Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20200827161237.889877377@infradead.org> <20200827161754.535381269@infradead.org>
 <20200827190804.GA128237@debian-boqun.qqnc3lrjykvubdpftowmye0fmh.lx.internal.cloudapp.net>
In-Reply-To: <20200827190804.GA128237@debian-boqun.qqnc3lrjykvubdpftowmye0fmh.lx.internal.cloudapp.net>
From:   Cameron <cameron@moodycamel.com>
Date:   Thu, 27 Aug 2020 15:57:22 -0400
Message-ID: <CAFCw3do_4TrZSQ6kYQ7Y1RYTuD+PfXRyZFp7gSDs2oUXrBZGqQ@mail.gmail.com>
Subject: Re: [RFC][PATCH 6/7] freelist: Lock less freelist
To:     Boqun Feng <boqun.feng@gmail.com>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        linux-kernel@vger.kernel.org, mhiramat@kernel.org,
        Eddy_Wu@trendmicro.com, x86@kernel.org, davem@davemloft.net,
        rostedt@goodmis.org, naveen.n.rao@linux.ibm.com,
        anil.s.keshavamurthy@intel.com, linux-arch@vger.kernel.org,
        oleg@redhat.com, will@kernel.org, paulmck@kernel.org
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, Aug 27, 2020 at 3:08 PM Boqun Feng <boqun.feng@gmail.com> wrote:
> So if try_cmpxchg_acquire() fails, we don't have ACQUIRE semantics on
> read of the new list->head, right? Then probably a
> smp_mb__after_atomic() is needed in that case?

Yes, there needs to be an acquire on the head after a failed cmpxchg;
does the atomic_fetch_add following that not have acquire semantics?

Cameron