Merge tag 'timers-core-2024-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "Core:

   - Overhaul of posix-timers in preparation of removing the workaround
     for periodic timers which have signal delivery ignored.

   - Remove the historical extra jiffie in msleep()

     msleep() adds an extra jiffie to the timeout value to ensure
     minimal sleep time. The timer wheel ensures minimal sleep time
     since the large rewrite to a non-cascading wheel, but the extra
     jiffie in msleep() remained unnoticed. Remove it.

   - Make the timer slack handling correct for realtime tasks.

     The procfs interface is inconsistent and does neither reflect
     reality nor conforms to the man page. Show the correct 0 slack for
     real time tasks and enforce it at the core level instead of having
     inconsistent individual checks in various timer setup functions.

   - The usual set of updates and enhancements all over the place.

  Drivers:

   - Allow the ACPI PM timer to be turned off during suspend

   - No new drivers

   - The usual updates and enhancements in various drivers"

* tag 'timers-core-2024-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
  ntp: Make sure RTC is synchronized when time goes backwards
  treewide: Fix wrong singular form of jiffies in comments
  cpu: Use already existing usleep_range()
  timers: Rename next_expiry_recalc() to be unique
  platform/x86:intel/pmc: Fix comment for the pmc_core_acpi_pm_timer_suspend_resume function
  clocksource/drivers/jcore: Use request_percpu_irq()
  clocksource/drivers/cadence-ttc: Add missing clk_disable_unprepare in ttc_setup_clockevent
  clocksource/drivers/asm9260: Add missing clk_disable_unprepare in asm9260_timer_init
  clocksource/drivers/qcom: Add missing iounmap() on errors in msm_dt_timer_init()
  clocksource/drivers/ingenic: Use devm_clk_get_enabled() helpers
  platform/x86:intel/pmc: Enable the ACPI PM Timer to be turned off when suspended
  clocksource: acpi_pm: Add external callback for suspend/resume
  clocksource/drivers/arm_arch_timer: Using for_each_available_child_of_node_scoped()
  dt-bindings: timer: rockchip: Add rk3576 compatible
  timers: Annotate possible non critical data race of next_expiry
  timers: Remove historical extra jiffie for timeout in msleep()
  hrtimer: Use and report correct timerslack values for realtime tasks
  hrtimer: Annotate hrtimer_cpu_base_.*_expiry() for sparse.
  timers: Add sparse annotation for timer_sync_wait_running().
  signal: Replace BUG_ON()s
  ...

15 files changed, 231 insertions, 213 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0c9c5dfc8ddd..d293d52a3e00 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -330,7 +330,7 @@ static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state st
 			/* Poll for one millisecond */
 			arch_cpuhp_sync_state_poll();
 		} else {
-			usleep_range_state(USEC_PER_MSEC, 2 * USEC_PER_MSEC, TASK_UNINTERRUPTIBLE);
+			usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC);
 		}
 		sync = atomic_read(st);
 	}
diff --git a/kernel/fork.c b/kernel/fork.c
index cc760491f201..c1b343cba560 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1861,7 +1861,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	prev_cputime_init(&sig->prev_cputime);
 
 #ifdef CONFIG_POSIX_TIMERS
-	INIT_LIST_HEAD(&sig->posix_timers);
+	INIT_HLIST_HEAD(&sig->posix_timers);
 	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	sig->real_timer.function = it_real_fn;
 #endif
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index ae1b42775ef9..195d2f2834a9 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -406,6 +406,14 @@ static void __setscheduler_params(struct task_struct *p,
 	else if (fair_policy(policy))
 		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
 
+	/* rt-policy tasks do not have a timerslack */
+	if (task_is_realtime(p)) {
+		p->timer_slack_ns = 0;
+	} else if (p->timer_slack_ns == 0) {
+		/* when switching back to non-rt policy, restore timerslack */
+		p->timer_slack_ns = p->default_timer_slack_ns;
+	}
+
 	/*
 	 * __sched_setscheduler() ensures attr->sched_priority == 0 when
 	 * !rt_policy. Always setting this ensures that things like
diff --git a/kernel/signal.c b/kernel/signal.c
index 60c737e423a1..6f3a5aa39b09 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -618,20 +618,18 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
 }
 
 /*
- * Dequeue a signal and return the element to the caller, which is
- * expected to free it.
- *
- * All callers have to hold the siglock.
+ * Try to dequeue a signal. If a deliverable signal is found fill in the
+ * caller provided siginfo and return the signal number. Otherwise return
+ * 0.
  */
-int dequeue_signal(struct task_struct *tsk, sigset_t *mask,
-		   kernel_siginfo_t *info, enum pid_type *type)
+int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type)
 {
+	struct task_struct *tsk = current;
 	bool resched_timer = false;
 	int signr;
 
