mptcp: do not reset MP_CAPABLE subflow on mapping errors

When some mapping related errors occurs we close the main
MPC subflow with a RST. We should instead fallback gracefully
to TCP, and do the reset only for MPJ subflows.

Fixes: d22f4988ffec ("mptcp: process MP_CAPABLE data option")
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/192
Reported-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c6ee811..ef3d037 100644 (file)
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1011,21 +1011,11 @@ static bool subflow_check_data_avail(struct sock *ssk)
 
                status = get_mapping_status(ssk, msk);
                trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
-               if (status == MAPPING_INVALID) {
-                       ssk->sk_err = EBADMSG;
-                       goto fatal;
-               }
-               if (status == MAPPING_DUMMY) {
-                       __mptcp_do_fallback(msk);
-                       skb = skb_peek(&ssk->sk_receive_queue);
-                       subflow->map_valid = 1;
-                       subflow->map_seq = READ_ONCE(msk->ack_seq);
-                       subflow->map_data_len = skb->len;
-                       subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq -
-                                                  subflow->ssn_offset;
-                       subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
-                       return true;
-               }
+               if (unlikely(status == MAPPING_INVALID))
+                       goto fallback;
+
+               if (unlikely(status == MAPPING_DUMMY))
+                       goto fallback;
 
                if (status != MAPPING_OK)
                        goto no_data;
@@ -1038,10 +1028,8 @@ static bool subflow_check_data_avail(struct sock *ssk)
                 * MP_CAPABLE-based mapping
                 */
                if (unlikely(!READ_ONCE(msk->can_ack))) {
-                       if (!subflow->mpc_map) {
-                               ssk->sk_err = EBADMSG;
-                               goto fatal;
-                       }
+                       if (!subflow->mpc_map)
+                               goto fallback;
                        WRITE_ONCE(msk->remote_key, subflow->remote_key);
                        WRITE_ONCE(msk->ack_seq, subflow->map_seq);
                        WRITE_ONCE(msk->can_ack, true);
@@ -1069,17 +1057,31 @@ static bool subflow_check_data_avail(struct sock *ssk)
 no_data:
        subflow_sched_work_if_closed(msk, ssk);
        return false;
-fatal:
-       /* fatal protocol error, close the socket */
-       /* This barrier is coupled with smp_rmb() in tcp_poll() */
-       smp_wmb();
-       ssk->sk_error_report(ssk);
-       tcp_set_state(ssk, TCP_CLOSE);
-       subflow->reset_transient = 0;
-       subflow->reset_reason = MPTCP_RST_EMPTCP;
-       tcp_send_active_reset(ssk, GFP_ATOMIC);
-       subflow->data_avail = 0;
-       return false;
+
+fallback:
+       /* RFC 8684 section 3.7. */
+       if (subflow->mp_join || subflow->fully_established) {
+               /* fatal protocol error, close the socket.
+                * subflow_error_report() will introduce the appropriate barriers
+                */
+               ssk->sk_err = EBADMSG;
+               ssk->sk_error_report(ssk);
+               tcp_set_state(ssk, TCP_CLOSE);
+               subflow->reset_transient = 0;
+               subflow->reset_reason = MPTCP_RST_EMPTCP;
+               tcp_send_active_reset(ssk, GFP_ATOMIC);
+               subflow->data_avail = 0;
+               return false;
+       }
+
+       __mptcp_do_fallback(msk);
+       skb = skb_peek(&ssk->sk_receive_queue);
+       subflow->map_valid = 1;
+       subflow->map_seq = READ_ONCE(msk->ack_seq);
+       subflow->map_data_len = skb->len;
+       subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
+       subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
+       return true;
 }
 
 bool mptcp_subflow_data_available(struct sock *sk)