Re: [PATCH v3] Avoid memory barrier in read_seqcount() through load acquire

From: Christoph Lameter (Ampere)
Date: Fri Oct 25 2024 - 16:44:41 EST


On Fri, 25 Oct 2024, Peter Zijlstra wrote:

> > atomic_inc_release(&seqcount)
>
> It would not be, making the increment itself atomic would make the whole
> thing far more expensive.

True. I was too much taken by a cool hw feature on ARM.