[TCP]: Make fackets_out accurate

Substraction for fackets_out is unconditional when snd_una
advances, thus there's no need to do it inside the loop. Just
make sure correct bounds are honored.

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 f9e4d7a..46aedd6 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2299,8 +2299,8 @@ tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag)
         * 1. Reno does not count dupacks (sacked_out) automatically. */
        if (!tp->packets_out)
                tp->sacked_out = 0;
         * 1. Reno does not count dupacks (sacked_out) automatically. */
        if (!tp->packets_out)
                tp->sacked_out = 0;

-       /* 2. SACK counts snd_fack in packets inaccurately. */
-       if (tp->sacked_out == 0)
+
+       if (WARN_ON(!tp->sacked_out && tp->fackets_out))

                tp->fackets_out = 0;
 
        /* Now state machine starts.
                tp->fackets_out = 0;
 
        /* Now state machine starts.


@@ -2568,10 +2568,6 @@ static int tcp_tso_acked(struct sock *sk, struct sk_buff *skb,
                } else if (*seq_rtt < 0)
                        *seq_rtt = now - scb->when;
 
                } else if (*seq_rtt < 0)
                        *seq_rtt = now - scb->when;
 

-               if (tp->fackets_out) {
-                       __u32 dval = min(tp->fackets_out, packets_acked);
-                       tp->fackets_out -= dval;
-               }

                /* hint's skb might be NULL but we don't need to care */
                tp->fastpath_cnt_hint -= min_t(u32, packets_acked,
                                               tp->fastpath_cnt_hint);
                /* hint's skb might be NULL but we don't need to care */
                tp->fastpath_cnt_hint -= min_t(u32, packets_acked,
                                               tp->fastpath_cnt_hint);


@@ -2657,7 +2653,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p)
                        seq_rtt = now - scb->when;
                        last_ackt = skb->tstamp;
                }
                        seq_rtt = now - scb->when;
                        last_ackt = skb->tstamp;
                }

-               tcp_dec_pcount_approx(&tp->fackets_out, skb);

                tp->packets_out -= tcp_skb_pcount(skb);
                tcp_unlink_write_queue(skb, sk);
                sk_stream_free_skb(sk, skb);
                tp->packets_out -= tcp_skb_pcount(skb);
                tcp_unlink_write_queue(skb, sk);
                sk_stream_free_skb(sk, skb);


@@ -2672,6 +2667,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p)
                tcp_ack_update_rtt(sk, acked, seq_rtt);
                tcp_rearm_rto(sk);
 
                tcp_ack_update_rtt(sk, acked, seq_rtt);
                tcp_rearm_rto(sk);
 

+               tp->fackets_out -= min(pkts_acked, tp->fackets_out);

                if (tcp_is_reno(tp))
                        tcp_remove_reno_sacks(sk, pkts_acked);
 
                if (tcp_is_reno(tp))
                        tcp_remove_reno_sacks(sk, pkts_acked);
 

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9df5b2a..cbe8bf6 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -652,6 +652,26 @@ 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.
+ */
+static void tcp_adjust_fackets_out(struct tcp_sock *tp, struct sk_buff *skb,
+                                  int decr)
+{
+       if (!tp->sacked_out)
+               return;
+
+       if (!before(tp->highest_sack, 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
  * to the specified size and appends a new segment with the rest of the
  * packet to the list.  This won't be called frequently, I hope.
 /* Function to create two new TCP segments.  Shrinks the given segment
  * to the specified size and appends a new segment with the rest of the
  * packet to the list.  This won't be called frequently, I hope.


@@ -746,21 +766,12 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss
                if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
                        tp->lost_out -= diff;
 
                if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
                        tp->lost_out -= diff;
 

-               if (diff > 0) {
-                       /* Adjust Reno SACK estimate. */
-                       if (tcp_is_reno(tp)) {
-                               tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
-                               tcp_verify_left_out(tp);
-                       }
-
-                       tcp_dec_pcount_approx_int(&tp->fackets_out, diff);
-                       /* SACK fastpath might overwrite it unless dealt with */
-                       if (tp->fastpath_skb_hint != NULL &&
-                           after(TCP_SKB_CB(tp->fastpath_skb_hint)->seq,
-                                 TCP_SKB_CB(skb)->seq)) {
-                               tcp_dec_pcount_approx_int(&tp->fastpath_cnt_hint, diff);
-                       }
+               /* Adjust Reno SACK estimate. */
+               if (tcp_is_reno(tp) && diff > 0) {
+                       tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
+                       tcp_verify_left_out(tp);

                }
                }

+               tcp_adjust_fackets_out(tp, skb, diff);

        }
 
        /* Link BUFF into the send queue. */
        }
 
        /* Link BUFF into the send queue. */


@@ -1746,10 +1757,7 @@ 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);
 
                if (tcp_is_reno(tp) && tp->sacked_out)
                        tcp_dec_pcount_approx(&tp->sacked_out, next_skb);
 

-               /* Not quite right: it can be > snd.fack, but
-                * it is better to underestimate fackets.
-                */
-               tcp_dec_pcount_approx(&tp->fackets_out, next_skb);
+               tcp_adjust_fackets_out(tp, skb, tcp_skb_pcount(next_skb));

                tp->packets_out -= tcp_skb_pcount(next_skb);
                sk_stream_free_skb(sk, next_skb);
        }
                tp->packets_out -= tcp_skb_pcount(next_skb);
                sk_stream_free_skb(sk, next_skb);
        }