netfilter: Pass socket pointer down through okfn().

On the output paths in particular, we have to sometimes deal with two socket contexts. First, and usually skb->sk, is the local socket that generated the frame. And second, is potentially the socket used to control a tunneling socket, such as one the encapsulates using UDP. We do not want to disassociate skb->sk when encapsulating in order to fix this, because that would break socket memory accounting. The most extreme case where this can cause huge problems is an AF_PACKET socket transmitting over a vxlan device. We hit code paths doing checks that assume they are dealing with an ipv4 socket, but are actually operating upon the AF_PACKET one. Signed-off-by: David S. Miller <davem@davemloft.net>
2026-03-06 15:25:10 -08:00 · 2015-04-05 22:19:04 -04:00
parent 1c984f8a5d
commit 7026b1ddb6
39 changed files with 277 additions and 218 deletions
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2165,8 +2165,12 @@ int dev_open(struct net_device *dev);
 int dev_close(struct net_device *dev);
 int dev_close_many(struct list_head *head, bool unlink);
 void dev_disable_lro(struct net_device *dev);
-int dev_loopback_xmit(struct sk_buff *newskb);
-int dev_queue_xmit(struct sk_buff *skb);
+int dev_loopback_xmit(struct sock *sk, struct sk_buff *newskb);
+int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb);
+static inline int dev_queue_xmit(struct sk_buff *skb)
+{
+	return dev_queue_xmit_sk(skb->sk, skb);
+}
 int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
@@ -2927,7 +2931,11 @@ static inline void dev_consume_skb_any(struct sk_buff *skb)

 int netif_rx(struct sk_buff *skb);
 int netif_rx_ni(struct sk_buff *skb);
-int netif_receive_skb(struct sk_buff *skb);
+int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb);
+static inline int netif_receive_skb(struct sk_buff *skb)
+{
+	return netif_receive_skb_sk(skb->sk, skb);
+}
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
 void napi_gro_flush(struct napi_struct *napi, bool flush_old);
 struct sk_buff *napi_get_frags(struct napi_struct *napi);
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -54,7 +54,7 @@ struct nf_hook_state {
 	struct net_device *in;
 	struct net_device *out;
 	struct sock *sk;
-	int (*okfn)(struct sk_buff *);
+	int (*okfn)(struct sock *, struct sk_buff *);
 };

 static inline void nf_hook_state_init(struct nf_hook_state *p,
@@ -63,7 +63,7 @@ static inline void nf_hook_state_init(struct nf_hook_state *p,
 				      struct net_device *indev,
 				      struct net_device *outdev,
 				      struct sock *sk,
-				      int (*okfn)(struct sk_buff *))
+				      int (*okfn)(struct sock *, struct sk_buff *))
 {
 	p->hook = hook;
 	p->thresh = thresh;
@@ -156,26 +156,29 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state);
 *	value indicates the packet has been consumed by the hook.
 */
 static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
+				 struct sock *sk,
 				 struct sk_buff *skb,
 				 struct net_device *indev,
 				 struct net_device *outdev,
-				 int (*okfn)(struct sk_buff *), int thresh)
+				 int (*okfn)(struct sock *, struct sk_buff *),
+				 int thresh)
 {
 	if (nf_hooks_active(pf, hook)) {
 		struct nf_hook_state state;

 		nf_hook_state_init(&state, hook, thresh, pf,
-				   indev, outdev, NULL, okfn);
+				   indev, outdev, sk, okfn);
 		return nf_hook_slow(skb, &state);
 	}
 	return 1;
 }

-static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
-			  struct net_device *indev, struct net_device *outdev,
-			  int (*okfn)(struct sk_buff *))
+static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk,
+			  struct sk_buff *skb, struct net_device *indev,
+			  struct net_device *outdev,
+			  int (*okfn)(struct sock *, struct sk_buff *))
 {
-	return nf_hook_thresh(pf, hook, skb, indev, outdev, okfn, INT_MIN);
+	return nf_hook_thresh(pf, hook, sk, skb, indev, outdev, okfn, INT_MIN);
 }
                   
