Re: [RFC] arm64: Enforce observed order for spinlock and data

From: Peter Zijlstra
Date: Tue Oct 04 2016 - 02:50:26 EST

On Mon, Oct 03, 2016 at 03:20:57PM -0400, bdegraaf@xxxxxxxxxxxxxx wrote:
> Thinking about this, as the reader/writer code has no known "abuse"
> case, I'll remove it from the patchset, then provide a v2 patchset
> with a detailed explanation for the lockref problem using the commits
> you provided as an example, as well as performance consideration.

Please, fix lockref in those patches. Touching the spinlock because
lockref does something dubious really is the wrong thing.