Re: [PATCH net-next] udp: allow forwarding of plain (non-fraglisted) UDP GRO packets

From: Alexander Duyck <alexander.duyck@gmail.com>
To: Alexander Lobakin <alobakin@pm.me>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>,
	Edward Cree <ecree@solarflare.com>,
	Willem de Bruijn <willemb@google.com>,
	Steffen Klassert <steffen.klassert@secunet.com>,
	Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>,
	Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH net-next] udp: allow forwarding of plain (non-fraglisted) UDP GRO packets
Date: Tue, 12 Jan 2021 19:10:40 -0800	[thread overview]
Message-ID: <6fb72534-d4d4-94d8-28d1-aabf16e11488@gmail.com> (raw)
In-Reply-To: <20210112211536.261172-1-alobakin@pm.me>

On 1/12/21 1:16 PM, Alexander Lobakin wrote:
> Commit 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.") actually
> not only added a support for fraglisted UDP GRO, but also tweaked
> some logics the way that non-fraglisted UDP GRO started to work for
> forwarding too.
> Tests showed that currently forwarding and NATing of plain UDP GRO
> packets are performed fully correctly, regardless if the target
> netdevice has a support for hardware/driver GSO UDP L4 or not.
> Add the last element and allow to form plain UDP GRO packets if
> there is no socket -> we are on forwarding path.
> 
> Plain UDP GRO forwarding even shows better performance than fraglisted
> UDP GRO in some cases due to not wasting one skbuff_head per every
> segment.
> 
> Signed-off-by: Alexander Lobakin <alobakin@pm.me>
> ---
>   net/ipv4/udp_offload.c | 5 +++--
>   1 file changed, 3 insertions(+), 2 deletions(-)
> 
> diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
> index ff39e94781bf..9d71df3d52ce 100644
> --- a/net/ipv4/udp_offload.c
> +++ b/net/ipv4/udp_offload.c
> @@ -460,12 +460,13 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
>   	if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
>   		NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1;
>   
> -	if ((sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) {
> +	if (!sk || (sk && udp_sk(sk)->gro_enabled) ||
> +	    NAPI_GRO_CB(skb)->is_flist) {
>   		pp = call_gro_receive(udp_gro_receive_segment, head, skb);
>   		return pp;
>   	}
>   

The second check for sk in "(sk && udp_sk(sk)->gro_enabled)" is 
redundant and can be dropped. You already verified it is present when 
you checked for !sk before the logical OR.

> -	if (!sk || NAPI_GRO_CB(skb)->encap_mark ||
> +	if (NAPI_GRO_CB(skb)->encap_mark ||
>   	    (skb->ip_summed != CHECKSUM_PARTIAL &&
>   	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
>   	     !NAPI_GRO_CB(skb)->csum_valid) ||
> 