1 files changed, 70 insertions, 30 deletions

diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 1f5d508..0fdf45e 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -14,22 +14,33 @@
 #include <net/inet_timewait_sock.h>
 #include <net/ip.h>
 
+
+/*
+ * unhash a timewait socket from established hash
+ * lock must be hold by caller
+ */
+int inet_twsk_unhash(struct inet_timewait_sock *tw)
+{
+	if (hlist_nulls_unhashed(&tw->tw_node))
+		return 0;
+
+	hlist_nulls_del_rcu(&tw->tw_node);
+	sk_nulls_node_init(&tw->tw_node);
+	return 1;
+}
+
 /* Must be called with locally disabled BHs. */
 static void __inet_twsk_kill(struct inet_timewait_sock *tw,
 			     struct inet_hashinfo *hashinfo)
 {
 	struct inet_bind_hashbucket *bhead;
 	struct inet_bind_bucket *tb;
+	int refcnt;
 	/* Unlink from established hashes. */
 	spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
 
 	spin_lock(lock);
-	if (hlist_nulls_unhashed(&tw->tw_node)) {
-		spin_unlock(lock);
-		return;
-	}
-	hlist_nulls_del_rcu(&tw->tw_node);
-	sk_nulls_node_init(&tw->tw_node);
+	refcnt = inet_twsk_unhash(tw);
 	spin_unlock(lock);
 
 	/* Disassociate with bind bucket. */
@@ -37,9 +48,12 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
 			hashinfo->bhash_size)];
 	spin_lock(&bhead->lock);
 	tb = tw->tw_tb;
-	__hlist_del(&tw->tw_bind_node);
-	tw->tw_tb = NULL;
-	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+	if (tb) {
+		__hlist_del(&tw->tw_bind_node);
+		tw->tw_tb = NULL;
+		inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+		refcnt++;
+	}
 	spin_unlock(&bhead->lock);
 #ifdef SOCK_REFCNT_DEBUG
 	if (atomic_read(&tw->tw_refcnt) != 1) {
@@ -47,7 +61,10 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
 		       tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt));
 	}
 #endif
-	inet_twsk_put(tw);
+	while (refcnt) {
+		inet_twsk_put(tw);
+		refcnt--;
+	}
 }
 
 static noinline void inet_twsk_free(struct inet_timewait_sock *tw)
@@ -101,13 +118,22 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 	 * Should be done before removing sk from established chain
 	 * because readers are lockless and search established first.
 	 */
-	atomic_inc(&tw->tw_refcnt);
 	inet_twsk_add_node_rcu(tw, &ehead->twchain);
 
 	/* Step 3: Remove SK from established hash. */
 	if (__sk_nulls_del_node_init_rcu(sk))
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 
+	/*
+	 * Notes :
+ 	 * - We initially set tw_refcnt to 0 in inet_twsk_alloc()
+	 * - We add one reference for the bhash link
+	 * - We add one reference for the ehash link
+	 * - We want this refcnt update done before allowing other
+	 *   threads to find this tw in ehash chain.
+	 */
+	atomic_add(1 + 1 + 1, &tw->tw_refcnt);
+
 	spin_unlock(lock);
 }
 
@@ -139,7 +165,12 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat
 		tw->tw_transparent  = inet->transparent;
 		tw->tw_prot	    = sk->sk_prot_creator;
 		twsk_net_set(tw, hold_net(sock_net(sk)));
-		atomic_set(&tw->tw_refcnt, 1);
+		/*
+		 * Because we use RCU lookups, we should not set tw_refcnt
+		 * to a non null value before everything is setup for this
+		 * timewait socket.
+		 */
+		atomic_set(&tw->tw_refcnt, 0);
 		inet_twsk_dead_node_init(tw);
 		__module_get(tw->tw_prot->owner);
 	}
@@ -421,37 +452,46 @@ out:
 
 EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick);
 
-void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo,
+void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 		     struct inet_timewait_death_row *twdr, int family)
 {
 	struct inet_timewait_sock *tw;
 	struct sock *sk;
 	struct hlist_nulls_node *node;
-	int h;
+	unsigned int slot;
 
-	local_bh_disable();
-	for (h = 0; h <= hashinfo->ehash_mask; h++) {
-		struct inet_ehash_bucket *head =
-			inet_ehash_bucket(hashinfo, h);
-		spinlock_t *lock = inet_ehash_lockp(hashinfo, h);
+	for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
+		struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
+restart_rcu:
+		rcu_read_lock();
 restart:
-		spin_lock(lock);
-		sk_nulls_for_each(sk, node, &head->twchain) {
-
+		sk_nulls_for_each_rcu(sk, node, &head->twchain) {
 			tw = inet_twsk(sk);
-			if (!net_eq(twsk_net(tw), net) ||
-			    tw->tw_family != family)
+			if ((tw->tw_family != family) ||
+				atomic_read(&twsk_net(tw)->count))
+				continue;
+
+			if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt)))
 				continue;
 
-			atomic_inc(&tw->tw_refcnt);
-			spin_unlock(lock);
+			if (unlikely((tw->tw_family != family) ||
+				     atomic_read(&twsk_net(tw)->count))) {
+				inet_twsk_put(tw);
+				goto restart;
+			}
+
+			rcu_read_unlock();
 			inet_twsk_deschedule(tw, twdr);
 			inet_twsk_put(tw);
-
-			goto restart;
+			goto restart_rcu;
 		}
-		spin_unlock(lock);
+		/* If the nulls value we got at the end of this lookup is
+		 * not the expected one, we must restart lookup.
+		 * We probably met an item that was moved to another chain.
+		 */
+		if (get_nulls_value(node) != slot)
+			goto restart;
+		rcu_read_unlock();
 	}
-	local_bh_enable();
 }
 EXPORT_SYMBOL_GPL(inet_twsk_purge);