Merge branch 'nf-hook-compress'

netfilter: Compress hook function signatures.

Currently netfilter hooks have a function signature that is huge and
has many arguments.  This propagates from the hook entry points down
into the individual hook implementations themselves.

This means that if, for example, we want to change the type of one of
these arguments then we have to touch hundreds of locations.

The main initial motivation behind this is that we'd like to change
the signature of "okfn" so that a socket pointer can be passed in (and
reference counted properly) for the sake of using the proper socket
context in the case of tunnels whilst not releasing the top level user
socket from skb->sk (and thus releasing it's socket memory quota
usage) in order to accomodate this.

This also makes it clear who actually uses 'okfn', nf_queue().  It is
absolutely critical to make this obvious because any user of 'okfn'
down in these hook chains have the be strictly audited for
escapability.  Specifically, escapability of references to objects
outside of the packet processing path.  And that's exactly what
nf_queue() does via it's packet reinjection framework.

In fact this points out a bug in Jiri's original attempt to push the
socket pointer down through netfilter's okfn.  It didn't grab and drop
a reference to the socket in net/netfilter/nf_queue.c as needed.

Furthermore, so many code paths are simplified, and should in fact be
more efficient because we aren't passing in arguments that often are
simply not used by the netfilter hook at all.

Further simplifications are probably possible, but this series takes
care of the main cases.

Unfortunately I couldn't convert ebt_do_table() because ebtables is
complete and utter crap and uses ebt_do_table() outside of the hook
call chains.  But that should not be news to anyone.

Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>

include/linux/netfilter.h

@@ -44,11 +44,19 @@ int netfilter_init(void);
 struct sk_buff;
 
 struct nf_hook_ops;
+
+struct nf_hook_state {
+	unsigned int hook;
+	int thresh;
+	u_int8_t pf;
+	struct net_device *in;
+	struct net_device *out;
+	int (*okfn)(struct sk_buff *);
+};
+
 typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops,
 			       struct sk_buff *skb,
-			       const struct net_device *in,
-			       const struct net_device *out,
-			       int (*okfn)(struct sk_buff *));
+			       const struct nf_hook_state *state);
 
 struct nf_hook_ops {
 	struct list_head list;
@@ -118,9 +126,7 @@ static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
 }
 #endif
 
-int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
-		 struct net_device *indev, struct net_device *outdev,
-		 int (*okfn)(struct sk_buff *), int thresh);
+int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state);
 
 /**
  *	nf_hook_thresh - call a netfilter hook
@@ -135,8 +141,18 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
 				 struct net_device *outdev,
 				 int (*okfn)(struct sk_buff *), int thresh)
 {
-	if (nf_hooks_active(pf, hook))
-		return nf_hook_slow(pf, hook, skb, indev, outdev, okfn, thresh);
+	if (nf_hooks_active(pf, hook)) {
+		struct nf_hook_state state = {
+			.hook = hook,
+			.thresh = thresh,
+			.pf = pf,
+			.in = indev,
+			.out = outdev,
+			.okfn = okfn
+		};
+
+		return nf_hook_slow(skb, &state);
+	}
 	return 1;
 }
 

include/linux/netfilter_arp/arp_tables.h

@@ -54,8 +54,7 @@ extern struct xt_table *arpt_register_table(struct net *net,
 extern void arpt_unregister_table(struct xt_table *table);
 extern unsigned int arpt_do_table(struct sk_buff *skb,
 				  unsigned int hook,
-				  const struct net_device *in,
-				  const struct net_device *out,
+				  const struct nf_hook_state *state,
 				  struct xt_table *table);
 
 #ifdef CONFIG_COMPAT

include/linux/netfilter_ipv4/ip_tables.h

@@ -65,8 +65,7 @@ struct ipt_error {
 extern void *ipt_alloc_initial_table(const struct xt_table *);
 extern unsigned int ipt_do_table(struct sk_buff *skb,
 				 unsigned int hook,
-				 const struct net_device *in,
-				 const struct net_device *out,
+				 const struct nf_hook_state *state,
 				 struct xt_table *table);
 
 #ifdef CONFIG_COMPAT

include/linux/netfilter_ipv6/ip6_tables.h

@@ -31,8 +31,7 @@ extern struct xt_table *ip6t_register_table(struct net *net,
 extern void ip6t_unregister_table(struct net *net, struct xt_table *table);
 extern unsigned int ip6t_do_table(struct sk_buff *skb,
 				  unsigned int hook,
-				  const struct net_device *in,
-				  const struct net_device *out,
+				  const struct nf_hook_state *state,
 				  struct xt_table *table);
 