 /* Activate hook; either okfn or kfree_skb called, unless a hook
@@ -196,35 +199,36 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
 */

 static inline int
-NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sk_buff *skb,
-	       struct net_device *in, struct net_device *out,
-	       int (*okfn)(struct sk_buff *), int thresh)
+NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sock *sk,
+	       struct sk_buff *skb, struct net_device *in,
+	       struct net_device *out,
+	       int (*okfn)(struct sock *, struct sk_buff *), int thresh)
 {
-	int ret = nf_hook_thresh(pf, hook, skb, in, out, okfn, thresh);
+	int ret = nf_hook_thresh(pf, hook, sk, skb, in, out, okfn, thresh);
 	if (ret == 1)
-		ret = okfn(skb);
+		ret = okfn(sk, skb);
 	return ret;
 }

 static inline int
-NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sk_buff *skb,
-	     struct net_device *in, struct net_device *out,
-	     int (*okfn)(struct sk_buff *), bool cond)
+NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sock *sk,
+	     struct sk_buff *skb, struct net_device *in, struct net_device *out,
+	     int (*okfn)(struct sock *, struct sk_buff *), bool cond)
 {
 	int ret;

 	if (!cond ||
-	    ((ret = nf_hook_thresh(pf, hook, skb, in, out, okfn, INT_MIN)) == 1))
-		ret = okfn(skb);
+	    ((ret = nf_hook_thresh(pf, hook, sk, skb, in, out, okfn, INT_MIN)) == 1))
+		ret = okfn(sk, skb);
 	return ret;
 }

 static inline int
-NF_HOOK(uint8_t pf, unsigned int hook, struct sk_buff *skb,
+NF_HOOK(uint8_t pf, unsigned int hook, struct sock *sk, struct sk_buff *skb,
 	struct net_device *in, struct net_device *out,
-	int (*okfn)(struct sk_buff *))
+	int (*okfn)(struct sock *, struct sk_buff *))
 {
-	return NF_HOOK_THRESH(pf, hook, skb, in, out, okfn, INT_MIN);
+	return NF_HOOK_THRESH(pf, hook, sk, skb, in, out, okfn, INT_MIN);
 }

 /* Call setsockopt() */
@@ -324,19 +328,21 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 }

 #else /* !CONFIG_NETFILTER */
-#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb)
-#define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) (okfn)(skb)
+#define NF_HOOK(pf, hook, sk, skb, indev, outdev, okfn) (okfn)(sk, skb)
+#define NF_HOOK_COND(pf, hook, sk, skb, indev, outdev, okfn, cond) (okfn)(sk, skb)
 static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
+				 struct sock *sk,
 				 struct sk_buff *skb,
 				 struct net_device *indev,
 				 struct net_device *outdev,
-				 int (*okfn)(struct sk_buff *), int thresh)
+				 int (*okfn)(struct sock *sk, struct sk_buff *), int thresh)
 {
-	return okfn(skb);
+	return okfn(sk, skb);
 }
-static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
-			  struct net_device *indev, struct net_device *outdev,
-			  int (*okfn)(struct sk_buff *))
+static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk,
+			  struct sk_buff *skb, struct net_device *indev,
+			  struct net_device *outdev,
+			  int (*okfn)(struct sock *, struct sk_buff *))
 {
 	return 1;
 }
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -30,7 +30,7 @@ static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
 	return 0;
 }

-int br_handle_frame_finish(struct sk_buff *skb);
+int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb);

 static inline void br_drop_fake_rtable(struct sk_buff *skb)
 {
--- a/include/net/dn_neigh.h
+++ b/include/net/dn_neigh.h
@@ -18,11 +18,11 @@ struct dn_neigh {

 void dn_neigh_init(void);
 void dn_neigh_cleanup(void);
-int dn_neigh_router_hello(struct sk_buff *skb);
-int dn_neigh_endnode_hello(struct sk_buff *skb);
+int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb);
+int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb);
 void dn_neigh_pointopoint_hello(struct sk_buff *skb);
 int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n);
-int dn_to_neigh_output(struct sk_buff *skb);
+int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb);

 extern struct neigh_table dn_neigh_table;

