mptcp: use mptcp release_cb for delayed tasks

We have some tasks triggered by the subflow receive path
which require to access the msk socket status, specifically:
mptcp_clean_una() and mptcp_push_pending()

We have almost everything in place to defer to the msk
release_cb such tasks when the msk sock is owned.

Since the worker is no more used to clean the acked data,
for fallback sockets we need to explicitly flush them.

As an added bonus we can move the wake-up code in __mptcp_clean_una(),
simplify a lot mptcp_poll() and move the timer update under
the data lock.

The worker is now used only to process and send DATA_FIN
packets and do the mptcp-level retransmissions.
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/mptcp/options.c

@@ -830,7 +830,7 @@ static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
 }
 
 static void ack_update_msk(struct mptcp_sock *msk,
-			   const struct sock *ssk,
+			   struct sock *ssk,
 			   struct mptcp_options_received *mp_opt)
 {
 	u64 new_wnd_end, new_snd_una, snd_nxt = READ_ONCE(msk->snd_nxt);
@@ -854,8 +854,7 @@ static void ack_update_msk(struct mptcp_sock *msk,
 
 	if (after64(new_wnd_end, msk->wnd_end)) {
 		msk->wnd_end = new_wnd_end;
-		if (mptcp_send_head(sk))
-			mptcp_schedule_work(sk);
+		__mptcp_wnd_updated(sk, ssk);
 	}
 
 	if (after64(new_snd_una, old_snd_una)) {
@@ -915,8 +914,19 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	struct mptcp_options_received mp_opt;
 	struct mptcp_ext *mpext;
 
-	if (__mptcp_check_fallback(msk))
+	if (__mptcp_check_fallback(msk)) {
+		/* Keep it simple and unconditionally trigger send data cleanup and
+		 * pending queue spooling. We will need to acquire the data lock
+		 * for more accurate checks, and once the lock is acquired, such
+		 * helpers are cheap.
+		 */
+		mptcp_data_lock(subflow->conn);
+		if (mptcp_send_head(subflow->conn))
+			__mptcp_wnd_updated(subflow->conn, sk);
+		__mptcp_data_acked(subflow->conn);
+		mptcp_data_unlock(subflow->conn);
 		return;
+	}
 
 	mptcp_get_options(skb, &mp_opt);
 	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))

net/mptcp/protocol.h

@@ -91,6 +91,8 @@
 #define MPTCP_WORK_EOF		3
 #define MPTCP_FALLBACK_DONE	4
 #define MPTCP_WORK_CLOSE_SUBFLOW 5
+#define MPTCP_PUSH_PENDING	6
+#define MPTCP_CLEAN_UNA		7
 
 static inline bool before64(__u64 seq1, __u64 seq2)
 {
@@ -495,6 +497,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
 void mptcp_data_ready(struct sock *sk, struct sock *ssk);
 bool mptcp_finish_join(struct sock *sk);
 bool mptcp_schedule_work(struct sock *sk);
+void __mptcp_wnd_updated(struct sock *sk, struct sock *ssk);
 void __mptcp_data_acked(struct sock *sk);
 void mptcp_subflow_eof(struct sock *sk);
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);

net/mptcp/subflow.c

@@ -995,19 +995,9 @@ static void subflow_data_ready(struct sock *sk)
 		mptcp_data_ready(parent, sk);
 }
 
-static void subflow_write_space(struct sock *sk)
+static void subflow_write_space(struct sock *ssk)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct socket *sock = READ_ONCE(sk->sk_socket);
-	struct sock *parent = subflow->conn;
-
-	if (!sk_stream_is_writeable(sk))
-		return;
-
-	if (sock && sk_stream_is_writeable(parent))
-		clear_bit(SOCK_NOSPACE, &sock->flags);
-
-	sk_stream_write_space(parent);
+	/* we take action in __mptcp_clean_una() */
 }
 
 static struct inet_connection_sock_af_ops *