Unfair qspinlocks on ARM64 without LSE atomics => 3ms delay in interrupt handling

[Sebastian Andrzej Siewior]

On 2023-04-27 15:45:09 [+0200], Kurt Kanzenbach wrote:
> > Are we aware of other concrete case where it bites? Even with just
> > "normal" contented spin_lock usage?
> 
> Well, some years ago I've observed a similar problem with ARM64
> spinlocks, cpu_relax() and retry loops (in the futex code). It also
> generated latency spikes up to 2-3ms. Back then, it was easily
> reproducible using stress-ng --ptrace 4.

That was fixed by
	https://patchwork.kernel.org/project/linux-arm-kernel/patch/1399528508-2806-1-git-send-email-arjun.kv@samsung.com

if my memory serves me well.

> Thanks,
> Kurt

Sebastian