-	/* We only dequeue private signals from ourselves, we don't let
-	 * signalfd steal them
-	 */
+	lockdep_assert_held(&tsk->sighand->siglock);
+
 	*type = PIDTYPE_PID;
 	signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer);
 	if (!signr) {
@@ -1940,10 +1938,11 @@ struct sigqueue *sigqueue_alloc(void)
 
 void sigqueue_free(struct sigqueue *q)
 {
-	unsigned long flags;
 	spinlock_t *lock = &current->sighand->siglock;
+	unsigned long flags;
 
-	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
+	if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC)))
+		return;
 	/*
 	 * We must hold ->siglock while testing q->list
 	 * to serialize with collect_signal() or with
@@ -1971,7 +1970,10 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
 	unsigned long flags;
 	int ret, result;
 
-	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
+	if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC)))
+		return 0;
+	if (WARN_ON_ONCE(q->info.si_code != SI_TIMER))
+		return 0;
 
 	ret = -1;
 	rcu_read_lock();
@@ -2006,7 +2008,6 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
 		 * If an SI_TIMER entry is already queue just increment
 		 * the overrun count.
 		 */
-		BUG_ON(q->info.si_code != SI_TIMER);
 		q->info.si_overrun++;
 		result = TRACE_SIGNAL_ALREADY_PENDING;
 		goto out;
@@ -2793,8 +2794,7 @@ relock:
 		type = PIDTYPE_PID;
 		signr = dequeue_synchronous_signal(&ksig->info);
 		if (!signr)
-			signr = dequeue_signal(current, &current->blocked,
-					       &ksig->info, &type);
+			signr = dequeue_signal(&current->blocked, &ksig->info, &type);
 
 		if (!signr)
 			break; /* will return 0 */
@@ -3648,7 +3648,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info,
 	signotset(&mask);
 
 	spin_lock_irq(&tsk->sighand->siglock);
-	sig = dequeue_signal(tsk, &mask, info, &type);
+	sig = dequeue_signal(&mask, info, &type);
 	if (!sig && timeout) {
 		/*
 		 * None ready, temporarily unblock those we're interested
@@ -3667,7 +3667,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info,
 		spin_lock_irq(&tsk->sighand->siglock);
 		__set_task_blocked(tsk, &tsk->real_blocked);
 		sigemptyset(&tsk->real_blocked);
-		sig = dequeue_signal(tsk, &mask, info, &type);
+		sig = dequeue_signal(&mask, info, &type);
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 3a2df1bd9f64..e3c4cffb520c 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2557,6 +2557,8 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			error = current->timer_slack_ns;
 		break;
 	case PR_SET_TIMERSLACK:
+		if (task_is_realtime(current))
+			break;
 		if (arg2 <= 0)
 			current->timer_slack_ns =
 					current->default_timer_slack_ns;
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 5abfa4390673..8bf888641694 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -493,7 +493,7 @@ static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throt
 		 * promised in the context of posix_timer_fn() never
 		 * materialized, but someone should really work on it.
 		 *
-		 * To prevent DOS fake @now to be 1 jiffie out which keeps
+		 * To prevent DOS fake @now to be 1 jiffy out which keeps
 		 * the overrun accounting correct but creates an
 		 * inconsistency vs. timer_gettime(2).
 		 */
@@ -574,15 +574,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
 					    it.alarm.alarmtimer);
 	enum alarmtimer_restart result = ALARMTIMER_NORESTART;
 	unsigned long flags;
-	int si_private = 0;
 
 	spin_lock_irqsave(&ptr->it_lock, flags);
 
-	ptr->it_active = 0;
-	if (ptr->it_interval)
-		si_private = ++ptr->it_requeue_pending;
-
-	if (posix_timer_event(ptr, si_private) && ptr->it_interval) {
+	if (posix_timer_queue_signal(ptr) && ptr->it_interval) {
 		/*
 		 * Handle ignored signals and rearm the timer. This will go
 		 * away once we handle ignored signals proper. Ensure that
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 60a6484831b1..78c7bd64d0dd 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -190,7 +190,7 @@ int clockevents_tick_resume(struct clock_event_device *dev)
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST
 
-/* Limit min_delta to a jiffie */
+/* Limit min_delta to a jiffy */
 #define MIN_DELTA_LIMIT		(NSEC_PER_SEC / HZ)
 
