[PATCH] sched/core: Convert remaining BUG_ON() instances to WARN_ON_ONCE()

[PATCH] sched/core: Convert remaining BUG_ON() instances to WARN_ON_ONCE()

[Amin Gattout]

Commit 09348d75a6ce ("sched/all: Change all BUG_ON() instances in the
scheduler to WARN_ON_ONCE()") left a few BUG_ON() behind in core.c.
Convert them as well.

As described in Documentation/process/deprecated.rst, BUG_ON() crashes
the system, which makes the failure harder to report and to debug, as
the message often never reaches the console or the syslog. With
WARN_ON_ONCE() the user gets a chance to see and report the problem
instead, and system owners who do not want to keep running after an
"impossible" condition can still set panic_on_warn.

Signed-off-by: Amin Gattout <amin.gattout@gmail.com>
---
Follow-up to commit 09348d75a6ce which converted the scheduler BUG_ON()
instances to WARN_ON_ONCE() but left a few behind in core.c.

Build tested on arm64 with CONFIG_NO_HZ_FULL and CONFIG_SCHED_CLASS_EXT
enabled so that every converted site is compiled.
---
 kernel/sched/core.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f78275192036..bab74b4f0dd6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5949,7 +5949,7 @@ static void sched_tick_stop(int cpu)
 int __init sched_tick_offload_init(void)
 {
 	tick_work_cpu = alloc_percpu(struct tick_work);
-	BUG_ON(!tick_work_cpu);
+	WARN_ON_ONCE(!tick_work_cpu);
 	return 0;
 }
 
@@ -7582,7 +7582,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 	enum ctx_state prev_state;
 
 	/* Catch callers which need to be fixed */
-	BUG_ON(preempt_count() || !irqs_disabled());
+	WARN_ON_ONCE(preempt_count() || !irqs_disabled());
 
 	prev_state = exception_enter();
 
@@ -8619,7 +8619,7 @@ static inline void sched_set_rq_online(struct rq *rq, int cpu)
 
 	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
-		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+		WARN_ON_ONCE(!cpumask_test_cpu(cpu, rq->rd->span));
 		set_rq_online(rq);
 	}
 	rq_unlock_irqrestore(rq, &rf);
@@ -8631,7 +8631,7 @@ static inline void sched_set_rq_offline(struct rq *rq, int cpu)
 
 	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
-		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+		WARN_ON_ONCE(!cpumask_test_cpu(cpu, rq->rd->span));
 		set_rq_offline(rq);
 	}
 	rq_unlock_irqrestore(rq, &rf);
@@ -8954,13 +8954,13 @@ void __init sched_init(void)
 	int i;
 
 	/* Make sure the linker didn't screw up */
-	BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class));
-	BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class));
-	BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class));
-	BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class));
+	WARN_ON_ONCE(!sched_class_above(&stop_sched_class, &dl_sched_class));
+	WARN_ON_ONCE(!sched_class_above(&dl_sched_class, &rt_sched_class));
+	WARN_ON_ONCE(!sched_class_above(&rt_sched_class, &fair_sched_class));
+	WARN_ON_ONCE(!sched_class_above(&fair_sched_class, &idle_sched_class));
 #ifdef CONFIG_SCHED_CLASS_EXT
-	BUG_ON(!sched_class_above(&fair_sched_class, &ext_sched_class));
-	BUG_ON(!sched_class_above(&ext_sched_class, &idle_sched_class));
+	WARN_ON_ONCE(!sched_class_above(&fair_sched_class, &ext_sched_class));
+	WARN_ON_ONCE(!sched_class_above(&ext_sched_class, &idle_sched_class));
 #endif
 
 	wait_bit_init();

---
base-commit: 73e3f0710014fe6d4ed98cfc02292f6121db7558
change-id: 20260827-warn_instead_bug-c9ea9389813c

Best regards,
--  
Amin Gattout <amin.gattout@gmail.com>

Re: [PATCH] sched/core: Convert remaining BUG_ON() instances to WARN_ON_ONCE()

[Peter Zijlstra]

On Thu, Aug 27, 2026 at 01:40:14PM +0200, Amin Gattout wrote:
> Commit 09348d75a6ce ("sched/all: Change all BUG_ON() instances in the
> scheduler to WARN_ON_ONCE()") left a few BUG_ON() behind in core.c.
> Convert them as well.
> 
> As described in Documentation/process/deprecated.rst, BUG_ON() crashes
> the system, which makes the failure harder to report and to debug, as
> the message often never reaches the console or the syslog. With
> WARN_ON_ONCE() the user gets a chance to see and report the problem
> instead, and system owners who do not want to keep running after an
> "impossible" condition can still set panic_on_warn.
> 
> Signed-off-by: Amin Gattout <amin.gattout@gmail.com>
> ---
> Follow-up to commit 09348d75a6ce which converted the scheduler BUG_ON()
> instances to WARN_ON_ONCE() but left a few behind in core.c.
> 
> Build tested on arm64 with CONFIG_NO_HZ_FULL and CONFIG_SCHED_CLASS_EXT
> enabled so that every converted site is compiled.
> ---
>  kernel/sched/core.c | 20 ++++++++++----------
>  1 file changed, 10 insertions(+), 10 deletions(-)
> 
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index f78275192036..bab74b4f0dd6 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -5949,7 +5949,7 @@ static void sched_tick_stop(int cpu)
>  int __init sched_tick_offload_init(void)
>  {
>  	tick_work_cpu = alloc_percpu(struct tick_work);
> -	BUG_ON(!tick_work_cpu);
> +	WARN_ON_ONCE(!tick_work_cpu);
>  	return 0;
>  }
>  