 /* Check for an extension */

include/net/netfilter/nf_nat_l3proto.h

@@ -44,81 +44,65 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
 				  unsigned int hooknum);
 
 unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
-			    const struct net_device *in,
-			    const struct net_device *out,
+			    const struct nf_hook_state *state,
 			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 						     struct sk_buff *skb,
-						     const struct net_device *in,
-						     const struct net_device *out,
+						     const struct nf_hook_state *state,
 						     struct nf_conn *ct));
 
 unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
-			     const struct net_device *in,
-			     const struct net_device *out,
+			     const struct nf_hook_state *state,
 			     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 						      struct sk_buff *skb,
-						      const struct net_device *in,
-						      const struct net_device *out,
+						      const struct nf_hook_state *state,
 						      struct nf_conn *ct));
 
 unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
 				  struct sk_buff *skb,
-				  const struct net_device *in,
-				  const struct net_device *out,
+				  const struct nf_hook_state *state,
 				  unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 							   struct sk_buff *skb,
-							   const struct net_device *in,
-							   const struct net_device *out,
+							   const struct nf_hook_state *state,
 							   struct nf_conn *ct));
 
 unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
-			    const struct net_device *in,
-			    const struct net_device *out,
+			    const struct nf_hook_state *state,
 			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 						     struct sk_buff *skb,
-						     const struct net_device *in,
-						     const struct net_device *out,
+						     const struct nf_hook_state *state,
 						     struct nf_conn *ct));
 
 int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
 				    enum ip_conntrack_info ctinfo,
 				    unsigned int hooknum, unsigned int hdrlen);
 
 unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
-			    const struct net_device *in,
-			    const struct net_device *out,
+			    const struct nf_hook_state *state,
 			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 						     struct sk_buff *skb,
-						     const struct net_device *in,
-						     const struct net_device *out,
+						     const struct nf_hook_state *state,
 						     struct nf_conn *ct));
 
 unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
-			     const struct net_device *in,
-			     const struct net_device *out,
+			     const struct nf_hook_state *state,
 			     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 						      struct sk_buff *skb,
-						      const struct net_device *in,
-						      const struct net_device *out,
+						      const struct nf_hook_state *state,
 						      struct nf_conn *ct));
 
 unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops,
 				  struct sk_buff *skb,
-				  const struct net_device *in,
-				  const struct net_device *out,
+				  const struct nf_hook_state *state,
 				  unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 							   struct sk_buff *skb,
-							   const struct net_device *in,
-							   const struct net_device *out,
+							   const struct nf_hook_state *state,
 							   struct nf_conn *ct));
 
 unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
-			    const struct net_device *in,
-			    const struct net_device *out,
+			    const struct nf_hook_state *state,
 			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 						     struct sk_buff *skb,
-						     const struct net_device *in,
-						     const struct net_device *out,
+						     const struct nf_hook_state *state,
 						     struct nf_conn *ct));
 
 #endif /* _NF_NAT_L3PROTO_H */

include/net/netfilter/nf_queue.h

@@ -12,12 +12,8 @@ struct nf_queue_entry {
 	unsigned int		id;
 
 	struct nf_hook_ops	*elem;
-	u_int8_t		pf;
+	struct nf_hook_state	state;
 	u16			size; /* sizeof(entry) + saved route keys */
-	unsigned int		hook;
-	struct net_device	*indev;
-	struct net_device	*outdev;
-	int			(*okfn)(struct sk_buff *);
 
 	/* extra space to store route keys */
 };

include/net/netfilter/nf_tables.h

@@ -26,12 +26,11 @@ struct nft_pktinfo {
 static inline void nft_set_pktinfo(struct nft_pktinfo *pkt,
 				   const struct nf_hook_ops *ops,
 				   struct sk_buff *skb,
-				   const struct net_device *in,
-				   const struct net_device *out)
+				   const struct nf_hook_state *state)
 {
 	pkt->skb = skb;
-	pkt->in = pkt->xt.in = in;
-	pkt->out = pkt->xt.out = out;
+	pkt->in = pkt->xt.in = state->in;
+	pkt->out = pkt->xt.out = state->out;
 	pkt->ops = ops;
 	pkt->xt.hooknum = ops->hooknum;
 	pkt->xt.family = ops->pf;

include/net/netfilter/nf_tables_ipv4.h

@@ -8,12 +8,11 @@ static inline void
 nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt,
 		     const struct nf_hook_ops *ops,
 		     struct sk_buff *skb,
-		     const struct net_device *in,
-		     const struct net_device *out)
+		     const struct nf_hook_state *state)
 {
 	struct iphdr *ip;
 
-	nft_set_pktinfo(pkt, ops, skb, in, out);
+	nft_set_pktinfo(pkt, ops, skb, state);
 
 	ip = ip_hdr(pkt->skb);
 	pkt->tprot = ip->protocol;

include/net/netfilter/nf_tables_ipv6.h

@@ -8,13 +8,12 @@ static inline int
 nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
 		     const struct nf_hook_ops *ops,
 		     struct sk_buff *skb,
-		     const struct net_device *in,
-		     const struct net_device *out)
+		     const struct nf_hook_state *state)
 {
 	int protohdr, thoff = 0;
 	unsigned short frag_off;
 
-	nft_set_pktinfo(pkt, ops, skb, in, out);
+	nft_set_pktinfo(pkt, ops, skb, state);
 
