1 files changed, 199 insertions, 274 deletions

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 70625dff62ce..30899a8cc52c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -58,6 +58,8 @@
 #define HRTIMER_ACTIVE_SOFT	(HRTIMER_ACTIVE_HARD << MASK_SHIFT)
 #define HRTIMER_ACTIVE_ALL	(HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD)
 
+static void retrigger_next_event(void *arg);
+
 /*
  * The timer bases:
  *
@@ -111,18 +113,17 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
 		},
-	}
+	},
+	.csd = CSD_INIT(retrigger_next_event, NULL)
 };
 
-static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
-	/* Make sure we catch unsupported clockids */
-	[0 ... MAX_CLOCKS - 1]	= HRTIMER_MAX_CLOCK_BASES,
-
-	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
-	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
-	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
-	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
-};
+static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base)
+{
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return true;
+	else
+		return likely(base->online);
+}
 
 /*
  * Functions and macros which are different for UP/SMP systems are kept in a
@@ -145,11 +146,6 @@ static struct hrtimer_cpu_base migration_cpu_base = {
 
 #define migration_base	migration_cpu_base.clock_base[0]
 
-static inline bool is_migration_base(struct hrtimer_clock_base *base)
-{
-	return base == &migration_base;
-}
-
 /*
  * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
  * means that all timers which are tied to this base via timer->base are
@@ -183,27 +179,54 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 }
 
 /*
- * We do not migrate the timer when it is expiring before the next
- * event on the target cpu. When high resolution is enabled, we cannot
- * reprogram the target cpu hardware and we would cause it to fire
- * late. To keep it simple, we handle the high resolution enabled and
- * disabled case similar.
+ * Check if the elected target is suitable considering its next
+ * event and the hotplug state of the current CPU.
+ *
+ * If the elected target is remote and its next event is after the timer
+ * to queue, then a remote reprogram is necessary. However there is no
+ * guarantee the IPI handling the operation would arrive in time to meet
+ * the high resolution deadline. In this case the local CPU becomes a
+ * preferred target, unless it is offline.
+ *
+ * High and low resolution modes are handled the same way for simplicity.
  *
  * Called with cpu_base->lock of target cpu held.
  */
-static int
-hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
+static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base,
+				    struct hrtimer_cpu_base *new_cpu_base,
+				    struct hrtimer_cpu_base *this_cpu_base)
 {
 	ktime_t expires;
 
+	/*
+	 * The local CPU clockevent can be reprogrammed. Also get_target_base()
+	 * guarantees it is online.
+	 */
+	if (new_cpu_base == this_cpu_base)
+		return true;
+
+	/*
+	 * The offline local CPU can't be the default target if the
+	 * next remote target event is after this timer. Keep the
+	 * elected new base. An IPI will we issued to reprogram
+	 * it as a last resort.
+	 */
+	if (!hrtimer_base_is_online(this_cpu_base))
+		return true;
+
 	expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
-	return expires < new_base->cpu_base->expires_next;
+
+	return expires >= new_base->cpu_base->expires_next;
 }
 
-static inline
-struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
-					 int pinned)
+static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned)
 {
+	if (!hrtimer_base_is_online(base)) {
+		int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER));
+
+		return &per_cpu(hrtimer_bases, cpu);
+	}
+
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 	if (static_branch_likely(&timers_migration_enabled) && !pinned)
 		return &per_cpu(hrtimer_bases, get_nohz_timer_target());
@@ -254,8 +277,8 @@ again:
 		raw_spin_unlock(&base->cpu_base->lock);
 		raw_spin_lock(&new_base->cpu_base->lock);
 
