udp6: fix socket leak on early demux

When an early demuxed packet reaches __udp6_lib_lookup_skb(), the
sk reference is retrieved and used, but the relevant reference
count is leaked and the socket destructor is never called.
Beyond leaking the sk memory, if there are pending UDP packets
in the receive queue, even the related accounted memory is leaked.

In the long run, this will cause persistent forward allocation errors
and no UDP skbs (both ipv4 and ipv6) will be able to reach the
user-space.

Fix this by explicitly accessing the early demux reference before
the lookup, and properly decreasing the socket reference count
after usage.

Also drop the skb_steal_sock() in __udp6_lib_lookup_skb(), and
the now obsoleted comment about "socket cache".

The newly added code is derived from the current ipv4 code for the
similar path.

v1 -> v2:
  fixed the __udp6_lib_rcv() return code for resubmission,
  as suggested by Eric

Reported-by: Sam Edwards <CFSworks@gmail.com>
Reported-by: Marc Haber <mh+netdev@zugschlus.de>
Fixes: 5425077d73e0 ("net: ipv6: Add early demux handler for UDP unicast")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/udp.h b/include/net/udp.h
index 56ce2d2a612d33fedaf8372faddd0a1d205bc64d..cc8036987dcb885012c6c5eda0fb2bed2e588841 100644 (file)
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -260,6 +260,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
 }
 
 void udp_v4_early_demux(struct sk_buff *skb);
+void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
 int udp_get_port(struct sock *sk, unsigned short snum,
                 int (*saddr_cmp)(const struct sock *,
                                  const struct sock *));

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index fac7cb9e3b0f7a029f5c89f0670c66481d4a20df..e6276fa3750b909615668fddf84495369bd7d369 100644 (file)
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1928,7 +1928,7 @@ drop:
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
-static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
        struct dst_entry *old;
 
@@ -1937,6 +1937,7 @@ static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
                dst_release(old);
        }
 }
+EXPORT_SYMBOL(udp_sk_rx_dst_set);
 
 /*
  *     Multicasts and broadcasts go to each listener.

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4a3e65626e8baddf5d7d1c246e6e5fded2b08b8a..98fe4560e24c4ec530b0ae993b6ecd3a94d8d82c 100644 (file)
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -291,11 +291,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
                                          struct udp_table *udptable)
 {
        const struct ipv6hdr *iph = ipv6_hdr(skb);
-       struct sock *sk;
 
-       sk = skb_steal_sock(skb);
-       if (unlikely(sk))
-               return sk;
        return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
                                 &iph->daddr, dport, inet6_iif(skb),
                                 udptable, skb);
@@ -804,6 +800,24 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
        if (udp6_csum_init(skb, uh, proto))
                goto csum_error;
 
+       /* Check if the socket is already available, e.g. due to early demux */
+       sk = skb_steal_sock(skb);
+       if (sk) {
+               struct dst_entry *dst = skb_dst(skb);
+               int ret;
+
+               if (unlikely(sk->sk_rx_dst != dst))
+                       udp_sk_rx_dst_set(sk, dst);
+
+               ret = udpv6_queue_rcv_skb(sk, skb);
+               sock_put(sk);
+
+               /* a return value > 0 means to resubmit the input */
+               if (ret > 0)
+                       return ret;
+               return 0;
+       }
+
        /*
         *      Multicast receive code
         */
@@ -812,11 +826,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
                                saddr, daddr, udptable, proto);
 
        /* Unicast */
-
-       /*
-        * check socket cache ... must talk to Alan about his plans
-        * for sock caches... i'll skip this for now.
-        */
        sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
        if (sk) {
                int ret;