[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANeU7Q=AXzG05BPcKPJvMDzmc8QK4UDKz+zaLQAx=RCrcsBkVA@mail.gmail.com>
Date: Wed, 20 Mar 2024 12:41:48 -0700
From: Chris Li <chrisl@...nel.org>
To: Yosry Ahmed <yosryahmed@...gle.com>
Cc: Johannes Weiner <hannes@...xchg.org>, Andrew Morton <akpm@...ux-foundation.org>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
Nhat Pham <nphamcs@...il.com>, "Matthew Wilcox (Oracle)" <willy@...radead.org>,
Chengming Zhou <zhouchengming@...edance.com>, Barry Song <v-songbaohua@...o.com>
Subject: Re: [PATCH v7] zswap: replace RB tree with xarray
On Wed, Mar 20, 2024 at 12:34 PM Yosry Ahmed <yosryahmed@...gle.com> wrote:
> > you can expect it to be coherent.
>
> Fair enough, but don't we still need a barrier there? Couldn't some
> initializations still be reorder after zswap_lru_add()?
I am under the impression that the lru list handling function already
handles the barrier. If an explicit barrier is needed, wouldn't all
other lru callers have barriers sprinkling all over the place?
Chris
Powered by blists - more mailing lists