Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
From:   Joel Fernandes <joel@joelfernandes.org>
Mime-Version: 1.0 (1.0)
Subject: Re: [RFC 0/2] srcu: Remove pre-flip memory barrier
Date:   Tue, 20 Dec 2022 23:26:12 -0500
Message-Id: <6BD506EA-77D2-4AC9-87A5-C8781594CF0F@joelfernandes.org>
References: <f4199d1f-306c-681f-8bb9-26d66ecf5121@efficios.com>
Cc:     Frederic Weisbecker <frederic@kernel.org>,
        linux-kernel@vger.kernel.org,
        Josh Triplett <josh@joshtriplett.org>,
        Lai Jiangshan <jiangshanlai@gmail.com>,
        "Paul E. McKenney" <paulmck@kernel.org>, rcu@vger.kernel.org,
        Steven Rostedt <rostedt@goodmis.org>
In-Reply-To: <f4199d1f-306c-681f-8bb9-26d66ecf5121@efficios.com>
To:     Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Precedence: bulk


> On Dec 20, 2022, at 10:43 PM, Mathieu Desnoyers <mathieu.desnoyers@efficio=
s.com> wrote:
>=20
> =EF=BB=BFOn 2022-12-20 19:58, Frederic Weisbecker wrote:
>>> On Wed, Dec 21, 2022 at 01:49:57AM +0100, Frederic Weisbecker wrote:
>>> On Tue, Dec 20, 2022 at 07:15:00PM -0500, Joel Fernandes wrote:
>>>> On Tue, Dec 20, 2022 at 5:45 PM Frederic Weisbecker <frederic@kernel.or=
g> wrote:
>>>> Agreed about (1).
>>>>=20
>>>>> _ In (2), E pairs with the address-dependency between idx and lock_cou=
nt.
>>>>=20
>>>> But that is not the only reason. If that was the only reason for (2),
>>>> then there is an smp_mb() just before the next-scan post-flip before
>>>> the lock counts are read.
>>>=20
>>> The post-flip barrier makes sure the new idx is visible on the next READ=
ER's
>>> turn, but it doesn't protect against the fact that "READ idx then WRITE l=
ock[idx]"
>>> may appear unordered from the update side POV if there is no barrier bet=
ween the
>>> scan and the flip.
>>>=20
>>> If you remove the smp_mb() from the litmus test I sent, things explode.
>> Or rather, look at it the other way, if there is no barrier between the l=
ock
>> scan and the index flip (E), then the index flip can appear to be written=
 before the
>> lock is read. Which means you may start activating the index before you f=
inish
>> reading it (at least it appears that way from the readers pont of view).
>=20
> Considering that you can have pre-existing readers from arbitrary index ap=
pearing anywhere in the grace period (because a reader can fetch the
> index and be preempted for an arbitrary amount of time before incrementing=
 the lock count), the grace period algorithm needs to deal with the fact tha=
t a newcoming reader can appear in a given index either before or after the f=
lip.
>=20
> I don't see how flipping the index before or after loading the unlock/lock=
 values would break anything (except for unlikely counter overflow situation=
s as previously discussed).

If you say unlikely, that means it can happen some times which is bad enough=
 ;-). Maybe you mean impossible. I would not settle for anything less than k=
eeping the memory barrier around if it helps unlikely cases, but only D does=
 help for the theoretical wrapping/overflow issue. E is broken and does not e=
ven help the theoretical issue IMO. And both D and E do not affect correctne=
ss IMO.

Anyway in all likelihood, I will be trying to remove E completely and clarif=
y docs on D in the coming weeks. And also try to drop the size of the counte=
rs per our discussions

Thanks.


>=20
> Thanks,
>=20
> Mathieu
>=20
> --=20
> Mathieu Desnoyers
> EfficiOS Inc.
> https://www.efficios.com
>=20