Merge tag 'timers-v7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/daniel.lezcano/linux into timers/clocksource

  - Use designated initializers for sh_mtu2, sh_cmt, and sh_tmu, and
    drop the unused initializer in the platform_device_id table for
    sh_mtu2 (Uwe Kleine-König)

  - Remove redundant dev_err()/dev_err_probe() messages when
    devm_request_*_irq() fails, as the helper already logs an error
    message (Pan Chuang)

  - Fix a boot hang on Allwinner D1 when a forced minimum delta is used
    with the sun4i timer (Felix Yan)

  - Fix an IRQ leak in the cpuhp_setup_state() error path by freeing the
    IRQ on failure in the NXP PIT driver (WenTao Liang)

  - Fix incorrect unmapping of shared MMIO between the clocksource and
    clockevent drivers. If one of them fails to initialize, the error
    path unmaps the shared MMIO region, leaving the other driver with an
    invalid mapping on clps711x (Guangshuo Li)

  - Make the samsung_pwm driver compatible with PREEMPT_RT by replacing
    regular spinlocks with raw_spinlock_t in atomic contexts (Marek
    Szyprowski)

  - Use __raw_readl() and __raw_writel() instead of ioread32() and
    iowrite32() to support SWAP_IO_SPACE in the rtl-otto driver (Rustam
    Adilov)

  - Fix a missing clk_disable_unprepare() call in the timer
    initialization error path of the Armada driver (Yuho Choi)

Link: https://lore.kernel.org/lkml/75feea31-683d-45a1-87f4-ab045e0152ae@oss.qualcomm.com

18 files changed, 637 insertions, 443 deletions

diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 02aac7c5aa76..d098ac39bde4 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -16,10 +16,6 @@ config ARCH_CLOCKSOURCE_INIT
 config ARCH_WANTS_CLOCKSOURCE_READ_INLINE
 	bool
 
-# Timekeeping vsyscall support
-config GENERIC_TIME_VSYSCALL
-	bool
-
 # The generic clock events infrastructure
 config GENERIC_CLOCKEVENTS
 	def_bool !LEGACY_TIMER_TICK
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 6e173d70d825..ea5be5870e51 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -337,48 +337,32 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
 EXPORT_SYMBOL_GPL(alarm_init);
 
 /**
- * alarm_start - Sets an absolute alarm to fire
- * @alarm: ptr to alarm to set
- * @start: time to run the alarm
+ * alarm_start_timer - Sets an alarm to fire
+ * @alarm:	Pointer to alarm to set
+ * @expires:	Expiry time
+ * @relative:	True if @expires is relative
+ *
+ * Returns: True if the alarm was queued. False if it already expired
  */
-void alarm_start(struct alarm *alarm, ktime_t start)
+bool alarm_start_timer(struct alarm *alarm, ktime_t expires, bool relative)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 
-	scoped_guard(spinlock_irqsave, &base->lock) {
-		alarm->node.expires = start;
-		alarmtimer_enqueue(base, alarm);
-		hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS);
-	}
+	if (relative)
+		expires = ktime_add_safe(expires, base->get_ktime());
 
 	trace_alarmtimer_start(alarm, base->get_ktime());
-}
-EXPORT_SYMBOL_GPL(alarm_start);
-
-/**
- * alarm_start_relative - Sets a relative alarm to fire
- * @alarm: ptr to alarm to set
- * @start: time relative to now to run the alarm
- */
-void alarm_start_relative(struct alarm *alarm, ktime_t start)
-{
-	struct alarm_base *base = &alarm_bases[alarm->type];
-
-	start = ktime_add_safe(start, base->get_ktime());
-	alarm_start(alarm, start);
-}
-EXPORT_SYMBOL_GPL(alarm_start_relative);
-
-void alarm_restart(struct alarm *alarm)
-{
-	struct alarm_base *base = &alarm_bases[alarm->type];
 
 	guard(spinlock_irqsave)(&base->lock);
-	hrtimer_set_expires(&alarm->timer, alarm->node.expires);
-	hrtimer_restart(&alarm->timer);
+	alarm->node.expires = expires;
 	alarmtimer_enqueue(base, alarm);
+	if (!hrtimer_start_range_ns_user(&alarm->timer, expires, 0, HRTIMER_MODE_ABS)) {
+		alarmtimer_dequeue(base, alarm);
+		return false;
+	}
+	return true;
 }
-EXPORT_SYMBOL_GPL(alarm_restart);
+EXPORT_SYMBOL_GPL(alarm_start_timer);
 
 /**
  * alarm_try_to_cancel - Tries to cancel an alarm timer
@@ -512,8 +496,6 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid)
  * @now: time at the timer expiration
  *
  * Posix timer callback for expired alarm timers.
- *
- * Return: whether the timer is to be restarted
  */
 static void alarm_handle_timer(struct alarm *alarm, ktime_t now)
 {
@@ -527,12 +509,12 @@ static void alarm_handle_timer(struct alarm *alarm, ktime_t now)
  * alarm_timer_rearm - Posix timer callback for rearming timer
  * @timr:	Pointer to the posixtimer data struct
  */
-static void alarm_timer_rearm(struct k_itimer *timr)
+static bool alarm_timer_rearm(struct k_itimer *timr)
 {
 	struct alarm *alarm = &timr->it.alarm.alarmtimer;
 
 	timr->it_overrun += alarm_forward_now(alarm, timr->it_interval);
-	alarm_start(alarm, alarm->node.expires);
+	return alarm_start_timer(alarm, alarm->node.expires, false);
 }
 
 /**
@@ -588,7 +570,7 @@ static void alarm_timer_wait_running(struct k_itimer *timr)
  * @absolute:	Expiry value is absolute time
  * @sigev_none:	Posix timer does not deliver signals
  */
-static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires,
+static bool alarm_timer_arm(struct k_itimer *timr, ktime_t expires,
 			    bool absolute, bool sigev_none)
 {
 	struct alarm *alarm = &timr->it.alarm.alarmtimer;
@@ -596,10 +578,16 @@ static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires,
 
 	if (!absolute)
 		expires = ktime_add_safe(expires, base->get_ktime());
-	if (sigev_none)
+
+	/*
+	 * sigev_none needs to update the expires value and pretend
+	 * that the timer is queued
+	 */
+	if (sigev_none) {
 		alarm->node.expires = expires;
-	else
-		alarm_start(&timr->it.alarm.alarmtimer, expires);
+		return true;
+	}
+	return alarm_start_timer(&timr->it.alarm.alarmtimer, expires, false);
 }
 
 /**
@@ -706,7 +694,9 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp,
 	alarm->data = (void *)current;
 	do {
 		set_current_state(TASK_INTERRUPTIBLE);
-		alarm_start(alarm, absexp);
+		if (!alarm_start_timer(alarm, absexp, false))
+			alarm->data = NULL;
+
 		if (likely(alarm->data))
 			schedule();
 
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 5e22697b098d..0014d163f989 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -301,7 +301,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 #include <asm/clock_inlined.h>
 #else
 static __always_inline void
-arch_inlined_clockevent_set_next_coupled(u64 u64 cycles, struct clock_event_device *dev) { }
+arch_inlined_clockevent_set_next_coupled(u64 cycles, struct clock_event_device *dev) { }
 #endif
 
 static inline bool clockevent_set_next_coupled(struct clock_event_device *dev, ktime_t expires)
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 313f6c88148e..e48c4d379a7c 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -1222,14 +1222,8 @@ static void clocksource_enqueue(struct clocksource *cs)
  * @cs:		clocksource to be registered
  * @scale:	Scale factor multiplied against freq to get clocksource hz
  * @freq:	clocksource frequency (cycles per second) divided by scale
- *
- * This should only be called from the clocksource->enable() method.
- *
- * This *SHOULD NOT* be called directly! Please use the
- * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper
- * functions.
  */
-void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq)
+static void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 	u64 sec;
 
@@ -1287,7 +1281,6 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq
 	pr_info("%s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
 		cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
 }
-EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
 
 /**
  * __clocksource_register_scale - Used to install new clocksources
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 5bd6efe598f0..313dcea127fe 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -799,7 +799,7 @@ static inline void hrtimer_switch_to_hres(void) { }
  *
  * This is only invoked when:
  *	- CONFIG_HIGH_RES_TIMERS is enabled.
- *	- CONFIG_NOHZ_COMMON is enabled
+ *	- CONFIG_NO_HZ_COMMON is enabled
  *
  * For the other cases this function is empty and because the call sites
  * are optimized out it vanishes as well, i.e. no need for lots of
@@ -1352,8 +1352,14 @@ static inline bool hrtimer_keep_base(struct hrtimer *timer, bool is_local, bool
 	return hrtimer_prefer_local(is_local, is_first, is_pinned);
 }
 
