1 files changed, 190 insertions, 12 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index fd472eae4f5c..754013fa393b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -135,10 +135,18 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 				  bool relax, bool reuseport_ok)
 {
 	struct sock *sk2;
+	bool reuseport_cb_ok;
 	bool reuse = sk->sk_reuse;
 	bool reuseport = !!sk->sk_reuseport;
+	struct sock_reuseport *reuseport_cb;
 	kuid_t uid = sock_i_uid((struct sock *)sk);
 
+	rcu_read_lock();
+	reuseport_cb = rcu_dereference(sk->sk_reuseport_cb);
+	/* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */
+	reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks);
+	rcu_read_unlock();
+
 	/*
 	 * Unlike other sk lookup places we do not check
 	 * for sk_net here, since _all_ the socks listed
@@ -156,14 +164,14 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 				if ((!relax ||
 				     (!reuseport_ok &&
 				      reuseport && sk2->sk_reuseport &&
-				      !rcu_access_pointer(sk->sk_reuseport_cb) &&
+				      reuseport_cb_ok &&
 				      (sk2->sk_state == TCP_TIME_WAIT ||
 				       uid_eq(uid, sock_i_uid(sk2))))) &&
 				    inet_rcv_saddr_equal(sk, sk2, true))
 					break;
 			} else if (!reuseport_ok ||
 				   !reuseport || !sk2->sk_reuseport ||
-				   rcu_access_pointer(sk->sk_reuseport_cb) ||
+				   !reuseport_cb_ok ||
 				   (sk2->sk_state != TCP_TIME_WAIT &&
 				    !uid_eq(uid, sock_i_uid(sk2)))) {
 				if (inet_rcv_saddr_equal(sk, sk2, true))
@@ -687,6 +695,66 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
 }
 EXPORT_SYMBOL(inet_rtx_syn_ack);
 
+static struct request_sock *inet_reqsk_clone(struct request_sock *req,
+					     struct sock *sk)
+{
+	struct sock *req_sk, *nreq_sk;
+	struct request_sock *nreq;
+
+	nreq = kmem_cache_alloc(req->rsk_ops->slab, GFP_ATOMIC | __GFP_NOWARN);
+	if (!nreq) {
+		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE);
+
+		/* paired with refcount_inc_not_zero() in reuseport_migrate_sock() */
+		sock_put(sk);
+		return NULL;
+	}
+
+	req_sk = req_to_sk(req);
+	nreq_sk = req_to_sk(nreq);
+
+	memcpy(nreq_sk, req_sk,
+	       offsetof(struct sock, sk_dontcopy_begin));
+	memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end,
+	       req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end));
+
+	sk_node_init(&nreq_sk->sk_node);
+	nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping;
+#ifdef CONFIG_XPS
+	nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping;
+#endif
+	nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu;
+
+	nreq->rsk_listener = sk;
+
+	/* We need not acquire fastopenq->lock
+	 * because the child socket is locked in inet_csk_listen_stop().
+	 */
+	if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener)
+		rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq);
+
+	return nreq;
+}
+
+static void reqsk_queue_migrated(struct request_sock_queue *queue,
+				 const struct request_sock *req)
+{
+	if (req->num_timeout == 0)
+		atomic_inc(&queue->young);
+	atomic_inc(&queue->qlen);
+}
+
+static void reqsk_migrate_reset(struct request_sock *req)
+{
+	req->saved_syn = NULL;
+#if IS_ENABLED(CONFIG_IPV6)
+	inet_rsk(req)->ipv6_opt = NULL;
+	inet_rsk(req)->pktopts = NULL;
+#else
+	inet_rsk(req)->ireq_opt = NULL;
+#endif
+}
+
 /* return true if req was found in the ehash table */
 static bool reqsk_queue_unlink(struct request_sock *req)
 {
@@ -727,15 +795,39 @@ EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
 static void reqsk_timer_handler(struct timer_list *t)
 {
 	struct request_sock *req = from_timer(req, t, rsk_timer);
+	struct request_sock *nreq = NULL, *oreq = req;
 	struct sock *sk_listener = req->rsk_listener;
-	struct net *net = sock_net(sk_listener);
-	struct inet_connection_sock *icsk = inet_csk(sk_listener);
-	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
+	struct inet_connection_sock *icsk;
+	struct request_sock_queue *queue;
+	struct net *net;
 	int max_syn_ack_retries, qlen, expire = 0, resend = 0;
 
-	if (inet_sk_state_load(sk_listener) != TCP_LISTEN)
-		goto drop;
+	if (inet_sk_state_load(sk_listener) != TCP_LISTEN) {
+		struct sock *nsk;
+
+		nsk = reuseport_migrate_sock(sk_listener, req_to_sk(req), NULL);
+		if (!nsk)
+			goto drop;
 
