tcp/dccp: avoid one atomic operation for timewait hashdance

index 1356fa6a7566bf8b53632215ef8de4b153848f9b..899495589a7ea2bf693cdda42f83cec160e861b5 100644
@@ -93,8 +93,8 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 					   struct inet_timewait_death_row *dr,
 					   const int state);
 
-void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
-			   struct inet_hashinfo *hashinfo);
+void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
+			 struct inet_hashinfo *hashinfo);
 
 void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
 			  bool rearm);

index 178bb9833311f83205317b07fe64cb2e45a9f734..37ccbe62eb1af3f9dffbf63323c008cc96cd8ea1 100644
@@ -63,9 +63,10 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 		 */
 		local_bh_disable();
 		inet_twsk_schedule(tw, timeo);
-		/* Linkage updates. */
-		__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
-		inet_twsk_put(tw);
+		/* Linkage updates.
+		 * Note that access to tw after this point is illegal.
+		 */
+		inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
 		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this

index b563e0c46bac2362acccf38495546a8b6b726384..277ff69a312dca1d0bc04be4b0b36db133aaf63b 100644
@@ -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)
 {

index b079b619b60ca577d5ef20a5065fce87acecd96c..a8384b0c11f8fa589e2ed5311899b62c80a269f8 100644
@@ -316,9 +316,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		 */
 		local_bh_disable();
 		inet_twsk_schedule(tw, timeo);
-		/* Linkage updates. */
-		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
-		inet_twsk_put(tw);
+		/* Linkage updates.
+		 * Note that access to tw after this point is illegal.
+		 */
+		inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
 		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this