Re: [PATCH v2 5/6] entry,hrtimer: Push reprogramming timers into the interrupt return path

[Peter Zijlstra]

On Tue, Feb 03, 2026 at 12:28:13AM +0100, Thomas Gleixner wrote:

> But looking at this there is already a problem without interrupt
> nesting:
> 
>         irq_enter_rcu();
>         timer_interrupt()
>           hrtimer_interrupt()
>             delay_rearm();
>         irq_exit_rcu()
>           __irq_exit_rcu()
>             invoke_softirq()  <- Here
> 
> Soft interrupts can run for quite some time, which means this already
> can cause timers being delayed for way too long. I think in
> __irq_exit_rcu() you want to do:
> 
>        if (!in_interrupt() && local_softirq_pending()) {
>          hrtimer_rearm();
>          invoke_softirq();
>        }

Right, and we can do the same on (nested) IRQ entry. Something like so:

---
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -63,6 +63,8 @@ static __always_inline unsigned long __e
 		if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) {
 			if (!rseq_grant_slice_extension(ti_work & TIF_SLICE_EXT_DENY))
 				schedule();
+			else
+				hrtimer_rearm();
 		}
 
 		if (ti_work & _TIF_UPROBE)
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -663,6 +663,13 @@ void irq_enter_rcu(void)
 {
 	__irq_enter_raw();
 
+	/*
+	 * If this is a nested IRQ that hits the exit_to_user_mode_loop
+	 * where it has enabled IRQs but before it has hit schedule()
+	 * we could have hrtimers in an undefined state. Fix it up here.
+	 */
+	hrtimer_rearm();
+
 	if (tick_nohz_full_cpu(smp_processor_id()) ||
 	    (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)))
 		tick_irq_enter();
@@ -719,8 +726,14 @@ static inline void __irq_exit_rcu(void)
 #endif
 	account_hardirq_exit(current);
 	preempt_count_sub(HARDIRQ_OFFSET);
-	if (!in_interrupt() && local_softirq_pending())
+	if (!in_interrupt() && local_softirq_pending()) {
+		/*
+		 * If we left hrtimers unarmed, make sure to arm them now,
+		 * before enabling interrupts to run SoftIRQ.
+		 */
+		hrtimer_rearm();
 		invoke_softirq();
+	}
 
 	if (IS_ENABLED(CONFIG_IRQ_FORCED_THREADING) && force_irqthreads() &&
 	    local_timers_pending_force_th() && !(in_nmi() | in_hardirq()))
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1279,8 +1279,8 @@ static int __hrtimer_start_range_ns(stru
 
 	if (timer->is_fuzzy) {
 		/*
-		 * XXX fuzzy implies pinned!  not sure how to deal with
-		 * retrigger_next_event() for the !local case.
+		 * Fuzzy requires pinned as the lazy programming only works
+		 * for CPU local timers.
 		 */
 		WARN_ON_ONCE(!(mode & HRTIMER_MODE_PINNED));
 		/*
@@ -1898,7 +1898,7 @@ static __latent_entropy void hrtimer_run
 
 /*
  * Very similar to hrtimer_force_reprogram(), except it deals with
- * in_hrirq and hang_detected.
+ * in_hrtirq and hang_detected.
  */
 static void __hrtimer_rearm(struct hrtimer_cpu_base *cpu_base,
 			    ktime_t now, ktime_t expires_next)