Re: [BUG 4.15-rc7] IRQ matrix management errors

[Thomas Gleixner]

On Tue, 16 Jan 2018, Keith Busch wrote:

> This is all way over my head, but the part that obviously shows
> something's gone wrong:
> 
>   kworker/u674:3-1421  [028] d...   335.307051: irq_matrix_reserve_managed: bit=56 cpu=0 online=1 avl=86 alloc=116 managed=3 online_maps=112 global_avl=22084, global_rsvd=157, total_alloc=570
>   kworker/u674:3-1421  [028] d...   335.307053: irq_matrix_remove_managed: bit=56 cpu=0 online=1 avl=87 alloc=116 managed=2 online_maps=112 global_avl=22085, global_rsvd=157, total_alloc=570
>   kworker/u674:3-1421  [028] ....   335.307054: vector_reserve_managed: irq=45 ret=-28
>   kworker/u674:3-1421  [028] ....   335.307054: vector_setup: irq=45 is_legacy=0 ret=-28
>   kworker/u674:3-1421  [028] d...   335.307055: vector_teardown: irq=45 is_managed=1 has_reserved=0
> 
> Which leads me to x86_vector_alloc_irqs goto error:
> 
> error:
> 	x86_vector_free_irqs(domain, virq, i + 1);
> 
> The last parameter looks weird. It's the nr_irqs, and since we failed and
> bailed, I would think we'd need to subtract 1 rather than add 1. Adding
> 1 would doublely remove the failed one, and remove the next one that
> was never setup, right?

Right. That's fishy. Let me stare at it.

> Or maybe irq_matrix_reserve_managed wasn't expected to fail in the
> first place?

Well, it can faul. I don't know why it fails in that case, but let me look
a bit more.

Thanks,

	tglx