net/hsr: Better frame dispatch

This patch removes the separate paths for frames coming from the outside, and
frames sent from the HSR device, and instead makes all frames go through
hsr_forward_skb() in hsr_forward.c. This greatly improves code readability and
also opens up the possibility for future support of the HSR Interlink device
that is the basis for HSR RedBoxes and HSR QuadBoxes, as well as VLAN
compatibility.

Other improvements:
* A reduction in the number of times an skb is copied on machines without
  HAVE_EFFICIENT_UNALIGNED_ACCESS, which improves throughput somewhat.
* Headers are now created using the standard eth_header(), and using the
  standard hard_header_len.
* Each HSR slave now gets its own private skb, so slave-specific fields can be
  correctly set.

Signed-off-by: Arvid Brodin <arvid.brodin@alten.se>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/hsr/hsr_netlink.c

@@ -358,7 +358,7 @@ fail:
 	return res;
 }
 
-/* Get a list of MacAddressA of all nodes known to this node (other than self).
+/* Get a list of MacAddressA of all nodes known to this node (including self).
  */
 static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 {