tcp/dccp: remove twchain

TCP listener refactoring, part 3 :

Our goal is to hash SYN_RECV sockets into main ehash for fast lookup,
and parallel SYN processing.

Current inet_ehash_bucket contains two chains, one for ESTABLISH (and
friend states) sockets, another for TIME_WAIT sockets only.

As the hash table is sized to get at most one socket per bucket, it
makes little sense to have separate twchain, as it makes the lookup
slightly more complicated, and doubles hash table memory usage.

If we make sure all socket types have the lookup keys at the same
offsets, we can use a generic and faster lookup. It turns out TIME_WAIT
and ESTABLISHED sockets already have common lookup fields for IPv4.

[ INET_TW_MATCH() is no longer needed ]

I'll provide a follow-up to factorize IPv6 lookup as well, to remove
INET6_TW_MATCH()

This way, SYN_RECV pseudo sockets will be supported the same.

A new sock_gen_put() helper is added, doing either a sock_put() or
inet_twsk_put() [ and will support SYN_RECV later ].

Note this helper should only be called in real slow path, when rcu
lookup found a socket that was moved to another identity (freed/reused
immediately), but could eventually be used in other contexts, like
sock_edemux()

Before patch :

dmesg | grep "TCP established"

TCP established hash table entries: 524288 (order: 11, 8388608 bytes)

After patch :

TCP established hash table entries: 524288 (order: 10, 4194304 bytes)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 28 insertions, 27 deletions

diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 9bcd8f7234ec..6d592f8555fb 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -87,19 +87,11 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
 	refcnt += inet_twsk_bind_unhash(tw, hashinfo);
 	spin_unlock(&bhead->lock);
 
-#ifdef SOCK_REFCNT_DEBUG
-	if (atomic_read(&tw->tw_refcnt) != 1) {
-		pr_debug("%s timewait_sock %p refcnt=%d\n",
-			 tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt));
-	}
-#endif
-	while (refcnt) {
-		inet_twsk_put(tw);
-		refcnt--;
-	}
+	BUG_ON(refcnt >= atomic_read(&tw->tw_refcnt));
+	atomic_sub(refcnt, &tw->tw_refcnt);
 }
 
-static noinline void inet_twsk_free(struct inet_timewait_sock *tw)
+void inet_twsk_free(struct inet_timewait_sock *tw)
 {
 	struct module *owner = tw->tw_prot->owner;
 	twsk_destructor((struct sock *)tw);
@@ -118,6 +110,18 @@ void inet_twsk_put(struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL_GPL(inet_twsk_put);
 
+static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
+				   struct hlist_nulls_head *list)
+{
+	hlist_nulls_add_head_rcu(&tw->tw_node, list);
+}
+
+static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
+				    struct hlist_head *list)
+{
+	hlist_add_head(&tw->tw_bind_node, list);
+}
+
 /*
  * Enter the time wait state. This is called with locally disabled BH.
  * Essentially we whip up a timewait bucket, copy the relevant info into it
@@ -146,26 +150,21 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 	spin_lock(lock);
 
 	/*
-	 * Step 2: Hash TW into TIMEWAIT chain.
-	 * Should be done before removing sk from established chain
-	 * because readers are lockless and search established first.
+	 * Step 2: Hash TW into tcp ehash chain.
+	 * Notes :
+	 * - tw_refcnt is set to 3 because :
+	 * - We have one reference from bhash chain.
+	 * - We have one reference from ehash chain.
+	 * We can use atomic_set() because prior spin_lock()/spin_unlock()
+	 * committed into memory all tw fields.
 	 */
-	inet_twsk_add_node_rcu(tw, &ehead->twchain);
+	atomic_set(&tw->tw_refcnt, 1 + 1 + 1);
+	inet_twsk_add_node_rcu(tw, &ehead->chain);
 
-	/* Step 3: Remove SK from established hash. */
+	/* Step 3: Remove SK from hash chain */
 	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);
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
@@ -490,7 +489,9 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 restart_rcu:
 		rcu_read_lock();
 restart:
-		sk_nulls_for_each_rcu(sk, node, &head->twchain) {
+		sk_nulls_for_each_rcu(sk, node, &head->chain) {
+			if (sk->sk_state != TCP_TIME_WAIT)
+				continue;
 			tw = inet_twsk(sk);
 			if ((tw->tw_family != family) ||
 				atomic_read(&twsk_net(tw)->count))