Merge branch 'ndo_set_rx_headroom'

Paolo Abeni says:

====================
bridge/ovs: avoid skb head copy on frame forwarding

Currently, while when an OVS or Linux bridge is used to forward frames towards
some tunnel device, a skb_head_copy() may occur if the ingress device do not
provide enough headroom for the tx encapsulation.

This patch series tries to address the issue implementing a new ndo operation to
allow the master device to control the headroom used when allocating the skb on
frame reception.

Said operation is used by the Linux bridge to notify the bridged ports of
needed_headroom changes, and similar bookkeeping and behaviour is also added to
openvswitch, on a per datapath basis.

Finally, the operation is implemented for veth and tun device, which give
performance improvement in the 6-12% range when forwarding frames from said
devices towards a vxlan tunnel.

v2:
- fix netdev_get_fwd_headroom() behaviour
- remove some code duplication with the netdev_set_rx_headroom() and
   netdev_reset_rx_headroom() helpers
- handle headroom reset on [v]port removal/deletion
- initialize tun align to the old default value

v3:
- fix a comment typo
====================

Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 31 insertions, 0 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e52077f..efe7cec 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1093,6 +1093,12 @@ struct tc_to_netdev {
  *	This function is used to get egress tunnel information for given skb.
  *	This is useful for retrieving outer tunnel header parameters while
  *	sampling packet.
+ * void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom);
+ *	This function is used to specify the headroom that the skb must
+ *	consider when allocation skb during packet reception. Setting
+ *	appropriate rx headroom value allows avoiding skb head copy on
+ *	forward. Setting a negative value reset the rx headroom to the
+ *	default value.
  *
  */
 struct net_device_ops {
@@ -1278,6 +1284,8 @@ struct net_device_ops {
 							 bool proto_down);
 	int			(*ndo_fill_metadata_dst)(struct net_device *dev,
 						       struct sk_buff *skb);
+	void			(*ndo_set_rx_headroom)(struct net_device *dev,
+						       int needed_headroom);
 };
 
 /**
@@ -1315,6 +1323,8 @@ struct net_device_ops {
  * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device
  * @IFF_TEAM: device is a team device
  * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured
+ * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external
+ *	entity (i.e. the master device for bridged veth)
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1343,6 +1353,7 @@ enum netdev_priv_flags {
 	IFF_L3MDEV_SLAVE		= 1<<23,
 	IFF_TEAM			= 1<<24,
 	IFF_RXFH_CONFIGURED		= 1<<25,
+	IFF_PHONY_HEADROOM		= 1<<26,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1937,6 +1948,26 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
 				    void *accel_priv);
 
+/* returns the headroom that the master device needs to take in account
+ * when forwarding to this dev
+ */
+static inline unsigned netdev_get_fwd_headroom(struct net_device *dev)
+{
+	return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom;
+}
+
+static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr)
+{
+	if (dev->netdev_ops->ndo_set_rx_headroom)
+		dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr);
+}
+
+/* set the device rx headroom to the dev's default */
+static inline void netdev_reset_rx_headroom(struct net_device *dev)
+{
+	netdev_set_rx_headroom(dev, -1);
+}
+
 /*
  * Net namespace inlines
  */