From mboxrd@z Thu Jan  1 00:00:00 1970
From: Stephen Hemminger <stephen@networkplumber.org>
Subject: Re: rte_mbuf library likely()/unlikely()
Date: Mon, 23 Jul 2018 10:37:57 -0700
Message-ID: <20180723103757.47e4c26b@xeon-e3>
References: <98CBD80474FA8B44BF855DF32C47DC35B421EE@smartserver.smartshare.dk>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Cc: "Olivier Matz" <olivier.matz@6wind.com>, <dev@dpdk.org>
To: Morten =?UTF-8?B?QnLDuHJ1cA==?= <mb@smartsharesystems.com>
Return-path: <dev-bounces@dpdk.org>
Received: from mail-pl0-f49.google.com (mail-pl0-f49.google.com
 [209.85.160.49]) by dpdk.org (Postfix) with ESMTP id B4DBF235
 for <dev@dpdk.org>; Mon, 23 Jul 2018 19:38:00 +0200 (CEST)
Received: by mail-pl0-f49.google.com with SMTP id j8-v6so457844pll.12
 for <dev@dpdk.org>; Mon, 23 Jul 2018 10:38:00 -0700 (PDT)
In-Reply-To: <98CBD80474FA8B44BF855DF32C47DC35B421EE@smartserver.smartshare.dk>
List-Id: DPDK patches and discussions <dev.dpdk.org>
List-Unsubscribe: <https://mails.dpdk.org/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://mails.dpdk.org/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <https://mails.dpdk.org/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>

On Mon, 23 Jul 2018 15:53:42 +0200
Morten Br=C3=B8rup <mb@smartsharesystems.com> wrote:

> Hi Olivier,
>=20
> =20
>=20
> I noticed that __rte_pktmbuf_read() could do with an unlikely(), so I wen=
t through the entire library. Here are my suggested modifications.
>=20
> =20
>=20
> =20
>=20
> diff -bu rte_mbuf.c.orig rte_mbuf.c
>=20
> --- rte_mbuf.c.orig     2018-07-23 15:13:22.000000000 +0200
>=20
> +++ rte_mbuf.c  2018-07-23 15:32:53.000000000 +0200
>=20
> @@ -173,19 +173,19 @@
>=20
> {
>=20
>         unsigned int nb_segs, pkt_len;
>=20
> =20
>=20
> -       if (m =3D=3D NULL)
>=20
> +       if (unlikely(m =3D=3D NULL))
>=20
>                 rte_panic("mbuf is NULL\n");
>=20
> =20

Adding is unlikely is not necessary since rte_panic is marked with cold att=
ribute
which has the same effect.