Commit f59798b8 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'mptcp-cleanups' 



Mat Martineau says:

====================
MPTCP: Cleanup and address advertisement fixes

This patch series contains cleanup and fixes we have been testing in the
MPTCP tree. MPTCP uses TCP option headers to advertise additional
address information after an initial connection is established. The main
fixes here deal with making those advertisements more reliable and
improving the way subflows are created after an advertisement is
received.

Patches 1, 2, 4, 10, and 12 are for various cleanup or refactoring.

Patch 3 skips an extra connection attempt if there's already a subflow
connection for the newly received advertisement.

Patches 5, 6, and 7 make sure that the next address is advertised when
there are multiple addresses to share, the advertisement has been
retried, and the peer has not echoed the advertisement. Self tests are
updated.

Patches 8 and 9 fix a problem similar to 5/6/7, but covers a case where
the failure was due to a subflow connection not completing.

Patches 11 and 13 send a bare ack to revoke an advertisement rather than
waiting for other activity to trigger a packet send. This mirrors the
way acks are sent for new advertisements. Self test is included.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 6cb502a3 ef360019

net/mptcp/options.c

+2 −1
Original line number Diff line number Diff line
@@ -882,7 +882,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, 
	subflow->pm_notified = 1;

	if (subflow->mp_join) {

		clear_3rdack_retransmission(ssk);

		mptcp_pm_subflow_established(msk, subflow);

		mptcp_pm_subflow_established(msk);

	} else {

		mptcp_pm_fully_established(msk, ssk, GFP_ATOMIC);

	}
@@ -1040,6 +1040,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) 
			mptcp_pm_add_addr_received(msk, &addr);

			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);

		} else {

			mptcp_pm_add_addr_echoed(msk, &addr);

			mptcp_pm_del_add_timer(msk, &addr);

			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD);

		}

net/mptcp/pm.c

+20 −5
Original line number Diff line number Diff line
@@ -14,7 +14,7 @@ 


int mptcp_pm_announce_addr(struct mptcp_sock *msk,

			   const struct mptcp_addr_info *addr,

			   bool echo, bool port)

			   bool echo)

{

	u8 add_addr = READ_ONCE(msk->pm.addr_signal);
@@ -33,7 +33,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, 
		add_addr |= BIT(MPTCP_ADD_ADDR_ECHO);

	if (addr->family == AF_INET6)

		add_addr |= BIT(MPTCP_ADD_ADDR_IPV6);

	if (port)

	if (addr->port)

		add_addr |= BIT(MPTCP_ADD_ADDR_PORT);

	WRITE_ONCE(msk->pm.addr_signal, add_addr);

	return 0;
@@ -53,6 +53,7 @@ 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_nl_addr_send_ack(msk);

	return 0;

}
@@ -152,8 +153,7 @@ void mptcp_pm_connection_closed(struct mptcp_sock *msk) 
	pr_debug("msk=%p", msk);

}



void mptcp_pm_subflow_established(struct mptcp_sock *msk,

				  struct mptcp_subflow_context *subflow)

void mptcp_pm_subflow_established(struct mptcp_sock *msk)

{

	struct mptcp_pm_data *pm = &msk->pm;
@@ -188,7 +188,7 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, 
	spin_lock_bh(&pm->lock);



	if (!READ_ONCE(pm->accept_addr)) {

		mptcp_pm_announce_addr(msk, addr, true, addr->port);

		mptcp_pm_announce_addr(msk, addr, true);

		mptcp_pm_add_addr_send_ack(msk);

	} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {

		pm->remote = *addr;
@@ -197,6 +197,21 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, 
	spin_unlock_bh(&pm->lock);

}



void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,

			      struct mptcp_addr_info *addr)

{

	struct mptcp_pm_data *pm = &msk->pm;



	pr_debug("msk=%p", msk);



	spin_lock_bh(&pm->lock);



	if (mptcp_lookup_anno_list_by_saddr(msk, addr) && READ_ONCE(pm->work_pending))

		mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED);



	spin_unlock_bh(&pm->lock);

}



void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk)

{

	if (!mptcp_pm_should_add_signal(msk))

net/mptcp/pm_netlink.c

+42 −27
Original line number Diff line number Diff line
@@ -56,8 +56,6 @@ struct pm_nl_pernet { 
#define MPTCP_PM_ADDR_MAX	8

#define ADD_ADDR_RETRANS_MAX	3



static void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk);



static bool addresses_equal(const struct mptcp_addr_info *a,

			    struct mptcp_addr_info *b, bool use_port)

{
@@ -140,6 +138,24 @@ static bool lookup_subflow_by_saddr(const struct list_head *list, 
	return false;

}



static bool lookup_subflow_by_daddr(const struct list_head *list,

				    struct mptcp_addr_info *daddr)

{

	struct mptcp_subflow_context *subflow;

	struct mptcp_addr_info cur;

	struct sock_common *skc;



	list_for_each_entry(subflow, list, node) {

		skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);



		remote_address(skc, &cur);

		if (addresses_equal(&cur, daddr, daddr->port))

			return true;

	}



	return false;

}



static struct mptcp_pm_addr_entry *

select_local_address(const struct pm_nl_pernet *pernet,

		     struct mptcp_sock *msk)
@@ -245,8 +261,8 @@ static void check_work_pending(struct mptcp_sock *msk) 
		WRITE_ONCE(msk->pm.work_pending, false);

}



static struct mptcp_pm_add_entry *

lookup_anno_list_by_saddr(struct mptcp_sock *msk,

struct mptcp_pm_add_entry *

mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk,

				struct mptcp_addr_info *addr)

{

	struct mptcp_pm_add_entry *entry;
@@ -308,7 +324,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) 


	if (!mptcp_pm_should_add_signal(msk)) {

		pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);

		mptcp_pm_announce_addr(msk, &entry->addr, false, entry->addr.port);

		mptcp_pm_announce_addr(msk, &entry->addr, false);

		mptcp_pm_add_addr_send_ack(msk);

		entry->retrans_times++;

	}
@@ -319,6 +335,9 @@ static void mptcp_pm_add_timer(struct timer_list *timer) 


	spin_unlock_bh(&msk->pm.lock);



	if (entry->retrans_times == ADD_ADDR_RETRANS_MAX)

		mptcp_pm_subflow_established(msk);



out:

	__sock_put(sk);

}
@@ -331,7 +350,7 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, 
	struct sock *sk = (struct sock *)msk;



	spin_lock_bh(&msk->pm.lock);

	entry = lookup_anno_list_by_saddr(msk, addr);

	entry = mptcp_lookup_anno_list_by_saddr(msk, addr);

	if (entry)

		entry->retrans_times = ADD_ADDR_RETRANS_MAX;

	spin_unlock_bh(&msk->pm.lock);
@@ -351,7 +370,7 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, 


	lockdep_assert_held(&msk->pm.lock);



	if (lookup_anno_list_by_saddr(msk, &entry->addr))

	if (mptcp_lookup_anno_list_by_saddr(msk, &entry->addr))

		return false;



	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
@@ -417,8 +436,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) 
		if (local) {

			if (mptcp_pm_alloc_anno_list(msk, local)) {

				msk->pm.add_addr_signaled++;

				mptcp_pm_announce_addr(msk, &local->addr, false, local->addr.port);

				mptcp_pm_nl_add_addr_send_ack(msk);

				mptcp_pm_announce_addr(msk, &local->addr, false);

				mptcp_pm_nl_addr_send_ack(msk);

			}

		} else {

			/* pick failed, avoid fourther attempts later */
@@ -468,7 +487,6 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) 
	struct mptcp_addr_info remote;

	struct mptcp_addr_info local;

	unsigned int subflows_max;

	bool use_port = false;



	add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);

	subflows_max = mptcp_pm_get_subflows_max(msk);
@@ -476,6 +494,10 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) 
	pr_debug("accepted %d:%d remote family %d",

		 msk->pm.add_addr_accepted, add_addr_accept_max,

		 msk->pm.remote.family);



	if (lookup_subflow_by_daddr(&msk->conn_list, &msk->pm.remote))

		goto add_addr_echo;



	msk->pm.add_addr_accepted++;

	msk->pm.subflows++;

	if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
@@ -488,8 +510,6 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) 
	remote = msk->pm.remote;

	if (!remote.port)

		remote.port = sk->sk_dport;

	else

		use_port = true;

	memset(&local, 0, sizeof(local));

	local.family = remote.family;
@@ -497,28 +517,30 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) 
	__mptcp_subflow_connect(sk, &local, &remote);

	spin_lock_bh(&msk->pm.lock);



	mptcp_pm_announce_addr(msk, &remote, true, use_port);

	mptcp_pm_nl_add_addr_send_ack(msk);

add_addr_echo:

	mptcp_pm_announce_addr(msk, &msk->pm.remote, true);

	mptcp_pm_nl_addr_send_ack(msk);

}



static void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk)

void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)

{

	struct mptcp_subflow_context *subflow;



	msk_owned_by_me(msk);

	lockdep_assert_held(&msk->pm.lock);



	if (!mptcp_pm_should_add_signal(msk))

	if (!mptcp_pm_should_add_signal(msk) &&

	    !mptcp_pm_should_rm_signal(msk))

		return;



	__mptcp_flush_join_list(msk);

	subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);

	if (subflow) {

		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		u8 add_addr;



		spin_unlock_bh(&msk->pm.lock);

		pr_debug("send ack for add_addr%s%s",

		pr_debug("send ack for %s%s%s",

			 mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr",

			 mptcp_pm_should_add_signal_ipv6(msk) ? " [ipv6]" : "",

			 mptcp_pm_should_add_signal_port(msk) ? " [port]" : "");
@@ -526,13 +548,6 @@ static void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk) 
		tcp_send_ack(ssk);

		release_sock(ssk);

		spin_lock_bh(&msk->pm.lock);



		add_addr = READ_ONCE(msk->pm.addr_signal);

		if (mptcp_pm_should_add_signal_ipv6(msk))

			add_addr &= ~BIT(MPTCP_ADD_ADDR_IPV6);

		if (mptcp_pm_should_add_signal_port(msk))

			add_addr &= ~BIT(MPTCP_ADD_ADDR_PORT);

		WRITE_ONCE(msk->pm.addr_signal, add_addr);

	}

}
@@ -627,7 +642,7 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk) 
	}

	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {

		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);

		mptcp_pm_nl_add_addr_send_ack(msk);

		mptcp_pm_nl_addr_send_ack(msk);

	}

	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {

		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);

net/mptcp/protocol.c

+11 −31
Original line number Diff line number Diff line
@@ -2047,28 +2047,21 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, 
	return copied;

}



static void mptcp_retransmit_handler(struct sock *sk)

{

	struct mptcp_sock *msk = mptcp_sk(sk);



	set_bit(MPTCP_WORK_RTX, &msk->flags);

	mptcp_schedule_work(sk);

}



static void mptcp_retransmit_timer(struct timer_list *t)

{

	struct inet_connection_sock *icsk = from_timer(icsk, t,

						       icsk_retransmit_timer);

	struct sock *sk = &icsk->icsk_inet.sk;

	struct mptcp_sock *msk = mptcp_sk(sk);



	bh_lock_sock(sk);

	if (!sock_owned_by_user(sk)) {

		mptcp_retransmit_handler(sk);

		/* we need a process context to retransmit */

		if (!test_and_set_bit(MPTCP_WORK_RTX, &msk->flags))

			mptcp_schedule_work(sk);

	} else {

		/* delegate our work to tcp_release_cb() */

		if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED,

				      &sk->sk_tsq_flags))

			sock_hold(sk);

		set_bit(MPTCP_RETRANSMIT, &msk->flags);

	}

	bh_unlock_sock(sk);

	sock_put(sk);
@@ -2958,17 +2951,16 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk) 
	}

}



#define MPTCP_DEFERRED_ALL (TCPF_WRITE_TIMER_DEFERRED)



/* processes deferred events and flush wmem */

static void mptcp_release_cb(struct sock *sk)

{

	unsigned long flags, nflags;



	for (;;) {

		flags = 0;

		unsigned long flags = 0;



		if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags))

			flags |= BIT(MPTCP_PUSH_PENDING);

		if (test_and_clear_bit(MPTCP_RETRANSMIT, &mptcp_sk(sk)->flags))

			flags |= BIT(MPTCP_RETRANSMIT);

		if (!flags)

			break;
@@ -2983,6 +2975,8 @@ static void mptcp_release_cb(struct sock *sk) 
		spin_unlock_bh(&sk->sk_lock.slock);

		if (flags & BIT(MPTCP_PUSH_PENDING))

			__mptcp_push_pending(sk, 0);

		if (flags & BIT(MPTCP_RETRANSMIT))

			__mptcp_retrans(sk);



		cond_resched();

		spin_lock_bh(&sk->sk_lock.slock);
@@ -2998,20 +2992,6 @@ static void mptcp_release_cb(struct sock *sk) 
	 */

	__mptcp_update_wmem(sk);

	__mptcp_update_rmem(sk);



	do {

		flags = sk->sk_tsq_flags;

		if (!(flags & MPTCP_DEFERRED_ALL))

			return;

		nflags = flags & ~MPTCP_DEFERRED_ALL;

	} while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags);



	sock_release_ownership(sk);



	if (flags & TCPF_WRITE_TIMER_DEFERRED) {

		mptcp_retransmit_handler(sk);

		__sock_put(sk);

	}

}



void mptcp_subflow_process_delegated(struct sock *ssk)

net/mptcp/protocol.h

+9 −3
Original line number Diff line number Diff line
@@ -104,6 +104,7 @@ 
#define MPTCP_PUSH_PENDING	6

#define MPTCP_CLEAN_UNA		7

#define MPTCP_ERROR_REPORT	8

#define MPTCP_RETRANSMIT	9



static inline bool before64(__u64 seq1, __u64 seq2)

{
@@ -642,12 +643,14 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int 
void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp);

bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);

void mptcp_pm_connection_closed(struct mptcp_sock *msk);

void mptcp_pm_subflow_established(struct mptcp_sock *msk,

				  struct mptcp_subflow_context *subflow);

void mptcp_pm_subflow_established(struct mptcp_sock *msk);

void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id);

void mptcp_pm_add_addr_received(struct mptcp_sock *msk,

				const struct mptcp_addr_info *addr);

void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,

			      struct mptcp_addr_info *addr);

void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);

void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk);

void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,

			       const struct mptcp_rm_list *rm_list);

void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
@@ -659,10 +662,13 @@ bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); 
struct mptcp_pm_add_entry *

mptcp_pm_del_add_timer(struct mptcp_sock *msk,

		       struct mptcp_addr_info *addr);

struct mptcp_pm_add_entry *

mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk,

				struct mptcp_addr_info *addr);



int mptcp_pm_announce_addr(struct mptcp_sock *msk,

			   const struct mptcp_addr_info *addr,

			   bool echo, bool port);

			   bool echo);

int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);

int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);