netdev - Re: [PATCH] net/mlx5e: Add bonding device for indr block to offload the packet received from bonding device

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:   Sun, 19 May 2019 08:07:50 +0000
From:   Roi Dayan <roid@...lanox.com>
To:     "wenxu@...oud.cn" <wenxu@...oud.cn>,
        Saeed Mahameed <saeedm@...lanox.com>
CC:     "netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: Re: [PATCH] net/mlx5e: Add bonding device for indr block to offload
 the packet received from bonding device



On 17/05/2019 11:21, wenxu@...oud.cn wrote:
> From: wenxu <wenxu@...oud.cn>
> 
> The mlx5e support the lag mode. When add mlx_p0 and mlx_p1 to bond0.
> packet received from mlx_p0 or mlx_p1 and in the ingress tc flower
> forward to vf0. The tc rule can't be offloaded for the non indr
> rejistor block for the bonding device.
> 
> Signed-off-by: wenxu <wenxu@...oud.cn>
> ---
>  drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
> index 91e24f1..134fa0b 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
> @@ -796,6 +796,7 @@ static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb,
>  	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
>  
>  	if (!mlx5e_tc_tun_device_to_offload(priv, netdev) &&
> +	    !netif_is_bond_master(netdev) &&
>  	    !is_vlan_dev(netdev))
>  		return NOTIFY_OK;
>  
> 

hmm. is this the only thing blocked you from offloading indirect from bond?
when u add the rule from bond like this this also need to make sure the rule
is duplicated to both eswitches in is_peer_flow_needed().

today we support bond offloading by using shared tc block.
i.e. you add a shared tc block to bond and its slaves.
then all rules you add to the shared block instead of a specific interface.

this is also how OVS currently offload the rules with bond.
when u add a bond port, ovs adds a shared tc block to the slaves.
then new rules added to the tc block instead of the bond interface.