Merge tag 'timers-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "Updates for timekeeping, timers and related drivers:

  Core code:

   - Cure a couple of correctness issues in the posix CPU timer code to
     prevent that the tick dependency for NOHZ full is kept alive for no
     reason.

   - Avoid expensive double reprogramming of the clockevent device in
     hrtimer_start_range_ns().

   - Avoid pointless SMP function calls when the clock was set to avoid
     disturbing CPUs which do not have any affected timers queued.

   - Make the clocksource watchdog test work correctly when CONFIG_HZ is
     less than 100.

  Drivers:

   - Prefer the ARM architected timer over the Exynos timer which is way
     more expensive to access.

   - Add device tree bindings for new Ingenic SoCs

   - The usual improvements and cleanups all over the place"

* tag 'timers-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
  clocksource: Make clocksource watchdog test safe for slow-HZ systems
  dt-bindings: timer: Add ABIs for new Ingenic SoCs
  clocksource/drivers/fttmr010: Pass around less pointers
  clocksource/drivers/mediatek: Optimize systimer irq clear flow on shutdown
  clocksource/drivers/ingenic: Use bitfield macro helpers
  clocksource/drivers/sh_cmt: Fix wrong setting if don't request IRQ for clock source channel
  dt-bindings: timer: convert rockchip,rk-timer.txt to YAML
  clocksource/drivers/exynos_mct: Mark MCT device as CLOCK_EVT_FEAT_PERCPU
  clocksource/drivers/exynos_mct: Prioritise Arm arch timer on arm64
  hrtimer: Unbreak hrtimer_force_reprogram()
  hrtimer: Use raw_cpu_ptr() in clock_was_set()
  hrtimer: Avoid more SMP function calls in clock_was_set()
  hrtimer: Avoid unnecessary SMP function calls in clock_was_set()
  hrtimer: Add bases argument to clock_was_set()
  time/timekeeping: Avoid invoking clock_was_set() twice
  timekeeping: Distangle resume and clock-was-set events
  timerfd: Provide timerfd_resume()
  hrtimer: Force clock_was_set() handling for the HIGHRES=n, NOHZ=y case
  hrtimer: Ensure timerfd notification for HIGHRES=n
  hrtimer: Consolidate reprogramming code
  ...

1 files changed, 73 insertions, 17 deletions

diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 517be7fd175ef..ee736861b18f7 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -291,6 +291,8 @@ static void thread_group_start_cputime(struct task_struct *tsk, u64 *samples)
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 	struct posix_cputimers *pct = &tsk->signal->posix_cputimers;
 
+	lockdep_assert_task_sighand_held(tsk);
+
 	/* Check if cputimer isn't running. This is accessed without locking. */
 	if (!READ_ONCE(pct->timers_active)) {
 		struct task_cputime sum;
@@ -405,6 +407,55 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
 	return 0;
 }
 
+static struct posix_cputimer_base *timer_base(struct k_itimer *timer,
+					      struct task_struct *tsk)
+{
+	int clkidx = CPUCLOCK_WHICH(timer->it_clock);
+
+	if (CPUCLOCK_PERTHREAD(timer->it_clock))
+		return tsk->posix_cputimers.bases + clkidx;
+	else
+		return tsk->signal->posix_cputimers.bases + clkidx;
+}
+
+/*
+ * Force recalculating the base earliest expiration on the next tick.
+ * This will also re-evaluate the need to keep around the process wide
+ * cputime counter and tick dependency and eventually shut these down
+ * if necessary.
+ */
+static void trigger_base_recalc_expires(struct k_itimer *timer,
+					struct task_struct *tsk)
+{
+	struct posix_cputimer_base *base = timer_base(timer, tsk);
+
+	base->nextevt = 0;
+}
+
+/*
+ * Dequeue the timer and reset the base if it was its earliest expiration.
+ * It makes sure the next tick recalculates the base next expiration so we
+ * don't keep the costly process wide cputime counter around for a random
+ * amount of time, along with the tick dependency.
+ *
+ * If another timer gets queued between this and the next tick, its
+ * expiration will update the base next event if necessary on the next
+ * tick.
+ */
+static void disarm_timer(struct k_itimer *timer, struct task_struct *p)
+{
+	struct cpu_timer *ctmr = &timer->it.cpu;
+	struct posix_cputimer_base *base;
+
+	if (!cpu_timer_dequeue(ctmr))
+		return;
+
+	base = timer_base(timer, p);
+	if (cpu_timer_getexpires(ctmr) == base->nextevt)
+		trigger_base_recalc_expires(timer, p);
+}
+
+
 /*
  * Clean up a CPU-clock timer that is about to be destroyed.
  * This is called from timer deletion with the timer already locked.
@@ -439,7 +490,7 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
 		if (timer->it.cpu.firing)
 			ret = TIMER_RETRY;
 		else
-			cpu_timer_dequeue(ctmr);
+			disarm_timer(timer, p);
 
 		unlock_task_sighand(p, &flags);
 	}
@@ -498,15 +549,9 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
  */
 static void arm_timer(struct k_itimer *timer, struct task_struct *p)
 {
-	int clkidx = CPUCLOCK_WHICH(timer->it_clock);
+	struct posix_cputimer_base *base = timer_base(timer, p);
 	struct cpu_timer *ctmr = &timer->it.cpu;
 	u64 newexp = cpu_timer_getexpires(ctmr);
-	struct posix_cputimer_base *base;
-
-	if (CPUCLOCK_PERTHREAD(timer->it_clock))
-		base = p->posix_cputimers.bases + clkidx;
-	else
-		base = p->signal->posix_cputimers.bases + clkidx;
 
 	if (!cpu_timer_enqueue(&base->tqhead, ctmr))
 		return;
@@ -703,16 +748,29 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	timer->it_overrun_last = 0;
 	timer->it_overrun = -1;
 
-	if (new_expires != 0 && !(val < new_expires)) {
+	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);
+		}
+
 		/*
-		 * The designated time already passed, so we notify
-		 * immediately, even if the thread never runs to
-		 * accumulate more time on this clock.
+		 * Make sure we don't keep around the process wide cputime
+		 * counter or the tick dependency if they are not necessary.
 		 */
-		cpu_timer_fire(timer);
-	}
+		sighand = lock_task_sighand(p, &flags);
+		if (!sighand)
+			goto out;
+
+		if (!cpu_timer_queued(ctmr))
+			trigger_base_recalc_expires(timer, p);
 
-	ret = 0;
+		unlock_task_sighand(p, &flags);
+	}
  out:
 	rcu_read_unlock();
 	if (old)
@@ -1346,8 +1404,6 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid,
 			}
 		}
 
-		if (!*newval)
-			return;
 		*newval += now;
 	}