aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv6/xfrm6_input.c
diff options
context:
space:
mode:
authorHerbert Xu <herbert@gondor.apana.org.au>2006-03-28 01:12:13 -0800
committerDavid S. Miller <davem@sunset.davemloft.net>2006-03-28 17:02:46 -0800
commitd2acc3479cbccd5cfbca6c787be713ef1de12ec6 (patch)
treeaa348e19e15027db9abdd2da175a0c9055047858 /net/ipv6/xfrm6_input.c
parent[NET]: deinline 200+ byte inlines in sock.h (diff)
downloadlinux-dev-d2acc3479cbccd5cfbca6c787be713ef1de12ec6.tar.xz
linux-dev-d2acc3479cbccd5cfbca6c787be713ef1de12ec6.zip
[INET]: Introduce tunnel4/tunnel6
Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv6/xfrm6_input.c')
-rw-r--r--net/ipv6/xfrm6_input.c5
1 files changed, 2 insertions, 3 deletions
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 1ca2da68ef69..cccf8b76f046 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -28,9 +28,8 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
IP6_ECN_set_ce(inner_iph);
}
-int xfrm6_rcv_spi(struct sk_buff **pskb, u32 spi)
+int xfrm6_rcv_spi(struct sk_buff *skb, u32 spi)
{
- struct sk_buff *skb = *pskb;
int err;
u32 seq;
struct sec_decap_state xfrm_vec[XFRM_MAX_DEPTH];
@@ -159,5 +158,5 @@ EXPORT_SYMBOL(xfrm6_rcv_spi);
int xfrm6_rcv(struct sk_buff **pskb)
{
- return xfrm6_rcv_spi(pskb, 0);
+ return xfrm6_rcv_spi(*pskb, 0);
}