--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -108,7 +108,8 @@ int ip_local_deliver(struct sk_buff *skb);
 int ip_mr_input(struct sk_buff *skb);
 int ip_output(struct sock *sk, struct sk_buff *skb);
 int ip_mc_output(struct sock *sk, struct sk_buff *skb);
-int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
+int ip_fragment(struct sock *sk, struct sk_buff *skb,
+		int (*output)(struct sock *, struct sk_buff *));
 int ip_do_nat(struct sk_buff *skb);
 void ip_send_check(struct iphdr *ip);
 int __ip_local_out(struct sk_buff *skb);
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -170,7 +170,8 @@ static inline bool ipv6_anycast_destination(const struct sk_buff *skb)
 	return rt->rt6i_flags & RTF_ANYCAST;
 }

-int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
+int ip6_fragment(struct sock *sk, struct sk_buff *skb,
+		 int (*output)(struct sock *, struct sk_buff *));

 static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 {
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -769,7 +769,7 @@ static inline u8 ip6_tclass(__be32 flowinfo)
 int ipv6_rcv(struct sk_buff *skb, struct net_device *dev,
 	     struct packet_type *pt, struct net_device *orig_dev);

-int ip6_rcv_finish(struct sk_buff *skb);
+int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb);

 /*
 *	upper-layer output functions
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -332,7 +332,7 @@ struct xfrm_state_afinfo {
 	int			(*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n);
 	int			(*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n);
 	int			(*output)(struct sock *sk, struct sk_buff *skb);
-	int			(*output_finish)(struct sk_buff *skb);
+	int			(*output_finish)(struct sock *sk, struct sk_buff *skb);
 	int			(*extract_input)(struct xfrm_state *x,
 						 struct sk_buff *skb);
 	int			(*extract_output)(struct xfrm_state *x,
@@ -1503,7 +1503,7 @@ int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
 int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
 int xfrm_output_resume(struct sk_buff *skb, int err);
-int xfrm_output(struct sk_buff *skb);
+int xfrm_output(struct sock *sk, struct sk_buff *skb);
 int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 void xfrm_local_error(struct sk_buff *skb, int mtu);
 int xfrm4_extract_header(struct sk_buff *skb);
@@ -1524,7 +1524,7 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
 int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm4_output(struct sock *sk, struct sk_buff *skb);
-int xfrm4_output_finish(struct sk_buff *skb);
+int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb);
 int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err);
 int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol);
 int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol);
@@ -1549,7 +1549,7 @@ __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr);
 int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm6_output(struct sock *sk, struct sk_buff *skb);
-int xfrm6_output_finish(struct sk_buff *skb);
+int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb);
 int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
 			  u8 **prevhdr);

--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -35,7 +35,7 @@ static inline int should_deliver(const struct net_bridge_port *p,
 		p->state == BR_STATE_FORWARDING;
 }

-int br_dev_queue_push_xmit(struct sk_buff *skb)
+int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb)
 {
 	if (!is_skb_forwardable(skb->dev, skb)) {
 		kfree_skb(skb);
@@ -49,9 +49,10 @@ int br_dev_queue_push_xmit(struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);

-int br_forward_finish(struct sk_buff *skb)
+int br_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, skb, NULL, skb->dev,
+	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, sk, skb,
+		       NULL, skb->dev,
 		       br_dev_queue_push_xmit);

 }
@@ -75,7 +76,8 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
 		return;
 	}

-	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
+	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb,
+		NULL, skb->dev,
 		br_forward_finish);
 }

@@ -96,7 +98,8 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
 	skb->dev = to->dev;
 	skb_forward_csum(skb);

-	NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev,
+	NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, NULL, skb,
+		indev, skb->dev,
 		br_forward_finish);
 }

--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -55,8 +55,9 @@ static int br_pass_frame_up(struct sk_buff *skb)
 	if (!skb)
 		return NET_RX_DROP;

