ipv4: add a sock pointer to dst->output() path.

In the dst->output() path for ipv4, the code assumes the skb it has to
transmit is attached to an inet socket, specifically via
ip_mc_output() : The sk_mc_loop() test triggers a WARN_ON() when the
provider of the packet is an AF_PACKET socket.

The dst->output() method gets an additional 'struct sock *sk'
parameter. This needs a cascade of changes so that this parameter can
be propagated from vxlan to final consumer.

Fixes: 8f646c922d55 ("vxlan: keep original skb ownership")
Reported-by: lucien xin <lucien.xin@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 24 insertions, 11 deletions

diff --git a/include/net/dst.h b/include/net/dst.h
index 46ed958e0c6..71c60f42be4 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -45,7 +45,7 @@ struct dst_entry {
 	void			*__pad1;
 #endif
 	int			(*input)(struct sk_buff *);
-	int			(*output)(struct sk_buff *);
+	int			(*output)(struct sock *sk, struct sk_buff *skb);
 
 	unsigned short		flags;
 #define DST_HOST		0x0001
@@ -367,7 +367,11 @@ static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb)
 	return child;
 }
 
-int dst_discard(struct sk_buff *skb);
+int dst_discard_sk(struct sock *sk, struct sk_buff *skb);
+static inline int dst_discard(struct sk_buff *skb)
+{
+	return dst_discard_sk(skb->sk, skb);
+}
 void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
 		int initial_obsolete, unsigned short flags);
 void __dst_free(struct dst_entry *dst);
@@ -449,9 +453,13 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout)
 }
 
 /* Output packet to network from transport.  */
+static inline int dst_output_sk(struct sock *sk, struct sk_buff *skb)
+{
+	return skb_dst(skb)->output(sk, skb);
+}
 static inline int dst_output(struct sk_buff *skb)
 {
-	return skb_dst(skb)->output(skb);
+	return dst_output_sk(skb->sk, skb);
 }
 
 /* Input packet from network to transport.  */
diff --git a/include/net/ip.h b/include/net/ip.h
index 77e73d293e0..3ec2b0fb9d8 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -104,13 +104,18 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 	   struct net_device *orig_dev);
 int ip_local_deliver(struct sk_buff *skb);
 int ip_mr_input(struct sk_buff *skb);
-int ip_output(struct sk_buff *skb);
-int ip_mc_output(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_do_nat(struct sk_buff *skb);
 void ip_send_check(struct iphdr *ip);
 int __ip_local_out(struct sk_buff *skb);
-int ip_local_out(struct sk_buff *skb);
+int ip_local_out_sk(struct sock *sk, struct sk_buff *skb);
+static inline int ip_local_out(struct sk_buff *skb)
+{
+	return ip_local_out_sk(skb->sk, skb);
+}
+
 int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
 void ip_init(void);
 int ip_append_data(struct sock *sk, struct flowi4 *fl4,
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index e77c10405d5..a4daf9eb856 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -153,7 +153,7 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
 }
 
 int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);
-int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
+int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 		  __be32 src, __be32 dst, __u8 proto,
 		  __u8 tos, __u8 ttl, __be16 df, bool xnet);
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4f541f11ce6..d640925bc45 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -731,7 +731,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net,
  *	skb processing functions
  */
 
-int ip6_output(struct sk_buff *skb);
+int ip6_output(struct sock *sk, struct sk_buff *skb);
 int ip6_forward(struct sk_buff *skb);
 int ip6_input(struct sk_buff *skb);
 int ip6_mc_input(struct sk_buff *skb);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 32682ae47b3..116e9c7e19c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -333,7 +333,7 @@ struct xfrm_state_afinfo {
 						const xfrm_address_t *saddr);
 	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 sk_buff *skb);
+	int			(*output)(struct sock *sk, struct sk_buff *skb);
 	int			(*output_finish)(struct sk_buff *skb);
 	int			(*extract_input)(struct xfrm_state *x,
 						 struct sk_buff *skb);
@@ -1540,7 +1540,7 @@ 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 sk_buff *skb);
+int xfrm4_output(struct sock *sk, struct sk_buff *skb);
 int xfrm4_output_finish(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);
@@ -1565,7 +1565,7 @@ __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
 __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 sk_buff *skb);
+int xfrm6_output(struct sock *sk, struct sk_buff *skb);
 int xfrm6_output_finish(struct sk_buff *skb);
 int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
 			  u8 **prevhdr);