-		if (new_cpu_base != this_cpu_base &&
-		    hrtimer_check_target(timer, new_base)) {
+		if (!hrtimer_suitable_target(timer, new_base, new_cpu_base,
+					     this_cpu_base)) {
 			raw_spin_unlock(&new_base->cpu_base->lock);
 			raw_spin_lock(&base->cpu_base->lock);
 			new_cpu_base = this_cpu_base;
@@ -264,8 +287,7 @@ again:
 		}
 		WRITE_ONCE(timer->base, new_base);
 	} else {
-		if (new_cpu_base != this_cpu_base &&
-		    hrtimer_check_target(timer, new_base)) {
+		if (!hrtimer_suitable_target(timer, new_base,  new_cpu_base, this_cpu_base)) {
 			new_cpu_base = this_cpu_base;
 			goto again;
 		}
@@ -275,11 +297,6 @@ again:
 
 #else /* CONFIG_SMP */
 
-static inline bool is_migration_base(struct hrtimer_clock_base *base)
-{
-	return false;
-}
-
 static inline struct hrtimer_clock_base *
 lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 	__acquires(&timer->base->cpu_base->lock)
@@ -349,7 +366,7 @@ static const struct debug_obj_descr hrtimer_debug_descr;
 
 static void *hrtimer_debug_hint(void *addr)
 {
-	return ((struct hrtimer *) addr)->function;
+	return ACCESS_PRIVATE((struct hrtimer *)addr, function);
 }
 
 /*
@@ -417,6 +434,11 @@ static inline void debug_hrtimer_init(struct hrtimer *timer)
 	debug_object_init(timer, &hrtimer_debug_descr);
 }
 
+static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer)
+{
+	debug_object_init_on_stack(timer, &hrtimer_debug_descr);
+}
+
 static inline void debug_hrtimer_activate(struct hrtimer *timer,
 					  enum hrtimer_mode mode)
 {
@@ -428,28 +450,6 @@ static inline void debug_hrtimer_deactivate(struct hrtimer *timer)
 	debug_object_deactivate(timer, &hrtimer_debug_descr);
 }
 
-static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
-			   enum hrtimer_mode mode);
-
-void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id,
-			   enum hrtimer_mode mode)
-{
-	debug_object_init_on_stack(timer, &hrtimer_debug_descr);
-	__hrtimer_init(timer, clock_id, mode);
-}
-EXPORT_SYMBOL_GPL(hrtimer_init_on_stack);
-
-static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
-				   clockid_t clock_id, enum hrtimer_mode mode);
-
-void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
-				   clockid_t clock_id, enum hrtimer_mode mode)
-{
-	debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr);
-	__hrtimer_init_sleeper(sl, clock_id, mode);
-}
-EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack);
-
 void destroy_hrtimer_on_stack(struct hrtimer *timer)
 {
 	debug_object_free(timer, &hrtimer_debug_descr);
@@ -459,17 +459,23 @@ EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack);
 #else
 
 static inline void debug_hrtimer_init(struct hrtimer *timer) { }
+static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { }
 static inline void debug_hrtimer_activate(struct hrtimer *timer,
 					  enum hrtimer_mode mode) { }
 static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
 #endif
 
-static inline void
-debug_init(struct hrtimer *timer, clockid_t clockid,
-	   enum hrtimer_mode mode)
+static inline void debug_setup(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode)
 {
 	debug_hrtimer_init(timer);
-	trace_hrtimer_init(timer, clockid, mode);
+	trace_hrtimer_setup(timer, clockid, mode);
+}
+
+static inline void debug_setup_on_stack(struct hrtimer *timer, clockid_t clockid,
+					enum hrtimer_mode mode)
+{
+	debug_hrtimer_init_on_stack(timer);
+	trace_hrtimer_setup(timer, clockid, mode);
 }
 
 static inline void debug_activate(struct hrtimer *timer,
@@ -644,17 +650,12 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 /*
  * Is the high resolution mode active ?
  */
-static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
+static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
 {
 	return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
 		cpu_base->hres_active : 0;
 }
 
