From mboxrd@z Thu Jan  1 00:00:00 1970
From: Stephen Hemminger <stephen@networkplumber.org>
Subject: Re: [PATCH v2] kni: fix build on SLE12 SP3
Date: Tue, 29 Aug 2017 08:12:52 -0700
Message-ID: <20170829081252.562f9313@xeon-e3>
References: <20170829150613.10597-1-ndas@suse.de>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Cc: ferruh.yigit@intel.com, dev@dpdk.org
To: Nirmoy Das <ndas@suse.de>
Return-path: <dev-bounces@dpdk.org>
Received: from mail-pg0-f41.google.com (mail-pg0-f41.google.com [74.125.83.41])
 by dpdk.org (Postfix) with ESMTP id 50CB62BD8
 for <dev@dpdk.org>; Tue, 29 Aug 2017 17:12:55 +0200 (CEST)
Received: by mail-pg0-f41.google.com with SMTP id r133so11621480pgr.3
 for <dev@dpdk.org>; Tue, 29 Aug 2017 08:12:55 -0700 (PDT)
In-Reply-To: <20170829150613.10597-1-ndas@suse.de>
List-Id: DPDK patches and discussions <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>

On Tue, 29 Aug 2017 17:06:13 +0200
Nirmoy Das <ndas@suse.de> wrote:

> compilation error:
> build/lib/librte_eal/linuxapp/kni/kni_net.c:215:5: error:
> =E2=80=98struct net_device=E2=80=99 has no member named =E2=80=98trans_st=
art=E2=80=99
>   dev->trans_start =3D jiffies;
>=20
> Signed-off-by: Nirmoy Das <ndas@suse.de>
> ---
>  lib/librte_eal/linuxapp/kni/compat.h | 32 ++++++++++++++++++++++++++++++=
+-
>  1 file changed, 31 insertions(+), 1 deletion(-)
>=20
> diff --git a/lib/librte_eal/linuxapp/kni/compat.h b/lib/librte_eal/linuxa=
pp/kni/compat.h
> index 6a1587b4e..19f8e96ce 100644
> --- a/lib/librte_eal/linuxapp/kni/compat.h
> +++ b/lib/librte_eal/linuxapp/kni/compat.h
> @@ -8,6 +8,34 @@
>  #define RHEL_RELEASE_VERSION(a, b) (((a) << 8) + (b))
>  #endif
> =20
> +/* SuSE version macro is the same as Linux kernel version */
> +#ifndef SLE_VERSION
> +#define SLE_VERSION(a, b, c) KERNEL_VERSION(a, b, c)
> +#endif
> +#ifdef CONFIG_SUSE_KERNEL
> +#if (LINUX_VERSION_CODE >=3D KERNEL_VERSION(4, 4, 57))
> +/* SLES12SP3 is at least 4.4.57+ based */
> +#define SLE_VERSION_CODE SLE_VERSION(12, 3, 0)
> +#elif (LINUX_VERSION_CODE >=3D KERNEL_VERSION(3, 12, 28))
> +/* SLES12 is at least 3.12.28+ based */
> +#define SLE_VERSION_CODE SLE_VERSION(12, 0, 0)
> +#elif ((LINUX_VERSION_CODE >=3D KERNEL_VERSION(3, 0, 61)) && \
> +       (LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)))
> +/* SLES11 SP3 is at least 3.0.61+ based */
> +#define SLE_VERSION_CODE SLE_VERSION(11, 3, 0)
> +#elif (LINUX_VERSION_CODE =3D=3D KERNEL_VERSION(2, 6, 32))
> +/* SLES11 SP1 is 2.6.32 based */
> +#define SLE_VERSION_CODE SLE_VERSION(11, 1, 0)
> +#elif (LINUX_VERSION_CODE =3D=3D KERNEL_VERSION(2, 6, 27))
> +/* SLES11 GA is 2.6.27 based */
> +#define SLE_VERSION_CODE SLE_VERSION(11, 0, 0)
> +#endif /* LINUX_VERSION_CODE =3D=3D KERNEL_VERSION(x,y,z) */
> +#endif /* CONFIG_SUSE_KERNEL */
> +#ifndef SLE_VERSION_CODE
> +#define SLE_VERSION_CODE 0
> +#endif /* SLE_VERSION_CODE */
> +
> +
>  #if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39) && \
>  	(!(defined(RHEL_RELEASE_CODE) && \
>  	   RHEL_RELEASE_CODE >=3D RHEL_RELEASE_VERSION(6, 4)))
> @@ -55,7 +83,9 @@
> =20
>  #if LINUX_VERSION_CODE >=3D KERNEL_VERSION(4, 7, 0) || \
>  	(defined(RHEL_RELEASE_CODE) && \
> -	 RHEL_RELEASE_CODE >=3D RHEL_RELEASE_VERSION(7, 4))
> +	 RHEL_RELEASE_CODE >=3D RHEL_RELEASE_VERSION(7, 4)) || \
> +	 (defined(SLE_VERSION_CODE) && \
> +	  SLE_VERSION_CODE =3D=3D SLE_VERSION(12, 3, 0))
>  #define HAVE_TRANS_START_HELPER
>  #endif
> =20

Sigh. KNI needs to get upstream, or we need to leave RHEL and SLES
version magic to the distros to manage as their own patches.

This kind of spaghetti of ifdef's is unmanageable, untestable, and=20
just plain ugly.