Commit 8846f9a0 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'mptcp-features-and-fixes-for-v6-7' 

Mat Martineau says:

====================
mptcp: Features and fixes for v6.7

Patch 1 adds a configurable timeout for the MPTCP connection when all
subflows are closed, to support break-before-make use cases.

Patch 2 is a fix for a 1-byte error in rx data counters with MPTCP
fastopen connections.

Patch 3 is a minor code cleanup.

Patches 4 & 5 add handling of rcvlowat for MPTCP sockets, with a
prerequisite patch to use a common scaling ratio between TCP and MPTCP.

Patch 6 improves efficiency of memory copying in MPTCP transmit code.

Patch 7 refactors syncing of socket options from the MPTCP socket to
its subflows.

Patches 8 & 9 help the MPTCP packet scheduler perform well by changing
the handling of notsent_lowat in subflows and how available buffer space
is calculated for MPTCP-level sends.
====================

Link: https://lore.kernel.org/r/20231023-send-net-next-20231023-2-v1-0-9dc60939d371@kernel.org


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents aad36cd3 8005184f

Documentation/networking/mptcp-sysctl.rst

+11 −0
Original line number Diff line number Diff line
@@ -25,6 +25,17 @@ add_addr_timeout - INTEGER (seconds) 


	Default: 120



close_timeout - INTEGER (seconds)

	Set the make-after-break timeout: in absence of any close or

	shutdown syscall, MPTCP sockets will maintain the status

	unchanged for such time, after the last subflow removal, before

	moving to TCP_CLOSE.



	The default value matches TCP_TIMEWAIT_LEN. This is a per-namespace

	sysctl.



	Default: 60



checksum_enabled - BOOLEAN

	Control whether DSS checksum can be enabled.

include/net/tcp.h

+7 −5
Original line number Diff line number Diff line
@@ -1489,13 +1489,15 @@ static inline int tcp_space_from_win(const struct sock *sk, int win) 
	return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win);

}



static inline void tcp_scaling_ratio_init(struct sock *sk)

{

/* Assume a conservative default of 1200 bytes of payload per 4K page.

 * This may be adjusted later in tcp_measure_rcv_mss().

 */

	tcp_sk(sk)->scaling_ratio = (1200 << TCP_RMEM_TO_WIN_SCALE) /

				    SKB_TRUESIZE(4096);

#define TCP_DEFAULT_SCALING_RATIO ((1200 << TCP_RMEM_TO_WIN_SCALE) / \

				   SKB_TRUESIZE(4096))



static inline void tcp_scaling_ratio_init(struct sock *sk)

{

	tcp_sk(sk)->scaling_ratio = TCP_DEFAULT_SCALING_RATIO;

}



/* Note: caller must be prepared to deal with negative returns */

net/mptcp/ctrl.c

+16 −0
Original line number Diff line number Diff line
@@ -27,6 +27,7 @@ struct mptcp_pernet { 
#endif



	unsigned int add_addr_timeout;

	unsigned int close_timeout;

	unsigned int stale_loss_cnt;

	u8 mptcp_enabled;

	u8 checksum_enabled;
@@ -65,6 +66,13 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net) 
	return mptcp_get_pernet(net)->stale_loss_cnt;

}



unsigned int mptcp_close_timeout(const struct sock *sk)

{

	if (sock_flag(sk, SOCK_DEAD))

		return TCP_TIMEWAIT_LEN;

	return mptcp_get_pernet(sock_net(sk))->close_timeout;

}



int mptcp_get_pm_type(const struct net *net)

{

	return mptcp_get_pernet(net)->pm_type;
@@ -79,6 +87,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) 
{

	pernet->mptcp_enabled = 1;

	pernet->add_addr_timeout = TCP_RTO_MAX;

	pernet->close_timeout = TCP_TIMEWAIT_LEN;

	pernet->checksum_enabled = 0;

	pernet->allow_join_initial_addr_port = 1;

	pernet->stale_loss_cnt = 4;
@@ -141,6 +150,12 @@ static struct ctl_table mptcp_sysctl_table[] = { 
		.mode = 0644,

		.proc_handler = proc_dostring,

	},

	{

		.procname = "close_timeout",

		.maxlen = sizeof(unsigned int),

		.mode = 0644,

		.proc_handler = proc_dointvec_jiffies,

	},

	{}

};
@@ -163,6 +178,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) 
	table[4].data = &pernet->stale_loss_cnt;

	table[5].data = &pernet->pm_type;

	table[6].data = &pernet->scheduler;

	table[7].data = &pernet->close_timeout;



	hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,

				     ARRAY_SIZE(mptcp_sysctl_table));

net/mptcp/fastopen.c

+1 −0
Original line number Diff line number Diff line
@@ -52,6 +52,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf 


	mptcp_set_owner_r(skb, sk);

