From deabc772f39405054a438d711f408d2d94d26d96 Mon Sep 17 00:00:00 2001 From: Helmut Schaa Date: Fri, 3 Sep 2010 02:39:56 +0000 Subject: net: fix tx queue selection for bridged devices implementing select_queue When a net device is implementing the select_queue callback and is part of a bridge, frames coming from the bridge already have a tx queue associated to the socket (introduced in commit a4ee3ce3293dc931fab19beb472a8bde1295aebe, "net: Use sk_tx_queue_mapping for connected sockets"). The call to sk_tx_queue_get will then return the tx queue used by the bridge instead of calling the select_queue callback. In case of mac80211 this broke QoS which is implemented by using the select_queue callback. Furthermore it introduced problems with rt2x00 because frames with the same TID and RA sometimes appeared on different tx queues which the hw cannot handle correctly. Fix this by always calling select_queue first if it is available and only afterwards use the socket tx queue mapping. Signed-off-by: Helmut Schaa Signed-off-by: David S. Miller --- net/core/dev.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 3721fbb..b9b22a3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2058,16 +2058,16 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { int queue_index; - struct sock *sk = skb->sk; + const struct net_device_ops *ops = dev->netdev_ops; - queue_index = sk_tx_queue_get(sk); - if (queue_index < 0) { - const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } else { + struct sock *sk = skb->sk; + queue_index = sk_tx_queue_get(sk); + if (queue_index < 0) { - if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } else { queue_index = 0; if (dev->real_num_tx_queues > 1) queue_index = skb_tx_hash(dev, skb); -- cgit v1.1 From ef885afbf8a37689afc1d9d545e2f3e7a8276c17 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 13 Sep 2010 12:24:54 +0000 Subject: net: use rcu_barrier() in rollback_registered_many netdev_wait_allrefs() waits that all references to a device vanishes. It currently uses a _very_ pessimistic 250 ms delay between each probe. Some users reported that no more than 4 devices can be dismantled per second, this is a pretty serious problem for some setups. Most of the time, a refcount is about to be released by an RCU callback, that is still in flight because rollback_registered_many() uses a synchronize_rcu() call instead of rcu_barrier(). Problem is visible if number of online cpus is one, because synchronize_rcu() is then a no op. time to remove 50 ipip tunnels on a UP machine : before patch : real 11.910s after patch : real 1.250s Reported-by: Nicolas Dichtel Reported-by: Octavian Purdila Reported-by: Benjamin LaHaise Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index b9b22a3..660dd41 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4845,7 +4845,7 @@ static void rollback_registered_many(struct list_head *head) dev = list_first_entry(head, struct net_device, unreg_list); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - synchronize_net(); + rcu_barrier(); list_for_each_entry(dev, head, unreg_list) dev_put(dev); -- cgit v1.1