ipvs: netfilter connection tracking changes

	Add more code to IPVS to work with Netfilter connection
tracking and fix some problems.

- Allow IPVS to be compiled without connection tracking as in
2.6.35 and before. This can avoid keeping conntracks for all
IPVS connections because this costs memory. ip_vs_ftp still
depends on connection tracking and NAT as implemented for 2.6.36.

- Add sysctl var "conntrack" to enable connection tracking for
all IPVS connections. For loaded IPVS directors it needs
tuning of nf_conntrack_max limit.

- Add IP_VS_CONN_F_NFCT connection flag to request the connection
to use connection tracking. This allows user space to provide this
flag, for example, in dest->conn_flags. This can be useful to
request connection tracking per real server instead of forcing it
for all connections with the "conntrack" sysctl. This flag is
set currently only by ip_vs_ftp and of course by "conntrack" sysctl.

- Add ip_vs_nfct.c file to hold all connection tracking code,
by this way main code should not depend of netfilter conntrack
support.

- Return back the ip_vs_post_routing handler as in 2.6.35 and use
skb->ipvs_property=1 to allow IPVS to work without connection
tracking

Connection tracking:

- most of the code is already in 2.6.36-rc

- alter conntrack reply tuple for LVS-NAT connections when first packet
from client is forwarded and conntrack state is NEW or RELATED.
Additionally, alter reply for RELATED connections from real server,
again for packet in original direction.

- add IP_VS_XMIT_TUNNEL to confirm conntrack (without altering
reply) for LVS-TUN early because we want to call nf_reset. It is
needed because we add IPIP header and the original conntrack
should be preserved, not destroyed. The transmitted IPIP packets
can reuse same conntrack, so we do not set skb->ipvs_property.

- try to destroy conntrack when the IPVS connection is destroyed.
It is not fatal if conntrack disappears before that, it depends
on the used timers.

Fix problems from long time:

- add skb->ip_summed = CHECKSUM_NONE for the LVS-TUN transmitters

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Patrick McHardy <kaber@trash.net>

1 files changed, 49 insertions, 49 deletions

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 49df6bea6a2..8817afa34e6 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -28,7 +28,6 @@
 #include <net/ip6_route.h>
 #include <linux/icmpv6.h>
 #include <linux/netfilter.h>
-#include <net/netfilter/nf_conntrack.h>
 #include <linux/netfilter_ipv4.h>
 
 #include <net/ip_vs.h>
@@ -194,12 +193,37 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
 	dst_release(old_dst);
 }
 
-#define IP_VS_XMIT(pf, skb, rt)				\
+#define IP_VS_XMIT_TUNNEL(skb, cp)				\
+({								\
+	int __ret = NF_ACCEPT;					\
+								\
+	if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT))		\
+		__ret = ip_vs_confirm_conntrack(skb, cp);	\
+	if (__ret == NF_ACCEPT) {				\
+		nf_reset(skb);					\
+		(skb)->ip_summed = CHECKSUM_NONE;		\
+	}							\
+	__ret;							\
+})
+
+#define IP_VS_XMIT_NAT(pf, skb, cp)				\
 do {							\
-	(skb)->ipvs_property = 1;			\
+	if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT)))	\
+		(skb)->ipvs_property = 1;		\
+	else						\
+		ip_vs_update_conntrack(skb, cp, 1);	\
 	skb_forward_csum(skb);				\
 	NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL,	\
-		(rt)->dst.dev, dst_output);		\
+		skb_dst(skb)->dev, dst_output);		\
+} while (0)
+
+#define IP_VS_XMIT(pf, skb, cp)				\
+do {							\
+	if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT)))	\
+		(skb)->ipvs_property = 1;		\
+	skb_forward_csum(skb);				\
+	NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL,	\
+		skb_dst(skb)->dev, dst_output);		\
 } while (0)
 
 
@@ -271,7 +295,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	IP_VS_XMIT(NFPROTO_IPV4, skb, rt);
+	IP_VS_XMIT(NFPROTO_IPV4, skb, cp);
 
 	LeaveFunction(10);
 	return NF_STOLEN;
@@ -335,7 +359,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	IP_VS_XMIT(NFPROTO_IPV6, skb, rt);
+	IP_VS_XMIT(NFPROTO_IPV6, skb, cp);
 
 	LeaveFunction(10);
 	return NF_STOLEN;
@@ -349,36 +373,6 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 }
 #endif
 
