[v3 0/9] parallelized "struct page" zeroing

[David Miller]

From: Michal Hocko <mhocko at kernel.org>
Date: Thu, 11 May 2017 10:05:38 +0200

> Anyway, do you agree that doing the struct page initialization along
> with other writes to it shouldn't add a measurable overhead comparing
> to pre-zeroing of larger block of struct pages?  We already have an
> exclusive cache line and doing one 64B write along with few other stores
> should be basically the same.

Yes, it should be reasonably cheap.