-	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
-		       netif_receive_skb);
+	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb,
+		       indev, NULL,
+		       netif_receive_skb_sk);
 }

 static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
@@ -119,7 +120,7 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
 }

 /* note: already called with rcu_read_lock */
-int br_handle_frame_finish(struct sk_buff *skb)
+int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb)
 {
 	const unsigned char *dest = eth_hdr(skb)->h_dest;
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
@@ -207,7 +208,7 @@ drop:
 EXPORT_SYMBOL_GPL(br_handle_frame_finish);

 /* note: already called with rcu_read_lock */
-static int br_handle_local_finish(struct sk_buff *skb)
+static int br_handle_local_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
 	u16 vid = 0;
@@ -277,8 +278,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		}

 		/* Deliver packet to local host only */
-		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev,
-			    NULL, br_handle_local_finish)) {
+		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb,
+			    skb->dev, NULL, br_handle_local_finish)) {
 			return RX_HANDLER_CONSUMED; /* consumed by filter */
 		} else {
 			*pskb = skb;
@@ -302,7 +303,8 @@ forward:
 		if (ether_addr_equal(p->br->dev->dev_addr, dest))
 			skb->pkt_type = PACKET_HOST;

-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+		NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, NULL, skb,
+			skb->dev, NULL,
 			br_handle_frame_finish);
 		break;
 	default:
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -814,7 +814,8 @@ static void __br_multicast_send_query(struct net_bridge *br,

 	if (port) {
 		skb->dev = port->dev;
-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
+		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb,
+			NULL, skb->dev,
 			br_dev_queue_push_xmit);
 	} else {
 		br_multicast_select_own_querier(br, ip, skb);
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -261,7 +261,7 @@ static void nf_bridge_update_protocol(struct sk_buff *skb)
 /* PF_BRIDGE/PRE_ROUTING *********************************************/
 /* Undo the changes made for ip6tables PREROUTING and continue the
 * bridge PRE_ROUTING hook. */
-static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
+static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 	struct rtable *rt;
@@ -282,7 +282,8 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
 	skb->dev = nf_bridge->physindev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
-	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb,
+		       skb->dev, NULL,
 		       br_handle_frame_finish, 1);

 	return 0;
@@ -293,7 +294,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
 * don't, we use the neighbour framework to find out. In both cases, we make
 * sure that br_handle_frame_finish() is called afterwards.
 */
-static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
+static int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 	struct neighbour *neigh;
@@ -310,7 +311,7 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
 		if (neigh->hh.hh_len) {
 			neigh_hh_bridge(&neigh->hh, skb);
 			skb->dev = nf_bridge->physindev;
-			ret = br_handle_frame_finish(skb);
+			ret = br_handle_frame_finish(sk, skb);
 		} else {
 			/* the neighbour function below overwrites the complete
 			 * MAC header, so we save the Ethernet source address and
@@ -387,7 +388,7 @@ static bool dnat_took_place(const struct sk_buff *skb)
 * device, we proceed as if ip_route_input() succeeded. If it differs from the
 * logical bridge port or if ip_route_output_key() fails we drop the packet.
 */
-static int br_nf_pre_routing_finish(struct sk_buff *skb)
+static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	struct iphdr *iph = ip_hdr(skb);
@@ -440,7 +441,7 @@ bridged_dnat:
 				nf_bridge_push_encap_header(skb);
 				NF_HOOK_THRESH(NFPROTO_BRIDGE,
 					       NF_BR_PRE_ROUTING,
-					       skb, skb->dev, NULL,
+					       sk, skb, skb->dev, NULL,
 					       br_nf_pre_routing_finish_bridge,
 					       1);
 				return 0;
@@ -460,7 +461,8 @@ bridged_dnat:
 	skb->dev = nf_bridge->physindev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
-	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb,
+		       skb->dev, NULL,
 		       br_handle_frame_finish, 1);

 	return 0;
@@ -596,7 +598,8 @@ static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
 		return NF_DROP;

 	skb->protocol = htons(ETH_P_IPV6);
-	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->sk, skb,
+		skb->dev, NULL,
 		br_nf_pre_routing_finish_ipv6);

 	return NF_STOLEN;
@@ -651,7 +654,8 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,

 	skb->protocol = htons(ETH_P_IP);

