On Thu, Jan 12, 2017 at 10:03 PM, Yuchung Cheng <[email protected]> wrote:
>
> Create a new helper tcp_rack_mark_skb_lost to prepare the
> upcoming RACK reordering timer support.
>
> Signed-off-by: Yuchung Cheng <[email protected]>
> Signed-off-by: Neal Cardwell <[email protected]>
> Acked-by: Eric Dumazet <[email protected]>
> ---
Oops I messed up the subject headers. Let me resubmit. Sorry.
> net/ipv4/tcp_recovery.c | 21 ++++++++++++++-------
> 1 file changed, 14 insertions(+), 7 deletions(-)
>
> diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
> index e36df4fcfeba..f38dba5aed7a 100644
> --- a/net/ipv4/tcp_recovery.c
> +++ b/net/ipv4/tcp_recovery.c
> @@ -3,6 +3,19 @@
>
> int sysctl_tcp_recovery __read_mostly = TCP_RACK_LOST_RETRANS;
>
> +static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
> +{
> + struct tcp_sock *tp = tcp_sk(sk);
> +
> + tcp_skb_mark_lost_uncond_verify(tp, skb);
> + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
> + /* Account for retransmits that are lost again */
> + TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
> + tp->retrans_out -= tcp_skb_pcount(skb);
> + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
> + }
> +}
> +
> /* Marks a packet lost, if some packet sent later has been (s)acked.
> * The underlying idea is similar to the traditional dupthresh and FACK
> * but they look at different metrics:
> @@ -61,13 +74,7 @@ int tcp_rack_mark_lost(struct sock *sk)
> continue;
>
> /* skb is lost if packet sent later is sacked */
> - tcp_skb_mark_lost_uncond_verify(tp, skb);
> - if (scb->sacked & TCPCB_SACKED_RETRANS) {
> - scb->sacked &= ~TCPCB_SACKED_RETRANS;
> - tp->retrans_out -= tcp_skb_pcount(skb);
> - NET_INC_STATS(sock_net(sk),
> - LINUX_MIB_TCPLOSTRETRANSMIT);
> - }
> + tcp_rack_mark_skb_lost(sk, skb);
> } else if (!(scb->sacked & TCPCB_RETRANS)) {
> /* Original data are sent sequentially so stop early
> * b/c the rest are all sent after rack_sent
> --
> 2.11.0.483.g087da7b7c-goog
>