 	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL);
 	/* If malformed, drop it */

net/bridge/br_netfilter.c

@@ -562,9 +562,7 @@ static int check_hbh_len(struct sk_buff *skb)
  * to ip6tables, which doesn't support NAT, so things are fairly simple. */
 static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
 					   struct sk_buff *skb,
-					   const struct net_device *in,
-					   const struct net_device *out,
-					   int (*okfn)(struct sk_buff *))
+					   const struct nf_hook_state *state)
 {
 	const struct ipv6hdr *hdr;
 	u32 pkt_len;
@@ -612,9 +610,7 @@ static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
  * address to be able to detect DNAT afterwards. */
 static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
 				      struct sk_buff *skb,
-				      const struct net_device *in,
-				      const struct net_device *out,
-				      int (*okfn)(struct sk_buff *))
+				      const struct nf_hook_state *state)
 {
 	struct net_bridge_port *p;
 	struct net_bridge *br;
@@ -623,7 +619,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
 	if (unlikely(!pskb_may_pull(skb, len)))
 		return NF_DROP;
 
-	p = br_port_get_rcu(in);
+	p = br_port_get_rcu(state->in);
 	if (p == NULL)
 		return NF_DROP;
 	br = p->br;
@@ -633,7 +629,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
 			return NF_ACCEPT;
 
 		nf_bridge_pull_encap_header_rcsum(skb);
-		return br_nf_pre_routing_ipv6(ops, skb, in, out, okfn);
+		return br_nf_pre_routing_ipv6(ops, skb, state);
 	}
 
 	if (!brnf_call_iptables && !br->nf_call_iptables)
@@ -671,9 +667,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
  * prevent this from happening. */
 static unsigned int br_nf_local_in(const struct nf_hook_ops *ops,
 				   struct sk_buff *skb,
-				   const struct net_device *in,
-				   const struct net_device *out,
-				   int (*okfn)(struct sk_buff *))
+				   const struct nf_hook_state *state)
 {
 	br_drop_fake_rtable(skb);
 	return NF_ACCEPT;
@@ -710,9 +704,7 @@ static int br_nf_forward_finish(struct sk_buff *skb)
  * bridge ports. */
 static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 				     struct sk_buff *skb,
-				     const struct net_device *in,
-				     const struct net_device *out,
-				     int (*okfn)(struct sk_buff *))
+				     const struct nf_hook_state *state)
 {
 	struct nf_bridge_info *nf_bridge;
 	struct net_device *parent;
@@ -726,7 +718,7 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 	if (!nf_bridge_unshare(skb))
 		return NF_DROP;
 
-	parent = bridge_parent(out);
+	parent = bridge_parent(state->out);
 	if (!parent)
 		return NF_DROP;
 
@@ -754,23 +746,21 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 	else
 		skb->protocol = htons(ETH_P_IPV6);
 
-	NF_HOOK(pf, NF_INET_FORWARD, skb, brnf_get_logical_dev(skb, in), parent,
-		br_nf_forward_finish);
+	NF_HOOK(pf, NF_INET_FORWARD, skb, brnf_get_logical_dev(skb, state->in),
+		parent,	br_nf_forward_finish);
 
 	return NF_STOLEN;
 }
 
 static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 				      struct sk_buff *skb,
-				      const struct net_device *in,
-				      const struct net_device *out,
-				      int (*okfn)(struct sk_buff *))
+				      const struct nf_hook_state *state)
 {
 	struct net_bridge_port *p;
 	struct net_bridge *br;
 	struct net_device **d = (struct net_device **)(skb->cb);
 
-	p = br_port_get_rcu(out);
+	p = br_port_get_rcu(state->out);
 	if (p == NULL)
 		return NF_ACCEPT;
 	br = p->br;
@@ -789,9 +779,9 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 			nf_bridge_push_encap_header(skb);
 		return NF_ACCEPT;
 	}
-	*d = (struct net_device *)in;
-	NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, skb, (struct net_device *)in,
-		(struct net_device *)out, br_nf_forward_finish);
+	*d = state->in;
+	NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, skb, state->in,
+		state->out, br_nf_forward_finish);
 
 	return NF_STOLEN;
 }
@@ -859,9 +849,7 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 /* PF_BRIDGE/POST_ROUTING ********************************************/
 static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
 				       struct sk_buff *skb,
-				       const struct net_device *in,
-				       const struct net_device *out,
-				       int (*okfn)(struct sk_buff *))
+				       const struct nf_hook_state *state)
 {
 	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 	struct net_device *realoutdev = bridge_parent(skb->dev);
@@ -910,9 +898,7 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
  * for the second time. */
 static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops,
 				   struct sk_buff *skb,
-				   const struct net_device *in,
-				   const struct net_device *out,
-				   int (*okfn)(struct sk_buff *))
+				   const struct nf_hook_state *state)
 {
 	if (skb->nf_bridge &&
 	    !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) {