Re: [PATCH v6 net-next 10/13] net: Postpone skb_clear_delivery_time() until knowing the skb is delivered locally

From: Eric Dumazet <edumazet@google.com>
To: Martin KaFai Lau <kafai@fb.com>
Cc: bpf <bpf@vger.kernel.org>, netdev <netdev@vger.kernel.org>,
	Alexei Starovoitov <ast@kernel.org>,
	Andrii Nakryiko <andrii@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	David Miller <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	kernel-team <kernel-team@fb.com>,
	Willem de Bruijn <willemb@google.com>
Subject: Re: [PATCH v6 net-next 10/13] net: Postpone skb_clear_delivery_time() until knowing the skb is delivered locally
Date: Wed, 2 Mar 2022 12:30:14 -0800	[thread overview]
Message-ID: <CANn89iKN06bKxjrEeZAmcj0x4tYMwRv-YzdZLWKbCcuTYT+SpQ@mail.gmail.com> (raw)
In-Reply-To: <20220302195622.3483941-1-kafai@fb.com>

On Wed, Mar 2, 2022 at 11:56 AM Martin KaFai Lau <kafai@fb.com> wrote:
>
> The previous patches handled the delivery_time in the ingress path
> before the routing decision is made.  This patch can postpone clearing
> delivery_time in a skb until knowing it is delivered locally and also
> set the (rcv) timestamp if needed.  This patch moves the
> skb_clear_delivery_time() from dev.c to ip_local_deliver_finish()
> and ip6_input_finish().
>
> Signed-off-by: Martin KaFai Lau <kafai@fb.com>
> ---
>  net/core/dev.c       | 8 ++------
>  net/ipv4/ip_input.c  | 1 +
>  net/ipv6/ip6_input.c | 1 +
>  3 files changed, 4 insertions(+), 6 deletions(-)
>
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 0fc02cf32476..3ff686cc8c84 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -5193,10 +5193,8 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
>                         goto out;
>         }
>
> -       if (skb_skip_tc_classify(skb)) {
> -               skb_clear_delivery_time(skb);
> +       if (skb_skip_tc_classify(skb))
>                 goto skip_classify;
> -       }
>
>         if (pfmemalloc)
>                 goto skip_taps;
> @@ -5225,14 +5223,12 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
>                         goto another_round;
>                 if (!skb)
>                         goto out;
> -               skb_clear_delivery_time(skb);
>
>                 nf_skip_egress(skb, false);
>                 if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0)
>                         goto out;
> -       } else
> +       }
>  #endif
> -               skb_clear_delivery_time(skb);
>         skb_reset_redirect(skb);
>  skip_classify:
>         if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
> diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
> index d94f9f7e60c3..95f7bb052784 100644
> --- a/net/ipv4/ip_input.c
> +++ b/net/ipv4/ip_input.c
> @@ -226,6 +226,7 @@ void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
>
>  static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
>  {
> +       skb_clear_delivery_time(skb);
>         __skb_pull(skb, skb_network_header_len(skb));
>
>         rcu_read_lock();
> diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
> index d4b1e2c5aa76..5b5ea35635f9 100644
> --- a/net/ipv6/ip6_input.c
> +++ b/net/ipv6/ip6_input.c
> @@ -459,6 +459,7 @@ void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
>
>  static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
>  {
> +       skb_clear_delivery_time(skb);
>         rcu_read_lock();
>         ip6_protocol_deliver_rcu(net, skb, 0, false);
>         rcu_read_unlock();
> --
> 2.30.2
>

It is not clear to me why we need to clear tstamp if packet is locally
delivered ?

TCP stack is using tstamp for incoming packets (look for
TCP_SKB_CB(skb)->has_rxtstamp)