> @@ -8954,13 +8954,13 @@ void __init sched_init(void)
>  	int i;
>  
>  	/* Make sure the linker didn't screw up */
> -	BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class));
> -	BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class));
> -	BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class));
> -	BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class));
> +	WARN_ON_ONCE(!sched_class_above(&stop_sched_class, &dl_sched_class));
> +	WARN_ON_ONCE(!sched_class_above(&dl_sched_class, &rt_sched_class));
> +	WARN_ON_ONCE(!sched_class_above(&rt_sched_class, &fair_sched_class));
> +	WARN_ON_ONCE(!sched_class_above(&fair_sched_class, &idle_sched_class));
>  #ifdef CONFIG_SCHED_CLASS_EXT
> -	BUG_ON(!sched_class_above(&fair_sched_class, &ext_sched_class));
> -	BUG_ON(!sched_class_above(&ext_sched_class, &idle_sched_class));
> +	WARN_ON_ONCE(!sched_class_above(&fair_sched_class, &ext_sched_class));
> +	WARN_ON_ONCE(!sched_class_above(&ext_sched_class, &idle_sched_class));
>  #endif
>  

These all really should be BUG_ON(), there is absolutely no point in
tying to complete the boot if they fail.

Re: [PATCH] sched/core: Convert remaining BUG_ON() instances to WARN_ON_ONCE()

[Amin]

Fair enough, thanks for the quick feedback.

Le jeu. 27 août 2026 à 13:42, Peter Zijlstra <peterz@infradead.org> a écrit :
>
> On Thu, Aug 27, 2026 at 01:40:14PM +0200, Amin Gattout wrote:
> > Commit 09348d75a6ce ("sched/all: Change all BUG_ON() instances in the
> > scheduler to WARN_ON_ONCE()") left a few BUG_ON() behind in core.c.
> > Convert them as well.
> >
> > As described in Documentation/process/deprecated.rst, BUG_ON() crashes
> > the system, which makes the failure harder to report and to debug, as
> > the message often never reaches the console or the syslog. With
> > WARN_ON_ONCE() the user gets a chance to see and report the problem
> > instead, and system owners who do not want to keep running after an
> > "impossible" condition can still set panic_on_warn.
> >
> > Signed-off-by: Amin Gattout <amin.gattout@gmail.com>
> > ---
> > Follow-up to commit 09348d75a6ce which converted the scheduler BUG_ON()
> > instances to WARN_ON_ONCE() but left a few behind in core.c.
> >
> > Build tested on arm64 with CONFIG_NO_HZ_FULL and CONFIG_SCHED_CLASS_EXT
> > enabled so that every converted site is compiled.
> > ---
> >  kernel/sched/core.c | 20 ++++++++++----------
> >  1 file changed, 10 insertions(+), 10 deletions(-)
> >
> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > index f78275192036..bab74b4f0dd6 100644
> > --- a/kernel/sched/core.c
> > +++ b/kernel/sched/core.c
> > @@ -5949,7 +5949,7 @@ static void sched_tick_stop(int cpu)
> >  int __init sched_tick_offload_init(void)
> >  {
> >       tick_work_cpu = alloc_percpu(struct tick_work);
> > -     BUG_ON(!tick_work_cpu);
> > +     WARN_ON_ONCE(!tick_work_cpu);
> >       return 0;
> >  }
> >
>
> > @@ -8954,13 +8954,13 @@ void __init sched_init(void)
> >       int i;
> >
> >       /* Make sure the linker didn't screw up */
> > -     BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class));
> > -     BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class));
> > -     BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class));
> > -     BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class));
> > +     WARN_ON_ONCE(!sched_class_above(&stop_sched_class, &dl_sched_class));
> > +     WARN_ON_ONCE(!sched_class_above(&dl_sched_class, &rt_sched_class));
> > +     WARN_ON_ONCE(!sched_class_above(&rt_sched_class, &fair_sched_class));
> > +     WARN_ON_ONCE(!sched_class_above(&fair_sched_class, &idle_sched_class));
> >  #ifdef CONFIG_SCHED_CLASS_EXT
> > -     BUG_ON(!sched_class_above(&fair_sched_class, &ext_sched_class));
> > -     BUG_ON(!sched_class_above(&ext_sched_class, &idle_sched_class));
> > +     WARN_ON_ONCE(!sched_class_above(&fair_sched_class, &ext_sched_class));
> > +     WARN_ON_ONCE(!sched_class_above(&ext_sched_class, &idle_sched_class));
> >  #endif
> >
>
> These all really should be BUG_ON(), there is absolutely no point in
> tying to complete the boot if they fail.
>
>