Re: [patch v2 03/14] genirq/proc: Utilize irq_desc::tot_count to avoid evaluation

[Radu Rendec <radu@rendec.net>]

On Fri, 2026-03-20 at 14:21 +0100, Thomas Gleixner wrote:
> Interrupts which are not marked per CPU increment not only the per CPU
> statistics, but also the accumulation counter irq_desc::tot_count.
> 
> Change the counter to type unsigned long so it does not produce sporadic
> zeros due to wrap arounds on 64-bit machines and do a quick check for non
> per CPU interrupts. If the counter is zero, then simply emit a full set of
> zero strings. That spares the evaluation of the per CPU counters completely
> for interrupts with zero events.
> 
> Signed-off-by: Thomas Gleixner <tglx@kernel.org>
> Reviewed-by: Dmitry Ilvokhin <d@ilvokhin.com>
> ---
>  include/linux/irqdesc.h |    6 +++---
>  kernel/irq/proc.c       |   11 ++++++++++-
>  2 files changed, 13 insertions(+), 4 deletions(-)
> 
> --- a/include/linux/irqdesc.h
> +++ b/include/linux/irqdesc.h
> @@ -52,8 +52,8 @@ struct irq_redirect {
>   * @depth:		disable-depth, for nested irq_disable() calls
>   * @wake_depth:		enable depth, for multiple irq_set_irq_wake() callers
>   * @tot_count:		stats field for non-percpu irqs
> - * @irq_count:		stats field to detect stalled irqs
>   * @last_unhandled:	aging timer for unhandled count
> + * @irq_count:		stats field to detect stalled irqs
>   * @irqs_unhandled:	stats field for spurious unhandled interrupts
>   * @threads_handled:	stats field for deferred spurious detection of threaded handlers
>   * @threads_handled_last: comparator field for deferred spurious detection of threaded handlers
> @@ -87,9 +87,9 @@ struct irq_desc {
>  	unsigned int		core_internal_state__do_not_mess_with_it;
>  	unsigned int		depth;		/* nested irq disables */
>  	unsigned int		wake_depth;	/* nested wake enables */
> -	unsigned int		tot_count;
> -	unsigned int		irq_count;	/* For detecting broken IRQs */
> +	unsigned long		tot_count;
>  	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
> +	unsigned int		irq_count;	/* For detecting broken IRQs */
>  	unsigned int		irqs_unhandled;
>  	atomic_t		threads_handled;
>  	int			threads_handled_last;
> --- a/kernel/irq/proc.c
> +++ b/kernel/irq/proc.c
> @@ -521,7 +521,16 @@ int show_interrupts(struct seq_file *p,
>  		return 0;
>  
>  	seq_printf(p, "%*d:", prec, i);
> -	irq_proc_emit_counts(p, &desc->kstat_irqs->cnt);
> +
> +	/*
> +	 * Always output per CPU interrupts. Output device interrupts only when
> +	 * desc::tot_count is not zero.
> +	 */
> +	if (irq_settings_is_per_cpu(desc) || irq_settings_is_per_cpu_devid(desc) ||
> +	    data_race(desc->tot_count))
> +		irq_proc_emit_counts(p, &desc->kstat_irqs->cnt);
> +	else
> +		irq_proc_emit_zero_counts(p, num_online_cpus());
>  	seq_putc(p, ' ');
>  
>  	guard(raw_spinlock_irq)(&desc->lock);

Reviewed-by: Radu Rendec <radu@rendec.net>