mptcp: add sched in mptcp_sock

This patch adds a new struct member sched in struct mptcp_sock.
And two helpers mptcp_init_sched() and mptcp_release_sched() to
init and release it.

Init it with the sysctl scheduler in mptcp_init_sock(), copy the
scheduler from the parent in mptcp_sk_clone(), and release it in
__mptcp_destroy_sock().
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-5-0c860fb256a8@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

net/mptcp/protocol.c

@@ -2697,6 +2697,7 @@ static void mptcp_ca_reset(struct sock *sk)
 static int mptcp_init_sock(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
+	int ret;
 
 	__mptcp_init_sock(sk);
 
@@ -2706,6 +2707,11 @@ static int mptcp_init_sock(struct sock *sk)
 	if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
 		return -ENOMEM;
 
+	ret = mptcp_init_sched(mptcp_sk(sk),
+			       mptcp_sched_find(mptcp_get_scheduler(net)));
+	if (ret)
+		return ret;
+
 	set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
 
 	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
@@ -2851,6 +2857,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	mptcp_stop_timer(sk);
 	sk_stop_timer(sk, &sk->sk_timer);
 	msk->pm.status = 0;
+	mptcp_release_sched(msk);
 
 	sk->sk_prot->destroy(sk);
 
@@ -3105,6 +3112,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	msk->snd_una = msk->write_seq;
 	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
+	mptcp_init_sched(msk, mptcp_sk(sk)->sched);
 
 	/* passive msk is created after the first/MPC subflow */
 	msk->subflow_id = 2;

net/mptcp/protocol.h

@@ -312,6 +312,7 @@ struct mptcp_sock {
 				 * lock as such sock is freed after close().
 				 */
 	struct mptcp_pm_data	pm;
+	struct mptcp_sched_ops	*sched;
 	struct {
 		u32	space;	/* bytes copied in last measurement window */
 		u32	copied; /* bytes copied in this measurement window */
@@ -659,6 +660,9 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 struct mptcp_sched_ops *mptcp_sched_find(const char *name);
 int mptcp_register_scheduler(struct mptcp_sched_ops *sched);
 void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
+int mptcp_init_sched(struct mptcp_sock *msk,
+		     struct mptcp_sched_ops *sched);
+void mptcp_release_sched(struct mptcp_sock *msk);
 
 static inline bool __tcp_can_send(const struct sock *ssk)
 {

net/mptcp/sched.c

@@ -54,3 +54,36 @@ void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
 	list_del_rcu(&sched->list);
 	spin_unlock(&mptcp_sched_list_lock);
 }
+
+int mptcp_init_sched(struct mptcp_sock *msk,
+		     struct mptcp_sched_ops *sched)
+{
+	if (!sched)
+		goto out;
+
+	if (!bpf_try_module_get(sched, sched->owner))
+		return -EBUSY;
+
+	msk->sched = sched;
+	if (msk->sched->init)
+		msk->sched->init(msk);
+
+	pr_debug("sched=%s", msk->sched->name);
+
+out:
+	return 0;
+}
+
+void mptcp_release_sched(struct mptcp_sock *msk)
+{
+	struct mptcp_sched_ops *sched = msk->sched;
+
+	if (!sched)
+		return;
+
+	msk->sched = NULL;
+	if (sched->release)
+		sched->release(msk);
+
+	bpf_module_put(sched, sched->owner);
+}