[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>

110 files changed, 396 insertions, 329 deletions

diff --git a/arch/ia64/sn/kernel/xpnet.c b/arch/ia64/sn/kernel/xpnet.c
index 68d59d912c99..eb416c95967d 100644
--- a/arch/ia64/sn/kernel/xpnet.c
+++ b/arch/ia64/sn/kernel/xpnet.c
@@ -264,7 +264,7 @@ xpnet_receive(partid_t partid, int channel, struct xpnet_message *msg)
 
         dev_dbg(xpnet, "<skb->head=0x%p skb->data=0x%p skb->tail=0x%p "
                 "skb->end=0x%p skb->len=%d\n", (void *) skb->head,
-                (void *) skb->data, (void *) skb->tail, (void *) skb->end,
+                (void *)skb->data, skb_tail_pointer(skb), (void *)skb->end,
                 skb->len);
 
         skb->protocol = eth_type_trans(skb, xpnet_device);
@@ -272,7 +272,7 @@ xpnet_receive(partid_t partid, int channel, struct xpnet_message *msg)
 
         dev_dbg(xpnet, "passing skb to network layer; \n\tskb->head=0x%p "
                 "skb->data=0x%p skb->tail=0x%p skb->end=0x%p skb->len=%d\n",
-                (void *) skb->head, (void *) skb->data, (void *) skb->tail,
+                (void *)skb->head, (void *)skb->data, skb_tail_pointer(skb),