cpus()) {
+		trace_suspend_resume(TPS("timekeeping_freeze"),
+				     smp_processor_id(), true);
+		/*
+		 * All other CPUs have their interrupts disabled and are
+		 * suspended to idle. Other tasks have been frozen so there
+		 * is no scheduling happening. This means that there is no
+		 * concurrency in the system at this point. Therefore it is
+		 * okay to acquire a sleeping lock on PREEMPT_RT, such as a
+		 * spinlock, because the lock cannot be held by other CPUs
+		 * or threads and acquiring it cannot block.
+		 *
+		 * Inform lockdep about the situation.
+		 */
+		lock_map_acquire_try(&tick_freeze_map);
+		system_state = SYSTEM_SUSPEND;
+		sched_clock_suspend();
+		timekeeping_suspend();
+		lock_map_release(&tick_freeze_map);
+	} else {
+		tick_suspend_local();
+	}
+
+	raw_spin_unlock(&tick_freeze_lock);
+}
+
+/**
+ * tick_unfreeze - Resume the local tick and (possibly) timekeeping.
+ *
+ * Check if this is the first CPU executing the function and if so, resume
+ * timekeeping.  Otherwise resume the local tick.
+ *
+ * Call with interrupts disabled.  Must be balanced with %tick_freeze().
+ * Interrupts must not be enabled after the preceding %tick_freeze().
+ */
+void tick_unfreeze(void)
+{
+	raw_spin_lock(&tick_freeze_lock);
+
+	if (tick_freeze_depth == num_online_cpus()) {
+		/*
+		 * Similar to tick_freeze(). On resumption the first CPU may
+		 * acquire uncontended sleeping locks while other CPUs block on
+		 * tick_freeze_lock.
+		 */
+		lock_map_acquire_try(&tick_freeze_map);
+		timekeeping_resume();
+		sched_clock_resume();
+		lock_map_release(&tick_freeze_map);
+
+		system_state = SYSTEM_RUNNING;
+		trace_suspend_resume(TPS("timekeeping_freeze"),
+				     smp_processor_id(), false);
+	} else {
+		touch_softlockup_watchdog();
+		tick_resume_local();
+	}
+
+	tick_freeze_depth--;
+
+	raw_spin_unlock(&tick_freeze_lock);
 }
+#endif /* CONFIG_SUSPEND */
 
 /**
  * tick_init - initialize the tick control
@@ -384,4 +590,5 @@ void tick_resume(void)
 void __init tick_init(void)
 {
 	tick_broadcast_init();
+	tick_nohz_init();
 }