netfilter: push reasm skb through instead of original frag skbs

Pushing original fragments through causes several problems. For example
for matching, frags may not be matched correctly. Take following
example:

<example>
On HOSTA do:
ip6tables -I INPUT -p icmpv6 -j DROP
ip6tables -I INPUT -p icmpv6 -m icmp6 --icmpv6-type 128 -j ACCEPT

and on HOSTB you do:
ping6 HOSTA -s2000    (MTU is 1500)

Incoming echo requests will be filtered out on HOSTA. This issue does
not occur with smaller packets than MTU (where fragmentation does not happen)
</example>

As was discussed previously, the only correct solution seems to be to use
reassembled skb instead of separete frags. Doing this has positive side
effects in reducing sk_buff by one pointer (nfct_reasm) and also the reams
dances in ipvs and conntrack can be removed.

Future plan is to remove net/ipv6/netfilter/nf_conntrack_reasm.c
entirely and use code in net/ipv6/reassembly.c instead.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 2 insertions, 66 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 036ec7d8a83a..215b5ea1cb30 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -337,11 +337,6 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
-#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \
-    defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-#define NET_SKBUFF_NF_DEFRAG_NEEDED 1
-#endif
-
 /** 
  *      struct sk_buff - socket buffer
  *      @next: Next buffer in list
@@ -374,7 +369,6 @@ typedef unsigned char *sk_buff_data_t;
  *      @protocol: Packet protocol from driver
  *      @destructor: Destruct function
  *      @nfct: Associated connection, if any
- *      @nfct_reasm: netfilter conntrack re-assembly pointer
  *      @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *      @skb_iif: ifindex of device we arrived on
  *      @tc_index: Traffic control index
@@ -463,9 +457,6 @@ struct sk_buff {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
         struct nf_conntrack     *nfct;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-        struct sk_buff          *nfct_reasm;
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
         struct nf_bridge_info   *nf_bridge;
 #endif
@@ -2595,18 +2586,6 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
                 atomic_inc(&nfct->use);
 }
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
-{
-        if (skb)
-                atomic_inc(&skb->users);
-}
-static inline void nf_conntrack_put_reasm(struct sk_buff *skb)
-{
-        if (skb)
-                kfree_skb(skb);
-}
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
 {
@@ -2625,10 +2604,6 @@ static inline void nf_reset(struct sk_buff *skb)
         nf_conntrack_put(skb->nfct);
         skb->nfct = NULL;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-        nf_conntrack_put_reasm(skb->nfct_reasm);
-        skb->nfct_reasm = NULL;
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
         nf_bridge_put(skb->nf_bridge);
         skb->nf_bridge = NULL;
@@ -2650,10 +2625,6 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
         nf_conntrack_get(src->nfct);
         dst->nfctinfo = src->nfctinfo;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-        dst->nfct_reasm = src->nfct_reasm;
-        nf_conntrack_get_reasm(src->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
         dst->nf_bridge  = src->nf_bridge;
         nf_bridge_get(src->nf_bridge);
@@ -2665,9 +2636,6 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
         nf_conntrack_put(dst->nfct);
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-        nf_conntrack_put_reasm(dst->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
         nf_bridge_put(dst->nf_bridge);
 #endif
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index cd7275f9c463..5679d927562b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -109,7 +109,6 @@ extern int ip_vs_conn_tab_size;
 struct ip_vs_iphdr {
         __u32 len;      /* IPv4 simply where L4 starts
                            IPv6 where L4 Transport Header starts */
-        __u32 thoff_reasm; /* Transport Header Offset in nfct_reasm skb */
         __u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
         __s16 protocol;
         __s32 flags;
@@ -117,34 +116,12 @@ struct ip_vs_iphdr {
         union nf_inet_addr daddr;
 };
 
-/* Dependency to module: nf_defrag_ipv6 */
-#if defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
-        return skb->nfct_reasm;
-}
-static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
-                                      int len, void *buffer,
-                                      const struct ip_vs_iphdr *ipvsh)
-{
-        if (unlikely(ipvsh->fragoffs && skb_nfct_reasm(skb)))
-                return skb_header_pointer(skb_nfct_reasm(skb),
-                                          ipvsh->thoff_reasm, len, buffer);
-
-        return skb_header_pointer(skb, offset, len, buffer);
-}
-#else
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
-        return NULL;
-}
 static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
                                       int len, void *buffer,
                                       const struct ip_vs_iphdr *ipvsh)
 {
         return skb_header_pointer(skb, offset, len, buffer);
 }
-#endif
 
 static inline void
 ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr)
@@ -171,19 +148,12 @@ ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr)
                         (struct ipv6hdr *)skb_network_header(skb);
                 iphdr->saddr.in6 = iph->saddr;
                 iphdr->daddr.in6 = iph->daddr;
-                /* ipv6_find_hdr() updates len, flags, thoff_reasm */
-                iphdr->thoff_reasm = 0;
+                /* ipv6_find_hdr() updates len, flags */
                 iphdr->len       = 0;
                 iphdr->flags     = 0;
                 iphdr->protocol  = ipv6_find_hdr(skb, &iphdr->len, -1,
                                                  &iphdr->fragoffs,
                                                  &iphdr->flags);
-                /* get proto from re-assembled packet and it's offset */
-                if (skb_nfct_reasm(skb))
-                        iphdr->protocol = ipv6_find_hdr(skb_nfct_reasm(skb),
-                                                        &iphdr->thoff_reasm,
-                                                        -1, NULL, NULL);
-
         } else
 #endif
         {
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index 5613412e7dc2..27666d8a0bd0 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -6,9 +6,7 @@ void nf_defrag_ipv6_enable(void);
 int nf_ct_frag6_init(void);
 void nf_ct_frag6_cleanup(void);
 struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
-void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-                        struct net_device *in, struct net_device *out,
-                        int (*okfn)(struct sk_buff *));
+void nf_ct_frag6_consume_orig(struct sk_buff *skb);
 
 struct inet_frags_ctl;