tcp: Make shifting not clear the hints

The earlier version was just very basic one which is "playing
safe" by always clearing the hints. However, clearing of a hint
is extremely costly operation with large windows, so it must be
avoided at all cost whenever possible, there is a way with
shifting too achieve not-clearing.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 97d57676b8eeb3ba59e300ab923a436c53028e0d..e6291dde33486021039c1eff3fe9764da81feed8 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1379,6 +1379,11 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
 
        BUG_ON(!pcount);
 
+       /* Tweak before seqno plays */
+       if (!tcp_is_fack(tp) && tcp_is_sack(tp) && tp->lost_skb_hint &&
+           !before(TCP_SKB_CB(tp->lost_skb_hint)->seq, TCP_SKB_CB(skb)->seq))
+               tp->lost_cnt_hint += pcount;
+
        TCP_SKB_CB(prev)->end_seq += shifted;
        TCP_SKB_CB(skb)->seq += shifted;
 
@@ -1408,8 +1413,6 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
        /* Difference in this won't matter, both ACKed by the same cumul. ACK */
        TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
 
-       tcp_clear_all_retrans_hints(tp);
-
        if (skb->len > 0) {
                BUG_ON(!tcp_skb_pcount(skb));
                return 0;
@@ -1417,6 +1420,15 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
 
        /* Whole SKB was eaten :-) */
 
+       if (skb == tp->retransmit_skb_hint)
+               tp->retransmit_skb_hint = prev;
+       if (skb == tp->scoreboard_skb_hint)
+               tp->scoreboard_skb_hint = prev;
+       if (skb == tp->lost_skb_hint) {
+               tp->lost_skb_hint = prev;
+               tp->lost_cnt_hint -= tcp_skb_pcount(prev);
+       }
+
        TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(prev)->flags;
        if (skb == tcp_highest_sack(sk))
                tcp_advance_highest_sack(sk, skb);