Re: [PATCH] ring-buffer: Use a housekeeping CPU to wake up waiters

[Steven Rostedt]

On Wed, 7 Jan 2026 10:51:37 +0100
Petr Tesarik <ptesa...@suse.com> wrote:

> Erm. It's actually good I had a look. :-(
> 
> A helpful comment in irq_work_queue_on() explains that "arch remote IPI
> send/receive backend aren't NMI safe". That's something I wasn't aware
> of, and I'm afraid it's the end of story. The comment is followed by a
> WARN_ON_ONCE(in_nmi()), and I can easily trigger it with "perf top"
> while nmi:nmi_handler is traced.
> 
> Please, remove the patch again. I'm sorry.

Or we simply change it to:

static inline void
rb_irq_work_queue(struct rb_irq_work *irq_work)
{
        int cpu;

        /* irq_work_queue_on() is not allowed in NMI context */
        if (in_nmi()) {
                irq_work_queue(&irq_work->work, cpu);
                return;
        }

        cpu = housekeeping_any_cpu(HK_TYPE_KERNEL_NOISE);
        /*
         * If CPU isolation is not active, cpu is always the current
         * CPU, and the following is equivallent to irq_work_queue().
         */
        irq_work_queue_on(&irq_work->work, cpu);
}


-- Steve