 /**
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 836157e09e25..12eb40d6290e 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1177,7 +1177,7 @@ 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)
@@ -1351,11 +1351,13 @@ 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);
 }
@@ -2072,14 +2074,9 @@ 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_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns);
 	ret = do_nanosleep(&t, mode);
 	if (ret != -ERESTART_RESTARTBLOCK)
 		goto out;
@@ -2249,7 +2246,7 @@ void __init hrtimers_init(void)
 /**
  * schedule_hrtimeout_range_clock - sleep until timeout
  * @expires:	timeout value (ktime_t)
- * @delta:	slack in expires timeout (ktime_t) for SCHED_OTHER tasks
+ * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode
  * @clock_id:	timer clock to be used
  */
@@ -2276,13 +2273,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
 		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);
@@ -2302,7 +2292,7 @@ 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
+ * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode
  *
  * Make the current task sleep until the given expiry time has
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 8d2dd214ec68..802b336f4b8c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -660,9 +660,17 @@ rearm:
 	sched_sync_hw_clock(offset_nsec, res != 0);
 }
 
-void ntp_notify_cmos_timer(void)
+void ntp_notify_cmos_timer(bool offset_set)
 {
 	/*
+	 * If the time jumped (using ADJ_SETOFFSET) cancels sync timer,
+	 * which may have been running if the time was synchronized
+	 * prior to the ADJ_SETOFFSET call.
+	 */
+	if (offset_set)
+		hrtimer_cancel(&sync_hrtimer);
+
+	/*
 	 * When the work is currently executed but has not yet the timer
 	 * rearmed this queues the work immediately again. No big issue,
 	 * just a pointless work scheduled.
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index 23d1b74c3065..5a633dce9057 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -14,9 +14,9 @@ extern int __do_adjtimex(struct __kernel_timex *txc,
 extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
 
 #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC)
-extern void ntp_notify_cmos_timer(void);
+extern void ntp_notify_cmos_timer(bool offset_set);
 #else
-static inline void ntp_notify_cmos_timer(void) { }
+static inline void ntp_notify_cmos_timer(bool offset_set) { }
 #endif
 
 #endif /* _LINUX_NTP_INTERNAL_H */
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index e9c6f9d0e42c..6bcee4704059 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -453,6 +453,7 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p)
 	struct cpu_timer *ctmr = &timer->it.cpu;
 	struct posix_cputimer_base *base;
 
+	timer->it_active = 0;
 	if (!cpu_timer_dequeue(ctmr))
 		return;
 
@@ -559,6 +560,7 @@ static void arm_timer(struct k_itimer *timer, struct task_struct *p)
 	struct cpu_timer *ctmr = &timer->it.cpu;
 	u64 newexp = cpu_timer_getexpires(ctmr);
 
+	timer->it_active = 1;
 	if (!cpu_timer_enqueue(&base->tqhead, ctmr))
 		return;
 
@@ -584,12 +586,8 @@ static void cpu_timer_fire(struct k_itimer *timer)
 {
 	struct cpu_timer *ctmr = &timer->it.cpu;
 
-	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
-		/*
-		 * User don't want any signal.
-		 */
-		cpu_timer_setexpires(ctmr, 0);
-	} else if (unlikely(timer->sigq == NULL)) {
+	timer->it_active = 0;
+	if (unlikely(timer->sigq == NULL)) {
 		/*
 		 * This a special case for clock_nanosleep,
 		 * not a normal timer from sys_timer_create.
@@ -600,9 +598,9 @@ static void cpu_timer_fire(struct k_itimer *timer)
 		/*
 		 * One-shot timer.  Clear it as soon as it's fired.
 		 */
-		posix_timer_event(timer, 0);
+		posix_timer_queue_signal(timer);
 		cpu_timer_setexpires(ctmr, 0);
-	} else if (posix_timer_event(timer, ++timer->it_requeue_pending)) {
+	} else if (posix_timer_queue_signal(timer)) {
 		/*
 		 * The signal did not get queued because the signal
 		 * was ignored, so we won't get any callback to
@@ -614,6 +612,8 @@ static void cpu_timer_fire(struct k_itimer *timer)
 	}
 }
 
+static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now);
+
 /*
  * Guts of sys_timer_settime for CPU timers.
  * This is called with the timer locked and interrupts disabled.
@@ -623,9 +623,10 @@ static void cpu_timer_fire(struct k_itimer *timer)
 static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 			       struct itimerspec64 *new, struct itimerspec64 *old)
 {
+	bool sigev_none = timer->it_sigev_notify == SIGEV_NONE;
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
-	u64 old_expires, new_expires, old_incr, val;
 	struct cpu_timer *ctmr = &timer->it.cpu;
+	u64 old_expires, new_expires, now;
 	struct sighand_struct *sighand;
 	struct task_struct *p;
 	unsigned long flags;
@@ -662,10 +663,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 		return -ESRCH;
 	}
 
