Commit c133acf3 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'mptcp-socket-options' 



Mat Martineau says:

====================
mptcp: Improve socket option handling

MPTCP sockets have previously had limited socket option support. The
architecture of MPTCP sockets (one userspace-facing MPTCP socket that
manages one or more in-kernel TCP subflow sockets) adds complexity for
passing options through to lower levels. This patch set adds MPTCP
support for socket options commonly used with TCP.

Patch 1 reverts an interim socket option fix (a socket option blocklist)
that was merged in the net tree for v5.12.

Patch 2 moves the socket option code to a separate file, with no
functional changes.

Patch 3 adds an allowlist for socket options that are known to function
with MPTCP. Later patches in this set add more allowed options.

Patches 4 and 5 add infrastructure for syncing MPTCP-level options with
the TCP subflows.

Patches 6-12 add support for specific socket options.

Patch 13 adds a socket option self test.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents a1150a04 dc65fe82

net/mptcp/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -2,7 +2,7 @@ 
obj-$(CONFIG_MPTCP) += mptcp.o



mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \

	   mib.o pm_netlink.o

	   mib.o pm_netlink.o sockopt.o



obj-$(CONFIG_SYN_COOKIES) += syncookies.o

obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o

net/mptcp/protocol.c

+45 −174
Original line number Diff line number Diff line
@@ -90,16 +90,6 @@ static bool mptcp_is_tcpsk(struct sock *sk) 
	return false;

}



static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)

{

	sock_owned_by_me((const struct sock *)msk);



	if (likely(!__mptcp_check_fallback(msk)))

		return NULL;



	return msk->first;

}



static int __mptcp_socket_create(struct mptcp_sock *msk)

{

	struct mptcp_subflow_context *subflow;
@@ -740,18 +730,47 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) 
		sk->sk_data_ready(sk);

}



void __mptcp_flush_join_list(struct mptcp_sock *msk)

static bool mptcp_do_flush_join_list(struct mptcp_sock *msk)

{

	struct mptcp_subflow_context *subflow;

	bool ret = false;



	if (likely(list_empty(&msk->join_list)))

		return;

		return false;



	spin_lock_bh(&msk->join_list_lock);

	list_for_each_entry(subflow, &msk->join_list, node)

	list_for_each_entry(subflow, &msk->join_list, node) {

		u32 sseq = READ_ONCE(subflow->setsockopt_seq);



		mptcp_propagate_sndbuf((struct sock *)msk, mptcp_subflow_tcp_sock(subflow));

		if (READ_ONCE(msk->setsockopt_seq) != sseq)

			ret = true;

	}

	list_splice_tail_init(&msk->join_list, &msk->conn_list);

	spin_unlock_bh(&msk->join_list_lock);



	return ret;

}



void __mptcp_flush_join_list(struct mptcp_sock *msk)

{

	if (likely(!mptcp_do_flush_join_list(msk)))

		return;



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

		mptcp_schedule_work((struct sock *)msk);

}



static void mptcp_flush_join_list(struct mptcp_sock *msk)

{

	bool sync_needed = test_and_clear_bit(MPTCP_WORK_SYNC_SETSOCKOPT, &msk->flags);



	might_sleep();



	if (!mptcp_do_flush_join_list(msk) && !sync_needed)

		return;



	mptcp_sockopt_sync_all(msk);

}



static bool mptcp_timer_pending(struct sock *sk)
@@ -1467,7 +1486,7 @@ static void __mptcp_push_pending(struct sock *sk, unsigned int flags) 
			int ret = 0;



			prev_ssk = ssk;

			__mptcp_flush_join_list(msk);

			mptcp_flush_join_list(msk);

			ssk = mptcp_subflow_get_send(msk);



			/* try to keep the subflow socket lock across
@@ -1893,7 +1912,7 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) 
	unsigned int moved = 0;

	bool ret, done;



	__mptcp_flush_join_list(msk);

	mptcp_flush_join_list(msk);

	do {

		struct sock *ssk = mptcp_subflow_recv_lookup(msk);

		bool slowpath;
@@ -2317,7 +2336,7 @@ static void mptcp_worker(struct work_struct *work) 
		goto unlock;



	mptcp_check_data_fin_ack(sk);

	__mptcp_flush_join_list(msk);

	mptcp_flush_join_list(msk);



	mptcp_check_fastclose(msk);
@@ -2380,6 +2399,9 @@ static int __mptcp_init_sock(struct sock *sk) 
	/* re-use the csk retrans timer for MPTCP-level retrans */

	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);

	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);



	tcp_assign_congestion_control(sk);



	return 0;

}
@@ -2517,7 +2539,7 @@ static void __mptcp_check_send_data_fin(struct sock *sk) 
		}

	}



	__mptcp_flush_join_list(msk);

	mptcp_flush_join_list(msk);

	mptcp_for_each_subflow(msk, subflow) {

		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
@@ -2573,6 +2595,8 @@ static void __mptcp_destroy_sock(struct sock *sk) 
	WARN_ON_ONCE(msk->rmem_released);

	sk_stream_kill_queues(sk);

	xfrm_sk_free_policy(sk);



	tcp_cleanup_congestion_control(sk);

	sk_refcnt_debug_release(sk);

	mptcp_dispose_initial_subflow(msk);

	sock_put(sk);
@@ -2654,7 +2678,8 @@ static int mptcp_disconnect(struct sock *sk, int flags) 
	struct mptcp_subflow_context *subflow;

	struct mptcp_sock *msk = mptcp_sk(sk);



