tcp: Update bind bucket state on port release

Today, once an inet_bind_bucket enters a state where fastreuse >= 0 or
fastreuseport >= 0 after a socket is explicitly bound to a port, it remains
in that state until all sockets are removed and the bucket is destroyed.

In this state, the bucket is skipped during ephemeral port selection in
connect(). For applications using a reduced ephemeral port
range (IP_LOCAL_PORT_RANGE socket option), this can cause faster port
exhaustion since blocked buckets are excluded from reuse.

The reason the bucket state isn't updated on port release is unclear.
Possibly a performance trade-off to avoid scanning bucket owners, or just
an oversight.

Fix it by recalculating the bucket state when a socket releases a port. To
limit overhead, each inet_bind2_bucket stores its own (fastreuse,
fastreuseport) state. On port release, only the relevant port-addr bucket
is scanned, and the overall state is derived from these.

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250917-update-bind-bucket-state-on-unhash-v5-1-57168b661b47@cloudflare.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 43 insertions, 1 deletions

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 4eb933f56fe6..b7024e3d9ac3 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -58,6 +58,14 @@ static u32 sk_ehashfn(const struct sock *sk)
 			    sk->sk_daddr, sk->sk_dport);
 }
 
+static bool sk_is_connect_bind(const struct sock *sk)
+{
+	if (sk->sk_state == TCP_TIME_WAIT)
+		return inet_twsk(sk)->tw_connect_bind;
+	else
+		return sk->sk_userlocks & SOCK_CONNECT_BIND;
+}
+
 /*
  * Allocate and initialize a new local port bind bucket.
  * The bindhash mutex for snum's hash chain must be held here.
@@ -87,10 +95,22 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
  */
 void inet_bind_bucket_destroy(struct inet_bind_bucket *tb)
 {
+	const struct inet_bind2_bucket *tb2;
+
 	if (hlist_empty(&tb->bhash2)) {
 		hlist_del_rcu(&tb->node);
 		kfree_rcu(tb, rcu);
+		return;
+	}
+
+	if (tb->fastreuse == -1 && tb->fastreuseport == -1)
+		return;
+	hlist_for_each_entry(tb2, &tb->bhash2, bhash_node) {
+		if (tb2->fastreuse != -1 || tb2->fastreuseport != -1)
+			return;
 	}
+	tb->fastreuse = -1;
+	tb->fastreuseport = -1;
 }
 
 bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net *net,
@@ -121,6 +141,8 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2,
 #else
 	tb2->rcv_saddr = sk->sk_rcv_saddr;
 #endif
+	tb2->fastreuse = 0;
+	tb2->fastreuseport = 0;
 	INIT_HLIST_HEAD(&tb2->owners);
 	hlist_add_head(&tb2->node, &head->chain);
 	hlist_add_head(&tb2->bhash_node, &tb->bhash2);
@@ -143,11 +165,23 @@ struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
 /* Caller must hold hashbucket lock for this tb with local BH disabled */
 void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
 {
+	const struct sock *sk;
+
 	if (hlist_empty(&tb->owners)) {
 		__hlist_del(&tb->node);
 		__hlist_del(&tb->bhash_node);
 		kmem_cache_free(cachep, tb);
+		return;
 	}
+
+	if (tb->fastreuse == -1 && tb->fastreuseport == -1)
+		return;
+	sk_for_each_bound(sk, &tb->owners) {
+		if (!sk_is_connect_bind(sk))
+			return;
+	}
+	tb->fastreuse = -1;
+	tb->fastreuseport = -1;
 }
 
 static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
@@ -191,6 +225,7 @@ static void __inet_put_port(struct sock *sk)
 	tb = inet_csk(sk)->icsk_bind_hash;
 	inet_csk(sk)->icsk_bind_hash = NULL;
 	inet_sk(sk)->inet_num = 0;
+	sk->sk_userlocks &= ~SOCK_CONNECT_BIND;
 
 	spin_lock(&head2->lock);
 	if (inet_csk(sk)->icsk_bind2_hash) {
@@ -277,7 +312,7 @@ bhash2_find:
 		}
 	}
 	if (update_fastreuse)
-		inet_csk_update_fastreuse(tb, child);
+		inet_csk_update_fastreuse(child, tb, tb2);
 	inet_bind_hash(child, tb, tb2, port);
 	spin_unlock(&head2->lock);
 	spin_unlock(&head->lock);
@@ -950,6 +985,10 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family,
 	if (!tb2) {
 		tb2 = new_tb2;
 		inet_bind2_bucket_init(tb2, net, head2, inet_csk(sk)->icsk_bind_hash, sk);
+		if (sk_is_connect_bind(sk)) {
+			tb2->fastreuse = -1;
+			tb2->fastreuseport = -1;
+		}
 	}
 	inet_csk(sk)->icsk_bind2_hash = tb2;
 	sk_add_bind_node(sk, &tb2->owners);
@@ -1120,6 +1159,8 @@ ok:
 					       head2, tb, sk);
 		if (!tb2)
 			goto error;
+		tb2->fastreuse = -1;
+		tb2->fastreuseport = -1;
 	}
 
 	/* Here we want to add a little bit of randomness to the next source
@@ -1132,6 +1173,7 @@ ok:
 
 	/* Head lock still held and bh's disabled */
 	inet_bind_hash(sk, tb, tb2, port);
+	sk->sk_userlocks |= SOCK_CONNECT_BIND;
 
 	if (sk_unhashed(sk)) {
 		inet_sk(sk)->inet_sport = htons(port);