net: revert 8728c544a9c ("net: dev_pick_tx() fix")

commit 8728c544a9cbdc ("net: dev_pick_tx() fix") and commit
b6fe83e9525a ("bonding: refine IFF_XMIT_DST_RELEASE capability")
are quite incompatible : Queue selection is disabled because skb
dst was dropped before entering bonding device.

This causes major performance regression, mainly because TCP packets
for a given flow can be sent to multiple queues.

This is particularly visible when using the new FQ packet scheduler
with MQ + FQ setup on the slaves.

We can safely revert the first commit now that 416186fbf8c5b
("net: Split core bits of netdev_pick_tx into __netdev_pick_tx")
properly caps the queue_index.

Reported-by: Xi Wang <xii@google.com>
Diagnosed-by: Xi Wang <xii@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Denys Fedorysychenko <nuclearcat@nuclearcat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index b84a1b155bc133e39d0f118b61be85fb1d2ed02f..d12e3a9a53562aca9cf58e68d35ae649493f2efd 100644 (file)
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -346,14 +346,9 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
                if (new_index < 0)
                        new_index = skb_tx_hash(dev, skb);
 
-               if (queue_index != new_index && sk) {
-                       struct dst_entry *dst =
-                                   rcu_dereference_check(sk->sk_dst_cache, 1);
-
-                       if (dst && skb_dst(skb) == dst)
-                               sk_tx_queue_set(sk, queue_index);
-
-               }
+               if (queue_index != new_index && sk &&
+                   rcu_access_pointer(sk->sk_dst_cache))
+                       sk_tx_queue_set(sk, queue_index);
 
                queue_index = new_index;
        }