aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorEric Dumazet <dada1@cosmosbay.com>2009-05-18 22:19:19 -0700
committerDavid S. Miller <davem@davemloft.net>2009-05-18 22:19:19 -0700
commit93f154b594fe47e4a7e5358b309add449a046cd3 (patch)
tree479d9f2db25922a2312547c97e73d5a11b68bb1c /net
parent496a60cdcd5d0d884dddf6c3b4ea912923a70f13 (diff)
net: release dst entry in dev_hard_start_xmit()
One point of contention in high network loads is the dst_release() performed when a transmited skb is freed. This is because NIC tx completion calls dev_kree_skb() long after original call to dev_queue_xmit(skb). CPU cache is cold and the atomic op in dst_release() stalls. On SMP, this is quite visible if one CPU is 100% handling softirqs for a network device, since dst_clone() is done by other cpus, involving cache line ping pongs. It seems right place to release dst is in dev_hard_start_xmit(), for most devices but ones that are virtual, and some exceptions. David Miller suggested to define a new device flag, set in alloc_netdev_mq() (so that most devices set it at init time), and carefuly unset in devices which dont want a NULL skb->dst in their ndo_start_xmit(). List of devices that must clear this flag is : - loopback device, because it calls netif_rx() and quoting Patrick : "ip_route_input() doesn't accept loopback addresses, so loopback packets already need to have a dst_entry attached." - appletalk/ipddp.c : needs skb->dst in its xmit function - And all devices that call again dev_queue_xmit() from their xmit function (as some classifiers need skb->dst) : bonding, vlan, macvlan, eql, ifb, hdlc_fr Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan_dev.c1
-rw-r--r--net/core/dev.c9
2 files changed, 10 insertions, 0 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 8faacee6863..ff7572ac548 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -739,6 +739,7 @@ void vlan_setup(struct net_device *dev)
ether_setup(dev);
dev->priv_flags |= IFF_802_1Q_VLAN;
+ dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
dev->tx_queue_len = 0;
dev->netdev_ops = &vlan_netdev_ops;
diff --git a/net/core/dev.c b/net/core/dev.c
index 6d3630d1627..92ebeca2990 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1688,6 +1688,14 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
goto gso;
}
+ /*
+ * If device doesnt need skb->dst, release it right now while
+ * its hot in this cpu cache
+ */
+ if ((dev->priv_flags & IFF_XMIT_DST_RELEASE) && skb->dst) {
+ dst_release(skb->dst);
+ skb->dst = NULL;
+ }
rc = ops->ndo_start_xmit(skb, dev);
/*
* TODO: if skb_orphan() was called by
@@ -5045,6 +5053,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
netdev_init_queues(dev);
INIT_LIST_HEAD(&dev->napi_list);
+ dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
strcpy(dev->name, name);
return dev;