Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

[pandora-kernel.git] / net / ipv4 / tcp_input.c

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 311c30f..eeb8a92 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -64,6 +64,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/sysctl.h>
+#include <linux/kernel.h>
 #include <net/dst.h>
 #include <net/tcp.h>
 #include <net/inet_common.h>
@@ -76,7 +77,7 @@ int sysctl_tcp_window_scaling __read_mostly = 1;
 int sysctl_tcp_sack __read_mostly = 1;
 int sysctl_tcp_fack __read_mostly = 1;
 int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
-int sysctl_tcp_ecn __read_mostly;
+int sysctl_tcp_ecn __read_mostly = 2;
 int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
 int sysctl_tcp_adv_win_scale __read_mostly = 2;
@@ -596,16 +597,6 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
                tcp_grow_window(sk, skb);
 }
 
-static u32 tcp_rto_min(struct sock *sk)
-{
-       struct dst_entry *dst = __sk_dst_get(sk);
-       u32 rto_min = TCP_RTO_MIN;
-
-       if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
-               rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
-       return rto_min;
-}
-
 /* Called to compute a smoothed rtt estimate. The data fed to this
  * routine either comes from timestamps, or from segments that were
  * known _not_ to have been retransmitted [see Karn/Partridge
@@ -927,6 +918,8 @@ static void tcp_init_metrics(struct sock *sk)
        tcp_set_rto(sk);
        if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp)
                goto reset;
+
+cwnd:
        tp->snd_cwnd = tcp_init_cwnd(tp, dst);
        tp->snd_cwnd_stamp = tcp_time_stamp;
        return;
@@ -941,6 +934,7 @@ reset:
                tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
                inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
        }
+       goto cwnd;
 }
 
 static void tcp_update_reordering(struct sock *sk, const int metric,
@@ -1802,11 +1796,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb,
        for (i = used_sacks - 1; i > 0; i--) {
                for (j = 0; j < i; j++) {
                        if (after(sp[j].start_seq, sp[j + 1].start_seq)) {
-                               struct tcp_sack_block tmp;
-
-                               tmp = sp[j];
-                               sp[j] = sp[j + 1];
-                               sp[j + 1] = tmp;
+                               swap(sp[j], sp[j + 1]);
 
                                /* Track where the first SACK block goes to */
                                if (j == first_sack_index)
@@ -2864,7 +2854,7 @@ void tcp_simple_retransmit(struct sock *sk)
        const struct inet_connection_sock *icsk = inet_csk(sk);
        struct tcp_sock *tp = tcp_sk(sk);
        struct sk_buff *skb;
-       unsigned int mss = tcp_current_mss(sk, 0);
+       unsigned int mss = tcp_current_mss(sk);
        u32 prior_lost = tp->lost_out;
 
        tcp_for_write_queue(skb, sk) {
@@ -3588,15 +3578,18 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
        int prior_packets;
        int frto_cwnd = 0;
 
-       /* If the ack is newer than sent or older than previous acks
+       /* If the ack is older than previous acks
         * then we can probably ignore it.
         */
-       if (after(ack, tp->snd_nxt))
-               goto uninteresting_ack;
-
        if (before(ack, prior_snd_una))
                goto old_ack;
 
+       /* If the ack includes data we haven't sent yet, discard
+        * this segment (RFC793 Section 3.9).
+        */
+       if (after(ack, tp->snd_nxt))
+               goto invalid_ack;
+
        if (after(ack, prior_snd_una))
                flag |= FLAG_SND_UNA_ADVANCED;
 
@@ -3686,6 +3679,10 @@ no_queue:
                tcp_ack_probe(sk);
        return 1;
 
+invalid_ack:
+       SOCK_DEBUG(sk, "Ack %u after %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
+       return -1;
+
 old_ack:
        if (TCP_SKB_CB(skb)->sacked) {
                tcp_sacktag_write_queue(sk, skb, prior_snd_una);
@@ -3693,8 +3690,7 @@ old_ack:
                        tcp_try_keep_open(sk);
        }
 
-uninteresting_ack:
-       SOCK_DEBUG(sk, "Ack %u out of %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
+       SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
        return 0;
 }
 
@@ -4156,20 +4152,6 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
        }
 }
 
-static inline void tcp_sack_swap(struct tcp_sack_block *sack1,
-                                struct tcp_sack_block *sack2)
-{
-       __u32 tmp;
-
-       tmp = sack1->start_seq;
-       sack1->start_seq = sack2->start_seq;
-       sack2->start_seq = tmp;
-
-       tmp = sack1->end_seq;
-       sack1->end_seq = sack2->end_seq;
-       sack2->end_seq = tmp;
-}
-
 static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
 {
        struct tcp_sock *tp = tcp_sk(sk);
@@ -4184,7 +4166,7 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
                if (tcp_sack_extend(sp, seq, end_seq)) {
                        /* Rotate this_sack to the first one. */
                        for (; this_sack > 0; this_sack--, sp--)
-                               tcp_sack_swap(sp, sp - 1);
+                               swap(*sp, *(sp - 1));
                        if (cur_sacks > 1)
                                tcp_sack_maybe_coalesce(tp);
                        return;
@@ -5158,7 +5140,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
         */
 
        if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags &&
-           TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
+           TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
+           !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
                int tcp_header_len = tp->tcp_header_len;
 
                /* Timestamp header prediction: tcp_header_len
@@ -5311,8 +5294,8 @@ slow_path:
                return -res;
 
 step5:
-       if (th->ack)
-               tcp_ack(sk, skb, FLAG_SLOWPATH);
+       if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
+               goto discard;
 
        tcp_rcv_rtt_measure_ts(sk, skb);
 
@@ -5649,7 +5632,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 
        /* step 5: check the ACK field */
        if (th->ack) {
-               int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH);
+               int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0;
 
                switch (sk->sk_state) {
                case TCP_SYN_RECV: