Re: [PATCH 0/4] move per-vma lock into vm_area_struct

[Davidlohr Bueso]

On Mon, 11 Nov 2024, Suren Baghdasaryan wrote:

> I'm not really trying to claim performance gains here. I just want to
> make sure there are no regressions.

You might also fine tune the atomics with acquire/release standard locking
semantics, you will probably see better numbers in Android than what you
currently have in patch 3 with full barriers - and not particularly risky
as callers expect that behaviour already.

Thanks,
Davidlohr