-static inline int hrtimer_hres_active(void)
-{
-	return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
-}
-
 static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base,
 				struct hrtimer *next_timer,
 				ktime_t expires_next)
@@ -678,7 +679,7 @@ static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base,
 	 * set. So we'd effectively block all timers until the T2 event
 	 * fires.
 	 */
-	if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
+	if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
 		return;
 
 	tick_program_event(expires_next, 1);
@@ -730,8 +731,6 @@ static inline int hrtimer_is_hres_enabled(void)
 	return hrtimer_hres_enabled;
 }
 
-static void retrigger_next_event(void *arg);
-
 /*
  * Switch to high resolution mode
  */
@@ -789,12 +788,12 @@ static void retrigger_next_event(void *arg)
 	 * function call will take care of the reprogramming in case the
 	 * CPU was in a NOHZ idle sleep.
 	 */
-	if (!__hrtimer_hres_active(base) && !tick_nohz_active)
+	if (!hrtimer_hres_active(base) && !tick_nohz_active)
 		return;
 
 	raw_spin_lock(&base->lock);
 	hrtimer_update_base(base);
-	if (__hrtimer_hres_active(base))
+	if (hrtimer_hres_active(base))
 		hrtimer_force_reprogram(base, 0);
 	else
 		hrtimer_update_next_event(base);
@@ -951,7 +950,7 @@ void clock_was_set(unsigned int bases)
 	cpumask_var_t mask;
 	int cpu;
 
-	if (!__hrtimer_hres_active(cpu_base) && !tick_nohz_active)
+	if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active)
 		goto out_timerfd;
 
 	if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
@@ -1081,11 +1080,10 @@ EXPORT_SYMBOL_GPL(hrtimer_forward);
  * The timer is inserted in expiry order. Insertion into the
  * red black tree is O(log(n)). Must hold the base lock.
  *
- * Returns 1 when the new timer is the leftmost timer in the tree.
+ * Returns true when the new timer is the leftmost timer in the tree.
  */
-static int enqueue_hrtimer(struct hrtimer *timer,
-			   struct hrtimer_clock_base *base,
-			   enum hrtimer_mode mode)
+static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base,
+			    enum hrtimer_mode mode)
 {
 	debug_activate(timer, mode);
 	WARN_ON_ONCE(!base->cpu_base->online);
@@ -1182,7 +1180,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
 	/*
 	 * CONFIG_TIME_LOW_RES indicates that the system has no way to return
 	 * granular time values. For relative timers we add hrtimer_resolution
-	 * (i.e. one jiffie) to prevent short timeouts.
+	 * (i.e. one jiffy) to prevent short timeouts.
 	 */
 	timer->is_rel = mode & HRTIMER_MODE_REL;
 	if (timer->is_rel)
@@ -1220,6 +1218,7 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 				    u64 delta_ns, const enum hrtimer_mode mode,
 				    struct hrtimer_clock_base *base)
 {
+	struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases);
 	struct hrtimer_clock_base *new_base;
 	bool force_local, first;
 
@@ -1231,10 +1230,16 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	 * and enforce reprogramming after it is queued no matter whether
 	 * it is the new first expiring timer again or not.
 	 */
-	force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
+	force_local = base->cpu_base == this_cpu_base;
 	force_local &= base->cpu_base->next_timer == timer;
 
 	/*
+	 * Don't force local queuing if this enqueue happens on a unplugged
+	 * CPU after hrtimer_cpu_dying() has been invoked.
+	 */
+	force_local &= this_cpu_base->online;
+
+	/*
 	 * Remove an active timer from the queue. In case it is not queued
 	 * on the current CPU, make sure that remove_hrtimer() updates the
 	 * remote data correctly.
@@ -1263,8 +1268,27 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	}
 
 	first = enqueue_hrtimer(timer, new_base, mode);
-	if (!force_local)
-		return first;
+	if (!force_local) {
+		/*
+		 * If the current CPU base is online, then the timer is
+		 * never queued on a remote CPU if it would be the first
+		 * expiring timer there.
+		 */
+		if (hrtimer_base_is_online(this_cpu_base))
+			return first;
+
+		/*
+		 * Timer was enqueued remote because the current base is
+		 * already offline. If the timer is the first to expire,
+		 * kick the remote CPU to reprogram the clock event.
+		 */
+		if (first) {
+			struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base;
+
+			smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd);
+		}
+		return 0;
+	}
 
 	/*
 	 * Timer was forced to stay on the current CPU to avoid
@@ -1354,11 +1378,13 @@ static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base)
 }
 
 static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base)
+	__acquires(&base->softirq_expiry_lock)
 {
 	spin_lock(&base->softirq_expiry_lock);
 }
 
 static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base)
+	__releases(&base->softirq_expiry_lock)
 {
 	spin_unlock(&base->softirq_expiry_lock);
 }
@@ -1381,13 +1407,25 @@ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base,
 	}
 }
 
+#ifdef CONFIG_SMP
+static __always_inline bool is_migration_base(struct hrtimer_clock_base *base)
+{
+	return base == &migration_base;
+}
+#else
+static __always_inline bool is_migration_base(struct hrtimer_clock_base *base)
+{
+	return false;
+}
+#endif
+
 /*
  * This function is called on PREEMPT_RT kernels when the fast path
  * deletion of a timer failed because the timer callback function was
  * running.
  *
  * This prevents priority inversion: if the soft irq thread is preempted
- * in the middle of a timer callback, then calling del_timer_sync() can
+ * in the middle of a timer callback, then calling hrtimer_cancel() can
  * lead to two issues:
  *
  *  - If the caller is on a remote CPU then it has to spin wait for the timer
@@ -1491,7 +1529,7 @@ u64 hrtimer_get_next_event(void)
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
-	if (!__hrtimer_hres_active(cpu_base))
+	if (!hrtimer_hres_active(cpu_base))
 		expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
@@ -1514,7 +1552,7 @@ u64 hrtimer_next_event_without(const struct hrtimer *exclude)
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
-	if (__hrtimer_hres_active(cpu_base)) {
+	if (hrtimer_hres_active(cpu_base)) {
 		unsigned int active;
 
 		if (!cpu_base->softirq_activated) {
@@ -1535,18 +1573,24 @@ u64 hrtimer_next_event_without(const struct hrtimer *exclude)
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 {
-	if (likely(clock_id < MAX_CLOCKS)) {
-		int base = hrtimer_clock_to_base_table[clock_id];
-
-		if (likely(base != HRTIMER_MAX_CLOCK_BASES))
-			return base;
+	switch (clock_id) {
+	case CLOCK_REALTIME:
+		return HRTIMER_BASE_REALTIME;
+	case CLOCK_MONOTONIC:
+		return HRTIMER_BASE_MONOTONIC;
+	case CLOCK_BOOTTIME:
+		return HRTIMER_BASE_BOOTTIME;
+	case CLOCK_TAI:
+		return HRTIMER_BASE_TAI;
+	default:
+		WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id);
+		return HRTIMER_BASE_MONOTONIC;
 	}
-	WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id);
-	return HRTIMER_BASE_MONOTONIC;
 }
 
-static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
-			   enum hrtimer_mode mode)
+static void __hrtimer_setup(struct hrtimer *timer,
+			    enum hrtimer_restart (*function)(struct hrtimer *),
+			    clockid_t clock_id, enum hrtimer_mode mode)
 {
 	bool softtimer = !!(mode & HRTIMER_MODE_SOFT);
 	struct hrtimer_cpu_base *cpu_base;
@@ -1579,11 +1623,17 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	timer->is_hard = !!(mode & HRTIMER_MODE_HARD);
 	timer->base = &cpu_base->clock_base[base];
 	timerqueue_init(&timer->node);
+
+	if (WARN_ON_ONCE(!function))
+		ACCESS_PRIVATE(timer, function) = hrtimer_dummy_timeout;
+	else
+		ACCESS_PRIVATE(timer, function) = function;
 }
 
 /**
- * hrtimer_init - initialize a timer to the given clock
+ * hrtimer_setup - initialize a timer to the given clock
  * @timer:	the timer to be initialized
+ * @function:	the callback function
  * @clock_id:	the clock to be used
  * @mode:       The modes which are relevant for initialization:
  *              HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT,
@@ -1593,13 +1643,32 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
  *              but the PINNED bit is ignored as pinning happens
  *              when the hrtimer is started
  */
-void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
-		  enum hrtimer_mode mode)
+void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *),
+		   clockid_t clock_id, enum hrtimer_mode mode)
+{
+	debug_setup(timer, clock_id, mode);
+	__hrtimer_setup(timer, function, clock_id, mode);
+}
+EXPORT_SYMBOL_GPL(hrtimer_setup);
+
+/**
+ * hrtimer_setup_on_stack - initialize a timer on stack memory
+ * @timer:	The timer to be initialized
+ * @function:	the callback function
+ * @clock_id:	The clock to be used
+ * @mode:       The timer mode
+ *
+ * Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack
+ * memory.
+ */
+void hrtimer_setup_on_stack(struct hrtimer *timer,
+			    enum hrtimer_restart (*function)(struct hrtimer *),
+			    clockid_t clock_id, enum hrtimer_mode mode)
 {
-	debug_init(timer, clock_id, mode);
-	__hrtimer_init(timer, clock_id, mode);
+	debug_setup_on_stack(timer, clock_id, mode);
+	__hrtimer_setup(timer, function, clock_id, mode);
 }
-EXPORT_SYMBOL_GPL(hrtimer_init);
+EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack);
 
 /*
  * A timer is active, when it is enqueued into the rbtree or the
@@ -1670,7 +1739,7 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	raw_write_seqcount_barrier(&base->seq);
 
 	__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
-	fn = timer->function;
+	fn = ACCESS_PRIVATE(timer, function);
 
 	/*
 	 * Clear the 'is relative' flag for the TIME_LOW_RES case. If the
@@ -1760,7 +1829,7 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now,
 	}
 }
 
-static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h)
+static __latent_entropy void hrtimer_run_softirq(void)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	unsigned long flags;
@@ -1812,7 +1881,7 @@ retry:
 	if (!ktime_before(now, cpu_base->softirq_expires_next)) {
 		cpu_base->softirq_expires_next = KTIME_MAX;
 		cpu_base->softirq_activated = 1;
-		raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+		raise_timer_softirq(HRTIMER_SOFTIRQ);
 	}
 
 	__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
@@ -1875,25 +1944,7 @@ retry:
 	tick_program_event(expires_next, 1);
 	pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta));
 }
-
-/* called with interrupts disabled */
-static inline void __hrtimer_peek_ahead_timers(void)
-{
-	struct tick_device *td;
-
-	if (!hrtimer_hres_active())
-		return;
-
-	td = this_cpu_ptr(&tick_cpu_device);
-	if (td && td->evtdev)
-		hrtimer_interrupt(td->evtdev);
-}
-
-#else /* CONFIG_HIGH_RES_TIMERS */
-
-static inline void __hrtimer_peek_ahead_timers(void) { }
-
-#endif	/* !CONFIG_HIGH_RES_TIMERS */
+#endif /* !CONFIG_HIGH_RES_TIMERS */
 
 /*
  * Called from run_local_timers in hardirq context every jiffy
@@ -1904,7 +1955,7 @@ void hrtimer_run_queues(void)
 	unsigned long flags;
 	ktime_t now;
 
-	if (__hrtimer_hres_active(cpu_base))
+	if (hrtimer_hres_active(cpu_base))
 		return;
 
 	/*
@@ -1925,7 +1976,7 @@ void hrtimer_run_queues(void)
 	if (!ktime_before(now, cpu_base->softirq_expires_next)) {
 		cpu_base->softirq_expires_next = KTIME_MAX;
 		cpu_base->softirq_activated = 1;
-		raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+		raise_timer_softirq(HRTIMER_SOFTIRQ);
 	}
 
