tcp: introduce TCPSpuriousRtxHostQueues SNMP counter

Host queues (Qdisc + NIC) can hold packets so long that TCP can
eventually retransmit a packet before the first transmit even left
the host.

Its not clear right now if we could avoid this in the first place :

- We could arm RTO timer not at the time we enqueue packets, but
  at the time we TX complete them (tcp_wfree())

- Cancel the sending of the new copy of the packet if prior one
  is still in queue.

This patch adds instrumentation so that we can at least see how
often this problem happens.

TCPSpuriousRtxHostQueues SNMP counter is incremented every time
we detect the fast clone is not yet freed in tcp_transmit_skb()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 9 insertions, 0 deletions

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index e00013a1debc..fefdec91c68b 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -247,6 +247,7 @@ enum
         LINUX_MIB_TCPFASTOPENPASSIVEFAIL,       /* TCPFastOpenPassiveFail */
         LINUX_MIB_TCPFASTOPENLISTENOVERFLOW,    /* TCPFastOpenListenOverflow */
         LINUX_MIB_TCPFASTOPENCOOKIEREQD,        /* TCPFastOpenCookieReqd */
+        LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */
         __LINUX_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index b6f2ea174898..6da51d55d03a 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -269,6 +269,7 @@ static const struct snmp_mib snmp4_net_list[] = {
         SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL),
         SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
         SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
+        SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
         SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d12694353540..5f28131eb37e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -846,6 +846,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
                 __net_timestamp(skb);
 
         if (likely(clone_it)) {
+                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);
+
                 if (unlikely(skb_cloned(skb)))
                         skb = pskb_copy(skb, gfp_mask);
                 else