Commit ebf32282 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'mptcp-another-set-of-miscellaneous-mptcp-fixes' 

Mat Martineau says:

====================
mptcp: Another set of miscellaneous MPTCP fixes

This is another collection of MPTCP fixes and enhancements that we have
tested in the MPTCP tree:

Patch 1 cleans up cgroup attachment for in-kernel subflow sockets.

Patches 2 and 3 make sure that deletion of advertised addresses by an
MPTCP path manager when flushing all addresses behaves similarly to the
remove-single-address operation, and adds related tests.

Patches 4 and 8 do some minor cleanup.

Patches 5-7 add MPTCP_FASTCLOSE functionality. Note that patch 6 adds MPTCP
option parsing to tcp_reset().

Patch 9 optimizes skb size for outgoing MPTCP packets.
====================

Link: https://lore.kernel.org/r/20201210222506.222251-1-mathew.j.martineau@linux.intel.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents efc36d3c 15e6ca97

include/net/tcp.h

+1 −1
Original line number Diff line number Diff line
@@ -611,7 +611,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, 
/* tcp_input.c */

void tcp_rearm_rto(struct sock *sk);

void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);

void tcp_reset(struct sock *sk);

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

void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);

void tcp_fin(struct sock *sk);

net/ipv4/tcp_input.c

+8 −5
Original line number Diff line number Diff line
@@ -4218,10 +4218,13 @@ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) 
}



/* When we get a reset we do this. */

void tcp_reset(struct sock *sk)

void tcp_reset(struct sock *sk, struct sk_buff *skb)

{

	trace_tcp_receive_reset(sk);



	if (sk_is_mptcp(sk))

		mptcp_incoming_options(sk, skb);



	/* We want the right error as BSD sees it (and indeed as we do). */

	switch (sk->sk_state) {

	case TCP_SYN_SENT:
@@ -5604,7 +5607,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, 
						  &tp->last_oow_ack_time))

				tcp_send_dupack(sk, skb);

		} else if (tcp_reset_check(sk, skb)) {

			tcp_reset(sk);

			tcp_reset(sk, skb);

		}

		goto discard;

	}
@@ -5640,7 +5643,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, 
		}



		if (rst_seq_match)

			tcp_reset(sk);

			tcp_reset(sk, skb);

		else {

			/* Disable TFO if RST is out-of-order

			 * and no data has been received
@@ -6077,7 +6080,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, 
		 */



		if (th->rst) {

			tcp_reset(sk);

			tcp_reset(sk, skb);

			goto discard;

		}
@@ -6519,7 +6522,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) 
			if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&

			    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {

				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);

				tcp_reset(sk);

				tcp_reset(sk, skb);

				return 1;

			}

		}

net/ipv4/tcp_minisocks.c

+1 −1
Original line number Diff line number Diff line
@@ -801,7 +801,7 @@ embryonic_reset: 
		req->rsk_ops->send_reset(sk, skb);

	} else if (fastopen) { /* received a valid RST pkt */

		reqsk_fastopen_remove(sk, req, true);

		tcp_reset(sk);

		tcp_reset(sk, skb);

	}

	if (!fastopen) {

		inet_csk_reqsk_queue_drop(sk, req);

net/mptcp/options.c

+17 −0
Original line number Diff line number Diff line
@@ -282,6 +282,16 @@ static void mptcp_parse_option(const struct sk_buff *skb, 
		pr_debug("RM_ADDR: id=%d", mp_opt->rm_id);

		break;



	case MPTCPOPT_MP_FASTCLOSE:

		if (opsize != TCPOLEN_MPTCP_FASTCLOSE)

			break;



		ptr += 2;

		mp_opt->rcvr_key = get_unaligned_be64(ptr);

		ptr += 8;

		mp_opt->fastclose = 1;

		break;



	default:

		break;

	}
@@ -299,6 +309,7 @@ void mptcp_get_options(const struct sk_buff *skb, 
	mp_opt->mp_join = 0;

	mp_opt->add_addr = 0;

	mp_opt->ahmac = 0;

	mp_opt->fastclose = 0;

	mp_opt->port = 0;

	mp_opt->rm_addr = 0;

	mp_opt->dss = 0;
@@ -942,6 +953,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) 
	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))

		return;



	if (mp_opt.fastclose &&

	    msk->local_key == mp_opt.rcvr_key) {

		WRITE_ONCE(msk->rcv_fastclose, true);

		mptcp_schedule_work((struct sock *)msk);

	}



	if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) {

		struct mptcp_addr_info addr;

net/mptcp/pm_netlink.c

+12 −9
Original line number Diff line number Diff line
@@ -135,7 +135,7 @@ select_local_address(const struct pm_nl_pernet *pernet, 
	struct mptcp_pm_addr_entry *entry, *ret = NULL;



	rcu_read_lock();

	spin_lock_bh(&msk->join_list_lock);

	__mptcp_flush_join_list(msk);

	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {

		if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))

			continue;
@@ -144,13 +144,11 @@ select_local_address(const struct pm_nl_pernet *pernet, 
		 * pending join

		 */

		if (entry->addr.family == ((struct sock *)msk)->sk_family &&

		    !lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&

		    !lookup_subflow_by_saddr(&msk->join_list, &entry->addr)) {

		    !lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) {

			ret = entry;

			break;

		}

	}

	spin_unlock_bh(&msk->join_list_lock);

	rcu_read_unlock();

	return ret;

}
@@ -867,13 +865,14 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) 
	return ret;

}



static void __flush_addrs(struct pm_nl_pernet *pernet)

static void __flush_addrs(struct net *net, struct list_head *list)

{

	while (!list_empty(&pernet->local_addr_list)) {

	while (!list_empty(list)) {

		struct mptcp_pm_addr_entry *cur;



		cur = list_entry(pernet->local_addr_list.next,

		cur = list_entry(list->next,

				 struct mptcp_pm_addr_entry, list);

		mptcp_nl_remove_subflow_and_signal_addr(net, &cur->addr);

		list_del_rcu(&cur->list);

		kfree_rcu(cur, rcu);

	}
@@ -890,11 +889,13 @@ static void __reset_counters(struct pm_nl_pernet *pernet) 
static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info)

{

	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);

	LIST_HEAD(free_list);



	spin_lock_bh(&pernet->lock);

	__flush_addrs(pernet);

	list_splice_init(&pernet->local_addr_list, &free_list);

	__reset_counters(pernet);

	spin_unlock_bh(&pernet->lock);

	__flush_addrs(sock_net(skb->sk), &free_list);

	return 0;

}
@@ -1156,10 +1157,12 @@ static void __net_exit pm_nl_exit_net(struct list_head *net_list) 
	struct net *net;



	list_for_each_entry(net, net_list, exit_list) {

		struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id);



		/* net is removed from namespace list, can't race with

		 * other modifiers

		 */

		__flush_addrs(net_generic(net, pm_nl_pernet_id));

		__flush_addrs(net, &pernet->local_addr_list);

	}

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE