mptcp: reset subflow when MP_FAIL doesn't respond

This patch adds a new msk->flags bit MPTCP_FAIL_NO_RESPONSE, then reuses
sk_timer to trigger a check if we have not received a response from the
peer after sending MP_FAIL. If the peer doesn't respond properly, reset
the subflow.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/mptcp/pm.c

@@ -287,6 +287,7 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	struct sock *s = (struct sock *)msk;
 
 	pr_debug("fail_seq=%llu", fail_seq);
 
@@ -299,6 +300,13 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
 		subflow->send_mp_fail = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
 		subflow->send_infinite_map = 1;
+	} else if (s && inet_sk_state_load(s) != TCP_CLOSE) {
+		pr_debug("MP_FAIL response received");
+
+		mptcp_data_lock(s);
+		if (inet_sk_state_load(s) != TCP_CLOSE)
+			sk_stop_timer(s, &s->sk_timer);
+		mptcp_data_unlock(s);
 	}
 }
 

net/mptcp/protocol.c

@@ -2169,10 +2169,38 @@ 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_check_mp_fail_response(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+
+	bh_lock_sock(sk);
+	subflow = mp_fail_response_expect_subflow(msk);
+	if (subflow)
+		__set_bit(MPTCP_FAIL_NO_RESPONSE, &msk->flags);
+	bh_unlock_sock(sk);
+}
+
 static void mptcp_timeout_timer(struct timer_list *t)
 {
 	struct sock *sk = from_timer(sk, t, sk_timer);
 
+	mptcp_check_mp_fail_response(mptcp_sk(sk));
 	mptcp_schedule_work(sk);
 	sock_put(sk);
 }
@@ -2499,6 +2527,23 @@ reset_timer:
 	mptcp_data_unlock(sk);
 }
 
+static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *ssk;
+	bool slow;
+
+	subflow = mp_fail_response_expect_subflow(msk);
+	if (subflow) {
+		pr_debug("MP_FAIL doesn't respond, reset the subflow");
+
+		ssk = mptcp_subflow_tcp_sock(subflow);
+		slow = lock_sock_fast(ssk);
+		mptcp_subflow_reset(ssk);
+		unlock_sock_fast(ssk, slow);
+	}
+}
+
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
@@ -2539,6 +2584,9 @@ static void mptcp_worker(struct work_struct *work)
 	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
 		__mptcp_retrans(sk);
 
+	if (test_and_clear_bit(MPTCP_FAIL_NO_RESPONSE, &msk->flags))
+		mptcp_mp_fail_no_response(msk);
+
 unlock:
 	release_sock(sk);
 	sock_put(sk);

net/mptcp/protocol.h

@@ -116,6 +116,7 @@
 #define MPTCP_WORK_EOF		3
 #define MPTCP_FALLBACK_DONE	4
 #define MPTCP_WORK_CLOSE_SUBFLOW 5
+#define MPTCP_FAIL_NO_RESPONSE	6
 
 /* MPTCP socket release cb flags */
 #define MPTCP_PUSH_PENDING	1

net/mptcp/subflow.c

@@ -968,6 +968,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	bool csum_reqd = READ_ONCE(msk->csum_enabled);
+	struct sock *sk = (struct sock *)msk;
 	struct mptcp_ext *mpext;
 	struct sk_buff *skb;
 	u16 data_len;
@@ -1009,6 +1010,12 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 		pr_debug("infinite mapping received");
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
 		subflow->map_data_len = 0;
+		if (sk && inet_sk_state_load(sk) != TCP_CLOSE) {
+			mptcp_data_lock(sk);
+			if (inet_sk_state_load(sk) != TCP_CLOSE)
+				sk_stop_timer(sk, &sk->sk_timer);
+			mptcp_data_unlock(sk);
+		}
 		return MAPPING_INVALID;
 	}
 
@@ -1219,6 +1226,10 @@ fallback:
 					sk_eat_skb(ssk, skb);
 			} else {
 				WRITE_ONCE(subflow->mp_fail_response_expect, true);
+				/* The data lock is acquired in __mptcp_move_skbs() */
+				sk_reset_timer((struct sock *)msk,
+					       &((struct sock *)msk)->sk_timer,
+					       jiffies + TCP_RTO_MAX);
 			}
 			WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
 			return true;