tcp/dccp: avoid one atomic operation for timewait hashdance

First, rename __inet_twsk_hashdance() to inet_twsk_hashdance()

Then, remove one inet_twsk_put() by setting tw_refcnt to 3 instead
of 4, but adding a fat warning that we do not have the right to access
tw anymore after inet_twsk_hashdance()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index b563e0c..277ff69 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -97,7 +97,7 @@ static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
  * Essentially we whip up a timewait bucket, copy the relevant info into it
  * from the SK, and mess with hash chains and list linkage.
  */
-void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
+void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 			   struct inet_hashinfo *hashinfo)
 {
 	const struct inet_sock *inet = inet_sk(sk);
@@ -119,18 +119,6 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 
 	spin_lock(lock);
 
-	/*
-	 * Step 2: Hash TW into tcp ehash chain.
-	 * Notes :
-	 * - tw_refcnt is set to 4 because :
-	 * - We have one reference from bhash chain.
-	 * - We have one reference from ehash chain.
-	 * - We have one reference from timer.
-	 * - One reference for ourself (our caller will release it).
-	 * We can use atomic_set() because prior spin_lock()/spin_unlock()
-	 * committed into memory all tw fields.
-	 */
-	refcount_set(&tw->tw_refcnt, 4);
 	inet_twsk_add_node_rcu(tw, &ehead->chain);
 
 	/* Step 3: Remove SK from hash chain */
@@ -138,8 +126,19 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 
 	spin_unlock(lock);
+
+	/* tw_refcnt is set to 3 because we have :
+	 * - one reference for bhash chain.
+	 * - one reference for ehash chain.
+	 * - one reference for timer.
+	 * We can use atomic_set() because prior spin_lock()/spin_unlock()
+	 * committed into memory all tw fields.
+	 * Also note that after this point, we lost our implicit reference
+	 * so we are not allowed to use tw anymore.
+	 */
+	refcount_set(&tw->tw_refcnt, 3);
 }
-EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
+EXPORT_SYMBOL_GPL(inet_twsk_hashdance);
 
 static void tw_timer_handler(struct timer_list *t)
 {