-	/*
-	 * Disarm any old timer after extracting its expiry time.
-	 */
-	old_incr = timer->it_interval;
+	/* Retrieve the current expiry time before disarming the timer */
 	old_expires = cpu_timer_getexpires(ctmr);
 
 	if (unlikely(timer->it.cpu.firing)) {
@@ -673,157 +671,122 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 		ret = TIMER_RETRY;
 	} else {
 		cpu_timer_dequeue(ctmr);
+		timer->it_active = 0;
 	}
 
 	/*
-	 * We need to sample the current value to convert the new
-	 * value from to relative and absolute, and to convert the
-	 * old value from absolute to relative.  To set a process
-	 * timer, we need a sample to balance the thread expiry
-	 * times (in arm_timer).  With an absolute time, we must
-	 * check if it's already passed.  In short, we need a sample.
+	 * Sample the current clock for saving the previous setting
+	 * and for rearming the timer.
 	 */
 	if (CPUCLOCK_PERTHREAD(timer->it_clock))
-		val = cpu_clock_sample(clkid, p);
+		now = cpu_clock_sample(clkid, p);
 	else
-		val = cpu_clock_sample_group(clkid, p, true);
+		now = cpu_clock_sample_group(clkid, p, !sigev_none);
 
+	/* Retrieve the previous expiry value if requested. */
 	if (old) {
-		if (old_expires == 0) {
-			old->it_value.tv_sec = 0;
-			old->it_value.tv_nsec = 0;
-		} else {
-			/*
-			 * Update the timer in case it has overrun already.
-			 * If it has, we'll report it as having overrun and
-			 * with the next reloaded timer already ticking,
-			 * though we are swallowing that pending
-			 * notification here to install the new setting.
-			 */
-			u64 exp = bump_cpu_timer(timer, val);
-
-			if (val < exp) {
-				old_expires = exp - val;
-				old->it_value = ns_to_timespec64(old_expires);
-			} else {
-				old->it_value.tv_nsec = 1;
-				old->it_value.tv_sec = 0;
-			}
-		}
+		old->it_value = (struct timespec64){ };
+		if (old_expires)
+			__posix_cpu_timer_get(timer, old, now);
 	}
 
+	/* Retry if the timer expiry is running concurrently */
 	if (unlikely(ret)) {
-		/*
-		 * We are colliding with the timer actually firing.
-		 * Punt after filling in the timer's old value, and
-		 * disable this firing since we are already reporting
-		 * it as an overrun (thanks to bump_cpu_timer above).
-		 */
 		unlock_task_sighand(p, &flags);
 		goto out;
 	}
 
-	if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
-		new_expires += val;
-	}
+	/* Convert relative expiry time to absolute */
+	if (new_expires && !(timer_flags & TIMER_ABSTIME))
+		new_expires += now;
+
+	/* Set the new expiry time (might be 0) */
+	cpu_timer_setexpires(ctmr, new_expires);
 
 	/*
-	 * Install the new expiry time (or zero).
-	 * For a timer with no notification action, we don't actually
-	 * arm the timer (we'll just fake it for timer_gettime).
+	 * Arm the timer if it is not disabled, the new expiry value has
+	 * not yet expired and the timer requires signal delivery.
+	 * SIGEV_NONE timers are never armed. In case the timer is not
+	 * armed, enforce the reevaluation of the timer base so that the
+	 * process wide cputime counter can be disabled eventually.
 	 */
-	cpu_timer_setexpires(ctmr, new_expires);
-	if (new_expires != 0 && val < new_expires) {
-		arm_timer(timer, p);
+	if (likely(!sigev_none)) {
+		if (new_expires && now < new_expires)
+			arm_timer(timer, p);
+		else
+			trigger_base_recalc_expires(timer, p);
 	}
 
 	unlock_task_sighand(p, &flags);
+
+	posix_timer_set_common(timer, new);
+
 	/*
-	 * Install the new reload setting, and
-	 * set up the signal and overrun bookkeeping.
+	 * If the new expiry time was already in the past the timer was not
+	 * queued. Fire it immediately even if the thread never runs to
+	 * accumulate more time on this clock.
 	 */
-	timer->it_interval = timespec64_to_ktime(new->it_interval);
+	if (!sigev_none && new_expires && now >= new_expires)
+		cpu_timer_fire(timer);
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now)
+{
+	bool sigev_none = timer->it_sigev_notify == SIGEV_NONE;
+	u64 expires, iv = timer->it_interval;
 
