mptcp: introduce MPTCP retransmission timer

The timer will be used to schedule retransmission. It's
frequency is based on the current subflow RTO estimation and
is reset on every una_seq update

The timer is clearer for good by __mptcp_clear_xmit()

Also clean MPTCP rtx queue before each transmission.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 88 insertions, 1 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 812a646c349a..002c6311357a 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -251,6 +251,46 @@ static void __mptcp_flush_join_list(struct mptcp_sock *msk)
 	spin_unlock_bh(&msk->join_list_lock);
 }
 
+static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk)
+{
+	long tout = ssk && inet_csk(ssk)->icsk_pending ?
+				      inet_csk(ssk)->icsk_timeout - jiffies : 0;
+
+	if (tout <= 0)
+		tout = mptcp_sk(sk)->timer_ival;
+	mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN;
+}
+
+static bool mptcp_timer_pending(struct sock *sk)
+{
+	return timer_pending(&inet_csk(sk)->icsk_retransmit_timer);
+}
+
+static void mptcp_reset_timer(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	unsigned long tout;
+
+	/* should never be called with mptcp level timer cleared */
+	tout = READ_ONCE(mptcp_sk(sk)->timer_ival);
+	if (WARN_ON_ONCE(!tout))
+		tout = TCP_RTO_MIN;
+	sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout);
+}
+
+void mptcp_data_acked(struct sock *sk)
+{
+	mptcp_reset_timer(sk);
+}
+
+static void mptcp_stop_timer(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
+	mptcp_sk(sk)->timer_ival = 0;
+}
+
 static bool mptcp_ext_cache_refill(struct mptcp_sock *msk)
 {
 	if (!msk->cached_ext)
@@ -596,10 +636,15 @@ fallback:
 		copied += ret;
 	}
 
+	mptcp_set_timeout(sk, ssk);
 	if (copied) {
 		ret = copied;
 		tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle,
 			 size_goal);
+
+		/* start the timer, if it's not pending */
+		if (!mptcp_timer_pending(sk))
+			mptcp_reset_timer(sk);
 	}
 
 	ssk_check_wmem(msk, ssk);
@@ -787,6 +832,35 @@ out_err:
 	return copied;
 }
 
+static void mptcp_retransmit_handler(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (atomic64_read(&msk->snd_una) == msk->write_seq)
+		mptcp_stop_timer(sk);
+	else
+		mptcp_reset_timer(sk);
+}
+
+static void mptcp_retransmit_timer(struct timer_list *t)
+{
+	struct inet_connection_sock *icsk = from_timer(icsk, t,
+						       icsk_retransmit_timer);
+	struct sock *sk = &icsk->icsk_inet.sk;
+
+	bh_lock_sock(sk);
+	if (!sock_owned_by_user(sk)) {
+		mptcp_retransmit_handler(sk);
+	} else {
+		/* delegate our work to tcp_release_cb() */
+		if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED,
+				      &sk->sk_tsq_flags))
+			sock_hold(sk);
+	}
+	bh_unlock_sock(sk);
+	sock_put(sk);
+}
+
 /* subflow sockets can be either outgoing (connect) or incoming
  * (accept).
  *
@@ -846,6 +920,9 @@ static int __mptcp_init_sock(struct sock *sk)
 
 	mptcp_pm_data_init(msk);
 
+	/* re-use the csk retrans timer for MPTCP-level retrans */
+	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
+
 	return 0;
 }
 
@@ -867,6 +944,8 @@ static void __mptcp_clear_xmit(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_data_frag *dtmp, *dfrag;
 
+	sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
+
 	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
 		dfrag_clear(dfrag);
 }
@@ -1155,7 +1234,8 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname,
 	return -EOPNOTSUPP;
 }
 
-#define MPTCP_DEFERRED_ALL TCPF_DELACK_TIMER_DEFERRED
+#define MPTCP_DEFERRED_ALL (TCPF_DELACK_TIMER_DEFERRED | \
+			    TCPF_WRITE_TIMER_DEFERRED)
 
 /* this is very alike tcp_release_cb() but we must handle differently a
  * different set of events
@@ -1171,6 +1251,8 @@ static void mptcp_release_cb(struct sock *sk)
 		nflags = flags & ~MPTCP_DEFERRED_ALL;
 	} while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags);
 
+	sock_release_ownership(sk);
+
 	if (flags & TCPF_DELACK_TIMER_DEFERRED) {
 		struct mptcp_sock *msk = mptcp_sk(sk);
 		struct sock *ssk;
@@ -1179,6 +1261,11 @@ static void mptcp_release_cb(struct sock *sk)
 		if (!ssk || !schedule_work(&msk->work))
 			__sock_put(sk);
 	}
+
+	if (flags & TCPF_WRITE_TIMER_DEFERRED) {
+		mptcp_retransmit_handler(sk);
+		__sock_put(sk);
+	}
 }
 
 static int mptcp_get_port(struct sock *sk, unsigned short snum)