diff options
| author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2007-04-19 20:29:13 -0700 |
|---|---|---|
| committer | David S. Miller <davem@sunset.davemloft.net> | 2007-04-25 22:26:28 -0700 |
| commit | 27a884dc3cb63b93c2b3b643f5b31eed5f8a4d26 (patch) | |
| tree | 5a267e40f9b94014be38dad5de0a52b6628834e0 /drivers/net/pcmcia | |
| parent | be8bd86321fa7f06359d866ef61fb4d2f3e9dce9 (diff) | |
| download | kernel-crypto-27a884dc3cb63b93c2b3b643f5b31eed5f8a4d26.tar.gz kernel-crypto-27a884dc3cb63b93c2b3b643f5b31eed5f8a4d26.tar.xz kernel-crypto-27a884dc3cb63b93c2b3b643f5b31eed5f8a4d26.zip | |
[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>
Diffstat (limited to 'drivers/net/pcmcia')
| -rw-r--r-- | drivers/net/pcmcia/nmclan_cs.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/drivers/net/pcmcia/nmclan_cs.c b/drivers/net/pcmcia/nmclan_cs.c index ec0af65cd5d..73da611fd53 100644 --- a/drivers/net/pcmcia/nmclan_cs.c +++ b/drivers/net/pcmcia/nmclan_cs.c @@ -1185,7 +1185,7 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt) skb_reserve(skb, 2); insw(ioaddr + AM2150_RCV, skb_put(skb, pkt_len), pkt_len>>1); if (pkt_len & 1) - *(skb->tail-1) = inb(ioaddr + AM2150_RCV); + *(skb_tail_pointer(skb) - 1) = inb(ioaddr + AM2150_RCV); skb->protocol = eth_type_trans(skb, dev); netif_rx(skb); /* Send the packet to the upper (protocol) layers. */ |