-void
-ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin)
-{
-	struct nf_conn *ct = (struct nf_conn *)skb->nfct;
-	struct nf_conntrack_tuple new_tuple;
-
-	if (ct == NULL || nf_ct_is_untracked(ct) || nf_ct_is_confirmed(ct))
-		return;
-
-	/*
-	 * The connection is not yet in the hashtable, so we update it.
-	 * CIP->VIP will remain the same, so leave the tuple in
-	 * IP_CT_DIR_ORIGINAL untouched.  When the reply comes back from the
-	 * real-server we will see RIP->DIP.
-	 */
-	new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
-	if (outin)
-		new_tuple.src.u3 = cp->daddr;
-	else
-		new_tuple.dst.u3 = cp->vaddr;
-	/*
-	 * This will also take care of UDP and other protocols.
-	 */
-	if (outin)
-		new_tuple.src.u.tcp.port = cp->dport;
-	else
-		new_tuple.dst.u.tcp.port = cp->vport;
-	nf_conntrack_alter_reply(ct, &new_tuple);
-}
-
 /*
  *      NAT transmitter (only for outside-to-inside nat forwarding)
  *      Not used for related ICMP
@@ -434,8 +428,6 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
 
-	ip_vs_update_conntrack(skb, cp, 1);
-
 	/* FIXME: when application helper enlarges the packet and the length
 	   is larger than the MTU of outgoing device, there will be still
 	   MTU problem. */
@@ -443,7 +435,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	IP_VS_XMIT(NFPROTO_IPV4, skb, rt);
+	IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp);
 
 	LeaveFunction(10);
 	return NF_STOLEN;
@@ -451,8 +443,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
   tx_error_icmp:
 	dst_link_failure(skb);
   tx_error:
-	LeaveFunction(10);
 	kfree_skb(skb);
+	LeaveFunction(10);
 	return NF_STOLEN;
   tx_error_put:
 	ip_rt_put(rt);
@@ -512,8 +504,6 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
 
-	ip_vs_update_conntrack(skb, cp, 1);
-
 	/* FIXME: when application helper enlarges the packet and the length
 	   is larger than the MTU of outgoing device, there will be still
 	   MTU problem. */
@@ -521,7 +511,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	IP_VS_XMIT(NFPROTO_IPV6, skb, rt);
+	IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp);
 
 	LeaveFunction(10);
 	return NF_STOLEN;
@@ -571,6 +561,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	struct iphdr  *iph;			/* Our new IP header */
 	unsigned int max_headroom;		/* The extra header space needed */
 	int    mtu;
+	int ret;
 
 	EnterFunction(10);
 
@@ -655,7 +646,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	ip_local_out(skb);
+	ret = IP_VS_XMIT_TUNNEL(skb, cp);
+	if (ret == NF_ACCEPT)
+		ip_local_out(skb);
+	else if (ret == NF_DROP)
+		kfree_skb(skb);
 
 	LeaveFunction(10);
 
@@ -681,6 +676,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	struct ipv6hdr  *iph;		/* Our new IP header */
 	unsigned int max_headroom;	/* The extra header space needed */
 	int    mtu;
+	int ret;
 
 	EnterFunction(10);
 
@@ -761,7 +757,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	ip6_local_out(skb);
+	ret = IP_VS_XMIT_TUNNEL(skb, cp);
+	if (ret == NF_ACCEPT)
+		ip6_local_out(skb);
+	else if (ret == NF_DROP)
+		kfree_skb(skb);
 
 	LeaveFunction(10);
 
@@ -820,7 +820,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	IP_VS_XMIT(NFPROTO_IPV4, skb, rt);
+	IP_VS_XMIT(NFPROTO_IPV4, skb, cp);
 
 	LeaveFunction(10);
 	return NF_STOLEN;
@@ -873,7 +873,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	IP_VS_XMIT(NFPROTO_IPV6, skb, rt);
+	IP_VS_XMIT(NFPROTO_IPV6, skb, cp);
 
 	LeaveFunction(10);
 	return NF_STOLEN;
@@ -947,7 +947,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	IP_VS_XMIT(NFPROTO_IPV4, skb, rt);
+	IP_VS_XMIT(NFPROTO_IPV4, skb, cp);
 
 	rc = NF_STOLEN;
 	goto out;
@@ -1022,7 +1022,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
 
-	IP_VS_XMIT(NFPROTO_IPV6, skb, rt);
+	IP_VS_XMIT(NFPROTO_IPV6, skb, cp);
 
 	rc = NF_STOLEN;
 	goto out;