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>

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);

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;
 }

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)
 {

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;
 

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);

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)
 {

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

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);
 

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);
 }
 

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 @@ int br_handle_frame_finish(struct sk_buff *skb)
 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 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		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:

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);