mptcp: invoke MP_FAIL response when needed

mptcp_mp_fail_no_response shouldn't be invoked on each worker run, it
should be invoked only when MP_FAIL response timeout occurs.

This patch refactors the MP_FAIL response logic.

It leverages the fact that only the MPC/first subflow can gracefully
fail to avoid unneeded subflows traversal: the failing subflow can
be only msk->first.

A new 'fail_tout' field is added to the subflow context to record the
MP_FAIL response timeout and use such field to reliably share the
timeout timer between the MP_FAIL event and the MPTCP socket close
timeout.

Finally, a new ack is generated to send out MP_FAIL notification as soon
as we hit the relevant condition, instead of waiting a possibly unbound
time for the next data packet.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/281
Fixes: d9fb797046c5 ("mptcp: Do not traverse the subflow connection list without lock")
Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 47 insertions, 30 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 17e13396024a..e6fcb61443dd 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -500,7 +500,7 @@ static void mptcp_set_timeout(struct sock *sk)
 	__mptcp_set_timeout(sk, tout);
 }
 
-static bool tcp_can_send_ack(const struct sock *ssk)
+static inline bool tcp_can_send_ack(const struct sock *ssk)
 {
 	return !((1 << inet_sk_state_load(ssk)) &
 	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
@@ -2175,21 +2175,6 @@ static void mptcp_retransmit_timer(struct timer_list *t)
 	sock_put(sk);
 }
 
-static struct mptcp_subflow_context *
-mp_fail_response_expect_subflow(struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow, *ret = NULL;
-
-	mptcp_for_each_subflow(msk, subflow) {
-		if (READ_ONCE(subflow->mp_fail_response_expect)) {
-			ret = subflow;
-			break;
-		}
-	}
-
-	return ret;
-}
-
 static void mptcp_timeout_timer(struct timer_list *t)
 {
 	struct sock *sk = from_timer(sk, t, sk_timer);
@@ -2518,27 +2503,50 @@ reset_timer:
 		mptcp_reset_timer(sk);
 }
 
+/* schedule the timeout timer for the relevant event: either close timeout
+ * or mp_fail timeout. The close timeout takes precedence on the mp_fail one
+ */
+void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout)
+{
+	struct sock *sk = (struct sock *)msk;
+	unsigned long timeout, close_timeout;
+
+	if (!fail_tout && !sock_flag(sk, SOCK_DEAD))
+		return;
+
+	close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN;
+
+	/* the close timeout takes precedence on the fail one, and here at least one of
+	 * them is active
+	 */
+	timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout;
+
+	sk_reset_timer(sk, &sk->sk_timer, timeout);
+}
+
 static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
 {
-	struct mptcp_subflow_context *subflow;
-	struct sock *ssk;
+	struct sock *ssk = msk->first;
 	bool slow;
 
-	subflow = mp_fail_response_expect_subflow(msk);
-	if (subflow) {
-		pr_debug("MP_FAIL doesn't respond, reset the subflow");
+	if (!ssk)
+		return;
 
-		ssk = mptcp_subflow_tcp_sock(subflow);
-		slow = lock_sock_fast(ssk);
-		mptcp_subflow_reset(ssk);
-		unlock_sock_fast(ssk, slow);
-	}
+	pr_debug("MP_FAIL doesn't respond, reset the subflow");
+
+	slow = lock_sock_fast(ssk);
+	mptcp_subflow_reset(ssk);
+	WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0);
+	unlock_sock_fast(ssk, slow);
+
+	mptcp_reset_timeout(msk, 0);
 }
 
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
 	struct sock *sk = &msk->sk.icsk_inet.sk;
+	unsigned long fail_tout;
 	int state;
 
 	lock_sock(sk);
@@ -2575,7 +2583,9 @@ static void mptcp_worker(struct work_struct *work)
 	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
 		__mptcp_retrans(sk);
 
-	mptcp_mp_fail_no_response(msk);
+	fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0;
+	if (fail_tout && time_after(jiffies, fail_tout))
+		mptcp_mp_fail_no_response(msk);
 
 unlock:
 	release_sock(sk);
@@ -2822,6 +2832,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 static void mptcp_close(struct sock *sk, long timeout)
 {
 	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk = mptcp_sk(sk);
 	bool do_cancel_work = false;
 
 	lock_sock(sk);
@@ -2840,10 +2851,16 @@ static void mptcp_close(struct sock *sk, long timeout)
 cleanup:
 	/* orphan all the subflows */
 	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
-	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		bool slow = lock_sock_fast_nested(ssk);
 
+		/* since the close timeout takes precedence on the fail one,
+		 * cancel the latter
+		 */
+		if (ssk == msk->first)
+			subflow->fail_tout = 0;
+
 		sock_orphan(ssk);
 		unlock_sock_fast(ssk, slow);
 	}
@@ -2852,13 +2869,13 @@ cleanup:
 	sock_hold(sk);
 	pr_debug("msk=%p state=%d", sk, sk->sk_state);
 	if (mptcp_sk(sk)->token)
-		mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL);
+		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
 
 	if (sk->sk_state == TCP_CLOSE) {
 		__mptcp_destroy_sock(sk);
 		do_cancel_work = true;
 	} else {
-		sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);
+		mptcp_reset_timeout(msk, 0);
 	}
 	release_sock(sk);
 	if (do_cancel_work)