-	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->sk, skb,
+		skb->dev, NULL,
 		br_nf_pre_routing_finish);

 	return NF_STOLEN;
@@ -674,7 +678,7 @@ static unsigned int br_nf_local_in(const struct nf_hook_ops *ops,
 }

 /* PF_BRIDGE/FORWARD *************************************************/
-static int br_nf_forward_finish(struct sk_buff *skb)
+static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 	struct net_device *in;
@@ -691,8 +695,8 @@ static int br_nf_forward_finish(struct sk_buff *skb)
 	}
 	nf_bridge_push_encap_header(skb);

-	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, in,
-		       skb->dev, br_forward_finish, 1);
+	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, sk, skb,
+		       in, skb->dev, br_forward_finish, 1);
 	return 0;
 }

@@ -746,7 +750,8 @@ 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, state->in),
+	NF_HOOK(pf, NF_INET_FORWARD, NULL, skb,
+		brnf_get_logical_dev(skb, state->in),
 		parent,	br_nf_forward_finish);

 	return NF_STOLEN;
@@ -780,8 +785,8 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 		return NF_ACCEPT;
 	}
 	*d = state->in;
-	NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, skb, state->in,
-		state->out, br_nf_forward_finish);
+	NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, state->sk, skb,
+		state->in, state->out, br_nf_forward_finish);

 	return NF_STOLEN;
 }
@@ -804,24 +809,24 @@ static bool nf_bridge_copy_header(struct sk_buff *skb)
 	return true;
 }

-static int br_nf_push_frag_xmit(struct sk_buff *skb)
+static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb)
 {
 	if (!nf_bridge_copy_header(skb)) {
 		kfree_skb(skb);
 		return 0;
 	}

-	return br_dev_queue_push_xmit(skb);
+	return br_dev_queue_push_xmit(sk, skb);
 }

-static int br_nf_dev_queue_xmit(struct sk_buff *skb)
+static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
 {
 	int ret;
 	int frag_max_size;
 	unsigned int mtu_reserved;

 	if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP))
-		return br_dev_queue_push_xmit(skb);
+		return br_dev_queue_push_xmit(sk, skb);

 	mtu_reserved = nf_bridge_mtu_reduction(skb);
 	/* This is wrong! We should preserve the original fragment
@@ -833,16 +838,16 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 			/* Drop invalid packet */
 			return NF_DROP;
 		IPCB(skb)->frag_max_size = frag_max_size;
-		ret = ip_fragment(skb, br_nf_push_frag_xmit);
+		ret = ip_fragment(sk, skb, br_nf_push_frag_xmit);
 	} else
-		ret = br_dev_queue_push_xmit(skb);
+		ret = br_dev_queue_push_xmit(sk, skb);

 	return ret;
 }
 #else
-static int br_nf_dev_queue_xmit(struct sk_buff *skb)
+static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
 {
-        return br_dev_queue_push_xmit(skb);
+        return br_dev_queue_push_xmit(sk, skb);
 }
 #endif

@@ -887,7 +892,8 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
 	else
 		skb->protocol = htons(ETH_P_IPV6);

-	NF_HOOK(pf, NF_INET_POST_ROUTING, skb, NULL, realoutdev,
+	NF_HOOK(pf, NF_INET_POST_ROUTING, state->sk, skb,
+		NULL, realoutdev,
 		br_nf_dev_queue_xmit);

 	return NF_STOLEN;
@@ -927,7 +933,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 	skb_copy_to_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN),
 				       skb->nf_bridge->data, ETH_HLEN-ETH_ALEN);
 	skb->dev = nf_bridge->physindev;
-	br_handle_frame_finish(skb);
+	br_handle_frame_finish(NULL, skb);
 }

 static int br_nf_dev_xmit(struct sk_buff *skb)
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -410,10 +410,10 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,