 	/*
-	 * This acts as a modification timestamp for the timer,
-	 * so any automatic reload attempt will punt on seeing
-	 * that we have reset the timer manually.
+	 * Make sure that interval timers are moved forward for the
+	 * following cases:
+	 *  - SIGEV_NONE timers which are never armed
+	 *  - Timers which expired, but the signal has not yet been
+	 *    delivered
 	 */
-	timer->it_requeue_pending = (timer->it_requeue_pending + 2) &
-		~REQUEUE_PENDING;
-	timer->it_overrun_last = 0;
-	timer->it_overrun = -1;
-
-	if (val >= new_expires) {
-		if (new_expires != 0) {
-			/*
-			 * The designated time already passed, so we notify
-			 * immediately, even if the thread never runs to
-			 * accumulate more time on this clock.
-			 */
-			cpu_timer_fire(timer);
-		}
+	if (iv && ((timer->it_requeue_pending & REQUEUE_PENDING) || sigev_none))
+		expires = bump_cpu_timer(timer, now);
+	else
+		expires = cpu_timer_getexpires(&timer->it.cpu);
 
+	/*
+	 * Expired interval timers cannot have a remaining time <= 0.
+	 * The kernel has to move them forward so that the next
+	 * timer expiry is > @now.
+	 */
+	if (now < expires) {
+		itp->it_value = ns_to_timespec64(expires - now);
+	} else {
 		/*
-		 * Make sure we don't keep around the process wide cputime
-		 * counter or the tick dependency if they are not necessary.
+		 * A single shot SIGEV_NONE timer must return 0, when it is
+		 * expired! Timers which have a real signal delivery mode
+		 * must return a remaining time greater than 0 because the
+		 * signal has not yet been delivered.
 		 */
-		sighand = lock_task_sighand(p, &flags);
-		if (!sighand)
-			goto out;
-
-		if (!cpu_timer_queued(ctmr))
-			trigger_base_recalc_expires(timer, p);
-
-		unlock_task_sighand(p, &flags);
+		if (!sigev_none)
+			itp->it_value.tv_nsec = 1;
 	}
- out:
-	rcu_read_unlock();
-	if (old)
-		old->it_interval = ns_to_timespec64(old_incr);
-
-	return ret;
 }
 
 static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp)
 {
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
-	struct cpu_timer *ctmr = &timer->it.cpu;
-	u64 now, expires = cpu_timer_getexpires(ctmr);
 	struct task_struct *p;
+	u64 now;
 
 	rcu_read_lock();
 	p = cpu_timer_task_rcu(timer);
-	if (!p)
-		goto out;
+	if (p && cpu_timer_getexpires(&timer->it.cpu)) {
+		itp->it_interval = ktime_to_timespec64(timer->it_interval);
 
-	/*
-	 * Easy part: convert the reload time.
-	 */
-	itp->it_interval = ktime_to_timespec64(timer->it_interval);
-
-	if (!expires)
-		goto out;
-
-	/*
-	 * Sample the clock to take the difference with the expiry time.
-	 */
-	if (CPUCLOCK_PERTHREAD(timer->it_clock))
-		now = cpu_clock_sample(clkid, p);
-	else
-		now = cpu_clock_sample_group(clkid, p, false);
+		if (CPUCLOCK_PERTHREAD(timer->it_clock))
+			now = cpu_clock_sample(clkid, p);
+		else
+			now = cpu_clock_sample_group(clkid, p, false);
 
-	if (now < expires) {
-		itp->it_value = ns_to_timespec64(expires - now);
-	} else {
-		/*
-		 * The timer should have expired already, but the firing
-		 * hasn't taken place yet.  Say it's just about to expire.
-		 */
-		itp->it_value.tv_nsec = 1;
-		itp->it_value.tv_sec = 0;
+		__posix_cpu_timer_get(timer, itp, now);
 	}
-out:
 	rcu_read_unlock();
 }
 
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index b924f0f096fa..4576aaed13b2 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -277,10 +277,17 @@ void posixtimer_rearm(struct kernel_siginfo *info)
 	unlock_timer(timr, flags);
 }
 
-int posix_timer_event(struct k_itimer *timr, int si_private)
+int posix_timer_queue_signal(struct k_itimer *timr)
 {
+	int ret, si_private = 0;
 	enum pid_type type;
-	int ret;
+
+	lockdep_assert_held(&timr->it_lock);
+
+	timr->it_active = 0;
+	if (timr->it_interval)
+		si_private = ++timr->it_requeue_pending;
+
 	/*
 	 * FIXME: if ->sigq is queued we can race with
 	 * dequeue_signal()->posixtimer_rearm().
@@ -309,19 +316,13 @@ int posix_timer_event(struct k_itimer *timr, int si_private)
  */
 static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 {
+	struct k_itimer *timr = container_of(timer, struct k_itimer, it.real.timer);
 	enum hrtimer_restart ret = HRTIMER_NORESTART;
-	struct k_itimer *timr;
 	unsigned long flags;
-	int si_private = 0;
 
-	timr = container_of(timer, struct k_itimer, it.real.timer);
 	spin_lock_irqsave(&timr->it_lock, flags);
 
