tcp: add coalescing attempt in tcp_ofo_queue()

In order to make TCP more resilient in presence of reorders, we need
to allow coalescing to happen when skbs from out of order queue are
transferred into receive queue. LRO/GRO can be completely canceled
in some pathological cases, like per packet load balancing on aggregated
links.

I had to move tcp_try_coalesce() up in the file above tcp_ofo_queue()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 13f3da4..f3f016a 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4061,6 +4061,44 @@ static void tcp_sack_remove(struct tcp_sock *tp)
        tp->rx_opt.num_sacks = num_sacks;
 }
 
+/**
+ * tcp_try_coalesce - try to merge skb to prior one
+ * @sk: socket
+ * @to: prior buffer
+ * @from: buffer to add in queue
+ * @fragstolen: pointer to boolean
+ *
+ * Before queueing skb @from after @to, try to merge them
+ * to reduce overall memory use and queue lengths, if cost is small.
+ * Packets in ofo or receive queues can stay a long time.
+ * Better try to coalesce them right now to avoid future collapses.
+ * Returns true if caller should free @from instead of queueing it
+ */
+static bool tcp_try_coalesce(struct sock *sk,
+                            struct sk_buff *to,
+                            struct sk_buff *from,
+                            bool *fragstolen)
+{
+       int delta;
+
+       *fragstolen = false;
+
+       /* Its possible this segment overlaps with prior segment in queue */
+       if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
+               return false;
+
+       if (!skb_try_coalesce(to, from, fragstolen, &delta))
+               return false;
+
+       atomic_add(delta, &sk->sk_rmem_alloc);
+       sk_mem_charge(sk, delta);
+       NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE);
+       TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
+       TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
+       TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags;
+       return true;
+}
+
 /* This one checks to see if we can put data from the
  * out_of_order queue into the receive_queue.
  */
@@ -4068,7 +4106,8 @@ static void tcp_ofo_queue(struct sock *sk)
 {
        struct tcp_sock *tp = tcp_sk(sk);
        __u32 dsack_high = tp->rcv_nxt;
-       struct sk_buff *skb;
+       struct sk_buff *skb, *tail;
+       bool fragstolen, eaten;
 
        while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) {
                if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
@@ -4081,9 +4120,9 @@ static void tcp_ofo_queue(struct sock *sk)
                        tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack);
                }
 
+               __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");
-                       __skb_unlink(skb, &tp->out_of_order_queue);
                        __kfree_skb(skb);
                        continue;
                }
@@ -4091,11 +4130,15 @@ static void tcp_ofo_queue(struct sock *sk)
                           tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
                           TCP_SKB_CB(skb)->end_seq);
 
-               __skb_unlink(skb, &tp->out_of_order_queue);
-               __skb_queue_tail(&sk->sk_receive_queue, skb);
+               tail = skb_peek_tail(&sk->sk_receive_queue);
+               eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
                tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+               if (!eaten)
+                       __skb_queue_tail(&sk->sk_receive_queue, skb);
                if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
                        tcp_fin(sk);
+               if (eaten)
+                       kfree_skb_partial(skb, fragstolen);
        }
 }
 
@@ -4122,44 +4165,6 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
        return 0;
 }
 
-/**
- * tcp_try_coalesce - try to merge skb to prior one
- * @sk: socket
- * @to: prior buffer
- * @from: buffer to add in queue
- * @fragstolen: pointer to boolean
- *
- * Before queueing skb @from after @to, try to merge them
- * to reduce overall memory use and queue lengths, if cost is small.
- * Packets in ofo or receive queues can stay a long time.
- * Better try to coalesce them right now to avoid future collapses.
- * Returns true if caller should free @from instead of queueing it
- */
-static bool tcp_try_coalesce(struct sock *sk,
-                            struct sk_buff *to,
-                            struct sk_buff *from,
-                            bool *fragstolen)
-{
-       int delta;
-
-       *fragstolen = false;
-
-       /* Its possible this segment overlaps with prior segment in queue */
-       if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
-               return false;
-
-       if (!skb_try_coalesce(to, from, fragstolen, &delta))
-               return false;
-
-       atomic_add(delta, &sk->sk_rmem_alloc);
-       sk_mem_charge(sk, delta);
-       NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE);
-       TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
-       TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
-       TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags;
-       return true;
-}
-
 static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 {
        struct tcp_sock *tp = tcp_sk(sk);