On Mon, Apr 25, 2016 at 5:44 PM, Martin KaFai Lau <ka...@fb.com> wrote:
> This patch:
> 1. Prevent next_skb from coalescing to the prev_skb if
> TCP_SKB_CB(prev_skb)->eor is set
> 2. Update the TCP_SKB_CB(prev_skb)->eor if coalescing is
> allowed
>
> Packetdrill script for testing:
> ~~~~~~
> +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 sendto(4, ..., 730, MSG_EOR, ..., ...) = 730
> 0.200 sendto(4, ..., 730, MSG_EOR, ..., ...) = 730
> 0.200 write(4, ..., 11680) = 11680
>
> 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 1461:13141,nop,nop>
> 0.300 > P. 1:731(730) ack 1
> 0.300 > P. 731:1461(730) 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 <ka...@fb.com>
> Cc: Eric Dumazet <eduma...@google.com>
> Cc: Neal Cardwell <ncardw...@google.com>
> Cc: Soheil Hassas Yeganeh <soh...@google.com>
> Cc: Willem de Bruijn <will...@google.com>
> Cc: Yuchung Cheng <ych...@google.com>
Acked-by: Soheil Hassas Yeganeh <soh...@google.com>
> ---
> net/ipv4/tcp_input.c | 4 ++++
> net/ipv4/tcp_output.c | 4 ++++
> 2 files changed, 8 insertions(+)
>
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index dcad8f9..65fb708 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -1303,6 +1303,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct
> sk_buff *skb,
> }
>
> TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
> + TCP_SKB_CB(prev)->eor = TCP_SKB_CB(skb)->eor;
> if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
> TCP_SKB_CB(prev)->end_seq++;
>
> @@ -1368,6 +1369,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock
> *sk, struct sk_buff *skb,
> if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
> goto fallback;
>
> + if (!tcp_skb_can_collapse_to(prev))
> + goto fallback;
> +
> in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
> !before(end_seq, TCP_SKB_CB(skb)->end_seq);
>
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 9d3b4b3..fa4d17f 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2494,6 +2494,7 @@ static void tcp_collapse_retrans(struct sock *sk,
> struct sk_buff *skb)
> * packet counting does not break.
> */
> TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked &
> TCPCB_EVER_RETRANS;
> + TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor;
>
> /* changed transmit queue under us so clear hints */
> tcp_clear_retrans_hints_partial(tp);
> @@ -2545,6 +2546,9 @@ static void tcp_retrans_try_collapse(struct sock *sk,
> struct sk_buff *to,
> if (!tcp_can_collapse(sk, skb))
> break;
>
> + if (!tcp_skb_can_collapse_to(to))
> + break;
> +
> space -= skb->len;
>
> if (first) {
> --
> 2.5.1
>
