RM_ADDR are sent over an active subflow, the first one in the subflows
list. There is then a high chance the initial subflow is picked. With
the in-kernel PM, when an endpoint is removed, a RM_ADDR is sent, then
linked subflows are closed. This is done for each active MPTCP
connection.

MPTCP endpoints are likely removed because the attached network is no
longer available or usable. In this case, it is better to avoid sending
this RM_ADDR over the subflow that is going to be removed, but prefer
sending it over another active and non stale subflow, if any.

This modification avoids situations where the other end is not notified
when a subflow is no longer usable: typically when the endpoint linked
to the initial subflow is removed, especially on the server side.

Fixes: 8dd5efb1f91b ("mptcp: send ack for rm_addr")
Cc: stable@vger.kernel.org
Reported-by: Frank Lorenz <lorenz-frank@web.de>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/612
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
 net/mptcp/pm.c | 55 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 43 insertions(+), 12 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 7298836469b3..57a456690406 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -212,9 +212,24 @@ void mptcp_pm_send_ack(struct mptcp_sock *msk,
 	spin_lock_bh(&msk->pm.lock);
 }
 
-void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow,
+			       const struct mptcp_rm_list *rm_list)
 {
-	struct mptcp_subflow_context *subflow, *alt = NULL;
+	u8 i, id = subflow_get_local_id(subflow);
+
+	for (i = 0; i < rm_list->nr; i++) {
+		if (rm_list->ids[i] == id)
+			return true;
+	}
+
+	return false;
+}
+
+static void
+mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk,
+				  const struct mptcp_rm_list *rm_list)
+{
+	struct mptcp_subflow_context *subflow, *stale = NULL, *same_id = NULL;
 
 	msk_owned_by_me(msk);
 	lockdep_assert_held(&msk->pm.lock);
@@ -224,19 +239,35 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
 		return;
 
 	mptcp_for_each_subflow(msk, subflow) {
-		if (__mptcp_subflow_active(subflow)) {
-			if (!subflow->stale) {
-				mptcp_pm_send_ack(msk, subflow, false, false);
-				return;
-			}
+		if (!__mptcp_subflow_active(subflow))
+			continue;
 
-			if (!alt)
-				alt = subflow;
+		if (unlikely(subflow->stale)) {
+			if (!stale)
+				stale = subflow;
+		} else if (unlikely(rm_list &&
+				    subflow_in_rm_list(subflow, rm_list))) {
+			if (!same_id)
+				same_id = subflow;
+		} else {
+			goto send_ack;
 		}
 	}
 
-	if (alt)
-		mptcp_pm_send_ack(msk, alt, false, false);
+	if (same_id)
+		subflow = same_id;
+	else if (stale)
+		subflow = stale;
+	else
+		return;
+
+send_ack:
+	mptcp_pm_send_ack(msk, subflow, false, false);
+}
+
+void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+{
+	mptcp_pm_addr_send_ack_avoid_list(msk, NULL);
 }
 
 int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
@@ -470,7 +501,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 	msk->pm.rm_list_tx = *rm_list;
 	rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL);
 	WRITE_ONCE(msk->pm.addr_signal, rm_addr);
-	mptcp_pm_addr_send_ack(msk);
+	mptcp_pm_addr_send_ack_avoid_list(msk, rm_list);
 	return 0;
 }
 

-- 
2.51.0