Merge branch 'pass_net_through_output_path'

Eric W. Biederman says:

====================
net: Pass net through the output path v2

This is the next installment of my work to pass struct net through the
output path so the code does not need to guess how to figure out which
network namespace it is in, and ultimately routes can have output
devices in another network namespace.

The first patch in this series is a fix for a bug that came in when sk
was passed through the functions in the output path, and as such is
probably a candidate for net.  At the same time my later patches depend
on it so sending the fix separately would be confusing.

The second patch in this series is another fix that for an issue that
came in when sk was passed through the output path.  I don't think it
needs a backport as I don't think anyone uses the path where the code
was incorrect.

The rest of the patchset focuses on the path from xxx_local_out to
dst_output and in the end succeeds in passing sock_net(sk) from the
socket a packet locally originates on to the dst->output function.

Given the size reduction in the code I think this counts as a cleanup as
much as feature work.

There remain a number of helper functions (like ip option processing) to
take care of before the network stack can support destination devices in
other network namespaces but with this set of changes the backbone of
the work is done.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 22 insertions, 30 deletions

diff --git a/include/net/dst.h b/include/net/dst.h
index 779206c15f8b..1279f9b09791 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 sock *sk, struct sk_buff *skb);
+	int			(*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
 
 	unsigned short		flags;
 #define DST_HOST		0x0001
@@ -365,10 +365,10 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
 	__skb_tunnel_rx(skb, dev, net);
 }
 
-int dst_discard_sk(struct sock *sk, struct sk_buff *skb);
+int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 static inline int dst_discard(struct sk_buff *skb)
 {
-	return dst_discard_sk(skb->sk, skb);
+	return dst_discard_out(&init_net, skb->sk, skb);
 }
 void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
 		int initial_obsolete, unsigned short flags);
@@ -454,13 +454,9 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout)
 }
 
 /* Output packet to network from transport.  */
-static inline int dst_output(struct sock *sk, struct sk_buff *skb)
+static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	return skb_dst(skb)->output(sk, skb);
-}
-static inline int dst_output_okfn(struct net *net, struct sock *sk, struct sk_buff *skb)
-{
-	return dst_output(sk, skb);
+	return skb_dst(skb)->output(net, sk, skb);
 }
 
 /* Input packet from network to transport.  */
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index d64253914a6a..a0d443ca16fc 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -9,6 +9,7 @@ struct kmem_cachep;
 struct net_device;
 struct sk_buff;
 struct sock;
+struct net;
 
 struct dst_ops {
 	unsigned short		family;
@@ -28,7 +29,7 @@ struct dst_ops {
 					       struct sk_buff *skb, u32 mtu);
 	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
 					    struct sk_buff *skb);
-	int			(*local_out)(struct sk_buff *skb);
+	int			(*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);
 	struct neighbour *	(*neigh_lookup)(const struct dst_entry *dst,
 						struct sk_buff *skb,
 						const void *daddr);
diff --git a/include/net/ip.h b/include/net/ip.h
index dd06ab3669f9..3c904a28d5e5 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -107,17 +107,13 @@ 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 sock *sk, struct sk_buff *skb);
-int ip_mc_output(struct sock *sk, struct sk_buff *skb);
+int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
+int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		   int (*output)(struct net *, struct sock *, struct sk_buff *));
 void ip_send_check(struct iphdr *ip);
-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_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
+int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 
 int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
 void ip_init(void);
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index fa915fa0f703..aaee6fa02cf1 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -87,7 +87,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 	int pkt_len, err;
 
 	pkt_len = skb->len - skb_inner_network_offset(skb);
-	err = ip6_local_out_sk(sk, skb);
+	err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
 
 	if (net_xmit_eval(err) == 0) {
 		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 3dde042bcd3f..e1a10b0ac0b0 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -860,14 +860,13 @@ struct dst_entry *ip6_blackhole_route(struct net *net,
  *	skb processing functions
  */
 
-int ip6_output(struct sock *sk, struct sk_buff *skb);
+int ip6_output(struct net *net, 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);
 
-int __ip6_local_out(struct sk_buff *skb);
-int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb);
-int ip6_local_out(struct sk_buff *skb);
+int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
+int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 
 /*
  *	Extension header (options) processing
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index fce0e35e74d0..66350ce3e955 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -18,7 +18,7 @@ struct lwtunnel_state {
 	__u16		type;
 	__u16		flags;
 	atomic_t	refcnt;
-	int		(*orig_output)(struct sock *sk, struct sk_buff *skb);
+	int		(*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb);
 	int		(*orig_input)(struct sk_buff *);
 	int             len;
 	__u8            data[0];
@@ -28,7 +28,7 @@ struct lwtunnel_encap_ops {
 	int (*build_state)(struct net_device *dev, struct nlattr *encap,
 			   unsigned int family, const void *cfg,
 			   struct lwtunnel_state **ts);
-	int (*output)(struct sock *sk, struct sk_buff *skb);
+	int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
 	int (*input)(struct sk_buff *skb);
 	int (*fill_encap)(struct sk_buff *skb,
 			  struct lwtunnel_state *lwtstate);
@@ -88,7 +88,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb,
 int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate);
 struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len);
 int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b);
-int lwtunnel_output(struct sock *sk, struct sk_buff *skb);
+int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int lwtunnel_input(struct sk_buff *skb);
 
 #else
@@ -160,7 +160,7 @@ static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a,
 	return 0;
 }
 
-static inline int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
+static inline int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index fd176106909a..4a9c21f9b4ea 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 sock *sk, struct sk_buff *skb);
+	int			(*output)(struct net *net, struct sock *sk, 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);
@@ -1527,7 +1527,7 @@ 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(struct net *net, struct sock *sk, 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);
@@ -1552,7 +1552,7 @@ __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 sock *sk, struct sk_buff *skb);
+int xfrm6_output(struct net *net, struct sock *sk, 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);