[SK_BUFF]: Convert skb->tail to sk_buff_data_t

So that it is also an offset from skb->head, reduces its size from 8 to 4 bytes
on 64bit architectures, allowing us to combine the 4 bytes hole left by the
layer headers conversion, reducing struct sk_buff size to 256 bytes, i.e. 4
64byte cachelines, and since the sk_buff slab cache is SLAB_HWCACHE_ALIGN...
:-)

Many calculations that previously required that skb->{transport,network,
mac}_header be first converted to a pointer now can be done directly, being
meaningful as offsets or pointers.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ecbdc6b..7482a95 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -813,7 +813,7 @@
 {
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
-	unsigned char	 *b = skb->tail;
+	unsigned char *b = skb_tail_pointer(skb);
 	struct gnet_dump d;
 
 	nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags);
@@ -847,7 +847,7 @@
 	if (gnet_stats_finish_copy(&d) < 0)
 		goto rtattr_failure;
 
-	nlh->nlmsg_len = skb->tail - b;
+	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 	return skb->len;
 
 nlmsg_failure:
@@ -1051,7 +1051,7 @@
 {
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
-	unsigned char	 *b = skb->tail;
+	unsigned char *b = skb_tail_pointer(skb);
 	struct gnet_dump d;
 	struct Qdisc_class_ops *cl_ops = q->ops->cl_ops;
 
@@ -1076,7 +1076,7 @@
 	if (gnet_stats_finish_copy(&d) < 0)
 		goto rtattr_failure;
 
-	nlh->nlmsg_len = skb->tail - b;
+	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 	return skb->len;
 
 nlmsg_failure: