Re: [PATCH v3 2/2] net: core: support XDP generic on stacked devices.

[Saeed Mahameed <saeedm@mellanox.com>]

On Thu, 2019-05-23 at 10:54 -0700, Stephen Hemminger wrote:
> When a device is stacked like (team, bonding, failsafe or netvsc) the
> XDP generic program for the parent device was not called.
> 
> Move the call to XDP generic inside __netif_receive_skb_core where
> it can be done multiple times for stacked case.
> 
> Suggested-by: Jiri Pirko <jiri@resnulli.us>
> Fixes: d445516966dc ("net: xdp: support xdp generic on virtual
> devices")
> Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
> ---
> v1 - call xdp_generic in netvsc handler
> v2 - do xdp_generic in generic rx handler processing
> v3 - move xdp_generic call inside the another pass loop
> 
>  net/core/dev.c | 56 ++++++++++------------------------------------
> ----
>  1 file changed, 11 insertions(+), 45 deletions(-)
> 
> diff --git a/net/core/dev.c b/net/core/dev.c
> index b6b8505cfb3e..696776e14d00 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -4502,23 +4502,6 @@ static int netif_rx_internal(struct sk_buff
> *skb)
>  
>  	trace_netif_rx(skb);
>  
> -	if (static_branch_unlikely(&generic_xdp_needed_key)) {
> -		int ret;
> -
> -		preempt_disable();
> -		rcu_read_lock();
> -		ret = do_xdp_generic(rcu_dereference(skb->dev-
> >xdp_prog), skb);
> -		rcu_read_unlock();
> -		preempt_enable();
> -
> -		/* Consider XDP consuming the packet a success from
> -		 * the netdev point of view we do not want to count
> -		 * this as an error.
> -		 */
> -		if (ret != XDP_PASS)
> -			return NET_RX_SUCCESS;
> -	}
> -

Adding Jesper, 

There is a small behavioral change due to this patch, 
the XDP program after this patch will run on the RPS CPU, if
configured, which could cause some behavioral changes in
xdp_redirect_cpu: bpf_redirect_map(cpu_map).

Maybe this is acceptable, but it should be documented, as the current
assumption dictates: XDP program runs on the core where the XDP
frame/SKB was first seen.

>  #ifdef CONFIG_RPS
>  	if (static_branch_unlikely(&rps_needed)) {
>  		struct rps_dev_flow voidflow, *rflow = &voidflow;
> @@ -4858,6 +4841,17 @@ static int __netif_receive_skb_core(struct
> sk_buff *skb, bool pfmemalloc,
>  
>  	__this_cpu_inc(softnet_data.processed);
>  
> +	if (static_branch_unlikely(&generic_xdp_needed_key)) {
> +		int ret2;
> +
> +		preempt_disable();
> +		ret2 = do_xdp_generic(rcu_dereference(skb->dev-
> >xdp_prog), skb);
> +		preempt_enable();
> +
> +		if (ret2 != XDP_PASS)
> +			return NET_RX_DROP;
> +	}
> +
>  	if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
>  	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
>  		skb = skb_vlan_untag(skb);
> @@ -5178,19 +5172,6 @@ static int netif_receive_skb_internal(struct
> sk_buff *skb)
>  	if (skb_defer_rx_timestamp(skb))
>  		return NET_RX_SUCCESS;
>  
> -	if (static_branch_unlikely(&generic_xdp_needed_key)) {
> -		int ret;
> -
> -		preempt_disable();
> -		rcu_read_lock();
> -		ret = do_xdp_generic(rcu_dereference(skb->dev-
> >xdp_prog), skb);
> -		rcu_read_unlock();
> -		preempt_enable();
> -
> -		if (ret != XDP_PASS)
> -			return NET_RX_DROP;
> -	}
> -
>  	rcu_read_lock();
>  #ifdef CONFIG_RPS
>  	if (static_branch_unlikely(&rps_needed)) {
> @@ -5224,21 +5205,6 @@ static void
> netif_receive_skb_list_internal(struct list_head *head)
>  	}
>  	list_splice_init(&sublist, head);
>  
> -	if (static_branch_unlikely(&generic_xdp_needed_key)) {
> -		preempt_disable();
> -		rcu_read_lock();
> -		list_for_each_entry_safe(skb, next, head, list) {
> -			xdp_prog = rcu_dereference(skb->dev->xdp_prog);
> -			skb_list_del_init(skb);
> -			if (do_xdp_generic(xdp_prog, skb) == XDP_PASS)
> -				list_add_tail(&skb->list, &sublist);
> -		}
> -		rcu_read_unlock();
> -		preempt_enable();
> -		/* Put passed packets back on main list */
> -		list_splice_init(&sublist, head);
> -	}
> -
>  	rcu_read_lock();
>  #ifdef CONFIG_RPS
>  	if (static_branch_unlikely(&rps_needed)) {