 /* br_forward.c */
 void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb);
-int br_dev_queue_push_xmit(struct sk_buff *skb);
+int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb);
 void br_forward(const struct net_bridge_port *to,
 		struct sk_buff *skb, struct sk_buff *skb0);
-int br_forward_finish(struct sk_buff *skb);
+int br_forward_finish(struct sock *sk, struct sk_buff *skb);
 void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast);
 void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
 		      struct sk_buff *skb2, bool unicast);
@@ -431,7 +431,7 @@ void br_port_flags_change(struct net_bridge_port *port, unsigned long mask);
 void br_manage_promisc(struct net_bridge *br);

 /* br_input.c */
-int br_handle_frame_finish(struct sk_buff *skb);
+int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb);
 rx_handler_result_t br_handle_frame(struct sk_buff **pskb);

 static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -54,8 +54,9 @@ static void br_send_bpdu(struct net_bridge_port *p,

 	skb_reset_mac_header(skb);

-	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
-		dev_queue_xmit);
+	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb,
+		NULL, skb->dev,
+		dev_queue_xmit_sk);
 }

 static inline void br_set_ticks(unsigned char *dest, int j)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2879,7 +2879,7 @@ EXPORT_SYMBOL(xmit_recursion);
 *	dev_loopback_xmit - loop back @skb
 *	@skb: buffer to transmit
 */
-int dev_loopback_xmit(struct sk_buff *skb)
+int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb)
 {
 	skb_reset_mac_header(skb);
 	__skb_pull(skb, skb_network_offset(skb));
@@ -3017,11 +3017,11 @@ out:
 	return rc;
 }

-int dev_queue_xmit(struct sk_buff *skb)
+int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb)
 {
 	return __dev_queue_xmit(skb, NULL);
 }
-EXPORT_SYMBOL(dev_queue_xmit);
+EXPORT_SYMBOL(dev_queue_xmit_sk);

 int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
 {
@@ -3853,13 +3853,13 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 *	NET_RX_SUCCESS: no congestion
 *	NET_RX_DROP: packet was dropped
 */
-int netif_receive_skb(struct sk_buff *skb)
+int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb)
 {
 	trace_netif_receive_skb_entry(skb);

 	return netif_receive_skb_internal(skb);
 }
-EXPORT_SYMBOL(netif_receive_skb);
+EXPORT_SYMBOL(netif_receive_skb_sk);

 /* Network device is going away, flush any packets still pending
 * Called with irqs disabled.
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -194,7 +194,7 @@ static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb)
 	return err;
 }

-static int dn_neigh_output_packet(struct sk_buff *skb)
+static int dn_neigh_output_packet(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct dn_route *rt = (struct dn_route *)dst;
@@ -206,7 +206,8 @@ static int dn_neigh_output_packet(struct sk_buff *skb)
 /*
 * For talking to broadcast devices: Ethernet & PPP
 */
-static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb)
+static int dn_long_output(struct neighbour *neigh, struct sock *sk,
+			  struct sk_buff *skb)
 {
 	struct net_device *dev = neigh->dev;
 	int headroom = dev->hard_header_len + sizeof(struct dn_long_packet) + 3;
@@ -245,14 +246,15 @@ static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb)

 	skb_reset_network_header(skb);

-	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, skb, NULL,
-		       neigh->dev, dn_neigh_output_packet);
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb,
+		       NULL, neigh->dev, dn_neigh_output_packet);
 }

 /*
 * For talking to pointopoint and multidrop devices: DDCMP and X.25
 */
-static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb)
+static int dn_short_output(struct neighbour *neigh, struct sock *sk,
+			   struct sk_buff *skb)
 {
 	struct net_device *dev = neigh->dev;
 	int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2;
@@ -284,8 +286,8 @@ static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb)

 	skb_reset_network_header(skb);

-	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, skb, NULL,
-		       neigh->dev, dn_neigh_output_packet);
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb,
+		       NULL, neigh->dev, dn_neigh_output_packet);
 }

