Merge branch 'mptcp-rx-path-refactor'

Matthieu Baerts says:

====================
mptcp: rx path refactor

Paolo worked on this RX path refactor for these two main reasons:

- Currently, the MPTCP RX path introduces quite a bit of 'exceptional'
  accounting/locking processing WRT to plain TCP, adding up to the
  implementation complexity in a miserable way.

- The performance gap WRT plain TCP for single subflow connections is
  quite measurable.

The present refactor addresses both the above items: most of the
additional complexity is dropped, and single stream performances
increase measurably, from 55Gbps to 71Gbps in Paolo's loopback test.
As a reference, plain TCP was around 84Gbps on the same host.

The above comes to a price: the patch are invasive, even in subtle ways.

Note: patch 5/7 removes the sk_forward_alloc_get() helper, which caused
some trivial modifications in different places in the net tree: sockets,
IPv4, sched. That's why a few more people have been Cc here. Feel free
to only look at this patch 5/7.
====================

Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-0-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 18 insertions, 18 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index fd021cf8286e..d2caffa56bdd 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -802,9 +802,6 @@ void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
 	subflow_set_remote_key(msk, subflow, mp_opt);
 	WRITE_ONCE(subflow->fully_established, true);
 	WRITE_ONCE(msk->fully_established, true);
-
-	if (subflow->is_mptfo)
-		__mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
 }
 
 static struct sock *subflow_syn_recv_sock(const struct sock *sk,
@@ -1271,7 +1268,12 @@ out:
 		subflow->map_valid = 0;
 }
 
-/* sched mptcp worker to remove the subflow if no more data is pending */
+static bool subflow_is_done(const struct sock *sk)
+{
+	return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE;
+}
+
+/* sched mptcp worker for subflow cleanup if no more data is pending */
 static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct sock *sk = (struct sock *)msk;
@@ -1281,8 +1283,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
 		    inet_sk_state_load(sk) != TCP_ESTABLISHED)))
 		return;
 
-	if (skb_queue_empty(&ssk->sk_receive_queue) &&
-	    !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+	if (!skb_queue_empty(&ssk->sk_receive_queue))
+		return;
+
+	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+		mptcp_schedule_work(sk);
+
+	/* when the fallback subflow closes the rx side, trigger a 'dummy'
+	 * ingress data fin, so that the msk state will follow along
+	 */
+	if (__mptcp_check_fallback(msk) && subflow_is_done(ssk) &&
+	    msk->first == ssk &&
+	    mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
 		mptcp_schedule_work(sk);
 }
 
@@ -1842,11 +1854,6 @@ static void __subflow_state_change(struct sock *sk)
 	rcu_read_unlock();
 }
 
-static bool subflow_is_done(const struct sock *sk)
-{
-	return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE;
-}
-
 static void subflow_state_change(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -1873,13 +1880,6 @@ static void subflow_state_change(struct sock *sk)
 		subflow_error_report(sk);
 
 	subflow_sched_work_if_closed(mptcp_sk(parent), sk);
-
-	/* when the fallback subflow closes the rx side, trigger a 'dummy'
-	 * ingress data fin, so that the msk state will follow along
-	 */
-	if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk &&
-	    mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
-		mptcp_schedule_work(parent);
 }
 
 void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)