Lines Matching full:subflows

194 	/* with 2 subflows, adding at end of ooo queue is quite likely  in mptcp_data_queue_ofo()
1906  * Only difference: Use highest rtt estimate of the subflows in use.
1978 			/* Make subflows follow along.  If we do not do this, we  in mptcp_rcv_space_adjust()
2039 		 * As an optimization avoid traversing the subflows list  in __mptcp_move_skbs()
2335  * Outgoing subflows use in-kernel sockets.
2336  * Incoming subflows do not have their own 'struct socket' allocated,
2416 	/* Catch every 'all subflows closed' scenario, including peers silently  in __mptcp_close_ssk()
2419 	 * as the protocol can still create more subflows.  in __mptcp_close_ssk()
2587 			/* limit retransmission to the bytes already sent on some subflows */  in __mptcp_retrans()
2904 	/* we still need to enqueue subflows or not really shutting down,  in mptcp_check_send_data_fin()
3016 	/* orphan all the subflows */  in __mptcp_close()
3038 	/* all the subflows are closed, only timeout can change the msk  in __mptcp_close()
3100 	 * subflows cleanup code due to lock nesting (we are already under  in mptcp_disconnect()
3454 	 * we hash the TCP subflows not the MPTCP socket  in mptcp_hash()