Commit 8179cc47 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'mptcp-mib-counters' 



Matthieu Baerts says:

====================
mptcp: add CurrEstab MIB counter

This MIB counter is similar to the one of TCP -- CurrEstab -- available
in /proc/net/snmp. This is useful to quickly list the number of MPTCP
connections without having to iterate over all of them.

Patch 1 prepares its support by adding new helper functions:

 - MPTCP_DEC_STATS(): similar to MPTCP_INC_STATS(), but this time to
   decrement a counter.

 - mptcp_set_state(): similar to tcp_set_state(), to change the state of
   an MPTCP socket, and to inc/decrement the new counter when needed.

Patch 2 uses mptcp_set_state() instead of directly calling
inet_sk_state_store() to change the state of MPTCP sockets.

Patch 3 and 4 validate the new feature in MPTCP "join" and "diag"
selftests.
====================

Signed-off-by: default avatarMatthieu Baerts <matttbe@kernel.org>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 42a7889a 81ab7728

net/mptcp/mib.c

+1 −0
Original line number Diff line number Diff line
@@ -66,6 +66,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { 
	SNMP_MIB_ITEM("RcvWndShared", MPTCP_MIB_RCVWNDSHARED),

	SNMP_MIB_ITEM("RcvWndConflictUpdate", MPTCP_MIB_RCVWNDCONFLICTUPDATE),

	SNMP_MIB_ITEM("RcvWndConflict", MPTCP_MIB_RCVWNDCONFLICT),

	SNMP_MIB_ITEM("MPCurrEstab", MPTCP_MIB_CURRESTAB),

	SNMP_MIB_SENTINEL

};

net/mptcp/mib.h

+8 −0
Original line number Diff line number Diff line
@@ -65,6 +65,7 @@ enum linux_mptcp_mib_field { 
					 * conflict with another subflow while updating msk rcv wnd

					 */

	MPTCP_MIB_RCVWNDCONFLICT,	/* Conflict with while updating msk rcv wnd */

	MPTCP_MIB_CURRESTAB,		/* Current established MPTCP connections */

	__MPTCP_MIB_MAX

};
@@ -95,4 +96,11 @@ static inline void __MPTCP_INC_STATS(struct net *net, 
		__SNMP_INC_STATS(net->mib.mptcp_statistics, field);

}



static inline void MPTCP_DEC_STATS(struct net *net,

				   enum linux_mptcp_mib_field field)

{

	if (likely(net->mib.mptcp_statistics))

		SNMP_DEC_STATS(net->mib.mptcp_statistics, field);

}



bool mptcp_mib_alloc(struct net *net);

net/mptcp/pm_netlink.c

+5 −0
Original line number Diff line number Diff line
@@ -1048,6 +1048,11 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, 
	if (err)

		return err;



	/* We don't use mptcp_set_state() here because it needs to be called

	 * under the msk socket lock. For the moment, that will not bring

	 * anything more than only calling inet_sk_state_store(), because the

	 * old status is known (TCP_CLOSE).

	 */

	inet_sk_state_store(newsk, TCP_LISTEN);

	lock_sock(ssk);

	err = __inet_listen_sk(ssk, backlog);

net/mptcp/protocol.c

+37 −19
Original line number Diff line number Diff line
@@ -429,11 +429,11 @@ static void mptcp_check_data_fin_ack(struct sock *sk) 


		switch (sk->sk_state) {

		case TCP_FIN_WAIT1:

			inet_sk_state_store(sk, TCP_FIN_WAIT2);

			mptcp_set_state(sk, TCP_FIN_WAIT2);

			break;

		case TCP_CLOSING:

		case TCP_LAST_ACK:

			inet_sk_state_store(sk, TCP_CLOSE);

			mptcp_set_state(sk, TCP_CLOSE);

			break;

		}
@@ -594,13 +594,13 @@ static bool mptcp_check_data_fin(struct sock *sk) 


		switch (sk->sk_state) {

		case TCP_ESTABLISHED:

			inet_sk_state_store(sk, TCP_CLOSE_WAIT);

			mptcp_set_state(sk, TCP_CLOSE_WAIT);

			break;

		case TCP_FIN_WAIT1:

			inet_sk_state_store(sk, TCP_CLOSING);

			mptcp_set_state(sk, TCP_CLOSING);

			break;

		case TCP_FIN_WAIT2:

			inet_sk_state_store(sk, TCP_CLOSE);

			mptcp_set_state(sk, TCP_CLOSE);

			break;

		default:

			/* Other states not expected */
@@ -775,7 +775,7 @@ static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) 
	 */

	ssk_state = inet_sk_state_load(ssk);

	if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))

		inet_sk_state_store(sk, ssk_state);

		mptcp_set_state(sk, ssk_state);

	WRITE_ONCE(sk->sk_err, -err);



	/* This barrier is coupled with smp_rmb() in mptcp_poll() */
@@ -2463,7 +2463,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, 
	    inet_sk_state_load(msk->first) == TCP_CLOSE) {

		if (sk->sk_state != TCP_ESTABLISHED ||

		    msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) {

			inet_sk_state_store(sk, TCP_CLOSE);

			mptcp_set_state(sk, TCP_CLOSE);

			mptcp_close_wake_up(sk);

		} else {

			mptcp_start_tout_timer(sk);
@@ -2558,7 +2558,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) 
		WRITE_ONCE(sk->sk_err, ECONNRESET);

