From mboxrd@z Thu Jan  1 00:00:00 1970
From: Stephen Hemminger <stephen-OTpzqLSitTUnbdJkjeBofR2eb7JE58TQ@public.gmane.org>
Subject: Re: Bit spinlocks in DPDK
Date: Fri, 20 Dec 2013 08:36:14 -0800
Message-ID: <20131220083614.2a996421@nehalam.linuxnetplumber.net>
References: <6895EAE0CA8DEE40B92D7CA88BB521F332BA572E6B@HQ1-EXCH02.corp.brocade.com>
 <4656219.tgqzelRNOJ@x220> <01d001cef375$7167e300$5437a900$@com>
 <201312201639.05277.thomas.monjalon@6wind.com>
 <04be01cefd9c$a3c36460$eb4a2d20$@com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
Cc: dev-VfR2kkLFssw@public.gmane.org
To: =?ISO-8859-1?B?RnJhbudvaXMtRnLpZOlyaWM=?= Ozog <ff-SpBG2i6TTxU@public.gmane.org>
Return-path: <dev-bounces-VfR2kkLFssw@public.gmane.org>
In-Reply-To: <04be01cefd9c$a3c36460$eb4a2d20$@com>
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request-VfR2kkLFssw@public.gmane.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev-VfR2kkLFssw@public.gmane.org>
List-Help: <mailto:dev-request-VfR2kkLFssw@public.gmane.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request-VfR2kkLFssw@public.gmane.org?subject=subscribe>
Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org
Sender: "dev" <dev-bounces-VfR2kkLFssw@public.gmane.org>

On Fri, 20 Dec 2013 17:00:43 +0100
Fran=E7ois-Fr=E9d=E9ric Ozog <ff-SpBG2i6TTxU@public.gmane.org> wrote:

>=20
>=20
> > -----Message d'origine-----
> > De=A0: Thomas Monjalon [mailto:thomas.monjalon-pdR9zngts4EAvxtiuMwx3w@public.gmane.org]
> > Envoy=E9=A0: vendredi 20 d=E9cembre 2013 16:39
> > =C0=A0: Fran=E7ois-Fr=E9d=E9ric Ozog
> > Cc=A0: dev-VfR2kkLFssw@public.gmane.org
> > Objet=A0: Re: [dpdk-dev] Bit spinlocks in DPDK
> >=20
> > Hello,
> >=20
> > 07/12/2013 18:54, Fran=E7ois-Fr=E9d=E9ric Ozog :
> > > 1) If the critical section deals with weakly ordered loads then
> > > explicit fencing MUST be used: if not, out of order execution will
> > > just kill your idea of critical section.
> > [...]
> > > So use rte_mb() or rte_wmb() or rte_rmb() where appropriate. I
> > > recommend the rte_unlock code and documentation explains the out of
> > > order execution issues and the conditions they have to be mitigated
> > > with rte*mb(). I wonder if having an explicit mfence in
> > > rte_sinlock_unlock wouldn't be just necessary to avoid "hairy" bugs.
> > > In addition, we would have rte_sinlock_unlock_no_mb used internally
> > > for performance reasons, and usable externally by advanced users.
> >=20
> > Using lock prefix is lighter than using memory barrier and have the same
> > effects.
>=20
> Well, in general yes BUT Intel states "../.. locked operations serialize =
all
> outstanding load and store operations ../.. with one exception. Load
> operations that reference weakly ordered memory types (such as the WC mem=
ory
> type) may *not* be serialized" in 8.1.2.2 Software Controlled Bus Locking;
> particularly if streaming loads are used (may happen on certain devices
> memory mapped I/O accesses and the compiler generating streaming loads).
>=20
> So this comment is essentially for the PMD writers: use the fencing where
> appropriate, even if the lock prefix is there. As I will be the one
> forgetting the rule, I like to have that in the documentation/comments as
> reminders to keep things neat.
>=20
> Fran=E7ois-Fr=E9d=E9ric

I recommend anyone who needs more information read:
  Documentation/memory-barriers.txt
in the Linux kernel source.