Re: [dpdk-dev] [PATCH 1/2] mk: add Marvell ARMADA architecture based on armv8-a

[Liron Himi <lironh@marvell.com>]

Hi,



Regards,
Liron

-----Original Message-----
From: Ruifeng Wang (Arm Technology China) <Ruifeng.Wang@arm.com> 
Sent: Wednesday, May 22, 2019 12:11
To: Liron Himi <lironh@marvell.com>; thomas@monjalon.net
Cc: dev@dpdk.org; nd <nd@arm.com>; nd <nd@arm.com>
Subject: [EXT] RE: [dpdk-dev] [PATCH 1/2] mk: add Marvell ARMADA architecture based on armv8-a

External Email

----------------------------------------------------------------------
Hi,

> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of lironh@marvell.com
> Sent: Saturday, May 18, 2019 05:27
> To: thomas@monjalon.net
> Cc: dev@dpdk.org; Liron Himi <lironh@marvell.com>
> Subject: [dpdk-dev] [PATCH 1/2] mk: add Marvell ARMADA architecture 
> based on armv8-a
> 
> From: Liron Himi <lironh@marvell.com>
> 
> This patch introduces armada target to address difference in number of 
> cores, no numa support
> 
> Change-Id: Ieaabe77b165000fe1280f98105329a0e63833b92
> Signed-off-by: Liron Himi <lironh@marvell.com>
> Reviewed-by: Alan Winkowski
> Tested-by: Liron Himi
> ---
>  config/defconfig_arm64-armada-linux-gcc    | 24
> ++++++++++++++++++++++++
>  config/defconfig_arm64-armada-linuxapp-gcc | 24
> ++++++++++++++++++++++++
>  2 files changed, 48 insertions(+)
>  create mode 100644 config/defconfig_arm64-armada-linux-gcc
>  create mode 100644 config/defconfig_arm64-armada-linuxapp-gcc
> 
> diff --git a/config/defconfig_arm64-armada-linux-gcc
> b/config/defconfig_arm64-armada-linux-gcc
> new file mode 100644
> index 0000000..573b278
> --- /dev/null
> +++ b/config/defconfig_arm64-armada-linux-gcc
> @@ -0,0 +1,24 @@
> +# SPDX-License-Identifier: BSD-3-Clause # Copyright(c) 2018 Marvell 
> +International Ltd #
> +
> +#include "defconfig_arm64-armv8a-linux-gcc"
> +
> +CONFIG_RTE_LIBRTE_MVEP_COMMON=y
> +CONFIG_RTE_LIBRTE_MVPP2_PMD=y
> +CONFIG_RTE_LIBRTE_MVNETA_PMD=y
> +CONFIG_RTE_LIBRTE_PMD_MVSAM_CRYPTO=y
> +
> +#
> +# Compile Environment Abstraction Layer #
> +CONFIG_RTE_MAX_LCORE=16
> +CONFIG_RTE_MAX_NUMA_NODES=1
> +CONFIG_RTE_CACHE_LINE_SIZE=64
> +
> +# Disable NXP as it is conflict with MUSDK
> CONFIG_RTE_LIBRTE_DPAA_BUS=n
> +
> +# Doesn't support NUMA
> +CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES=n
> +CONFIG_RTE_LIBRTE_VHOST_NUMA=n
> diff --git a/config/defconfig_arm64-armada-linuxapp-gcc
> b/config/defconfig_arm64-armada-linuxapp-gcc
> new file mode 100644
> index 0000000..573b278
> --- /dev/null
> +++ b/config/defconfig_arm64-armada-linuxapp-gcc
> @@ -0,0 +1,24 @@
> +# SPDX-License-Identifier: BSD-3-Clause # Copyright(c) 2018 Marvell 
> +International Ltd #
> +
> +#include "defconfig_arm64-armv8a-linux-gcc"
> +
> +CONFIG_RTE_LIBRTE_MVEP_COMMON=y
> +CONFIG_RTE_LIBRTE_MVPP2_PMD=y
> +CONFIG_RTE_LIBRTE_MVNETA_PMD=y

There is a note in MVPP2 PMD guide, " When MVPP2 PMD is enabled CONFIG_RTE_LIBRTE_MVNETA_PMD must be disabled ".
I think this configuration conflicts with the guide. Does the guide need to be updated?
[L.H.] yes, I will submit another patch with documentation updates.

> +CONFIG_RTE_LIBRTE_PMD_MVSAM_CRYPTO=y
> +
> +#
> +# Compile Environment Abstraction Layer #
> +CONFIG_RTE_MAX_LCORE=16
> +CONFIG_RTE_MAX_NUMA_NODES=1
> +CONFIG_RTE_CACHE_LINE_SIZE=64
> +
> +# Disable NXP as it is conflict with MUSDK
> CONFIG_RTE_LIBRTE_DPAA_BUS=n
> +
> +# Doesn't support NUMA
> +CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES=n
> +CONFIG_RTE_LIBRTE_VHOST_NUMA=n
> --
> 2.7.4