 /*
@@ -293,7 +295,8 @@ static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb)
 * Phase 3 output is the same as short output, execpt that
 * it clears the area bits before transmission.
 */
-static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb)
+static int dn_phase3_output(struct neighbour *neigh, struct sock *sk,
+			    struct sk_buff *skb)
 {
 	struct net_device *dev = neigh->dev;
 	int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2;
@@ -324,11 +327,11 @@ static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb)

 	skb_reset_network_header(skb);

-	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, skb, NULL,
-		       neigh->dev, dn_neigh_output_packet);
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb,
+		       NULL, neigh->dev, dn_neigh_output_packet);
 }

-int dn_to_neigh_output(struct sk_buff *skb)
+int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct dn_route *rt = (struct dn_route *) dst;
@@ -347,11 +350,11 @@ int dn_to_neigh_output(struct sk_buff *skb)
 	rcu_read_unlock();

 	if (dn->flags & DN_NDFLAG_P3)
-		return dn_phase3_output(neigh, skb);
+		return dn_phase3_output(neigh, sk, skb);
 	if (use_long)
-		return dn_long_output(neigh, skb);
+		return dn_long_output(neigh, sk, skb);
 	else
-		return dn_short_output(neigh, skb);
+		return dn_short_output(neigh, sk, skb);
 }

 /*
@@ -372,7 +375,7 @@ void dn_neigh_pointopoint_hello(struct sk_buff *skb)
 /*
 * Ethernet router hello message received
 */
-int dn_neigh_router_hello(struct sk_buff *skb)
+int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb)
 {
 	struct rtnode_hello_message *msg = (struct rtnode_hello_message *)skb->data;

@@ -434,7 +437,7 @@ int dn_neigh_router_hello(struct sk_buff *skb)
 /*
 * Endnode hello message received
 */
-int dn_neigh_endnode_hello(struct sk_buff *skb)
+int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb)
 {
 	struct endnode_hello_message *msg = (struct endnode_hello_message *)skb->data;
 	struct neighbour *neigh;
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -714,7 +714,7 @@ out:
 	return ret;
 }

-static int dn_nsp_rx_packet(struct sk_buff *skb)
+static int dn_nsp_rx_packet(struct sock *sk2, struct sk_buff *skb)
 {
 	struct dn_skb_cb *cb = DN_SKB_CB(skb);
 	struct sock *sk = NULL;
@@ -814,7 +814,8 @@ free_out:

 int dn_nsp_rx(struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, skb, skb->dev, NULL,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, NULL, skb,
+		       skb->dev, NULL,
 		       dn_nsp_rx_packet);
 }

--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -512,7 +512,7 @@ static int dn_return_long(struct sk_buff *skb)
 *
 * Returns: result of input function if route is found, error code otherwise
 */
-static int dn_route_rx_packet(struct sk_buff *skb)
+static int dn_route_rx_packet(struct sock *sk, struct sk_buff *skb)
 {
 	struct dn_skb_cb *cb;
 	int err;
@@ -573,7 +573,8 @@ static int dn_route_rx_long(struct sk_buff *skb)
 	ptr++;
 	cb->hops = *ptr++; /* Visit Count */

-	return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, skb, skb->dev, NULL,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, NULL, skb,
+		       skb->dev, NULL,
 		       dn_route_rx_packet);

 drop_it:
@@ -600,7 +601,8 @@ static int dn_route_rx_short(struct sk_buff *skb)
 	ptr += 2;
 	cb->hops = *ptr & 0x3f;

-	return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, skb, skb->dev, NULL,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, NULL, skb,
+		       skb->dev, NULL,
 		       dn_route_rx_packet);

 drop_it:
@@ -608,7 +610,7 @@ drop_it:
 	return NET_RX_DROP;
 }

-static int dn_route_discard(struct sk_buff *skb)
+static int dn_route_discard(struct sock *sk, struct sk_buff *skb)
 {
 	/*
 	 * I know we drop the packet here, but thats considered success in
@@ -618,7 +620,7 @@ static int dn_route_discard(struct sk_buff *skb)
 	return NET_RX_SUCCESS;
 }

