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>

drivers/net/appletalk/ipddp.c

@@ -71,6 +71,7 @@ static struct net_device * __init ipddp_init(void)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
+	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 	strcpy(dev->name, "ipddp%d");
 
 	if (version_printed++ == 0)

drivers/net/bonding/bond_main.c

@@ -5148,6 +5148,7 @@ int bond_create(char *name, struct bond_params *params)
 		goto out_rtnl;
 	}
 
+	bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 	if (!name) {
 		res = dev_alloc_name(bond_dev, "bond%d");
 		if (res < 0)

drivers/net/eql.c

@@ -194,6 +194,7 @@ static void __init eql_setup(struct net_device *dev)
 
 	dev->type       	= ARPHRD_SLIP;
 	dev->tx_queue_len 	= 5;		/* Hands them off fast */
+	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
 }
 
 static int eql_open(struct net_device *dev)

drivers/net/ifb.c

@@ -156,6 +156,7 @@ static void ifb_setup(struct net_device *dev)
 
 	dev->flags |= IFF_NOARP;
 	dev->flags &= ~IFF_MULTICAST;
+	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 	random_ether_addr(dev->dev_addr);
 }
 

drivers/net/loopback.c

@@ -170,6 +170,7 @@ static void loopback_setup(struct net_device *dev)
 	dev->tx_queue_len	= 0;
 	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
 	dev->flags		= IFF_LOOPBACK;
+	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
 	dev->features 		= NETIF_F_SG | NETIF_F_FRAGLIST
 		| NETIF_F_TSO
 		| NETIF_F_NO_CSUM

drivers/net/macvlan.c

@@ -414,6 +414,7 @@ static void macvlan_setup(struct net_device *dev)
 {
 	ether_setup(dev);
 
+	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
 	dev->netdev_ops		= &macvlan_netdev_ops;
 	dev->destructor		= free_netdev;
 	dev->header_ops		= &macvlan_hard_header_ops,

drivers/net/wan/hdlc_fr.c

@@ -1054,6 +1054,7 @@ static void pvc_setup(struct net_device *dev)
 	dev->flags = IFF_POINTOPOINT;
 	dev->hard_header_len = 10;
 	dev->addr_len = 2;
+	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 }
 
 static const struct net_device_ops pvc_ops = {

include/linux/if.h

@@ -67,6 +67,9 @@
 #define IFF_ISATAP	0x80		/* ISATAP interface (RFC4214)	*/
 #define IFF_MASTER_ARPMON 0x100		/* bonding master, ARP mon in use */
 #define IFF_WAN_HDLC	0x200		/* WAN HDLC device		*/
+#define IFF_XMIT_DST_RELEASE 0x400	/* dev_hard_start_xmit() is allowed to
+					 * release skb->dst
+					 */
 
 #define IF_GET_IFACE	0x0001		/* for querying only */
 #define IF_GET_PROTO	0x0002

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;

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;