	__skb_queue_tail(&sk->sk_receive_queue, skb);

	mptcp_sk(sk)->bytes_received += skb->len;



	sk->sk_data_ready(sk);

net/mptcp/protocol.c

+45 −24
Original line number Diff line number Diff line
@@ -121,8 +121,6 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) 
		ret = __mptcp_socket_create(msk);

		if (ret)

			return ERR_PTR(ret);



		mptcp_sockopt_sync(msk, msk->first);

	}



	return msk->first;
@@ -863,9 +861,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) 


	/* Wake-up the reader only for in-sequence data */

	mptcp_data_lock(sk);

	if (move_skbs_to_msk(msk, ssk))

	if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk))

		sk->sk_data_ready(sk);



	mptcp_data_unlock(sk);

}
@@ -893,6 +890,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) 
	mptcp_sockopt_sync_locked(msk, ssk);

	mptcp_subflow_joined(msk, ssk);

	mptcp_stop_tout_timer(sk);

	__mptcp_propagate_sndbuf(sk, ssk);

	return true;

}
@@ -1079,15 +1077,16 @@ static void mptcp_enter_memory_pressure(struct sock *sk) 
	struct mptcp_sock *msk = mptcp_sk(sk);

	bool first = true;



	sk_stream_moderate_sndbuf(sk);

	mptcp_for_each_subflow(msk, subflow) {

		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);



		if (first)

			tcp_enter_memory_pressure(ssk);

		sk_stream_moderate_sndbuf(ssk);



		first = false;

	}

	__mptcp_sync_sndbuf(sk);

}



/* ensure we get enough memory for the frag hdr, beyond some minimal amount of
@@ -1761,6 +1760,18 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, 
	return ret;

}



static int do_copy_data_nocache(struct sock *sk, int copy,

				struct iov_iter *from, char *to)

{

	if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {

		if (!copy_from_iter_full_nocache(to, copy, from))

			return -EFAULT;

	} else if (!copy_from_iter_full(to, copy, from)) {

		return -EFAULT;

	}

	return 0;

}



static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

{

	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1834,11 +1845,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 
		if (!sk_wmem_schedule(sk, total_ts))

			goto wait_for_memory;



		if (copy_page_from_iter(dfrag->page, offset, psize,

					&msg->msg_iter) != psize) {

			ret = -EFAULT;

		ret = do_copy_data_nocache(sk, psize, &msg->msg_iter,

					   page_address(dfrag->page) + offset);

		if (ret)

			goto do_error;

		}



		/* data successfully copied into the write queue */

		sk_forward_alloc_add(sk, -total_ts);
@@ -1922,6 +1932,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, 
			if (!(flags & MSG_PEEK)) {

				MPTCP_SKB_CB(skb)->offset += count;

				MPTCP_SKB_CB(skb)->map_seq += count;

				msk->bytes_consumed += count;

			}

			break;

		}
@@ -1932,6 +1943,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, 
			WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);

			__skb_unlink(skb, &msk->receive_queue);

			__kfree_skb(skb);

			msk->bytes_consumed += count;

		}



		if (copied >= len)
@@ -2391,8 +2403,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, 
	if (msk->in_accept_queue && msk->first == ssk &&

	    (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) {

		/* ensure later check in mptcp_worker() will dispose the msk */

		mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1));

		sock_set_flag(sk, SOCK_DEAD);

		mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1));

		lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);

		mptcp_subflow_drop_ctx(ssk);

		goto out_release;
@@ -2448,6 +2460,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, 
		WRITE_ONCE(msk->first, NULL);



out:

	__mptcp_sync_sndbuf(sk);

	if (need_push)

		__mptcp_push_pending(sk, 0);
@@ -2516,7 +2529,7 @@ static bool mptcp_close_tout_expired(const struct sock *sk) 
		return false;



	return time_after32(tcp_jiffies32,

		  inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN);

		  inet_csk(sk)->icsk_mtup.probe_timestamp + mptcp_close_timeout(sk));

}



static void mptcp_check_fastclose(struct mptcp_sock *msk)
@@ -2659,7 +2672,7 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) 
		return;



	close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies +

			TCP_TIMEWAIT_LEN;

			mptcp_close_timeout(sk);