-static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns,
-				     const enum hrtimer_mode mode, struct hrtimer_clock_base *base)
+enum {
+	HRTIMER_REPROGRAM_NONE,
+	HRTIMER_REPROGRAM,
+	HRTIMER_REPROGRAM_FORCE,
+};
+
+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);
 	bool is_pinned, first, was_first, keep_base = false;
@@ -1410,7 +1416,7 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del
 	/* If a deferred rearm is pending skip reprogramming the device */
 	if (cpu_base->deferred_rearm) {
 		cpu_base->deferred_needs_update = true;
-		return false;
+		return HRTIMER_REPROGRAM_NONE;
 	}
 
 	if (!was_first || cpu_base != this_cpu_base) {
@@ -1423,7 +1429,7 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del
 		 * callbacks.
 		 */
 		if (likely(hrtimer_base_is_online(this_cpu_base)))
-			return first;
+			return first ? HRTIMER_REPROGRAM : HRTIMER_REPROGRAM_NONE;
 
 		/*
 		 * Timer was enqueued remote because the current base is
@@ -1432,7 +1438,7 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del
 		 */
 		if (first)
 			smp_call_function_single_async(cpu_base->cpu, &cpu_base->csd);
-		return false;
+		return HRTIMER_REPROGRAM_NONE;
 	}
 
 	/*
@@ -1446,7 +1452,7 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del
 	 */
 	if (timer->is_lazy) {
 		if (cpu_base->expires_next <= hrtimer_get_expires(timer))
-			return false;
+			return HRTIMER_REPROGRAM_NONE;
 	}
 
 	/*
@@ -1455,8 +1461,24 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del
 	 * reprogram the hardware by evaluating the new first expiring
 	 * timer.
 	 */
-	hrtimer_force_reprogram(cpu_base, /* skip_equal */ true);
-	return false;
+	return HRTIMER_REPROGRAM_FORCE;
+}
+
+static int hrtimer_start_range_ns_common(struct hrtimer *timer, ktime_t tim,
+					 u64 delta_ns, const enum hrtimer_mode mode,
+					 struct hrtimer_clock_base *base)
+{
+	/*
+	 * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft
+	 * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard
+	 * expiry mode because unmarked timers are moved to softirq expiry.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft);
+	else
+		WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard);
+
+	return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, base);
 }
 
 /**
@@ -1476,24 +1498,104 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns,
 
 	debug_hrtimer_assert_init(timer);
 
+	base = lock_hrtimer_base(timer, &flags);
+
+	switch (hrtimer_start_range_ns_common(timer, tim, delta_ns, mode, base)) {
+	case HRTIMER_REPROGRAM:
+		hrtimer_reprogram(timer, true);
+		break;
+	case HRTIMER_REPROGRAM_FORCE:
+		hrtimer_force_reprogram(timer->base->cpu_base, 1);
+		break;
+	case HRTIMER_REPROGRAM_NONE:
+		break;
+	}
+
+	unlock_hrtimer_base(timer, &flags);
+}
+EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
+
+static inline bool hrtimer_check_user_timer(struct hrtimer *timer)
+{
+	struct hrtimer_cpu_base *cpu_base = timer->base->cpu_base;
+	ktime_t expires;
+
 	/*
-	 * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft
-	 * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard
-	 * expiry mode because unmarked timers are moved to softirq expiry.
+	 * This uses soft expires because that's the user provided
+	 * expiry time, while expires can be further in the past
+	 * due to a slack value added to the user expiry time.
 	 */
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
-		WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft);
-	else
-		WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard);
+	expires = hrtimer_get_softexpires(timer);
+
+	/* Convert to monotonic */
+	expires = ktime_sub(expires, timer->base->offset);
+
+	/*
+	 * Check whether this timer will end up as the first expiring timer in
+	 * the CPU base. If not, no further checks required as it's then
+	 * guaranteed to expire in the future.
+	 */
+	if (expires >= cpu_base->expires_next)
+		return true;
+
+	/* Validate that the expiry time is in the future. */
+	if (expires > ktime_get())
+		return true;
+
+	debug_hrtimer_deactivate(timer);
+	__remove_hrtimer(timer, timer->base, HRTIMER_STATE_INACTIVE, false);
+	trace_hrtimer_start_expired(timer);
+	return false;
+}
+
+/**
+ * hrtimer_start_range_ns_user - (re)start an user controlled hrtimer
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @delta_ns:	"slack" range for the timer
+ * @mode:	timer mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED);
+ *		softirq based mode is considered for debug purpose only!
+ *
+ * Returns: True when the timer was queued, false if it was already expired
+ *
+ * This function cannot invoke the timer callback for expired timers as it might
+ * be called under a lock which the timer callback needs to acquire. So the
+ * caller has to handle that case.
+ */
+bool hrtimer_start_range_ns_user(struct hrtimer *timer, ktime_t tim,
+				 u64 delta_ns, const enum hrtimer_mode mode)
+{
+	struct hrtimer_clock_base *base;
+	unsigned long flags;
+	bool ret = true;
+
+	debug_hrtimer_assert_init(timer);
 
 	base = lock_hrtimer_base(timer, &flags);
 
-	if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base))
-		hrtimer_reprogram(timer, true);
+	switch (hrtimer_start_range_ns_common(timer, tim, delta_ns, mode, base)) {
+	case HRTIMER_REPROGRAM:
+		ret = hrtimer_check_user_timer(timer);
+		if (ret)
+			hrtimer_reprogram(timer, true);
+		break;
+	case HRTIMER_REPROGRAM_FORCE:
+		ret = hrtimer_check_user_timer(timer);
+		/*
+		 * The base must always be reevaluated, independent of the
+		 * result above because the timer was the first pending timer.
+		 */
+		hrtimer_force_reprogram(timer->base->cpu_base, 1);
+		break;
+	case HRTIMER_REPROGRAM_NONE:
+		break;
+	}
 
 	unlock_hrtimer_base(timer, &flags);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
+EXPORT_SYMBOL_GPL(hrtimer_start_range_ns_user);
 
 /**
  * hrtimer_try_to_cancel - try to deactivate a timer
@@ -1681,10 +1783,10 @@ EXPORT_SYMBOL_GPL(__hrtimer_get_remaining);
  *
  * Returns the next expiry time or KTIME_MAX if no timer is pending.
  */
-u64 hrtimer_get_next_event(void)
+ktime_t hrtimer_get_next_event(void)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	u64 expires = KTIME_MAX;
+	ktime_t expires = KTIME_MAX;
 
 	guard(raw_spinlock_irqsave)(&cpu_base->lock);
 	if (!hrtimer_hres_active(cpu_base))
@@ -1700,10 +1802,10 @@ u64 hrtimer_get_next_event(void)
  * Returns the next expiry time over all timers except for the @exclude one or
  * KTIME_MAX if none of them is pending.
  */
-u64 hrtimer_next_event_without(const struct hrtimer *exclude)
+ktime_t hrtimer_next_event_without(const struct hrtimer *exclude)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	u64 expires = KTIME_MAX;
+	ktime_t expires = KTIME_MAX;
 	unsigned int active;
 
 	guard(raw_spinlock_irqsave)(&cpu_base->lock);
@@ -2213,7 +2315,11 @@ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode
 	if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard)
 		mode |= HRTIMER_MODE_HARD;
 
-	hrtimer_start_expires(&sl->timer, mode);
+	/* If already expired, clear the task pointer and set current state to running */
+	if (!hrtimer_start_expires_user(&sl->timer, mode)) {
+		sl->task = NULL;
+		__set_current_state(TASK_RUNNING);
+	}
 }
 EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires);
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 1c954f330dfe..d51428867a33 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -60,15 +60,14 @@ EXPORT_SYMBOL(get_jiffies_64);
 
 EXPORT_SYMBOL(jiffies);
 
-static int __init init_jiffies_clocksource(void)
-{
-	return __clocksource_register(&clocksource_jiffies);
-}
-
-core_initcall(init_jiffies_clocksource);
+static bool cs_jiffies_registered __initdata;
 
 struct clocksource * __init __weak clocksource_default_clock(void)
 {
+	if (!cs_jiffies_registered) {
+		__clocksource_register(&clocksource_jiffies);
+		cs_jiffies_registered = true;
+	}
 	return &clocksource_jiffies;
 }
 
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 4bca3f78c8ea..5fa0af66cf3f 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -57,6 +57,7 @@ ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim,
 
 	return tim;
 }
+EXPORT_SYMBOL_GPL(do_timens_ktime_to_host);
 
 static struct ucounts *inc_time_namespaces(struct user_namespace *ns)
 {
@@ -351,6 +352,7 @@ struct time_namespace init_time_ns = {
 	.user_ns	= &init_user_ns,
 	.frozen_offsets	= true,
 };
+EXPORT_SYMBOL_GPL(init_time_ns);
 
 void __init time_ns_init(void)
 {
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 0de2bb7cbec0..5e633d8750d1 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -19,7 +19,7 @@
 
 #include "posix-timers.h"
 
-static void posix_cpu_timer_rearm(struct k_itimer *timer);
+static bool posix_cpu_timer_rearm(struct k_itimer *timer);
 
 void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit)
 {
@@ -41,7 +41,7 @@ void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit)
  */
 int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
 {
-	u64 nsecs = rlim_new * NSEC_PER_SEC;
+	u64 nsecs = (u64)rlim_new * NSEC_PER_SEC;
 	unsigned long irq_fl;
 
 	if (!lock_task_sighand(task, &irq_fl))
@@ -1011,24 +1011,27 @@ static void check_process_timers(struct task_struct *tsk,
 /*
  * This is called from the signal code (via posixtimer_rearm)
  * when the last timer signal was delivered and we have to reload the timer.
+ *
+ * Return true unconditionally so the core code assumes the timer to be
+ * armed. Otherwise it would requeue the signal.
  */
-static void posix_cpu_timer_rearm(struct k_itimer *timer)
+static bool posix_cpu_timer_rearm(struct k_itimer *timer)
 {
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
-	struct task_struct *p;
 	struct sighand_struct *sighand;
+	struct task_struct *p;
 	unsigned long flags;
 	u64 now;
 
-	rcu_read_lock();
+	guard(rcu)();
 	p = cpu_timer_task_rcu(timer);
 	if (!p)
-		goto out;
+		return true;
 
 	/* Protect timer list r/w in arm_timer() */
 	sighand = lock_task_sighand(p, &flags);
 	if (unlikely(sighand == NULL))
-		goto out;
+		return true;
 
 	/*
 	 * Fetch the current sample and update the timer's expiry time.
@@ -1045,8 +1048,7 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
 	 */
 	arm_timer(timer, p);
 	unlock_task_sighand(p, &flags);
-out:
-	rcu_read_unlock();
+	return true;
 }
 
 /**
@@ -1504,6 +1506,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		spin_lock_irq(&timer.it_lock);
 		error = posix_cpu_timer_set(&timer, flags, &it, NULL);
 		if (error) {
+			posix_cpu_timer_del(&timer);
 			spin_unlock_irq(&timer.it_lock);
 			return error;
 		}
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 9331e1614124..436ba794cc0b 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -288,16 +288,18 @@ static inline int timer_overrun_to_int(struct k_itimer *timr)
 	return (int)timr->it_overrun_last;
 }
 
-static void common_hrtimer_rearm(struct k_itimer *timr)
+static bool common_hrtimer_rearm(struct k_itimer *timr)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
 
 	timr->it_overrun += hrtimer_forward_now(timer, timr->it_interval);
-	hrtimer_restart(timer);
+	return hrtimer_start_expires_user(timer, HRTIMER_MODE_ABS);
 }
 
 static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_itimer *timr)
 {
+	bool queued;
+
 	guard(spinlock)(&timr->it_lock);
 
 	/*
@@ -311,12 +313,18 @@ static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_it
 	if (!timr->it_interval || WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING))
 		return true;
 
-	timr->kclock->timer_rearm(timr);
-	timr->it_status = POSIX_TIMER_ARMED;
+	/* timer_rearm() updates timr::it_overrun */
+	queued = timr->kclock->timer_rearm(timr);
+
 	timr->it_overrun_last = timr->it_overrun;
 	timr->it_overrun = -1LL;
 	++timr->it_signal_seq;
 	info->si_overrun = timer_overrun_to_int(timr);
+
+	if (queued)
+		timr->it_status = POSIX_TIMER_ARMED;
+	else
+		posix_timer_queue_signal(timr);
 	return true;
 }
 
@@ -795,7 +803,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 		return timer_overrun_to_int(scoped_timer);
 }
 
-static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires,
+static bool common_hrtimer_arm(struct k_itimer *timr, ktime_t expires,
 			       bool absolute, bool sigev_none)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
@@ -820,8 +828,11 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires,
 		expires = ktime_add_safe(expires, hrtimer_cb_get_time(timer));
 	hrtimer_set_expires(timer, expires);
 
-	if (!sigev_none)
-		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+	/* For sigev_none pretend that the timer is queued */
+	if (sigev_none)
+		return true;
+
+	return hrtimer_start_expires_user(timer, HRTIMER_MODE_ABS);
 }
 
 static int common_hrtimer_try_to_cancel(struct k_itimer *timr)
@@ -903,9 +914,13 @@ int common_timer_set(struct k_itimer *timr, int flags,
 		expires = timens_ktime_to_host(timr->it_clock, expires);
 	sigev_none = timr->it_sigev_notify == SIGEV_NONE;
 
-	kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none);
-	if (!sigev_none)
-		timr->it_status = POSIX_TIMER_ARMED;
+	if (kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none)) {
+		if (!sigev_none)
+			timr->it_status = POSIX_TIMER_ARMED;
+	} else {
+		/* Timer was already expired, queue the signal */
+		posix_timer_queue_signal(timr);
+	}
 	return 0;
 }
 
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index 7f259e845d24..4ea9611dd716 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -27,11 +27,11 @@ struct k_clock {
 	int	(*timer_del)(struct k_itimer *timr);
 	void	(*timer_get)(struct k_itimer *timr,
 			     struct itimerspec64 *cur_setting);
-	void	(*timer_rearm)(struct k_itimer *timr);
+	bool	(*timer_rearm)(struct k_itimer *timr);
 	s64	(*timer_forward)(struct k_itimer *timr, ktime_t now);
 	ktime_t	(*timer_remaining)(struct k_itimer *timr, ktime_t now);
 	int	(*timer_try_to_cancel)(struct k_itimer *timr);
-	void	(*timer_arm)(struct k_itimer *timr, ktime_t expires,
+	bool	(*timer_arm)(struct k_itimer *timr, ktime_t expires,
 			     bool absolute, bool sigev_none);
 	void	(*timer_wait_running)(struct k_itimer *timr);
 };
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index cbbb87a0c6e7..98a9cae915c0 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -285,8 +285,6 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) &&
 	    tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
 		touch_softlockup_watchdog_sched();
-		if (is_idle_task(current))
-			ts->idle_jiffies++;
 		/*
 		 * In case the current tick fired too early past its expected
 		 * expiration, make sure we don't bypass the next clock reprogramming
@@ -751,119 +749,6 @@ static void tick_nohz_update_jiffies(ktime_t now)
 	touch_softlockup_watchdog_sched();
 }
 
-static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
-{
-	ktime_t delta;
-
-	if (WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)))
-		return;
-
-	delta = ktime_sub(now, ts->idle_entrytime);
-
-	write_seqcount_begin(&ts->idle_sleeptime_seq);
-	if (nr_iowait_cpu(smp_processor_id()) > 0)
-		ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
-	else
-		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-
-	ts->idle_entrytime = now;
-	tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE);
-	write_seqcount_end(&ts->idle_sleeptime_seq);
-
-	sched_clock_idle_wakeup_event();
-}
-
-static void tick_nohz_start_idle(struct tick_sched *ts)
-{
-	write_seqcount_begin(&ts->idle_sleeptime_seq);
-	ts->idle_entrytime = ktime_get();
-	tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE);
-	write_seqcount_end(&ts->idle_sleeptime_seq);
-
-	sched_clock_idle_sleep_event();
-}
-
-static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
-				 bool compute_delta, u64 *last_update_time)
-{
-	ktime_t now, idle;
-	unsigned int seq;
-
-	if (!tick_nohz_active)
-		return -1;
-
-	now = ktime_get();
-	if (last_update_time)
-		*last_update_time = ktime_to_us(now);
-
-	do {
-		seq = read_seqcount_begin(&ts->idle_sleeptime_seq);
-
-		if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) {
-			ktime_t delta = ktime_sub(now, ts->idle_entrytime);
-
-			idle = ktime_add(*sleeptime, delta);
-		} else {
-			idle = *sleeptime;
-		}
-	} while (read_seqcount_retry(&ts->idle_sleeptime_seq, seq));
-
-	return ktime_to_us(idle);
-
-}
-
-/**
- * get_cpu_idle_time_us - get the total idle time of a CPU
- * @cpu: CPU number to query
- * @last_update_time: variable to store update time in. Do not update
- * counters if NULL.
- *
- * Return the cumulative idle time (since boot) for a given
- * CPU, in microseconds. Note that this is partially broken due to
- * the counter of iowait tasks that can be remotely updated without
- * any synchronization. Therefore it is possible to observe backward
- * values within two consecutive reads.
- *
- * This time is measured via accounting rather than sampling,
- * and is as accurate as ktime_get() is.
- *
- * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu
- */
-u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
-{
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-
-	return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime,
-				     !nr_iowait_cpu(cpu), last_update_time);
-}
-EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
-
-/**
- * get_cpu_iowait_time_us - get the total iowait time of a CPU
- * @cpu: CPU number to query
- * @last_update_time: variable to store update time in. Do not update
- * counters if NULL.
- *
- * Return the cumulative iowait time (since boot) for a given
- * CPU, in microseconds. Note this is partially broken due to
- * the counter of iowait tasks that can be remotely updated without
- * any synchronization. Therefore it is possible to observe backward
- * values within two consecutive reads.
- *
- * This time is measured via accounting rather than sampling,
- * and is as accurate as ktime_get() is.
- *
- * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu
- */
-u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
-{
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-
-	return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime,
-				     nr_iowait_cpu(cpu), last_update_time);
-}
-EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
-
 /* Simplified variant of hrtimer_forward_now() */
 static ktime_t tick_forward_now(ktime_t expires, ktime_t now)
 {
@@ -1273,7 +1158,7 @@ void tick_nohz_idle_stop_tick(void)
 		ts->idle_expires = expires;
 
 		if (!was_stopped && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
-			ts->idle_jiffies = ts->last_jiffies;
+			kcpustat_dyntick_start(ts->idle_entrytime);
 			nohz_balance_enter_idle(cpu);
 		}
 	} else {
@@ -1286,6 +1171,20 @@ void tick_nohz_idle_retain_tick(void)
 	tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched));
 }
 
+static void tick_nohz_clock_sleep(struct tick_sched *ts)
+{
+	tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE);
+	sched_clock_idle_sleep_event();
+}
+
+static void tick_nohz_clock_wakeup(struct tick_sched *ts)
+{
+	if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)) {
+		tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE);
+		sched_clock_idle_wakeup_event();
+	}
+}
+
 /**
  * tick_nohz_idle_enter - prepare for entering idle on the current CPU
  *
@@ -1300,11 +1199,10 @@ void tick_nohz_idle_enter(void)
 	local_irq_disable();
 
 	ts = this_cpu_ptr(&tick_cpu_sched);
-
 	WARN_ON_ONCE(ts->timer_expires_base);
-
 	tick_sched_flag_set(ts, TS_FLAG_INIDLE);
-	tick_nohz_start_idle(ts);
+	ts->idle_entrytime = ktime_get();
+	tick_nohz_clock_sleep(ts);
 
 	local_irq_enable();
 }
@@ -1332,10 +1230,14 @@ void tick_nohz_irq_exit(void)
 {
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
-	if (tick_sched_flag_test(ts, TS_FLAG_INIDLE))
-		tick_nohz_start_idle(ts);
-	else
+	if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) {
+		tick_nohz_clock_sleep(ts);
+		ts->idle_entrytime = ktime_get();
+		if (tick_sched_flag_test(ts, TS_FLAG_STOPPED))
+			kcpustat_irq_exit(ts->idle_entrytime);
+	} else {
 		tick_nohz_full_update_tick(ts);
+	}
 }
 
 /**
@@ -1407,8 +1309,7 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 	 * If the next highres timer to expire is earlier than 'next_event', the
 	 * idle governor needs to know that.
 	 */
-	next_event = min_t(u64, next_event,
-			   hrtimer_next_event_without(&ts->sched_timer));
+	next_event = min(next_event, hrtimer_next_event_without(&ts->sched_timer));
 
 	return ktime_sub(next_event, now);
 }
@@ -1429,36 +1330,20 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
 	return ts->idle_calls;
 }
 
-static void tick_nohz_account_idle_time(struct tick_sched *ts,
-					ktime_t now)
-{
-	unsigned long ticks;
-
-	ts->idle_exittime = now;
-
-	if (vtime_accounting_enabled_this_cpu())
-		return;
-	/*
-	 * We stopped the tick in idle. update_process_times() would miss the
-	 * time we slept, as it does only a 1 tick accounting.
-	 * Enforce that this is accounted to idle !
-	 */
-	ticks = jiffies - ts->idle_jiffies;
-	/*
-	 * We might be one off. Do not randomly account a huge number of ticks!
-	 */
-	if (ticks && ticks < LONG_MAX)
-		account_idle_ticks(ticks);
-}
-
 void tick_nohz_idle_restart_tick(void)
 {
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
-		ktime_t now = ktime_get();
-		tick_nohz_restart_sched_tick(ts, now);
-		tick_nohz_account_idle_time(ts, now);
+		/*
+		 * Update entrytime here in case the tick restart is due to temporary
+		 * polling on forced broadcast. The tick may be stopped again later within
+		 * the same idle trip. The idle_entrytime was updated recently but make sure
+		 * no tiny amount of idle time is accounted twice.
+		 */
+		ts->idle_entrytime = ktime_get();
+		kcpustat_dyntick_stop(ts->idle_entrytime);
+		tick_nohz_restart_sched_tick(ts, ts->idle_entrytime);
 	}
 }
 
@@ -1468,8 +1353,6 @@ static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now)
 		__tick_nohz_full_update_tick(ts, now);
 	else
 		tick_nohz_restart_sched_tick(ts, now);
-
-	tick_nohz_account_idle_time(ts, now);
 }
 
 /**
@@ -1491,7 +1374,6 @@ static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now)
 void tick_nohz_idle_exit(void)
 {
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
-	bool idle_active, tick_stopped;
 	ktime_t now;
 
 	local_irq_disable();
@@ -1500,17 +1382,13 @@ void tick_nohz_idle_exit(void)
 	WARN_ON_ONCE(ts->timer_expires_base);
 
 	tick_sched_flag_clear(ts, TS_FLAG_INIDLE);
-	idle_active = tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE);
-	tick_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
+	tick_nohz_clock_wakeup(ts);
 
-	if (idle_active || tick_stopped)
+	if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
 		now = ktime_get();
-
-	if (idle_active)
-		tick_nohz_stop_idle(ts, now);
-
-	if (tick_stopped)
+		kcpustat_dyntick_stop(now);
 		tick_nohz_idle_update_tick(ts, now);
+	}
 
 	local_irq_enable();
 }
@@ -1565,11 +1443,14 @@ static inline void tick_nohz_irq_enter(void)
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t now;
 
-	if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED | TS_FLAG_IDLE_ACTIVE))
+	tick_nohz_clock_wakeup(ts);
+
+	if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED))
 		return;
+
 	now = ktime_get();
-	if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE))
-		tick_nohz_stop_idle(ts, now);
+	kcpustat_irq_enter(now);
+
 	/*
 	 * If all CPUs are idle we may need to update a stale jiffies value.
 	 * Note nohz_full is a special case: a timekeeper is guaranteed to stay
@@ -1577,8 +1458,7 @@ static inline void tick_nohz_irq_enter(void)
 	 * rare case (typically stop machine). So we must make sure we have a
 	 * last resort.
 	 */
-	if (tick_sched_flag_test(ts, TS_FLAG_STOPPED))
-		tick_nohz_update_jiffies(now);
+	tick_nohz_update_jiffies(now);
 }
 
 #else
@@ -1648,20 +1528,15 @@ void tick_setup_sched_timer(bool hrtimer)
 void tick_sched_timer_dying(int cpu)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-	ktime_t idle_sleeptime, iowait_sleeptime;
 	unsigned long idle_calls, idle_sleeps;
 
 	/* This must happen before hrtimers are migrated! */
 	if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES))
 		hrtimer_cancel(&ts->sched_timer);
 
-	idle_sleeptime = ts->idle_sleeptime;
-	iowait_sleeptime = ts->iowait_sleeptime;
 	idle_calls = ts->idle_calls;
 	idle_sleeps = ts->idle_sleeps;
 	memset(ts, 0, sizeof(*ts));
-	ts->idle_sleeptime = idle_sleeptime;
-	ts->iowait_sleeptime = iowait_sleeptime;
 	ts->idle_calls = idle_calls;
 	ts->idle_sleeps = idle_sleeps;
 }
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index b4a7822f495d..79b9252047b1 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -44,9 +44,7 @@ struct tick_device {
  *			to resume the tick timer operation in the timeline
  *			when the CPU returns from nohz sleep.
  * @next_tick:		Next tick to be fired when in dynticks mode.
- * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_waketime:	Time when the idle was interrupted
- * @idle_sleeptime_seq:	sequence counter for data consistency
  * @idle_entrytime:	Time when the idle call was entered
  * @last_jiffies:	Base jiffies snapshot when next event was last computed
  * @timer_expires_base:	Base time clock monotonic for @timer_expires
@@ -55,9 +53,6 @@ struct tick_device {
  * @idle_expires:	Next tick in idle, for debugging purpose only
  * @idle_calls:		Total number of idle calls
  * @idle_sleeps:	Number of idle calls, where the sched tick was stopped
- * @idle_exittime:	Time when the idle state was left
- * @idle_sleeptime:	Sum of the time slept in idle with sched tick stopped
- * @iowait_sleeptime:	Sum of the time slept in idle with sched tick stopped, with IO outstanding
  * @tick_dep_mask:	Tick dependency mask - is set, if someone needs the tick
  * @check_clocks:	Notification mechanism about clocksource changes
  */
@@ -73,12 +68,10 @@ struct tick_sched {
 	struct hrtimer			sched_timer;
 	ktime_t				last_tick;
 	ktime_t				next_tick;
-	unsigned long			idle_jiffies;
 	ktime_t				idle_waketime;
 	unsigned int			got_idle_tick;
 
 	/* Idle entry */
-	seqcount_t			idle_sleeptime_seq;
 	ktime_t				idle_entrytime;
 
 	/* Tick stop */
@@ -90,11 +83,6 @@ struct tick_sched {
 	unsigned long			idle_calls;
 	unsigned long			idle_sleeps;
 
-	/* Idle exit */
-	ktime_t				idle_exittime;
-	ktime_t				idle_sleeptime;
-	ktime_t				iowait_sleeptime;
-
 	/* Full dynticks handling */
 	atomic_t			tick_dep_mask;
 
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 0d832317d576..0dd63a91e7c5 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -207,7 +207,7 @@ SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv,
 		    get_user(new_ts.tv_nsec, &tv->tv_usec))
 			return -EFAULT;
 
-		if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0)
+		if (new_ts.tv_nsec >= USEC_PER_SEC || new_ts.tv_nsec < 0)
 			return -EINVAL;
 
 		new_ts.tv_nsec *= NSEC_PER_USEC;
@@ -251,7 +251,7 @@ COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv,
 		    get_user(new_ts.tv_nsec, &tv->tv_usec))
 			return -EFAULT;
 
-		if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0)
+		if (new_ts.tv_nsec >= USEC_PER_SEC || new_ts.tv_nsec < 0)
 			return -EINVAL;
 
 		new_ts.tv_nsec *= NSEC_PER_USEC;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index c493a4010305..b1b5ec43c0f2 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -67,6 +67,7 @@ static inline bool tk_is_aux(const struct timekeeper *tk)
 {
 	return tk->id >= TIMEKEEPER_AUX_FIRST && tk->id <= TIMEKEEPER_AUX_LAST;
 }
+static inline struct tk_data *aux_get_tk_data(clockid_t id);
 #else
 static inline bool tk_get_aux_ts64(unsigned int tkid, struct timespec64 *ts)
 {
@@ -77,6 +78,10 @@ static inline bool tk_is_aux(const struct timekeeper *tk)
 {
 	return false;
 }
+static inline struct tk_data *aux_get_tk_data(clockid_t id)
+{
+	return NULL;
+}
 #endif
 
 static inline void tk_update_aux_offs(struct timekeeper *tk, ktime_t offs)
@@ -315,6 +320,7 @@ static __always_inline u64 tk_clock_read(const struct tk_read_base *tkr)
 
 	return clock->read(clock);
 }
+
 static inline void clocksource_disable_inline_read(void) { }
 static inline void clocksource_enable_inline_read(void) { }
 #endif
@@ -1182,44 +1188,107 @@ noinstr time64_t __ktime_get_real_seconds(void)
 	return tk->xtime_sec;
 }
 
-/**
- * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter
- * @systime_snapshot:	pointer to struct receiving the system time snapshot
- */
-void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
+static inline u64 tk_clock_read_snapshot(const struct tk_read_base *tkr,
+					 struct clocksource_hw_snapshot *chs)
 {
-	struct timekeeper *tk = &tk_core.timekeeper;
+	struct clocksource *clock = READ_ONCE(tkr->clock);
+
+	if (unlikely(clock->read_snapshot))
+		return clock->read_snapshot(clock, chs);
+
+	return clock->read(clock);
+}
+
+
+/**
+ * ktime_get_snapshot_id -  Simultaneously snapshot a given clock ID with
+ *			    CLOCK_MONOTONIC_RAW and the underlying
+ *			    clocksource counter value.
+ * @clock_id:		The clock ID to snapshot
+ * @systime_snapshot:	Pointer to struct receiving the system time snapshot
+ */
+void ktime_get_snapshot_id(clockid_t clock_id, struct system_time_snapshot *systime_snapshot)
+{
+	ktime_t base_raw, base_sys, offs_sys, *offs, offs_zero = 0;
+	u64 nsec_raw, nsec_sys, now;
+	struct timekeeper *tk;
+	struct tk_data *tkd;
 	unsigned int seq;
-	ktime_t base_raw;
-	ktime_t base_real;
-	ktime_t base_boot;
-	u64 nsec_raw;
-	u64 nsec_real;
-	u64 now;
 
-	WARN_ON_ONCE(timekeeping_suspended);
+	/* Invalidate the snapshot for all failure cases */
+	systime_snapshot->valid = false;
+
+	if (WARN_ON_ONCE(timekeeping_suspended))
+		return;
+
+	switch (clock_id) {
+	case CLOCK_REALTIME:
+		tkd = &tk_core;
+		offs = &tk_core.timekeeper.offs_real;
+		break;
+	/* Map RAW to MONOTONIC so the loop below is trivial */
+	case CLOCK_MONOTONIC_RAW:
+	case CLOCK_MONOTONIC:
+		tkd = &tk_core;
+		offs = &offs_zero;
+		break;
+	case CLOCK_BOOTTIME:
+		tkd = &tk_core;
+		offs = &tk_core.timekeeper.offs_boot;
+		break;
+	case CLOCK_AUX ... CLOCK_AUX_LAST:
+		tkd = aux_get_tk_data(clock_id);
+		if (!tkd)
+			return;
+		offs = &tkd->timekeeper.offs_aux;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	tk = &tkd->timekeeper;
 
 	do {
-		seq = read_seqcount_begin(&tk_core.seq);
-		now = tk_clock_read(&tk->tkr_mono);
+		struct clocksource_hw_snapshot chs = { };
+
+		seq = read_seqcount_begin(&tkd->seq);
+
+		/* Aux clocks can be invalid */
+		if (!tk->clock_valid)
+			return;
+
+		now = tk_clock_read_snapshot(&tk->tkr_mono, &chs);
 		systime_snapshot->cs_id = tk->tkr_mono.clock->id;
+
+		systime_snapshot->hw_cycles = chs.hw_cycles;
+		systime_snapshot->hw_csid = chs.hw_csid;
+
 		systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq;
 		systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq;
-		base_real = ktime_add(tk->tkr_mono.base,
-				      tk_core.timekeeper.offs_real);
-		base_boot = ktime_add(tk->tkr_mono.base,
-				      tk_core.timekeeper.offs_boot);
+
+		base_sys = tk->tkr_mono.base;
+		offs_sys = *offs;
 		base_raw = tk->tkr_raw.base;
-		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now);
-		nsec_raw  = timekeeping_cycles_to_ns(&tk->tkr_raw, now);
-	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+		nsec_sys = timekeeping_cycles_to_ns(&tk->tkr_mono, now);
+		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now);
+	} while (read_seqcount_retry(&tkd->seq, seq));
 
 	systime_snapshot->cycles = now;
-	systime_snapshot->real = ktime_add_ns(base_real, nsec_real);
-	systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real);
-	systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw);
+	systime_snapshot->systime = ktime_add_ns(base_sys, offs_sys + nsec_sys);
+	systime_snapshot->monoraw = ktime_add_ns(base_raw, nsec_raw);
+
+	/*
+	 * Special case for PTP. Just transfer the raw time into sys,
+	 * so the call sites can consistently use snap::systime.
+	 */
+	if (clock_id == CLOCK_MONOTONIC_RAW)
+		systime_snapshot->systime = systime_snapshot->monoraw;
+	/* Tell the consumer that this snapshot is valid */
+	systime_snapshot->valid = true;
 }
-EXPORT_SYMBOL_GPL(ktime_get_snapshot);
+EXPORT_SYMBOL_GPL(ktime_get_snapshot_id);
 
 /* Scale base by mult/div checking for overflow */
 static int scale64_check_overflow(u64 mult, u64 div, u64 *base)
@@ -1262,7 +1331,7 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history,
 					 struct system_device_crosststamp *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	u64 corr_raw, corr_real;
+	u64 corr_raw, corr_sys;
 	bool interp_forward;
 	int ret;
 
@@ -1279,8 +1348,7 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history,
 	 * Scale the monotonic raw time delta by:
 	 *	partial_history_cycles / total_history_cycles
 	 */
-	corr_raw = (u64)ktime_to_ns(
-		ktime_sub(ts->sys_monoraw, history->raw));
+	corr_raw = (u64)ktime_to_ns(ktime_sub(ts->sys_monoraw, history->monoraw));
 	ret = scale64_check_overflow(partial_history_cycles,
 				     total_history_cycles, &corr_raw);
 	if (ret)
@@ -1288,30 +1356,29 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history,
 
 	/*
 	 * If there is a discontinuity in the history, scale monotonic raw
-	 *	correction by:
-	 *	mult(real)/mult(raw) yielding the realtime correction
-	 * Otherwise, calculate the realtime correction similar to monotonic
-	 *	raw calculation
+	 * correction by:
+	 *	mult(sys)/mult(raw) yielding the system time correction
+	 *
+	 * Otherwise, calculate the system time correction similar to monotonic
+	 * raw calculation
 	 */
 	if (discontinuity) {
-		corr_real = mul_u64_u32_div
-			(corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult);
+		corr_sys = mul_u64_u32_div(corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult);
 	} else {
-		corr_real = (u64)ktime_to_ns(
-			ktime_sub(ts->sys_realtime, history->real));
-		ret = scale64_check_overflow(partial_history_cycles,
-					     total_history_cycles, &corr_real);
+		corr_sys = (u64)ktime_to_ns(ktime_sub(ts->sys_systime, history->systime));
+		ret = scale64_check_overflow(partial_history_cycles, total_history_cycles,
+					     &corr_sys);
 		if (ret)
 			return ret;
 	}
 
-	/* Fixup monotonic raw and real time time values */
+	/* Fixup monotonic raw and system time time values */
 	if (interp_forward) {
-		ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw);
-		ts->sys_realtime = ktime_add_ns(history->real, corr_real);
+		ts->sys_monoraw = ktime_add_ns(history->monoraw, corr_raw);
+		ts->sys_systime = ktime_add_ns(history->systime, corr_sys);
 	} else {
 		ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw);
-		ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real);
+		ts->sys_systime = ktime_sub_ns(ts->sys_systime, corr_sys);
 	}
 
 	return 0;
@@ -1368,6 +1435,8 @@ static bool convert_base_to_cs(struct system_counterval_t *scv)
 		return false;
 
 	scv->cycles += base->offset;
+	/* Set the clocksource ID as scv::cycles is now clocksource based */
+	scv->cs_id = cs->id;
 	return true;
 }
 
@@ -1435,11 +1504,11 @@ EXPORT_SYMBOL_GPL(ktime_real_to_base_clock);
 
 /**
  * get_device_system_crosststamp - Synchronously capture system/device timestamp
- * @get_time_fn:	Callback to get simultaneous device time and
- *	system counter from the device driver
+ * @get_time_fn:	Callback to get simultaneous device time and system counter
+ *			from the device driver
  * @ctx:		Context passed to get_time_fn()
- * @history_begin:	Historical reference point used to interpolate system
- *	time when counter provided by the driver is before the current interval
+ * @history_begin:	Historical reference point used to interpolate system time when
+ *			the counter value provided by the driver is before the current interval
  * @xtstamp:		Receives simultaneously captured system and device time
  *
  * Reads a timestamp from a device and correlates it to system time
@@ -1452,36 +1521,54 @@ int get_device_system_crosststamp(int (*get_time_fn)
 				  struct system_time_snapshot *history_begin,
 				  struct system_device_crosststamp *xtstamp)
 {
-	struct system_counterval_t system_counterval = {};
-	struct timekeeper *tk = &tk_core.timekeeper;
-	u64 cycles, now, interval_start;
-	unsigned int clock_was_set_seq = 0;
-	ktime_t base_real, base_raw;
-	u64 nsec_real, nsec_raw;
+	u64 syscnt_cycles, cycles, now, interval_start;
+	unsigned int seq, clock_was_set_seq = 0;
+	ktime_t base_sys, base_raw, *offs;
+	u64 nsec_sys, nsec_raw;
 	u8 cs_was_changed_seq;
-	unsigned int seq;
 	bool do_interp;
+	struct timekeeper *tk;
+	struct tk_data *tkd;
 	int ret;
 
+	switch (xtstamp->clock_id) {
+	case CLOCK_REALTIME:
+		tkd = &tk_core;
+		offs = &tk_core.timekeeper.offs_real;
+		break;
+	case CLOCK_AUX ... CLOCK_AUX_LAST:
+		tkd = aux_get_tk_data(xtstamp->clock_id);
+		if (!tkd)
+			return -ENODEV;
+		offs = &tkd->timekeeper.offs_aux;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -ENODEV;
+	}
+
+	tk = &tkd->timekeeper;
+
 	do {
-		seq = read_seqcount_begin(&tk_core.seq);
+		seq = read_seqcount_begin(&tkd->seq);
 		/*
 		 * Try to synchronously capture device time and a system
 		 * counter value calling back into the device driver
 		 */
-		ret = get_time_fn(&xtstamp->device, &system_counterval, ctx);
+		ret = get_time_fn(&xtstamp->device, &xtstamp->sys_counter, ctx);
 		if (ret)
 			return ret;
 
 		/*
 		 * Verify that the clocksource ID associated with the captured
 		 * system counter value is the same as for the currently
-		 * installed timekeeper clocksource
+		 * installed timekeeper clocksource and convert to it.
 		 */
-		if (system_counterval.cs_id == CSID_GENERIC ||
-		    !convert_base_to_cs(&system_counterval))
+		if (xtstamp->sys_counter.cs_id == CSID_GENERIC ||
+		    !convert_base_to_cs(&xtstamp->sys_counter))
 			return -ENODEV;
-		cycles = system_counterval.cycles;
+
+		cycles = syscnt_cycles = xtstamp->sys_counter.cycles;
 
 		/*
 		 * Check whether the system counter value provided by the
@@ -1498,15 +1585,14 @@ int get_device_system_crosststamp(int (*get_time_fn)
 			do_interp = false;
 		}
 
-		base_real = ktime_add(tk->tkr_mono.base,
-				      tk_core.timekeeper.offs_real);
+		base_sys = ktime_add(tk->tkr_mono.base, *offs);
 		base_raw = tk->tkr_raw.base;
 
-		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles);
+		nsec_sys = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles);
 		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles);
-	} while (read_seqcount_retry(&tk_core.seq, seq));
+	} while (read_seqcount_retry(&tkd->seq, seq));
 
-	xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real);
+	xtstamp->sys_systime = ktime_add_ns(base_sys, nsec_sys);
 	xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw);
 
 	/*
@@ -1523,24 +1609,19 @@ int get_device_system_crosststamp(int (*get_time_fn)
 		 * clocksource change
 		 */
 		if (!history_begin ||
-		    !timestamp_in_interval(history_begin->cycles,
-					   cycles, system_counterval.cycles) ||
+		    !timestamp_in_interval(history_begin->cycles, cycles, syscnt_cycles) ||
 		    history_begin->cs_was_changed_seq != cs_was_changed_seq)
 			return -EINVAL;
-		partial_history_cycles = cycles - system_counterval.cycles;
+
+		partial_history_cycles = cycles - syscnt_cycles;
 		total_history_cycles = cycles - history_begin->cycles;
-		discontinuity =
-			history_begin->clock_was_set_seq != clock_was_set_seq;
+		discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq;
 
-		ret = adjust_historical_crosststamp(history_begin,
-						    partial_history_cycles,
-						    total_history_cycles,
-						    discontinuity, xtstamp);
-		if (ret)
-			return ret;
+		ret = adjust_historical_crosststamp(history_begin, partial_history_cycles,
+						    total_history_cycles, discontinuity, xtstamp);
 	}
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(get_device_system_crosststamp);
 
@@ -1980,13 +2061,14 @@ void __init timekeeping_init(void)
 	 */
 	wall_to_mono = timespec64_sub(boot_offset, wall_time);
 
+	clock = clocksource_default_clock();
+	if (clock->enable)
+		clock->enable(clock);
+
 	guard(raw_spinlock_irqsave)(&tk_core.lock);
 
 	ntp_init();
 
-	clock = clocksource_default_clock();
-	if (clock->enable)
-		clock->enable(clock);
 	tk_setup_internals(tks, clock);
 
 	tk_set_xtime(tks, &wall_time);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 04d928c21aba..655a8c6cd84d 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1932,7 +1932,7 @@ static void timer_recalc_next_expiry(struct timer_base *base)
  */
 static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
 {
-	u64 nextevt = hrtimer_get_next_event();
+	u64 nextevt = ktime_to_ns(hrtimer_get_next_event());
 
 	/*
 	 * If high resolution timers are enabled
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 427d7ddea3af..514802def1e0 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -152,14 +152,10 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 		P_flag(highres, TS_FLAG_HIGHRES);
 		P_ns(last_tick);
 		P_flag(tick_stopped, TS_FLAG_STOPPED);
-		P(idle_jiffies);
 		P(idle_calls);
 		P(idle_sleeps);
 		P_ns(idle_entrytime);
 		P_ns(idle_waketime);
-		P_ns(idle_exittime);
-		P_ns(idle_sleeptime);
-		P_ns(iowait_sleeptime);
 		P(last_jiffies);
 		P(next_timer);
 		P_ns(idle_expires);
@@ -256,7 +252,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m)
 
 static inline void timer_list_header(struct seq_file *m, u64 now)
 {
-	SEQ_printf(m, "Timer List Version: v0.10\n");
+	SEQ_printf(m, "Timer List Version: v0.11\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 	SEQ_printf(m, "\n");
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 1d0d3a4058d5..806c23cf71fc 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -102,7 +102,7 @@
  * active CPU/group information atomic_try_cmpxchg() is used instead and only
  * the per CPU tmigr_cpu->lock is held.
  *
- * During the setup of groups tmigr_level_list is required. It is protected by
+ * During the setup of groups, hier->level_list is required. It is protected by
  * @tmigr_mutex.
  *
  * When @timer_base->lock as well as tmigr related locks are required, the lock
@@ -416,13 +416,12 @@
  */
 
 static DEFINE_MUTEX(tmigr_mutex);
-static struct list_head *tmigr_level_list __read_mostly;
+
+static LIST_HEAD(tmigr_hierarchy_list);
 
 static unsigned int tmigr_hierarchy_levels __read_mostly;
 static unsigned int tmigr_crossnode_level __read_mostly;
 
-static struct tmigr_group *tmigr_root;
-
 static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu);
 
 /*
@@ -978,8 +977,12 @@ static void tmigr_handle_remote_cpu(unsigned int cpu, u64 now,
 	/* Drop the lock to allow the remote CPU to exit idle */
 	raw_spin_unlock_irq(&tmc->lock);
 
-	if (cpu != smp_processor_id())
-		timer_expire_remote(cpu);
+	/*
+	 * This can't exclude the local CPU because jiffies might have advanced
+	 * after the timer softirq invoked run_timer_base(BASE_GLOBAL) and the
+	 * point where the jiffies snapshot @jif was taken in tmigr_handle_remote().
+	 */
+	timer_expire_remote(cpu);
 
 	/*
 	 * Lock ordering needs to be preserved - timer_base locks before tmigr
@@ -1465,6 +1468,34 @@ static long tmigr_trigger_active(void *unused)
 	return 0;
 }
 
+static unsigned int tmigr_get_capacity(int cpu)
+{
+	/*
+	 * nohz_full CPUs need to make sure there is always an available (online)
+	 * and never idle migrator to handle all their global timers. That duty
+	 * is served by the timekeeper which then never stops its tick. But the
+	 * timekeeper must then belong to the same hierarchy as all the nohz_full
+	 * CPUs. Simply turn off capacity awareness when nohz_full is running.
+	 */
+	if (tick_nohz_full_enabled() || !IS_ENABLED(CONFIG_BROKEN))
+		return SCHED_CAPACITY_SCALE;
+	else
+		return arch_scale_cpu_capacity(cpu);
+}
+
+static struct tmigr_hierarchy *__tmigr_get_hierarchy(int cpu)
+{
+	unsigned int capacity = tmigr_get_capacity(cpu);
+	struct tmigr_hierarchy *iter;
+
+	list_for_each_entry(iter, &tmigr_hierarchy_list, node) {
+		if (iter->capacity == capacity)
+			return iter;
+	}
+
+	return NULL;
+}
+
 static int tmigr_clear_cpu_available(unsigned int cpu)
 {
 	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
@@ -1489,8 +1520,21 @@ static int tmigr_clear_cpu_available(unsigned int cpu)
 	}
 
 	if (firstexp != KTIME_MAX) {
-		migrator = cpumask_any(tmigr_available_cpumask);
-		work_on_cpu(migrator, tmigr_trigger_active, NULL);
+		struct tmigr_hierarchy *hier = __tmigr_get_hierarchy(cpu);
+
+		if (WARN_ON_ONCE(!hier))
+			return -EINVAL;
+
+		migrator = cpumask_any_and(tmigr_available_cpumask, hier->cpumask);
+		if (migrator < nr_cpu_ids) {
+			work_on_cpu(migrator, tmigr_trigger_active, NULL);
+		} else {
+			/*
+			 * If deactivation returned an expiration, it belongs to an available
+			 * nohz CPU in the hierarchy.
+			 */
+			WARN_ONCE(1, "Expected available CPU in the hierarchy\n");
+		}
 	}
 
 	return 0;
@@ -1653,14 +1697,14 @@ static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl,
 	group->groupevt.ignore = true;
 }
 
-static struct tmigr_group *tmigr_get_group(int node, unsigned int lvl)
+static struct tmigr_group *tmigr_get_group(struct tmigr_hierarchy *hier, int node, unsigned int lvl)
 {
 	struct tmigr_group *tmp, *group = NULL;
 
 	lockdep_assert_held(&tmigr_mutex);
 
 	/* Try to attach to an existing group first */
-	list_for_each_entry(tmp, &tmigr_level_list[lvl], list) {
+	list_for_each_entry(tmp, &hier->level_list[lvl], list) {
 		/*
 		 * If @lvl is below the cross NUMA node level, check whether
 		 * this group belongs to the same NUMA node.
@@ -1694,14 +1738,14 @@ static struct tmigr_group *tmigr_get_group(int node, unsigned int lvl)
 	tmigr_init_group(group, lvl, node);
 
 	/* Setup successful. Add it to the hierarchy */
-	list_add(&group->list, &tmigr_level_list[lvl]);
+	list_add(&group->list, &hier->level_list[lvl]);
 	trace_tmigr_group_set(group);
 	return group;
 }
 
-static bool tmigr_init_root(struct tmigr_group *group, bool activate)
+static bool tmigr_init_root(struct tmigr_hierarchy *hier, struct tmigr_group *group, bool activate)
 {
-	if (!group->parent && group != tmigr_root) {
+	if (!group->parent && group != hier->root) {
 		/*
 		 * This is the new top-level, prepare its groupmask in advance
 		 * to avoid accidents where yet another new top-level is
@@ -1717,11 +1761,10 @@ static bool tmigr_init_root(struct tmigr_group *group, bool activate)
 
 }
 
-static void tmigr_connect_child_parent(struct tmigr_group *child,
-				       struct tmigr_group *parent,
-				       bool activate)
+static void tmigr_connect_child_parent(struct tmigr_hierarchy *hier, struct tmigr_group *child,
+				       struct tmigr_group *parent, bool activate)
 {
-	if (tmigr_init_root(parent, activate)) {
+	if (tmigr_init_root(hier, parent, activate)) {
 		/*
 		 * The previous top level had prepared its groupmask already,
 		 * simply account it in advance as the first child. If some groups
@@ -1754,13 +1797,13 @@ static void tmigr_connect_child_parent(struct tmigr_group *child,
 	 */
 	smp_store_release(&child->parent, parent);
 
-	trace_tmigr_connect_child_parent(child);
+	trace_tmigr_connect_child_parent(hier, child);
 }
 
-static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
-			      struct tmigr_group *start, bool activate)
+static int tmigr_setup_groups(struct tmigr_hierarchy *hier, unsigned int cpu,
+			      unsigned int node, struct tmigr_group *start, bool activate)
 {
-	struct tmigr_group *group, *child, **stack;
+	struct tmigr_group *root = hier->root, *group, *child, **stack;
 	int i, top = 0, err = 0, start_lvl = 0;
 	bool root_mismatch = false;
 
@@ -1773,11 +1816,11 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 		start_lvl = start->level + 1;
 	}
 
-	if (tmigr_root)
-		root_mismatch = tmigr_root->numa_node != node;
+	if (root)
+		root_mismatch = root->numa_node != node;
 
 	for (i = start_lvl; i < tmigr_hierarchy_levels; i++) {
-		group = tmigr_get_group(node, i);
+		group = tmigr_get_group(hier, node, i);
 		if (IS_ERR(group)) {
 			err = PTR_ERR(group);
 			i--;
@@ -1799,7 +1842,7 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 		if (group->parent)
 			break;
 		if ((!root_mismatch || i >= tmigr_crossnode_level) &&
-		    list_is_singular(&tmigr_level_list[i]))
+		    list_is_singular(&hier->level_list[i]))
 			break;
 	}
 
@@ -1827,15 +1870,15 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 			tmc->tmgroup = group;
 			tmc->groupmask = BIT(group->num_children++);
 
-			tmigr_init_root(group, activate);
+			tmigr_init_root(hier, group, activate);
 
-			trace_tmigr_connect_cpu_parent(tmc);
+			trace_tmigr_connect_cpu_parent(hier, tmc);
 
 			/* There are no children that need to be connected */
 			continue;
 		} else {
 			child = stack[i - 1];
-			tmigr_connect_child_parent(child, group, activate);
+			tmigr_connect_child_parent(hier, child, group, activate);
 		}
 	}
 
@@ -1891,18 +1934,23 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 			data.childmask = start->groupmask;
 			__walk_groups_from(tmigr_active_up, &data, start, start->parent);
 		}
+	} else if (start) {
+		union tmigr_state state;
+
+		/* Remote activation assumes the whole target's hierarchy is inactive */
+		state.state = atomic_read(&start->migr_state);
+		WARN_ON_ONCE(state.active);
 	}
 
 	/* Root update */
-	if (list_is_singular(&tmigr_level_list[top])) {
-		group = list_first_entry(&tmigr_level_list[top],
-					 typeof(*group), list);
+	if (list_is_singular(&hier->level_list[top])) {
+		group = list_first_entry(&hier->level_list[top], typeof(*group), list);
 		WARN_ON_ONCE(group->parent);
-		if (tmigr_root) {
+		if (root) {
 			/* Old root should be the same or below */
-			WARN_ON_ONCE(tmigr_root->level > top);
+			WARN_ON_ONCE(root->level > top);
 		}
-		tmigr_root = group;
+		hier->root = group;
 	}
 out:
 	kfree(stack);
@@ -1910,34 +1958,123 @@ out:
 	return err;
 }
 
+static struct tmigr_hierarchy *tmigr_get_hierarchy(int cpu)
+{
+	struct tmigr_hierarchy *hier;
+
+	hier = __tmigr_get_hierarchy(cpu);
+
+	if (hier)
+		return hier;
+
+	hier = kzalloc_flex(*hier, level_list, tmigr_hierarchy_levels);
+	if (!hier)
+		return ERR_PTR(-ENOMEM);
+
+	hier->cpumask = kzalloc(cpumask_size(), GFP_KERNEL);
+	if (!hier->cpumask) {
+		kfree(hier);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (int i = 0; i < tmigr_hierarchy_levels; i++)
+		INIT_LIST_HEAD(&hier->level_list[i]);
+
+	hier->capacity = tmigr_get_capacity(cpu);
+	list_add_tail(&hier->node, &tmigr_hierarchy_list);
+
+	return hier;
+}
+
+static int tmigr_connect_old_root(struct tmigr_hierarchy *hier, int cpu,
+				  struct tmigr_group *old_root,	bool activate)
+{
+	/*
+	 * The target CPU must never do the prepare work, except
+	 * on early boot when the boot CPU is the target. Otherwise
+	 * it may spuriously activate the old top level group inside
+	 * the new one (nevertheless whether old top level group is
+	 * active or not) and/or release an uninitialized childmask.
+	 */
+	WARN_ON_ONCE(cpu == smp_processor_id());
+	if (activate) {
+		/*
+		 * The current CPU is expected to be online in the hierarchy,
+		 * otherwise the old root may not be active as expected.
+		 */
+		WARN_ON_ONCE(!__this_cpu_read(tmigr_cpu.available));
+	}
+
+	return tmigr_setup_groups(hier, -1, old_root->numa_node, old_root, activate);
+}
+
+static long connect_old_root_work(void *arg)
+{
+	struct tmigr_group *old_root = arg;
+	struct tmigr_hierarchy *hier;
+	int cpu = smp_processor_id();
+
+	hier = __tmigr_get_hierarchy(cpu);
+	if (WARN_ON_ONCE(!hier))
+		return -EINVAL;
+
+	return tmigr_connect_old_root(hier, cpu, old_root, true);
+}
+
 static int tmigr_add_cpu(unsigned int cpu)
 {
-	struct tmigr_group *old_root = tmigr_root;
+	struct tmigr_hierarchy *hier;
+	struct tmigr_group *old_root;
 	int node = cpu_to_node(cpu);
 	int ret;
 
 	guard(mutex)(&tmigr_mutex);
 
-	ret = tmigr_setup_groups(cpu, node, NULL, false);
+	hier = tmigr_get_hierarchy(cpu);
+	if (IS_ERR(hier))
+		return PTR_ERR(hier);
+
+	old_root = hier->root;
+
+	ret = tmigr_setup_groups(hier, cpu, node, NULL, false);
+
+	if (ret < 0)
+		return ret;
 
 	/* Root has changed? Connect the old one to the new */
-	if (ret >= 0 && old_root && old_root != tmigr_root) {
-		/*
-		 * The target CPU must never do the prepare work, except
-		 * on early boot when the boot CPU is the target. Otherwise
-		 * it may spuriously activate the old top level group inside
-		 * the new one (nevertheless whether old top level group is
-		 * active or not) and/or release an uninitialized childmask.
-		 */
-		WARN_ON_ONCE(cpu == raw_smp_processor_id());
-		/*
-		 * The (likely) current CPU is expected to be online in the hierarchy,
-		 * otherwise the old root may not be active as expected.
-		 */
-		WARN_ON_ONCE(!per_cpu_ptr(&tmigr_cpu, raw_smp_processor_id())->available);
-		ret = tmigr_setup_groups(-1, old_root->numa_node, old_root, true);
+	if (old_root && old_root != hier->root) {
+		guard(migrate)();
+
+		if (cpumask_test_cpu(smp_processor_id(), hier->cpumask)) {
+			/*
+			 * If the target belong to the same hierarchy, the old root is expected
+			 * to be active. Link and propagate to the new root.
+			 */
+			ret = tmigr_connect_old_root(hier, cpu, old_root, true);
+		} else {
+			int target = cpumask_first_and(hier->cpumask, tmigr_available_cpumask);
+
+			if (target < nr_cpu_ids) {
+				/*
+				 * If the target doesn't belong to the same hierarchy as the current
+				 * CPU, activate from a relevant one to make sure the old root is
+				 * active.
+				 */
+				ret = work_on_cpu(target, connect_old_root_work, old_root);
+			} else {
+				/*
+				 * No other available CPUs in the remote hierarchy. Link the
+				 * old root remotely but don't propagate activation since the
+				 * old root is not expected to be active.
+				 */
+				ret = tmigr_connect_old_root(hier, cpu, old_root, false);
+			}
+		}
 	}
 
+	if (ret >= 0)
+		cpumask_set_cpu(cpu, hier->cpumask);
+
 	return ret;
 }
 
@@ -1970,7 +2107,7 @@ static int tmigr_cpu_prepare(unsigned int cpu)
 
 static int __init tmigr_init(void)
 {
-	unsigned int cpulvl, nodelvl, cpus_per_node, i;
+	unsigned int cpulvl, nodelvl, cpus_per_node;
 	unsigned int nnodes = num_possible_nodes();
 	unsigned int ncpus = num_possible_cpus();
 	int ret = -ENOMEM;
@@ -2017,14 +2154,6 @@ static int __init tmigr_init(void)
 	 */
 	tmigr_crossnode_level = cpulvl;
 
-	tmigr_level_list = kzalloc_objs(struct list_head,
-					tmigr_hierarchy_levels);
-	if (!tmigr_level_list)
-		goto err;
-
-	for (i = 0; i < tmigr_hierarchy_levels; i++)
-		INIT_LIST_HEAD(&tmigr_level_list[i]);
-
 	pr_info("Timer migration: %d hierarchy levels; %d children per group;"
 		" %d crossnode level\n",
 		tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP,
diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h
index 70879cde6fdd..31735dd52327 100644
--- a/kernel/time/timer_migration.h
+++ b/kernel/time/timer_migration.h
@@ -6,6 +6,24 @@
 #define TMIGR_CHILDREN_PER_GROUP 8
 
 /**
+ * struct tmigr_hierarchy - a hierarchy associated to a given CPU capacity.
+ *                          Homogeneous systems have only one hierarchy.
+ *                          Heterogenous have one hierarchy per CPU capacity.
+ * @cpumask:	CPUs belonging to this hierarchy
+ * @root:	The current root of the hierarchy
+ * @capacity:	CPU capacity associated to this hierarchy
+ * @node:	Node in the global hierarchy list
+ * @level_list:	Per level lists of tmigr groups
+ */
+struct tmigr_hierarchy {
+	struct cpumask		*cpumask;
+	struct tmigr_group	*root;
+	unsigned long		capacity;
+	struct list_head	node;
+	struct list_head	level_list[];
+};
+
+/**
  * struct tmigr_event - a timer event associated to a CPU
  * @nextevt:	The node to enqueue an event in the parent group queue
  * @cpu:	The CPU to which this event belongs
@@ -75,15 +93,17 @@ struct tmigr_group {
 /**
  * struct tmigr_cpu - timer migration per CPU group
  * @lock:		Lock protecting the tmigr_cpu group information
- * @online:		Indicates whether the CPU is online; In deactivate path
- *			it is required to know whether the migrator in the top
- *			level group is to be set offline, while a timer is
- *			pending. Then another online CPU needs to be notified to
- *			take over the migrator role. Furthermore the information
- *			is required in CPU hotplug path as the CPU is able to go
- *			idle before the timer migration hierarchy hotplug AP is
- *			reached. During this phase, the CPU has to handle the
+ * @available:		Indicates whether the CPU is available for handling
+ *			global timers. In the deactivate path it is required to
+ *			know whether the migrator in the top level group is to
+ *			be set offline, while a timer is pending. Then another
+ *			available CPU needs to be notified to take over the
+ *			migrator role. Furthermore the information is required
+ *			in the CPU hotplug path as the CPU is able to go idle
+ *			before the timer migration hierarchy hotplug callback is
+ *			reached.  During this phase, the CPU has to handle the
  *			global timers on its own and must not act as a migrator.
+
  * @idle:		Indicates whether the CPU is idle in the timer migration
  *			hierarchy
  * @remote:		Is set when timers of the CPU are expired remotely