[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_hfsc.c b/net/sched/sch_hfsc.c
index 5197b6c..80e6f81 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1363,7 +1363,7 @@
 		struct tcmsg *tcm)
 {
 	struct hfsc_class *cl = (struct hfsc_class *)arg;
-	unsigned char *b = skb->tail;
+	unsigned char *b = skb_tail_pointer(skb);
 	struct rtattr *rta = (struct rtattr *)b;
 
 	tcm->tcm_parent = cl->cl_parent ? cl->cl_parent->classid : TC_H_ROOT;
@@ -1374,7 +1374,7 @@
 	RTA_PUT(skb, TCA_OPTIONS, 0, NULL);
 	if (hfsc_dump_curves(skb, cl) < 0)
 		goto rtattr_failure;
-	rta->rta_len = skb->tail - b;
+	rta->rta_len = skb_tail_pointer(skb) - b;
 	return skb->len;
 
  rtattr_failure:
@@ -1576,7 +1576,7 @@
 hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct hfsc_sched *q = qdisc_priv(sch);
-	unsigned char *b = skb->tail;
+	unsigned char *b = skb_tail_pointer(skb);
 	struct tc_hfsc_qopt qopt;
 
 	qopt.defcls = q->defcls;