Re: [PATCH] clockevents: Prevent timer interrupt starvation

[Thomas Gleixner <tglx@kernel.org>]

On Fri, Apr 03 2026 at 14:16, Peter Zijlstra wrote:
> On Thu, Apr 02, 2026 at 07:07:49PM +0200, Thomas Gleixner wrote:
>  /**
> @@ -324,16 +325,31 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
>  		return dev->set_next_ktime(expires, dev);
>  
>  	delta = ktime_to_ns(ktime_sub(expires, ktime_get()));
> -	if (delta <= 0)
> -		return force ? clockevents_program_min_delta(dev) : -ETIME;
> +	if (delta <= 0) {
> +		rc = -ETIME;
> +		goto error;
> +	}

That's not working in the case that user space manages to set the expiry
time so it stays in the min_delta_ns window, which is doable. I just
tried. Then we are back to square one.

Less convoluted but untested version of my initial idea below.

Thanks,

        tglx
---
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -80,6 +80,7 @@ enum clock_event_state {
  * @shift:		nanoseconds to cycles divisor (power of two)
  * @state_use_accessors:current state of the device, assigned by the core code
  * @features:		features
+ * @next_event_forced:	True if the last programming was a forced event
  * @retries:		number of forced programming retries
  * @set_state_periodic:	switch state to periodic
  * @set_state_oneshot:	switch state to oneshot
@@ -108,6 +109,7 @@ struct clock_event_device {
 	u32			shift;
 	enum clock_event_state	state_use_accessors;
 	unsigned int		features;
+	unsigned int		next_event_forced;
 	unsigned long		retries;
 
 	int			(*set_state_periodic)(struct clock_event_device *);
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -172,6 +172,7 @@ void clockevents_shutdown(struct clock_e
 {
 	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 	dev->next_event = KTIME_MAX;
+	dev->next_event_forced = 0;
 }
 
 /**
@@ -224,13 +225,7 @@ static int clockevents_increase_min_delt
 	return 0;
 }
 
-/**
- * clockevents_program_min_delta - Set clock event device to the minimum delay.
- * @dev:	device to program
- *
- * Returns 0 on success, -ETIME when the retry loop failed.
- */
-static int clockevents_program_min_delta(struct clock_event_device *dev)
+static int __clockevents_program_min_delta(struct clock_event_device *dev)
 {
 	unsigned long long clc;
 	int64_t delta;
@@ -263,13 +258,7 @@ static int clockevents_program_min_delta
 
 #else  /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */
 
-/**
- * clockevents_program_min_delta - Set clock event device to the minimum delay.
- * @dev:	device to program
- *
- * Returns 0 on success, -ETIME when the retry loop failed.
- */
-static int clockevents_program_min_delta(struct clock_event_device *dev)
+static int __clockevents_program_min_delta(struct clock_event_device *dev)
 {
 	unsigned long long clc;
 	int64_t delta = 0;
@@ -293,6 +282,21 @@ static int clockevents_program_min_delta
 #endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */
 
 /**
+ * clockevents_program_min_delta - Set clock event device to the minimum delay.
+ * @dev:	device to program
+ *
+ * Returns 0 on success, -ETIME when the retry loop failed.
+ */
+static int clockevents_program_min_delta(struct clock_event_device *dev)
+{
+	if (dev->next_event_forced)
+		return 0;
+
+	dev->next_event_forced = 1;
+	return __clockevents_program_min_delta(dev);
+}
+
+/**
  * clockevents_program_event - Reprogram the clock event device.
  * @dev:	device to program
  * @expires:	absolute expiry time (monotonic clock)
@@ -324,16 +328,18 @@ int clockevents_program_event(struct clo
 		return dev->set_next_ktime(expires, dev);
 
 	delta = ktime_to_ns(ktime_sub(expires, ktime_get()));
-	if (delta <= 0)
-		return force ? clockevents_program_min_delta(dev) : -ETIME;
 
-	delta = min(delta, (int64_t) dev->max_delta_ns);
-	delta = max(delta, (int64_t) dev->min_delta_ns);
+	if (!dev->next_event_forced || delta > dev->min_delta_ns) {
 
-	clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
-	rc = dev->set_next_event((unsigned long) clc, dev);
+		delta = min(delta, (int64_t) dev->max_delta_ns);
+		delta = max(delta, (int64_t) dev->min_delta_ns);
+		clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+		rc = dev->set_next_event((unsigned long) clc, dev);
+		if (!rc)
+			return 0;
+	}
 
-	return (rc && force) ? clockevents_program_min_delta(dev) : rc;
+	return force ? clockevents_program_min_delta(dev) : rc;
 }
 
 /*
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1888,6 +1888,7 @@ void hrtimer_interrupt(struct clock_even
 	BUG_ON(!cpu_base->hres_active);
 	cpu_base->nr_events++;
 	dev->next_event = KTIME_MAX;
+	dev->next_event_forced = 0;
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 	entry_time = now = hrtimer_update_base(cpu_base);
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -110,6 +110,7 @@ void tick_handle_periodic(struct clock_e
 	int cpu = smp_processor_id();
 	ktime_t next = dev->next_event;
 
+	dev->next_event_forced = 0;
 	tick_periodic(cpu);
 
 	/*
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1513,6 +1513,7 @@ static void tick_nohz_lowres_handler(str
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	dev->next_event = KTIME_MAX;
+	dev->next_event_forced = 0;
 
 	if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART))
 		tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);