+		nreq = inet_reqsk_clone(req, nsk);
+		if (!nreq)
+			goto drop;
+
+		/* The new timer for the cloned req can decrease the 2
+		 * by calling inet_csk_reqsk_queue_drop_and_put(), so
+		 * hold another count to prevent use-after-free and
+		 * call reqsk_put() just before return.
+		 */
+		refcount_set(&nreq->rsk_refcnt, 2 + 1);
+		timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
+		reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req);
+
+		req = nreq;
+		sk_listener = nsk;
+	}
+
+	icsk = inet_csk(sk_listener);
+	net = sock_net(sk_listener);
 	max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
 	/* Normally all the openreqs are young and become mature
 	 * (i.e. converted to established socket) for first timeout.
@@ -754,6 +846,7 @@ static void reqsk_timer_handler(struct timer_list *t)
 	 * embrions; and abort old ones without pity, if old
 	 * ones are about to clog our table.
 	 */
+	queue = &icsk->icsk_accept_queue;
 	qlen = reqsk_queue_len(queue);
 	if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) {
 		int young = reqsk_queue_len_young(queue) << 1;
@@ -778,10 +871,39 @@ static void reqsk_timer_handler(struct timer_list *t)
 			atomic_dec(&queue->young);
 		timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
 		mod_timer(&req->rsk_timer, jiffies + timeo);
+
+		if (!nreq)
+			return;
+
+		if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) {
+			/* delete timer */
+			inet_csk_reqsk_queue_drop(sk_listener, nreq);
+			goto no_ownership;
+		}
+
+		__NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQSUCCESS);
+		reqsk_migrate_reset(oreq);
+		reqsk_queue_removed(&inet_csk(oreq->rsk_listener)->icsk_accept_queue, oreq);
+		reqsk_put(oreq);
+
+		reqsk_put(nreq);
 		return;
 	}
+
+	/* Even if we can clone the req, we may need not retransmit any more
+	 * SYN+ACKs (nreq->num_timeout > max_syn_ack_retries, etc), or another
+	 * CPU may win the "own_req" race so that inet_ehash_insert() fails.
+	 */
+	if (nreq) {
+		__NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQFAILURE);
+no_ownership:
+		reqsk_migrate_reset(nreq);
+		reqsk_queue_removed(queue, nreq);
+		__reqsk_free(nreq);
+	}
+
 drop:
-	inet_csk_reqsk_queue_drop_and_put(sk_listener, req);
+	inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq);
 }
 
 static void reqsk_queue_hash_req(struct request_sock *req,
@@ -997,12 +1119,42 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
 					 struct request_sock *req, bool own_req)
 {
 	if (own_req) {
-		inet_csk_reqsk_queue_drop(sk, req);
-		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
-		if (inet_csk_reqsk_queue_add(sk, req, child))
+		inet_csk_reqsk_queue_drop(req->rsk_listener, req);
+		reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
+
+		if (sk != req->rsk_listener) {
+			/* another listening sk has been selected,
+			 * migrate the req to it.
+			 */
+			struct request_sock *nreq;
+
+			/* hold a refcnt for the nreq->rsk_listener
+			 * which is assigned in inet_reqsk_clone()
+			 */
+			sock_hold(sk);
+			nreq = inet_reqsk_clone(req, sk);
+			if (!nreq) {
+				inet_child_forget(sk, req, child);
+				goto child_put;
+			}
+
+			refcount_set(&nreq->rsk_refcnt, 1);
+			if (inet_csk_reqsk_queue_add(sk, nreq, child)) {
+				__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQSUCCESS);
+				reqsk_migrate_reset(req);
+				reqsk_put(req);
+				return child;
+			}
+
+			__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE);
+			reqsk_migrate_reset(nreq);
+			__reqsk_free(nreq);
+		} else if (inet_csk_reqsk_queue_add(sk, req, child)) {
 			return child;
+		}
 	}
 	/* Too bad, another child took ownership of the request, undo. */
+child_put:
 	bh_unlock_sock(child);
 	sock_put(child);
 	return NULL;
@@ -1028,14 +1180,40 @@ void inet_csk_listen_stop(struct sock *sk)
 	 * of the variants now.			--ANK
 	 */
 	while ((req = reqsk_queue_remove(queue, sk)) != NULL) {
-		struct sock *child = req->sk;
+		struct sock *child = req->sk, *nsk;
+		struct request_sock *nreq;
 
 		local_bh_disable();
 		bh_lock_sock(child);
 		WARN_ON(sock_owned_by_user(child));
 		sock_hold(child);
 
+		nsk = reuseport_migrate_sock(sk, child, NULL);
+		if (nsk) {
+			nreq = inet_reqsk_clone(req, nsk);
+			if (nreq) {
+				refcount_set(&nreq->rsk_refcnt, 1);
+
+				if (inet_csk_reqsk_queue_add(nsk, nreq, child)) {
+					__NET_INC_STATS(sock_net(nsk),
+							LINUX_MIB_TCPMIGRATEREQSUCCESS);
+					reqsk_migrate_reset(req);
+				} else {
+					__NET_INC_STATS(sock_net(nsk),
+							LINUX_MIB_TCPMIGRATEREQFAILURE);
+					reqsk_migrate_reset(nreq);
+					__reqsk_free(nreq);
+				}
+
+				/* inet_csk_reqsk_queue_add() has already
+				 * called inet_child_forget() on failure case.
+				 */
+				goto skip_child_forget;
+			}
+		}
+
 		inet_child_forget(sk, req, child);
+skip_child_forget:
 		reqsk_put(req);
 		bh_unlock_sock(child);
 		local_bh_enable();