-	timr->it_active = 0;
-	if (timr->it_interval != 0)
-		si_private = ++timr->it_requeue_pending;
-
-	if (posix_timer_event(timr, si_private)) {
+	if (posix_timer_queue_signal(timr)) {
 		/*
 		 * The signal was not queued due to SIG_IGN. As a
 		 * consequence the timer is not going to be rearmed from
@@ -338,14 +339,14 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 			 * change to the signal handling code.
 			 *
 			 * For now let timers with an interval less than a
-			 * jiffie expire every jiffie and recheck for a
+			 * jiffy expire every jiffy and recheck for a
 			 * valid signal handler.
 			 *
 			 * This avoids interrupt starvation in case of a
 			 * very small interval, which would expire the
 			 * timer immediately again.
 			 *
-			 * Moving now ahead of time by one jiffie tricks
+			 * Moving now ahead of time by one jiffy tricks
 			 * hrtimer_forward() to expire the timer later,
 			 * while it still maintains the overrun accuracy
 			 * for the price of a slight inconsistency in the
@@ -515,7 +516,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event,
 	spin_lock_irq(&current->sighand->siglock);
 	/* This makes the timer valid in the hash table */
 	WRITE_ONCE(new_timer->it_signal, current->signal);
-	list_add(&new_timer->list, &current->signal->posix_timers);
+	hlist_add_head(&new_timer->list, &current->signal->posix_timers);
 	spin_unlock_irq(&current->sighand->siglock);
 	/*
 	 * After unlocking sighand::siglock @new_timer is subject to
@@ -856,6 +857,23 @@ static struct k_itimer *timer_wait_running(struct k_itimer *timer,
 	return lock_timer(timer_id, flags);
 }
 
+/*
+ * Set up the new interval and reset the signal delivery data
+ */
+void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting)
+{
+	if (new_setting->it_value.tv_sec || new_setting->it_value.tv_nsec)
+		timer->it_interval = timespec64_to_ktime(new_setting->it_interval);
+	else
+		timer->it_interval = 0;
+
+	/* Prevent reloading in case there is a signal pending */
+	timer->it_requeue_pending = (timer->it_requeue_pending + 2) & ~REQUEUE_PENDING;
+	/* Reset overrun accounting */
+	timer->it_overrun_last = 0;
+	timer->it_overrun = -1LL;
+}
+
 /* Set a POSIX.1b interval timer. */
 int common_timer_set(struct k_itimer *timr, int flags,
 		     struct itimerspec64 *new_setting,
@@ -878,15 +896,12 @@ int common_timer_set(struct k_itimer *timr, int flags,
 		return TIMER_RETRY;
 
 	timr->it_active = 0;
-	timr->it_requeue_pending = (timr->it_requeue_pending + 2) &
-		~REQUEUE_PENDING;
-	timr->it_overrun_last = 0;
+	posix_timer_set_common(timr, new_setting);
 
-	/* Switch off the timer when it_value is zero */
+	/* Keep timer disarmed when it_value is zero */
 	if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec)
 		return 0;
 
-	timr->it_interval = timespec64_to_ktime(new_setting->it_interval);
 	expires = timespec64_to_ktime(new_setting->it_value);
 	if (flags & TIMER_ABSTIME)
 		expires = timens_ktime_to_host(timr->it_clock, expires);
@@ -904,7 +919,7 @@ static int do_timer_settime(timer_t timer_id, int tmr_flags,
 	const struct k_clock *kc;
 	struct k_itimer *timr;
 	unsigned long flags;
-	int error = 0;
+	int error;
 
 	if (!timespec64_valid(&new_spec64->it_interval) ||
 	    !timespec64_valid(&new_spec64->it_value))
@@ -918,6 +933,9 @@ retry:
 	if (!timr)
 		return -EINVAL;
 
+	if (old_spec64)
+		old_spec64->it_interval = ktime_to_timespec64(timr->it_interval);
+
 	kc = timr->kclock;
 	if (WARN_ON_ONCE(!kc || !kc->timer_set))
 		error = -EINVAL;
@@ -1021,7 +1039,7 @@ retry_delete:
 	}
 
 	spin_lock(&current->sighand->siglock);
-	list_del(&timer->list);
+	hlist_del(&timer->list);
 	spin_unlock(&current->sighand->siglock);
 	/*
 	 * A concurrent lookup could check timer::it_signal lockless. It
@@ -1071,7 +1089,7 @@ retry_delete:
 
 		goto retry_delete;
 	}
-	list_del(&timer->list);
+	hlist_del(&timer->list);
 
 	/*
 	 * Setting timer::it_signal to NULL is technically not required
@@ -1092,22 +1110,19 @@ retry_delete:
  */
 void exit_itimers(struct task_struct *tsk)
 {
-	struct list_head timers;
-	struct k_itimer *tmr;
+	struct hlist_head timers;
 
