ipv6: protect skb->sk accesses from recursive dereference inside the stack

We should not consult skb->sk for output decisions in xmit recursion
levels > 0 in the stack. Otherwise local socket settings could influence
the result of e.g. tunnel encapsulation process.

ipv6 does not conform with this in three places:

1) ip6_fragment: we do consult ipv6_npinfo for frag_size

2) sk_mc_loop in ipv6 uses skb->sk and checks if we should
   loop the packet back to the local socket

3) ip6_skb_dst_mtu could query the settings from the user socket and
   force a wrong MTU

Furthermore:
In sk_mc_loop we could potentially land in WARN_ON(1) if we use a
PF_PACKET socket ontop of an IPv6-backed vxlan device.

Reuse xmit_recursion as we are currently only interested in protecting
tunnel devices.

Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 34 insertions, 19 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dcf6ec27739b..278738873703 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2185,6 +2185,12 @@ void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
+DECLARE_PER_CPU(int, xmit_recursion);
+static inline int dev_recursion_level(void)
+{
+	return this_cpu_read(xmit_recursion);
+}
+
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
diff --git a/include/net/ip.h b/include/net/ip.h
index 025c61c0dffb..6cc1eafb153a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -453,22 +453,6 @@ static __inline__ void inet_reset_saddr(struct sock *sk)
 
 #endif
 
-static inline int sk_mc_loop(struct sock *sk)
-{
-	if (!sk)
-		return 1;
-	switch (sk->sk_family) {
-	case AF_INET:
-		return inet_sk(sk)->mc_loop;
-#if IS_ENABLED(CONFIG_IPV6)
-	case AF_INET6:
-		return inet6_sk(sk)->mc_loop;
-#endif
-	}
-	WARN_ON(1);
-	return 1;
-}
-
 bool ip_call_ra_chain(struct sk_buff *skb);
 
 /*
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 1d09b46c1e48..eda131d179d9 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -174,7 +174,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
 
 static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 {
-	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
+	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
+				inet6_sk(skb->sk) : NULL;
 
 	return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ?
 	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
diff --git a/include/net/sock.h b/include/net/sock.h
index ab186b1d31ff..e4079c28e6b8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1762,6 +1762,8 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
 
 struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
 
+bool sk_mc_loop(struct sock *sk);
+
 static inline bool sk_can_gso(const struct sock *sk)
 {
 	return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
diff --git a/net/core/dev.c b/net/core/dev.c
index 962ee9d71964..45109b70664e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2848,7 +2848,9 @@ static void skb_update_prio(struct sk_buff *skb)
 #define skb_update_prio(skb)
 #endif
 
-static DEFINE_PER_CPU(int, xmit_recursion);
+DEFINE_PER_CPU(int, xmit_recursion);
+EXPORT_SYMBOL(xmit_recursion);
+
 #define RECURSION_LIMIT 10
 
 /**
diff --git a/net/core/sock.c b/net/core/sock.c
index 78e89eb7eb70..71e3e5f1eaa0 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -653,6 +653,25 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
 		sock_reset_flag(sk, bit);
 }
 
+bool sk_mc_loop(struct sock *sk)
+{
+	if (dev_recursion_level())
+		return false;
+	if (!sk)
+		return true;
+	switch (sk->sk_family) {
+	case AF_INET:
+		return inet_sk(sk)->mc_loop;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		return inet6_sk(sk)->mc_loop;
+#endif
+	}
+	WARN_ON(1);
+	return true;
+}
+EXPORT_SYMBOL(sk_mc_loop);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7e80b61b51ff..36cf0ab685a0 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -542,7 +542,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
-	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
+	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
+				inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
 	unsigned int mtu, hlen, left, len;