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
  ...

1 files changed, 85 insertions, 122 deletions

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();
 }