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().

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c                          |  7 ++++
 net/mptcp/protocol.h                          |  4 +++
 net/mptcp/sched.c                             | 34 +++++++++++++++++++
 .../testing/selftests/bpf/bpf_mptcp_helpers.h |  1 +
 4 files changed, 46 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3f2e1f18e970..70ba43c18e45 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2665,6 +2665,11 @@ static int mptcp_init_sock(struct sock *sk)
 	if (ret)
 		return ret;
 
+	ret = mptcp_init_sched(mptcp_sk(sk),
+			       mptcp_sched_find(mptcp_get_scheduler(net)));
+	if (ret)
+		return ret;
+
 	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
 	 * propagate the correct value
 	 */
@@ -2824,6 +2829,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sk_stop_timer(sk, &sk->sk_timer);
 	mptcp_data_unlock(sk);
 	msk->pm.status = 0;
+	mptcp_release_sched(msk);
 
 	/* clears msk->subflow, allowing the following loop to close
 	 * even the initial subflow
@@ -3001,6 +3007,7 @@ struct sock *mptcp_sk_clone(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);
 
 	if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) {
 		msk->can_ack = true;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 0b17b4f7b134..9ded79c942b0 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -298,6 +298,7 @@ struct mptcp_sock {
 	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
 	struct sock	*first;
 	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 */
@@ -628,6 +629,9 @@ void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
 void mptcp_get_subflow_default(struct mptcp_sock *msk, bool reinject,
 			       struct mptcp_sched_data *data);
 void mptcp_sched_init(void);
+int mptcp_init_sched(struct mptcp_sock *msk,
+		     struct mptcp_sched_ops *sched);
+void mptcp_release_sched(struct mptcp_sock *msk);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index bd0beff8cac8..8025dc51fbe9 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -68,3 +68,37 @@ void mptcp_sched_init(void)
 {
 	mptcp_register_scheduler(&mptcp_sched_default);
 }
+
+int mptcp_init_sched(struct mptcp_sock *msk,
+		     struct mptcp_sched_ops *sched)
+{
+	struct mptcp_sched_ops *sched_init = &mptcp_sched_default;
+
+	if (sched)
+		sched_init = sched;
+
+	if (!bpf_try_module_get(sched_init, sched_init->owner))
+		return -EBUSY;
+
+	msk->sched = sched_init;
+	if (msk->sched->init)
+		msk->sched->init(msk);
+
+	pr_debug("sched=%s", msk->sched->name);
+
+	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);
+}
diff --git a/tools/testing/selftests/bpf/bpf_mptcp_helpers.h b/tools/testing/selftests/bpf/bpf_mptcp_helpers.h
index de20fbdb6d98..a0b83fbe8133 100644
--- a/tools/testing/selftests/bpf/bpf_mptcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_mptcp_helpers.h
@@ -29,6 +29,7 @@ struct mptcp_sock {
 
 	__u32		token;
 	struct sock	*first;
+	struct mptcp_sched_ops *sched;
 	char		ca_name[TCP_CA_NAME_MAX];
 } __attribute__((preserve_access_index));
 
-- 
2.34.1