 	__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
@@ -1963,7 +2014,7 @@ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl,
 	 * Make the enqueue delivery mode check work on RT. If the sleeper
 	 * was initialized for hard interrupt delivery, force the mode bit.
 	 * This is a special case for hrtimer_sleepers because
-	 * hrtimer_init_sleeper() determines the delivery mode on RT so the
+	 * __hrtimer_setup_sleeper() determines the delivery mode on RT so the
 	 * fiddling with this decision is avoided at the call sites.
 	 */
 	if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard)
@@ -1973,8 +2024,8 @@ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl,
 }
 EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires);
 
-static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
-				   clockid_t clock_id, enum hrtimer_mode mode)
+static void __hrtimer_setup_sleeper(struct hrtimer_sleeper *sl,
+				    clockid_t clock_id, enum hrtimer_mode mode)
 {
 	/*
 	 * On PREEMPT_RT enabled kernels hrtimers which are not explicitly
@@ -1996,29 +2047,27 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 	 * expiry.
 	 */
 	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
-		if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT))
+		if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT))
 			mode |= HRTIMER_MODE_HARD;
 	}
 
-	__hrtimer_init(&sl->timer, clock_id, mode);
-	sl->timer.function = hrtimer_wakeup;
+	__hrtimer_setup(&sl->timer, hrtimer_wakeup, clock_id, mode);
 	sl->task = current;
 }
 
 /**
- * hrtimer_init_sleeper - initialize sleeper to the given clock
+ * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory
  * @sl:		sleeper to be initialized
  * @clock_id:	the clock to be used
  * @mode:	timer mode abs/rel
  */
-void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id,
-			  enum hrtimer_mode mode)
+void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl,
+				    clockid_t clock_id, enum hrtimer_mode mode)
 {
-	debug_init(&sl->timer, clock_id, mode);
-	__hrtimer_init_sleeper(sl, clock_id, mode);
-
+	debug_setup_on_stack(&sl->timer, clock_id, mode);
+	__hrtimer_setup_sleeper(sl, clock_id, mode);
 }
-EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
+EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack);
 
 int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts)
 {
@@ -2079,8 +2128,7 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 	struct hrtimer_sleeper t;
 	int ret;
 
-	hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid,
-				      HRTIMER_MODE_ABS);
+	hrtimer_setup_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS);
 	hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
 	ret = do_nanosleep(&t, HRTIMER_MODE_ABS);
 	destroy_hrtimer_on_stack(&t.timer);
@@ -2093,14 +2141,9 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
 	struct restart_block *restart;
 	struct hrtimer_sleeper t;
 	int ret = 0;
-	u64 slack;
 
-	slack = current->timer_slack_ns;
-	if (rt_task(current))
-		slack = 0;
-
-	hrtimer_init_sleeper_on_stack(&t, clockid, mode);
-	hrtimer_set_expires_range_ns(&t.timer, rqtp, slack);
+	hrtimer_setup_sleeper_on_stack(&t, clockid, mode);
+	hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns);
 	ret = do_nanosleep(&t, mode);
 	if (ret != -ERESTART_RESTARTBLOCK)
 		goto out;
@@ -2180,6 +2223,15 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	}
 
 	cpu_base->cpu = cpu;
+	hrtimer_cpu_base_init_expiry_lock(cpu_base);
+	return 0;
+}
+
+int hrtimers_cpu_starting(unsigned int cpu)
+{
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+
+	/* Clear out any left over state from a CPU down operation */
 	cpu_base->active_bases = 0;
 	cpu_base->hres_active = 0;
 	cpu_base->hang_detected = 0;
@@ -2188,7 +2240,6 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	cpu_base->expires_next = KTIME_MAX;
 	cpu_base->softirq_expires_next = KTIME_MAX;
 	cpu_base->online = 1;
-	hrtimer_cpu_base_init_expiry_lock(cpu_base);
 	return 0;
 }
 
