[dpdk-dev] [PATCH v10 07/11] net/failsafe: support offload capabilities

[Ferruh Yigit]

On 7/15/2017 6:57 PM, Gaetan Rivet wrote:
> Signed-off-by: Gaetan Rivet <gaetan.rivet at 6wind.com>
> Acked-by: Olga Shern <olgas at mellanox.com>
> ---
>  doc/guides/nics/features/failsafe.ini |   6 ++
>  drivers/net/failsafe/failsafe_ops.c   | 131 +++++++++++++++++++++++++++++++++-
>  2 files changed, 135 insertions(+), 2 deletions(-)
> 
> diff --git a/doc/guides/nics/features/failsafe.ini b/doc/guides/nics/features/failsafe.ini
> index 9167b59..257f579 100644
> --- a/doc/guides/nics/features/failsafe.ini
> +++ b/doc/guides/nics/features/failsafe.ini
> @@ -14,6 +14,12 @@ Unicast MAC filter   = Y
>  Multicast MAC filter = Y
>  VLAN filter          = Y
>  Flow API             = Y
> +VLAN offload         = Y
> +QinQ offload         = Y
> +L3 checksum offload  = Y
> +L4 checksum offload  = Y
> +Inner L3 checksum    = Y
> +Inner L4 checksum    = Y

As previous comment on features, these are advertised as supported but
depends on sub-devices.

Overall I don't know what does these mean for failsafe like abstract device.

>  Packet type parsing  = Y
>  Basic stats          = Y
>  Stats per queue      = Y
> diff --git a/drivers/net/failsafe/failsafe_ops.c b/drivers/net/failsafe/failsafe_ops.c
> index 0c8aa35..654b411 100644
> --- a/drivers/net/failsafe/failsafe_ops.c
> +++ b/drivers/net/failsafe/failsafe_ops.c
> @@ -64,22 +64,149 @@ static struct rte_eth_dev_info default_infos = {
>  		.nb_seg_max = UINT16_MAX,
>  		.nb_mtu_seg_max = UINT16_MAX,
>  	},
> -	/* Set of understood capabilities */
> -	.rx_offload_capa = 0x0,
> +	/*
> +	 * Set of capabilities that can be verified upon
> +	 * configuring a sub-device.
> +	 */
> +	.rx_offload_capa =
> +		DEV_RX_OFFLOAD_VLAN_STRIP |
> +		DEV_RX_OFFLOAD_QINQ_STRIP |
> +		DEV_RX_OFFLOAD_IPV4_CKSUM |
> +		DEV_RX_OFFLOAD_UDP_CKSUM |
> +		DEV_RX_OFFLOAD_TCP_CKSUM |
> +		DEV_RX_OFFLOAD_TCP_LRO,

These are not dynamic, even though some may be disabled via
fs_port_disable_offload() same these values will be returned to the
application, which is wrong.

>  	.tx_offload_capa = 0x0,

Claiming support for most of the offloads means supporting it both for
Rx and Tx path. This patch only takes account the Rx ones.

>  	.flow_type_rss_offloads = 0x0,
>  };
> 

<...>