1 files changed, 26 insertions, 8 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 29dde97c3c41..20847de991ea 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -878,15 +878,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
         BUG_ON(!skb || !tcp_skb_pcount(skb));
 
         if (clone_it) {
-                const struct sk_buff *fclone = skb + 1;
-
                 skb_mstamp_get(&skb->skb_mstamp);
 
-                if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
-                             fclone->fclone == SKB_FCLONE_CLONE))
-                        NET_INC_STATS(sock_net(sk),
-                                      LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
-
                 if (unlikely(skb_cloned(skb)))
                         skb = pskb_copy(skb, gfp_mask);
                 else
@@ -2061,6 +2054,25 @@ bool tcp_schedule_loss_probe(struct sock *sk)
         return true;
 }
 
+/* Thanks to skb fast clones, we can detect if a prior transmit of
+ * a packet is still in a qdisc or driver queue.
+ * In this case, there is very little point doing a retransmit !
+ * Note: This is called from BH context only.
+ */
+static bool skb_still_in_host_queue(const struct sock *sk,
+                                    const struct sk_buff *skb)
+{
+        const struct sk_buff *fclone = skb + 1;
+
+        if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
+                     fclone->fclone == SKB_FCLONE_CLONE)) {
+                NET_INC_STATS_BH(sock_net(sk),
+                                 LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
+                return true;
+        }
+        return false;
+}
+
 /* When probe timeout (PTO) fires, send a new segment if one exists, else
  * retransmit the last segment.
  */
@@ -2086,6 +2098,9 @@ void tcp_send_loss_probe(struct sock *sk)
         if (WARN_ON(!skb))
                 goto rearm_timer;
 
+        if (skb_still_in_host_queue(sk, skb))
+                goto rearm_timer;
+
         pcount = tcp_skb_pcount(skb);
         if (WARN_ON(!pcount))
                 goto rearm_timer;
@@ -2407,6 +2422,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
             min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
                 return -EAGAIN;
 
+        if (skb_still_in_host_queue(sk, skb))
+                return -EBUSY;
+
         if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
                 if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
                         BUG();
@@ -2500,7 +2518,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
                  * see tcp_input.c tcp_sacktag_write_queue().
                  */
                 TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
-        } else {
+        } else if (err != -EBUSY) {
                 NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
         }
         return err;