udp: ipv4: must add synchronization in udp_sk_rx_dst_set()

Unlike TCP, UDP input path does not hold the socket lock.

Before messing with sk->sk_rx_dst, we must use a spinlock, otherwise
multiple cpus could leak a refcount.

This patch also takes care of renewing a stale dst entry.
(When the sk->sk_rx_dst would not be used by IP early demux)

Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Shawn Bohrer <sbohrer@rgmadvisors.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 16d246a51a02a128c97bc92b858b28333177fa06..62c19fdd102d9bb1f3d8757c6de1debd6533ed50 100644 (file)
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1599,12 +1599,21 @@ static void flush_stack(struct sock **stack, unsigned int count,
                kfree_skb(skb1);
 }
 
-static void udp_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+/* For TCP sockets, sk_rx_dst is protected by socket lock
+ * For UDP, we use sk_dst_lock to guard against concurrent changes.
+ */
+static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
-       struct dst_entry *dst = skb_dst(skb);
+       struct dst_entry *old;
 
-       dst_hold(dst);
-       sk->sk_rx_dst = dst;
+       spin_lock(&sk->sk_dst_lock);
+       old = sk->sk_rx_dst;
+       if (likely(old != dst)) {
+               dst_hold(dst);
+               sk->sk_rx_dst = dst;
+               dst_release(old);
+       }
+       spin_unlock(&sk->sk_dst_lock);
 }
 
 /*
@@ -1737,10 +1746,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 
        sk = skb_steal_sock(skb);
        if (sk) {
+               struct dst_entry *dst = skb_dst(skb);
                int ret;
 
-               if (unlikely(sk->sk_rx_dst == NULL))
-                       udp_sk_rx_dst_set(sk, skb);
+               if (unlikely(sk->sk_rx_dst != dst))
+                       udp_sk_rx_dst_set(sk, dst);
 
                ret = udp_queue_rcv_skb(sk, skb);
                sock_put(sk);