net: core: explicitly select a txq before doing l2 forwarding

Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The
will cause several issues:

- NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan
  instead of lower device which misses the necessary txq synchronization for
  lower device such as txq stopping or frozen required by dev watchdog or
  control path.
- dev_hard_start_xmit() was called with NULL txq which bypasses the net device
  watchdog.
- dev_hard_start_xmit() does not check txq everywhere which will lead a crash
  when tso is disabled for lower device.

Fix this by explicitly introducing a new param for .ndo_select_queue() for just
selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also
extended to accept this parameter and dev_queue_xmit_accel() was used to do l2
forwarding transmission.

With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need
to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep
a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of
dev_queue_xmit() to do the transmission.

In the future, it was also required for macvtap l2 forwarding support since it
provides a necessary synchronization method.

Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: e1000-devel@lists.sourceforge.net
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 8 insertions, 4 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5faaadb0c74f..ce2a1f5f9a1e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -769,7 +769,8 @@ struct netdev_phys_port_id {
  *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
  *	Required can not be NULL.
  *
- * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb);
+ * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
+ *                         void *accel_priv);
  *	Called to decide which queue to when device supports multiple
  *	transmit queues.
  *
@@ -990,7 +991,8 @@ struct net_device_ops {
 	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
 						   struct net_device *dev);
 	u16			(*ndo_select_queue)(struct net_device *dev,
-						    struct sk_buff *skb);
+						    struct sk_buff *skb,
+						    void *accel_priv);
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
 	void			(*ndo_set_rx_mode)(struct net_device *dev);
@@ -1529,7 +1531,8 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 }
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-				    struct sk_buff *skb);
+				    struct sk_buff *skb,
+				    void *accel_priv);
 u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
 
 /*
@@ -1819,6 +1822,7 @@ int dev_close(struct net_device *dev);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct sk_buff *newskb);
 int dev_queue_xmit(struct sk_buff *skb);
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
 void unregister_netdevice_many(struct list_head *head);
@@ -2426,7 +2430,7 @@ int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_port_id *ppid);
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq, void *accel_priv);
+			struct netdev_queue *txq);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 
 extern int		netdev_budget;