	}



	inet_sk_state_store(sk, TCP_CLOSE);

	mptcp_set_state(sk, TCP_CLOSE);

	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);

	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */

	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
@@ -2693,7 +2693,7 @@ static void mptcp_do_fastclose(struct sock *sk) 
	struct mptcp_subflow_context *subflow, *tmp;

	struct mptcp_sock *msk = mptcp_sk(sk);



	inet_sk_state_store(sk, TCP_CLOSE);

	mptcp_set_state(sk, TCP_CLOSE);

	mptcp_for_each_subflow_safe(msk, subflow, tmp)

		__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow),

				  subflow, MPTCP_CF_FASTCLOSE);
@@ -2871,6 +2871,24 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) 
	release_sock(ssk);

}



void mptcp_set_state(struct sock *sk, int state)

{

	int oldstate = sk->sk_state;



	switch (state) {

	case TCP_ESTABLISHED:

		if (oldstate != TCP_ESTABLISHED)

			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);

		break;



	default:

		if (oldstate == TCP_ESTABLISHED)

			MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);

	}



	inet_sk_state_store(sk, state);

}



static const unsigned char new_state[16] = {

	/* current state:     new state:      action:	*/

	[0 /* (Invalid) */] = TCP_CLOSE,
@@ -2893,7 +2911,7 @@ static int mptcp_close_state(struct sock *sk) 
	int next = (int)new_state[sk->sk_state];

	int ns = next & TCP_STATE_MASK;



	inet_sk_state_store(sk, ns);

	mptcp_set_state(sk, ns);



	return next & TCP_ACTION_FIN;

}
@@ -3004,7 +3022,7 @@ bool __mptcp_close(struct sock *sk, long timeout) 


	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {

		mptcp_check_listen_stop(sk);

		inet_sk_state_store(sk, TCP_CLOSE);

		mptcp_set_state(sk, TCP_CLOSE);

		goto cleanup;

	}
@@ -3047,7 +3065,7 @@ bool __mptcp_close(struct sock *sk, long timeout) 
	 * state, let's not keep resources busy for no reasons

	 */

	if (subflows_alive == 0)

		inet_sk_state_store(sk, TCP_CLOSE);

		mptcp_set_state(sk, TCP_CLOSE);



	sock_hold(sk);

	pr_debug("msk=%p state=%d", sk, sk->sk_state);
@@ -3113,7 +3131,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) 
		return -EBUSY;



	mptcp_check_listen_stop(sk);

	inet_sk_state_store(sk, TCP_CLOSE);

	mptcp_set_state(sk, TCP_CLOSE);



	mptcp_stop_rtx_timer(sk);

	mptcp_stop_tout_timer(sk);
@@ -3201,7 +3219,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, 
	/* this can't race with mptcp_close(), as the msk is

	 * not yet exposted to user-space

	 */

	inet_sk_state_store(nsk, TCP_ESTABLISHED);

	mptcp_set_state(nsk, TCP_ESTABLISHED);



	/* The msk maintain a ref to each subflow in the connections list */

	WRITE_ONCE(msk->first, ssk);
@@ -3622,7 +3640,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) 
	if (IS_ERR(ssk))

		return PTR_ERR(ssk);



	inet_sk_state_store(sk, TCP_SYN_SENT);

	mptcp_set_state(sk, TCP_SYN_SENT);

	subflow = mptcp_subflow_ctx(ssk);

#ifdef CONFIG_TCP_MD5SIG

	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
@@ -3672,7 +3690,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) 
	if (unlikely(err)) {

		/* avoid leaving a dangling token in an unconnected socket */

		mptcp_token_destroy(msk);

		inet_sk_state_store(sk, TCP_CLOSE);

		mptcp_set_state(sk, TCP_CLOSE);

		return err;

	}
@@ -3761,13 +3779,13 @@ static int mptcp_listen(struct socket *sock, int backlog) 
		goto unlock;

	}



	inet_sk_state_store(sk, TCP_LISTEN);

	mptcp_set_state(sk, TCP_LISTEN);

	sock_set_flag(sk, SOCK_RCU_FREE);



	lock_sock(ssk);

	err = __inet_listen_sk(ssk, backlog);

	release_sock(ssk);

	inet_sk_state_store(sk, inet_sk_state_load(ssk));

	mptcp_set_state(sk, inet_sk_state_load(ssk));



	if (!err) {

		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -3845,7 +3863,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, 
			__mptcp_close_ssk(newsk, msk->first,

					  mptcp_subflow_ctx(msk->first), 0);

			if (unlikely(list_is_singular(&msk->conn_list)))

				inet_sk_state_store(newsk, TCP_CLOSE);

				mptcp_set_state(newsk, TCP_CLOSE);

		}

	} else {

		MPTCP_INC_STATS(sock_net(ssk),

net/mptcp/protocol.h

+1 −0
Original line number Diff line number Diff line
@@ -641,6 +641,7 @@ bool __mptcp_close(struct sock *sk, long timeout); 
void mptcp_cancel_work(struct sock *sk);

void __mptcp_unaccepted_force_close(struct sock *sk);

void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk);

void mptcp_set_state(struct sock *sk, int state);



bool mptcp_addresses_equal(const struct mptcp_addr_info *a,

			   const struct mptcp_addr_info *b, bool use_port);