Re: [PATCH net 1/2] tcp: Merge tx_flags and tskey in tcp_collapse_retrans

[Soheil Hassas Yeganeh <soheil@google.com>]

On Wed, Apr 20, 2016 at 1:39 AM, Martin KaFai Lau <kafai@fb.com> wrote:
> If two skbs are merged/collapsed during retransmission, the current
> logic does not merge the tx_flags and tskey.  The end result is
> the SCM_TSTAMP_ACK timestamp could be missing for a packet.
>
> The patch:
> 1. Merge the tx_flags
> 2. Overwrite the prev_skb's tskey with the next_skb's tskey
>
> BPF Output Before:
> ~~~~~~
> <no-output-due-to-missing-tstamp-event>
>
> BPF Output After:
> ~~~~~~
> packetdrill-2092  [001] d.s.   453.998486: : ee_data:1459
>
> Packetdrill Script:
> ~~~~~~
> +0 `sysctl -q -w net.ipv4.tcp_min_tso_segs=10`
> +0 `sysctl -q -w net.ipv4.tcp_no_metrics_save=1`
> +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
> +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
> +0 bind(3, ..., ...) = 0
> +0 listen(3, 1) = 0
>
> 0.100 < S 0:0(0) win 32792 <mss 1460,sackOK,nop,nop,nop,wscale 7>
> 0.100 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7>
> 0.200 < . 1:1(0) ack 1 win 257
> 0.200 accept(3, ..., ...) = 4
> +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0
>
> 0.200 write(4, ..., 730) = 730
> +0 setsockopt(4, SOL_SOCKET, 37, [2688], 4) = 0
> 0.200 write(4, ..., 730) = 730
> +0 setsockopt(4, SOL_SOCKET, 37, [2176], 4) = 0
> 0.200 write(4, ..., 11680) = 11680
> +0 setsockopt(4, SOL_SOCKET, 37, [2688], 4) = 0
>
> 0.200 > P. 1:731(730) ack 1
> 0.200 > P. 731:1461(730) ack 1
> 0.200 > . 1461:8761(7300) ack 1
> 0.200 > P. 8761:13141(4380) ack 1
>
> 0.300 < . 1:1(0) ack 1 win 257 <sack 1461:2921,nop,nop>
> 0.300 < . 1:1(0) ack 1 win 257 <sack 1461:4381,nop,nop>
> 0.300 < . 1:1(0) ack 1 win 257 <sack 1461:5841,nop,nop>
> 0.300 > P. 1:1461(1460) ack 1
> 0.400 < . 1:1(0) ack 13141 win 257
>
> 0.400 close(4) = 0
> 0.400 > F. 13141:13141(0) ack 1
> 0.500 < F. 1:1(0) ack 13142 win 257
> 0.500 > . 13142:13142(0) ack 2
>
> Signed-off-by: Martin KaFai Lau <kafai@fb.com>
> Cc: Eric Dumazet <edumazet@google.com>
> Cc: Neal Cardwell <ncardwell@google.com>
> Cc: Soheil Hassas Yeganeh <soheil@google.com>
> Cc: Willem de Bruijn <willemb@google.com>
> Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Tested-by: Soheil Hassas Yeganeh <soheil@google.com>
> ---
>  net/ipv4/tcp_output.c | 16 ++++++++++++++++
>  1 file changed, 16 insertions(+)
>
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 7d2dc01..5bc3c30 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2441,6 +2441,20 @@ u32 __tcp_select_window(struct sock *sk)
>         return window;
>  }
>
> +static void tcp_skb_collapse_tstamp(struct sk_buff *skb,
> +                                   const struct sk_buff *next_skb)
> +{
> +       const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb);
> +       u8 tsflags = next_shinfo->tx_flags & SKBTX_ANY_TSTAMP;
> +
> +       if (unlikely(tsflags)) {
> +               struct skb_shared_info *shinfo = skb_shinfo(skb);
> +
> +               shinfo->tx_flags |= tsflags;
> +               shinfo->tskey = next_shinfo->tskey;
> +       }
> +}
> +
>  /* Collapses two adjacent SKB's during retransmission. */
>  static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
>  {
> @@ -2484,6 +2498,8 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
>
>         tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb));
>
> +       tcp_skb_collapse_tstamp(skb, next_skb);
> +
>         sk_wmem_free_skb(sk, next_skb);
>  }
>
> --
> 2.5.1
>