tcp-tso: do not split TSO packets at retransmit time

[cascardo/linux.git] / net / ipv4 / tcp_input.c

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a26e2d2..dcad8f9 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1309,6 +1309,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
        if (skb == tcp_highest_sack(sk))
                tcp_advance_highest_sack(sk, skb);
 
+       tcp_skb_collapse_tstamp(prev, skb);
        tcp_unlink_write_queue(skb, sk);
        sk_wmem_free_skb(sk, skb);
 
@@ -3087,7 +3088,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
 
        shinfo = skb_shinfo(skb);
        if ((shinfo->tx_flags & SKBTX_ACK_TSTAMP) &&
-           between(shinfo->tskey, prior_snd_una, tcp_sk(sk)->snd_una - 1))
+           !before(shinfo->tskey, prior_snd_una) &&
+           before(shinfo->tskey, tcp_sk(sk)->snd_una))
                __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
 }
 
@@ -4307,6 +4309,12 @@ static bool tcp_try_coalesce(struct sock *sk,
        return true;
 }
 
+static void tcp_drop(struct sock *sk, struct sk_buff *skb)
+{
+       sk_drops_add(sk, skb);
+       __kfree_skb(skb);
+}
+
 /* This one checks to see if we can put data from the
  * out_of_order queue into the receive_queue.
  */
@@ -4331,7 +4339,7 @@ static void tcp_ofo_queue(struct sock *sk)
                __skb_unlink(skb, &tp->out_of_order_queue);
                if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
                        SOCK_DEBUG(sk, "ofo packet was already received\n");
-                       __kfree_skb(skb);
+                       tcp_drop(sk, skb);
                        continue;
                }
                SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n",
@@ -4383,7 +4391,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
        if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
                NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP);
-               __kfree_skb(skb);
+               tcp_drop(sk, skb);
                return;
        }
 
@@ -4447,7 +4455,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
                if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
                        /* All the bits are present. Drop. */
                        NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE);
-                       __kfree_skb(skb);
+                       tcp_drop(sk, skb);
                        skb = NULL;
                        tcp_dsack_set(sk, seq, end_seq);
                        goto add_sack;
@@ -4486,7 +4494,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
                tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
                                 TCP_SKB_CB(skb1)->end_seq);
                NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE);
-               __kfree_skb(skb1);
+               tcp_drop(sk, skb1);
        }
 
 add_sack:
@@ -4569,12 +4577,13 @@ err:
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
        struct tcp_sock *tp = tcp_sk(sk);
-       int eaten = -1;
        bool fragstolen = false;
+       int eaten = -1;
 
-       if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
-               goto drop;
-
+       if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
+               __kfree_skb(skb);
+               return;
+       }
        skb_dst_drop(skb);
        __skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
@@ -4656,7 +4665,7 @@ out_of_window:
                tcp_enter_quickack_mode(sk);
                inet_csk_schedule_ack(sk);
 drop:
-               __kfree_skb(skb);
+               tcp_drop(sk, skb);
                return;
        }
 
@@ -5233,7 +5242,7 @@ syn_challenge:
        return true;
 
 discard:
-       __kfree_skb(skb);
+       tcp_drop(sk, skb);
        return false;
 }
 
@@ -5451,7 +5460,7 @@ csum_error:
        TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
 
 discard:
-       __kfree_skb(skb);
+       tcp_drop(sk, skb);
 }
 EXPORT_SYMBOL(tcp_rcv_established);
 
@@ -5536,7 +5545,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
        if (data) { /* Retransmit unacked data in SYN */
                tcp_for_write_queue_from(data, sk) {
                        if (data == tcp_send_head(sk) ||
-                           __tcp_retransmit_skb(sk, data))
+                           __tcp_retransmit_skb(sk, data, 1))
                                break;
                }
                tcp_rearm_rto(sk);
@@ -5682,7 +5691,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
                                                  TCP_DELACK_MAX, TCP_RTO_MAX);
 
 discard:
-                       __kfree_skb(skb);
+                       tcp_drop(sk, skb);
                        return 0;
                } else {
                        tcp_send_ack(sk);
@@ -5789,8 +5798,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
        int queued = 0;
        bool acceptable;
 
-       tp->rx_opt.saw_tstamp = 0;
-
        switch (sk->sk_state) {
        case TCP_CLOSE:
                goto discard;
@@ -5831,6 +5838,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
                goto discard;
 
        case TCP_SYN_SENT:
+               tp->rx_opt.saw_tstamp = 0;
                queued = tcp_rcv_synsent_state_process(sk, skb, th);
                if (queued >= 0)
                        return queued;
@@ -5842,6 +5850,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
                return 0;
        }
 
+       tp->rx_opt.saw_tstamp = 0;
        req = tp->fastopen_rsk;
        if (req) {
                WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
@@ -6043,7 +6052,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
        if (!queued) {
 discard:
-               __kfree_skb(skb);
+               tcp_drop(sk, skb);
        }
        return 0;
 }
@@ -6320,7 +6329,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
        }
        if (fastopen_sk) {
                af_ops->send_synack(fastopen_sk, dst, &fl, req,
-                                   &foc, false);
+                                   &foc, TCP_SYNACK_FASTOPEN);
                /* Add the child socket directly into the accept queue */
                inet_csk_reqsk_queue_add(sk, req, fastopen_sk);
                sk->sk_data_ready(sk);
@@ -6330,10 +6339,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
                tcp_rsk(req)->tfo_listener = false;
                if (!want_cookie)
                        inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
-               af_ops->send_synack(sk, dst, &fl, req,
-                                   &foc, !want_cookie);
-               if (want_cookie)
-                       goto drop_and_free;
+               af_ops->send_synack(sk, dst, &fl, req, &foc,
+                                   !want_cookie ? TCP_SYNACK_NORMAL :
+                                                  TCP_SYNACK_COOKIE);
+               if (want_cookie) {
+                       reqsk_free(req);
+                       return 0;
+               }
        }
        reqsk_put(req);
        return 0;
@@ -6343,7 +6355,7 @@ drop_and_release:
 drop_and_free:
        reqsk_free(req);
 drop:
-       NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+       tcp_listendrop(sk);
        return 0;
 }
 EXPORT_SYMBOL(tcp_conn_request);