diff mbox series

[v8,bpf-next,05/11] tcp: Migrate TCP_ESTABLISHED/TCP_SYN_RECV sockets in accept queues.

Message ID 20210612123224.12525-6-kuniyu@amazon.co.jp
State New
Headers show
Series Socket migration for SO_REUSEPORT. | expand

Commit Message

Kuniyuki Iwashima June 12, 2021, 12:32 p.m. UTC 
When we call close() or shutdown() for listening sockets, each child socket
in the accept queue are freed at inet_csk_listen_stop(). If we can get a
new listener by reuseport_migrate_sock() and clone the request by
inet_reqsk_clone(), we try to add it into the new listener's accept queue
by inet_csk_reqsk_queue_add(). If it fails, we have to call __reqsk_free()
to call sock_put() for its listener and free the cloned request.

After putting the full socket into ehash, tcp_v[46]_syn_recv_sock() sets
NULL to ireq_opt/pktopts in struct inet_request_sock, but ipv6_opt can be
non-NULL. So, we have to set NULL to ipv6_opt of the old request to avoid
double free.

Note that we do not update req->rsk_listener and instead clone the req to
migrate because another path may reference the original request. If we
protected it by RCU, we would need to add rcu_read_lock() in many places.

Link: https://lore.kernel.org/netdev/20201209030903.hhow5r53l6fmozjn@kafai-mbp.dhcp.thefacebook.com/
Suggested-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
 net/ipv4/inet_connection_sock.c | 70 ++++++++++++++++++++++++++++++++-
 1 file changed, 69 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index fa806e9167ec..08878ef1bc70 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -695,6 +695,52 @@  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) {
+		/* 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_migrate_reset(struct request_sock *req)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	inet_rsk(req)->ipv6_opt = NULL;
+#endif
+}
+
 /* return true if req was found in the ehash table */
 static bool reqsk_queue_unlink(struct request_sock *req)
 {
@@ -1036,14 +1082,36 @@  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)) {
+					reqsk_migrate_reset(req);
+				} else {
+					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();