-static int dn_route_ptp_hello(struct sk_buff *skb)
+static int dn_route_ptp_hello(struct sock *sk, struct sk_buff *skb)
 {
 	dn_dev_hello(skb);
 	dn_neigh_pointopoint_hello(skb);
@@ -704,22 +706,22 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type
 		switch (flags & DN_RT_CNTL_MSK) {
 		case DN_RT_PKT_HELO:
 			return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO,
-				       skb, skb->dev, NULL,
+				       NULL, skb, skb->dev, NULL,
 				       dn_route_ptp_hello);

 		case DN_RT_PKT_L1RT:
 		case DN_RT_PKT_L2RT:
 			return NF_HOOK(NFPROTO_DECNET, NF_DN_ROUTE,
-				       skb, skb->dev, NULL,
+				       NULL, skb, skb->dev, NULL,
 				       dn_route_discard);
 		case DN_RT_PKT_ERTH:
 			return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO,
-				       skb, skb->dev, NULL,
+				       NULL, skb, skb->dev, NULL,
 				       dn_neigh_router_hello);

 		case DN_RT_PKT_EEDH:
 			return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO,
-				       skb, skb->dev, NULL,
+				       NULL, skb, skb->dev, NULL,
 				       dn_neigh_endnode_hello);
 		}
 	} else {
@@ -768,7 +770,8 @@ static int dn_output(struct sock *sk, struct sk_buff *skb)
 	cb->rt_flags |= DN_RT_F_IE;
 	cb->hops = 0;

-	return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, skb, NULL, dev,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, sk, skb,
+		       NULL, dev,
 		       dn_to_neigh_output);

 error:
@@ -816,7 +819,8 @@ static int dn_forward(struct sk_buff *skb)
 	if (rt->rt_flags & RTCF_DOREDIRECT)
 		cb->rt_flags |= DN_RT_F_IE;

-	return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, skb, dev, skb->dev,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, NULL, skb,
+		       dev, skb->dev,
 		       dn_to_neigh_output);

 drop:
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -591,7 +591,8 @@ EXPORT_SYMBOL(arp_create);
 void arp_xmit(struct sk_buff *skb)
 {
 	/* Send it off, maybe filter it using firewalling first.  */
-	NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, skb, NULL, skb->dev, dev_queue_xmit);
+	NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, NULL, skb,
+		NULL, skb->dev, dev_queue_xmit_sk);
 }
 EXPORT_SYMBOL(arp_xmit);

@@ -625,7 +626,7 @@ EXPORT_SYMBOL(arp_send);
 *	Process an arp request.
 */

-static int arp_process(struct sk_buff *skb)
+static int arp_process(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -846,7 +847,7 @@ out:

 static void parp_redo(struct sk_buff *skb)
 {
-	arp_process(skb);
+	arp_process(NULL, skb);
 }


@@ -879,7 +880,8 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev,

 	memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));

-	return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process);
+	return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, NULL, skb,
+		       dev, NULL, arp_process);

 consumeskb:
 	consume_skb(skb);
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -57,7 +57,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 }


-static int ip_forward_finish(struct sk_buff *skb)
+static int ip_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct ip_options *opt	= &(IPCB(skb)->opt);

@@ -68,7 +68,7 @@ static int ip_forward_finish(struct sk_buff *skb)
 		ip_forward_options(skb);

 	skb_sender_cpu_clear(skb);
-	return dst_output(skb);
+	return dst_output_sk(sk, skb);
 }

 int ip_forward(struct sk_buff *skb)
@@ -136,8 +136,8 @@ int ip_forward(struct sk_buff *skb)

 	skb->priority = rt_tos2priority(iph->tos);

-	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev,
-		       rt->dst.dev, ip_forward_finish);
+	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, NULL, skb,
+		       skb->dev, rt->dst.dev, ip_forward_finish);

 sr_failed:
 	/*
--- a/Show More
+++ b/Show More