@@ -2264,132 +2315,6 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
 void __init hrtimers_init(void)
 {
 	hrtimers_prepare_cpu(smp_processor_id());
+	hrtimers_cpu_starting(smp_processor_id());
 	open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq);
 }
-
-/**
- * schedule_hrtimeout_range_clock - sleep until timeout
- * @expires:	timeout value (ktime_t)
- * @delta:	slack in expires timeout (ktime_t) for SCHED_OTHER tasks
- * @mode:	timer mode
- * @clock_id:	timer clock to be used
- */
-int __sched
-schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
-			       const enum hrtimer_mode mode, clockid_t clock_id)
-{
-	struct hrtimer_sleeper t;
-
-	/*
-	 * Optimize when a zero timeout value is given. It does not
-	 * matter whether this is an absolute or a relative time.
-	 */
-	if (expires && *expires == 0) {
-		__set_current_state(TASK_RUNNING);
-		return 0;
-	}
-
-	/*
-	 * A NULL parameter means "infinite"
-	 */
-	if (!expires) {
-		schedule();
-		return -EINTR;
-	}
-
-	/*
-	 * Override any slack passed by the user if under
-	 * rt contraints.
-	 */
-	if (rt_task(current))
-		delta = 0;
-
-	hrtimer_init_sleeper_on_stack(&t, clock_id, mode);
-	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
-	hrtimer_sleeper_start_expires(&t, mode);
-
-	if (likely(t.task))
-		schedule();
-
-	hrtimer_cancel(&t.timer);
-	destroy_hrtimer_on_stack(&t.timer);
-
-	__set_current_state(TASK_RUNNING);
-
-	return !t.task ? 0 : -EINTR;
-}
-EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock);
-
-/**
- * schedule_hrtimeout_range - sleep until timeout
- * @expires:	timeout value (ktime_t)
- * @delta:	slack in expires timeout (ktime_t) for SCHED_OTHER tasks
- * @mode:	timer mode
- *
- * Make the current task sleep until the given expiry time has
- * elapsed. The routine will return immediately unless
- * the current task state has been set (see set_current_state()).
- *
- * The @delta argument gives the kernel the freedom to schedule the
- * actual wakeup to a time that is both power and performance friendly
- * for regular (non RT/DL) tasks.
- * The kernel give the normal best effort behavior for "@expires+@delta",
- * but may decide to fire the timer earlier, but no earlier than @expires.
- *
- * You can set the task state as follows -
- *
- * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
- * pass before the routine returns unless the current task is explicitly
- * woken up, (e.g. by wake_up_process()).
- *
- * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
- * delivered to the current task or the current task is explicitly woken
- * up.
- *
- * The current task state is guaranteed to be TASK_RUNNING when this
- * routine returns.
- *
- * Returns 0 when the timer has expired. If the task was woken before the
- * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or
- * by an explicit wakeup, it returns -EINTR.
- */
-int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta,
-				     const enum hrtimer_mode mode)
-{
-	return schedule_hrtimeout_range_clock(expires, delta, mode,
-					      CLOCK_MONOTONIC);
-}
-EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
-
-/**
- * schedule_hrtimeout - sleep until timeout
- * @expires:	timeout value (ktime_t)
- * @mode:	timer mode
- *
- * Make the current task sleep until the given expiry time has
- * elapsed. The routine will return immediately unless
- * the current task state has been set (see set_current_state()).
- *
- * You can set the task state as follows -
- *
- * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
- * pass before the routine returns unless the current task is explicitly
- * woken up, (e.g. by wake_up_process()).
- *
- * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
- * delivered to the current task or the current task is explicitly woken
- * up.
- *
- * The current task state is guaranteed to be TASK_RUNNING when this
- * routine returns.
- *
- * Returns 0 when the timer has expired. If the task was woken before the
- * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or
- * by an explicit wakeup, it returns -EINTR.
- */
-int __sched schedule_hrtimeout(ktime_t *expires,
-			       const enum hrtimer_mode mode)
-{
-	return schedule_hrtimeout_range(expires, 0, mode);
-}
-EXPORT_SYMBOL_GPL(schedule_hrtimeout);