	/* the close timeout takes precedence on the fail one, and here at least one of

	 * them is active
@@ -2755,6 +2768,7 @@ static void __mptcp_init_sock(struct sock *sk) 
	msk->rmem_fwd_alloc = 0;

	WRITE_ONCE(msk->rmem_released, 0);

	msk->timer_ival = TCP_RTO_MIN;

	msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO;



	WRITE_ONCE(msk->first, NULL);

	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
@@ -2964,16 +2978,9 @@ void __mptcp_unaccepted_force_close(struct sock *sk) 
	__mptcp_destroy_sock(sk);

}



static __poll_t mptcp_check_readable(struct mptcp_sock *msk)

static __poll_t mptcp_check_readable(struct sock *sk)

{

	/* Concurrent splices from sk_receive_queue into receive_queue will

	 * always show at least one non-empty queue when checked in this order.

	 */

	if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) &&

	    skb_queue_empty_lockless(&msk->receive_queue))

		return 0;



	return EPOLLIN | EPOLLRDNORM;

	return mptcp_epollin_ready(sk) ? EPOLLIN | EPOLLRDNORM : 0;

}



static void mptcp_check_listen_stop(struct sock *sk)
@@ -3011,7 +3018,7 @@ bool __mptcp_close(struct sock *sk, long timeout) 
		goto cleanup;

	}



	if (mptcp_check_readable(msk) || timeout < 0) {

	if (mptcp_data_avail(msk) || timeout < 0) {

		/* If the msk has read data, or the caller explicitly ask it,

		 * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose

		 */
@@ -3138,6 +3145,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) 
	msk->snd_data_fin_enable = false;

	msk->rcv_fastclose = false;

	msk->use_64bit_ack = false;

	msk->bytes_consumed = 0;

	WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));

	mptcp_pm_data_reset(msk);

	mptcp_ca_reset(sk);
@@ -3219,7 +3227,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, 
	 * uses the correct data

	 */

	mptcp_copy_inaddrs(nsk, ssk);

	mptcp_propagate_sndbuf(nsk, ssk);

	__mptcp_propagate_sndbuf(nsk, ssk);



	mptcp_rcv_space_init(msk, ssk);

	bh_unlock_sock(nsk);
@@ -3397,6 +3405,8 @@ static void mptcp_release_cb(struct sock *sk) 
			__mptcp_set_connected(sk);

		if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))

			__mptcp_error_report(sk);

		if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags))

			__mptcp_sync_sndbuf(sk);

	}



	__mptcp_update_rmem(sk);
@@ -3441,6 +3451,14 @@ void mptcp_subflow_process_delegated(struct sock *ssk, long status) 
			__set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags);

		mptcp_data_unlock(sk);

	}

	if (status & BIT(MPTCP_DELEGATE_SNDBUF)) {

		mptcp_data_lock(sk);

		if (!sock_owned_by_user(sk))

			__mptcp_sync_sndbuf(sk);

		else

			__set_bit(MPTCP_SYNC_SNDBUF, &mptcp_sk(sk)->cb_flags);

		mptcp_data_unlock(sk);

	}

	if (status & BIT(MPTCP_DELEGATE_ACK))

		schedule_3rdack_retransmission(ssk);

}
@@ -3525,6 +3543,7 @@ bool mptcp_finish_join(struct sock *ssk) 
	/* active subflow, already present inside the conn_list */

	if (!list_empty(&subflow->node)) {

		mptcp_subflow_joined(msk, ssk);

		mptcp_propagate_sndbuf(parent, ssk);

		return true;

	}
@@ -3909,7 +3928,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, 
		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;



	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {

		mask |= mptcp_check_readable(msk);

		mask |= mptcp_check_readable(sk);

		if (shutdown & SEND_SHUTDOWN)

			mask |= EPOLLOUT | EPOLLWRNORM;

		else
@@ -3947,6 +3966,7 @@ static const struct proto_ops mptcp_stream_ops = { 
	.sendmsg	   = inet_sendmsg,

	.recvmsg	   = inet_recvmsg,

	.mmap		   = sock_no_mmap,

	.set_rcvlowat	   = mptcp_set_rcvlowat,

};



static struct inet_protosw mptcp_protosw = {
@@ -4048,6 +4068,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { 
#ifdef CONFIG_COMPAT

	.compat_ioctl	   = inet6_compat_ioctl,

#endif

	.set_rcvlowat	   = mptcp_set_rcvlowat,

};



static struct proto mptcp_v6_prot;