-	if (list_empty(&tsk->signal->posix_timers))
+	if (hlist_empty(&tsk->signal->posix_timers))
 		return;
 
 	/* Protect against concurrent read via /proc/$PID/timers */
 	spin_lock_irq(&tsk->sighand->siglock);
-	list_replace_init(&tsk->signal->posix_timers, &timers);
+	hlist_move_list(&tsk->signal->posix_timers, &timers);
 	spin_unlock_irq(&tsk->sighand->siglock);
 
 	/* The timers are not longer accessible via tsk::signal */
-	while (!list_empty(&timers)) {
-		tmr = list_first_entry(&timers, struct k_itimer, list);
-		itimer_delete(tmr);
-	}
+	while (!hlist_empty(&timers))
+		itimer_delete(hlist_entry(timers.first, struct k_itimer, list));
 }
 
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index f32a2ebba9b8..4784ea65f685 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -36,10 +36,11 @@ extern const struct k_clock clock_process;
 extern const struct k_clock clock_thread;
 extern const struct k_clock alarm_clock;
 
-int posix_timer_event(struct k_itimer *timr, int si_private);
+int posix_timer_queue_signal(struct k_itimer *timr);
 
 void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting);
 int common_timer_set(struct k_itimer *timr, int flags,
 		     struct itimerspec64 *new_setting,
 		     struct itimerspec64 *old_setting);
+void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting);
 int common_timer_del(struct k_itimer *timer);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 5391e4167d60..7e6f409bf311 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2553,6 +2553,7 @@ int do_adjtimex(struct __kernel_timex *txc)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct audit_ntp_data ad;
+	bool offset_set = false;
 	bool clock_set = false;
 	struct timespec64 ts;
 	unsigned long flags;
@@ -2575,6 +2576,7 @@ int do_adjtimex(struct __kernel_timex *txc)
 		if (ret)
 			return ret;
 
+		offset_set = delta.tv_sec != 0;
 		audit_tk_injoffset(delta);
 	}
 
@@ -2608,7 +2610,7 @@ int do_adjtimex(struct __kernel_timex *txc)
 	if (clock_set)
 		clock_was_set(CLOCK_SET_WALL);
 
-	ntp_notify_cmos_timer();
+	ntp_notify_cmos_timer(offset_set);
 
 	return ret;
 }
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 760bbeb1f331..0fc9d066a7be 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -365,7 +365,7 @@ static unsigned long round_jiffies_common(unsigned long j, int cpu,
 	rem = j % HZ;
 
 	/*
-	 * If the target jiffie is just after a whole second (which can happen
+	 * If the target jiffy is just after a whole second (which can happen
 	 * due to delays of the timer irq, long irq off times etc etc) then
 	 * we should round down to the whole second, not up. Use 1/4th second
 	 * as cutoff for this rounding as an extreme upper bound for this.
@@ -672,7 +672,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
 		 * Set the next expiry time and kick the CPU so it
 		 * can reevaluate the wheel:
 		 */
-		base->next_expiry = bucket_expiry;
+		WRITE_ONCE(base->next_expiry, bucket_expiry);
 		base->timers_pending = true;
 		base->next_expiry_recalc = false;
 		trigger_dyntick_cpu(base, timer);
@@ -1561,6 +1561,8 @@ static inline void timer_base_unlock_expiry(struct timer_base *base)
  * the waiter to acquire the lock and make progress.
  */
 static void timer_sync_wait_running(struct timer_base *base)
+	__releases(&base->lock) __releases(&base->expiry_lock)
+	__acquires(&base->expiry_lock) __acquires(&base->lock)
 {
 	if (atomic_read(&base->timer_waiters)) {
 		raw_spin_unlock_irq(&base->lock);
@@ -1898,7 +1900,7 @@ static int next_pending_bucket(struct timer_base *base, unsigned offset,
  *
  * Store next expiry time in base->next_expiry.
  */
-static void next_expiry_recalc(struct timer_base *base)
+static void timer_recalc_next_expiry(struct timer_base *base)
 {
 	unsigned long clk, next, adj;
 	unsigned lvl, offset = 0;
@@ -1928,7 +1930,7 @@ static void next_expiry_recalc(struct timer_base *base)
 		 * bits are zero, we look at the next level as is. If not we
 		 * need to advance it by one because that's going to be the
 		 * next expiring bucket in that level. base->clk is the next
-		 * expiring jiffie. So in case of:
+		 * expiring jiffy. So in case of:
 		 *
 		 * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
 		 *  0    0    0    0    0    0
@@ -1964,7 +1966,7 @@ static void next_expiry_recalc(struct timer_base *base)
 		clk += adj;
 	}
 
-	base->next_expiry = next;
+	WRITE_ONCE(base->next_expiry, next);
 	base->next_expiry_recalc = false;
 	base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
 }
@@ -1993,7 +1995,7 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
 		return basem;
 
 	/*
-	 * Round up to the next jiffie. High resolution timers are
+	 * Round up to the next jiffy. High resolution timers are
 	 * off, so the hrtimers are expired in the tick and we need to
 	 * make sure that this tick really expires the timer to avoid
 	 * a ping pong of the nohz stop code.
@@ -2007,7 +2009,7 @@ static unsigned long next_timer_interrupt(struct timer_base *base,
 					  unsigned long basej)
 {
 	if (base->next_expiry_recalc)
-		next_expiry_recalc(base);
+		timer_recalc_next_expiry(base);
 
 	/*
 	 * Move next_expiry for the empty base into the future to prevent an
@@ -2018,7 +2020,7 @@ static unsigned long next_timer_interrupt(struct timer_base *base,
 	 * easy comparable to find out which base holds the first pending timer.
 	 */
 	if (!base->timers_pending)
-		base->next_expiry = basej + NEXT_TIMER_MAX_DELTA;
+		WRITE_ONCE(base->next_expiry, basej + NEXT_TIMER_MAX_DELTA);
 
 	return base->next_expiry;
 }
@@ -2252,7 +2254,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem,
 					     base_global, &tevt);
 
 	/*
-	 * If the next event is only one jiffie ahead there is no need to call
+	 * If the next event is only one jiffy ahead there is no need to call
 	 * timer migration hierarchy related functions. The value for the next
 	 * global timer in @tevt struct equals then KTIME_MAX. This is also
 	 * true, when the timer base is idle.
@@ -2411,7 +2413,7 @@ static inline void __run_timers(struct timer_base *base)
 		 * jiffies to avoid endless requeuing to current jiffies.
 		 */
 		base->clk++;
-		next_expiry_recalc(base);
+		timer_recalc_next_expiry(base);
 
 		while (levels--)
 			expire_timers(base, heads + levels);
@@ -2462,8 +2464,40 @@ static void run_local_timers(void)
 	hrtimer_run_queues();
 
 	for (int i = 0; i < NR_BASES; i++, base++) {
-		/* Raise the softirq only if required. */
-		if (time_after_eq(jiffies, base->next_expiry) ||
+		/*
+		 * Raise the softirq only if required.
+		 *
+		 * timer_base::next_expiry can be written by a remote CPU while
+		 * holding the lock. If this write happens at the same time than
+		 * the lockless local read, sanity checker could complain about
+		 * data corruption.
+		 *
+		 * There are two possible situations where
+		 * timer_base::next_expiry is written by a remote CPU:
+		 *
+		 * 1. Remote CPU expires global timers of this CPU and updates
+		 * timer_base::next_expiry of BASE_GLOBAL afterwards in
+		 * next_timer_interrupt() or timer_recalc_next_expiry(). The
+		 * worst outcome is a superfluous raise of the timer softirq
+		 * when the not yet updated value is read.
+		 *
+		 * 2. A new first pinned timer is enqueued by a remote CPU
+		 * and therefore timer_base::next_expiry of BASE_LOCAL is
+		 * updated. When this update is missed, this isn't a
+		 * problem, as an IPI is executed nevertheless when the CPU
+		 * was idle before. When the CPU wasn't idle but the update
+		 * is missed, then the timer would expire one jiffy late -
+		 * bad luck.
+		 *
+		 * Those unlikely corner cases where the worst outcome is only a
+		 * one jiffy delay or a superfluous raise of the softirq are
+		 * not that expensive as doing the check always while holding
+		 * the lock.
+		 *
+		 * Possible remote writers are using WRITE_ONCE(). Local reader
+		 * uses therefore READ_ONCE().
+		 */
+		if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) ||
 		    (i == BASE_DEF && tmigr_requires_handle_remote())) {
 			raise_softirq(TIMER_SOFTIRQ);
 			return;
@@ -2730,7 +2764,7 @@ void __init init_timers(void)
  */
 void msleep(unsigned int msecs)
 {
-	unsigned long timeout = msecs_to_jiffies(msecs) + 1;
+	unsigned long timeout = msecs_to_jiffies(msecs);
 
 	while (timeout)
 		timeout = schedule_timeout_uninterruptible(timeout);
@@ -2744,7 +2778,7 @@ EXPORT_SYMBOL(msleep);
  */
 unsigned long msleep_interruptible(unsigned int msecs)
 {
-	unsigned long timeout = msecs_to_jiffies(msecs) + 1;
+	unsigned long timeout = msecs_to_jiffies(msecs);
 
 	while (timeout && !signal_pending(current))
 		timeout = schedule_timeout_interruptible(timeout);