[TCP]: Rewrite SACK block processing & sack_recv_cache use

[linux-2.6-omap-h63xx.git] / net / ipv4 / tcp_output.c

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f46d24b8410fc771288779387309143fbeed88e4..030fc69ea217b9495b87b706ba4e35e28ce412d4 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -653,23 +653,18 @@ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned
 }
 
 /* When a modification to fackets out becomes necessary, we need to check
- * skb is counted to fackets_out or not. Another important thing is to
- * tweak SACK fastpath hint too as it would overwrite all changes unless
- * hint is also changed.
+ * skb is counted to fackets_out or not.
  */
-static void tcp_adjust_fackets_out(struct tcp_sock *tp, struct sk_buff *skb,
+static void tcp_adjust_fackets_out(struct sock *sk, struct sk_buff *skb,
                                   int decr)
 {
-       if (!tp->sacked_out)
+       struct tcp_sock *tp = tcp_sk(sk);
+
+       if (!tp->sacked_out || tcp_is_reno(tp))
                return;
 
-       if (!before(tp->highest_sack, TCP_SKB_CB(skb)->seq))
+       if (!before(tcp_highest_sack_seq(tp), TCP_SKB_CB(skb)->seq))
                tp->fackets_out -= decr;
-
-       /* cnt_hint is "off-by-one" compared with fackets_out (see sacktag) */
-       if (tp->fastpath_skb_hint != NULL &&
-           after(TCP_SKB_CB(tp->fastpath_skb_hint)->seq, TCP_SKB_CB(skb)->seq))
-               tp->fastpath_cnt_hint -= decr;
 }
 
 /* Function to create two new TCP segments.  Shrinks the given segment
@@ -687,7 +682,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss
 
        BUG_ON(len > skb->len);
 
-       tcp_clear_all_retrans_hints(tp);
+       tcp_clear_retrans_hints_partial(tp);
        nsize = skb_headlen(skb) - len;
        if (nsize < 0)
                nsize = 0;
@@ -712,8 +707,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss
        TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
        TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;
 
-       if (tp->sacked_out && (TCP_SKB_CB(skb)->seq == tp->highest_sack))
-               tp->highest_sack = TCP_SKB_CB(buff)->seq;
+       if (tcp_is_sack(tp) && tp->sacked_out && (skb == tp->highest_sack))
+               tp->highest_sack = buff;
 
        /* PSH and FIN should only be set in the second packet. */
        flags = TCP_SKB_CB(skb)->flags;
@@ -771,7 +766,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss
                        tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
                        tcp_verify_left_out(tp);
                }
-               tcp_adjust_fackets_out(tp, skb, diff);
+               tcp_adjust_fackets_out(sk, skb, diff);
        }
 
        /* Link BUFF into the send queue. */
@@ -1161,8 +1156,7 @@ int tcp_may_send_now(struct sock *sk)
        return (skb &&
                tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
                             (tcp_skb_is_last(sk, skb) ?
-                             TCP_NAGLE_PUSH :
-                             tp->nonagle)));
+                             tp->nonagle : TCP_NAGLE_PUSH)));
 }
 
 /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
@@ -1294,6 +1288,7 @@ static int tcp_mtu_probe(struct sock *sk)
        struct sk_buff *skb, *nskb, *next;
        int len;
        int probe_size;
+       int size_needed;
        unsigned int pif;
        int copy;
        int mss_now;
@@ -1312,27 +1307,20 @@ static int tcp_mtu_probe(struct sock *sk)
        /* Very simple search strategy: just double the MSS. */
        mss_now = tcp_current_mss(sk, 0);
        probe_size = 2*tp->mss_cache;
+       size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
        if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
                /* TODO: set timer for probe_converge_event */
                return -1;
        }
 
        /* Have enough data in the send queue to probe? */
-       len = 0;
-       if ((skb = tcp_send_head(sk)) == NULL)
-               return -1;
-       while ((len += skb->len) < probe_size && !tcp_skb_is_last(sk, skb))
-               skb = tcp_write_queue_next(sk, skb);
-       if (len < probe_size)
+       if (tp->write_seq - tp->snd_nxt < size_needed)
                return -1;
 
-       /* Receive window check. */
-       if (after(TCP_SKB_CB(skb)->seq + probe_size, tp->snd_una + tp->snd_wnd)) {
-               if (tp->snd_wnd < probe_size)
-                       return -1;
-               else
-                       return 0;
-       }
+       if (tp->snd_wnd < size_needed)
+               return -1;
+       if (after(tp->snd_nxt + size_needed, tp->snd_una + tp->snd_wnd))
+               return 0;
 
        /* Do we need to wait to drain cwnd? */
        pif = tcp_packets_in_flight(tp);
@@ -1351,7 +1339,6 @@ static int tcp_mtu_probe(struct sock *sk)
 
        skb = tcp_send_head(sk);
        tcp_insert_write_queue_before(nskb, skb, sk);
-       tcp_advance_send_head(sk, skb);
 
        TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
        TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
@@ -1718,8 +1705,9 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int m
                BUG_ON(tcp_skb_pcount(skb) != 1 ||
                       tcp_skb_pcount(next_skb) != 1);
 
-               /* changing transmit queue under us so clear hints */
-               tcp_clear_all_retrans_hints(tp);
+               if (WARN_ON(tcp_is_sack(tp) && tp->sacked_out &&
+                   (next_skb == tp->highest_sack)))
+                       return;
 
                /* Ok.  We will be able to collapse the packet. */
                tcp_unlink_write_queue(next_skb, sk);
@@ -1737,10 +1725,6 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int m
                /* Update sequence range on original skb. */
                TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq;
 
-               if (WARN_ON(tp->sacked_out &&
-                   (TCP_SKB_CB(next_skb)->seq == tp->highest_sack)))
-                       return;
-
                /* Merge over control information. */
                flags |= TCP_SKB_CB(next_skb)->flags; /* This moves PSH/FIN etc. over */
                TCP_SKB_CB(skb)->flags = flags;
@@ -1757,8 +1741,12 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int m
                if (tcp_is_reno(tp) && tp->sacked_out)
                        tcp_dec_pcount_approx(&tp->sacked_out, next_skb);
 
-               tcp_adjust_fackets_out(tp, skb, tcp_skb_pcount(next_skb));
+               tcp_adjust_fackets_out(sk, next_skb, tcp_skb_pcount(next_skb));
                tp->packets_out -= tcp_skb_pcount(next_skb);
+
+               /* changed transmit queue under us so clear hints */
+               tcp_clear_retrans_hints_partial(tp);
+
                sk_stream_free_skb(sk, next_skb);
        }
 }
@@ -1907,6 +1895,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
                                printk(KERN_DEBUG "retrans_out leaked.\n");
                }
 #endif
+               if (!tp->retrans_out)
+                       tp->lost_retrans_low = tp->snd_nxt;
                TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS;
                tp->retrans_out += tcp_skb_pcount(skb);
 
@@ -2027,7 +2017,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
                        break;
                tp->forward_skb_hint = skb;
 
-               if (after(TCP_SKB_CB(skb)->seq, tp->highest_sack))
+               if (after(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
                        break;
 
                if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)