	__mptcp_flush_join_list(msk);

	mptcp_do_flush_join_list(msk);



	mptcp_for_each_subflow(msk, subflow) {

		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -2703,6 +2728,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, 
	msk->snd_nxt = msk->write_seq;

	msk->snd_una = msk->write_seq;

	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;

	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;



	if (mp_opt->mp_capable) {

		msk->can_ack = true;
@@ -2811,161 +2837,6 @@ static void mptcp_destroy(struct sock *sk) 
	sk_sockets_allocated_dec(sk);

}



static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,

				       sockptr_t optval, unsigned int optlen)

{

	struct sock *sk = (struct sock *)msk;

	struct socket *ssock;

	int ret;



	switch (optname) {

	case SO_REUSEPORT:

	case SO_REUSEADDR:

		lock_sock(sk);

		ssock = __mptcp_nmpc_socket(msk);

		if (!ssock) {

			release_sock(sk);

			return -EINVAL;

		}



		ret = sock_setsockopt(ssock, SOL_SOCKET, optname, optval, optlen);

		if (ret == 0) {

			if (optname == SO_REUSEPORT)

				sk->sk_reuseport = ssock->sk->sk_reuseport;

			else if (optname == SO_REUSEADDR)

				sk->sk_reuse = ssock->sk->sk_reuse;

		}

		release_sock(sk);

		return ret;

	}



	return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen);

}



static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,

			       sockptr_t optval, unsigned int optlen)

{

	struct sock *sk = (struct sock *)msk;

	int ret = -EOPNOTSUPP;

	struct socket *ssock;



	switch (optname) {

	case IPV6_V6ONLY:

		lock_sock(sk);

		ssock = __mptcp_nmpc_socket(msk);

		if (!ssock) {

			release_sock(sk);

			return -EINVAL;

		}



		ret = tcp_setsockopt(ssock->sk, SOL_IPV6, optname, optval, optlen);

		if (ret == 0)

			sk->sk_ipv6only = ssock->sk->sk_ipv6only;



		release_sock(sk);

		break;

	}



	return ret;

}



static bool mptcp_unsupported(int level, int optname)

{

	if (level == SOL_IP) {

		switch (optname) {

		case IP_ADD_MEMBERSHIP:

		case IP_ADD_SOURCE_MEMBERSHIP:

		case IP_DROP_MEMBERSHIP:

		case IP_DROP_SOURCE_MEMBERSHIP:

		case IP_BLOCK_SOURCE:

		case IP_UNBLOCK_SOURCE:

		case MCAST_JOIN_GROUP:

		case MCAST_LEAVE_GROUP:

		case MCAST_JOIN_SOURCE_GROUP:

		case MCAST_LEAVE_SOURCE_GROUP:

		case MCAST_BLOCK_SOURCE:

		case MCAST_UNBLOCK_SOURCE:

		case MCAST_MSFILTER:

			return true;

		}

		return false;

	}

	if (level == SOL_IPV6) {

		switch (optname) {

		case IPV6_ADDRFORM:

		case IPV6_ADD_MEMBERSHIP:

		case IPV6_DROP_MEMBERSHIP:

		case IPV6_JOIN_ANYCAST:

		case IPV6_LEAVE_ANYCAST:

		case MCAST_JOIN_GROUP:

		case MCAST_LEAVE_GROUP:

		case MCAST_JOIN_SOURCE_GROUP:

		case MCAST_LEAVE_SOURCE_GROUP:

		case MCAST_BLOCK_SOURCE:

		case MCAST_UNBLOCK_SOURCE:

		case MCAST_MSFILTER:

			return true;

		}

		return false;

	}

	return false;

}



static int mptcp_setsockopt(struct sock *sk, int level, int optname,

			    sockptr_t optval, unsigned int optlen)

{

	struct mptcp_sock *msk = mptcp_sk(sk);

	struct sock *ssk;



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



	if (mptcp_unsupported(level, optname))

		return -ENOPROTOOPT;



	if (level == SOL_SOCKET)

		return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);



	/* @@ the meaning of setsockopt() when the socket is connected and

	 * there are multiple subflows is not yet defined. It is up to the

	 * MPTCP-level socket to configure the subflows until the subflow

	 * is in TCP fallback, when TCP socket options are passed through

	 * to the one remaining subflow.

	 */

	lock_sock(sk);

	ssk = __mptcp_tcp_fallback(msk);

	release_sock(sk);

	if (ssk)

		return tcp_setsockopt(ssk, level, optname, optval, optlen);



	if (level == SOL_IPV6)

		return mptcp_setsockopt_v6(msk, optname, optval, optlen);



	return -EOPNOTSUPP;

}



static int mptcp_getsockopt(struct sock *sk, int level, int optname,

			    char __user *optval, int __user *option)

{

	struct mptcp_sock *msk = mptcp_sk(sk);

	struct sock *ssk;



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



	/* @@ the meaning of setsockopt() when the socket is connected and

	 * there are multiple subflows is not yet defined. It is up to the

	 * MPTCP-level socket to configure the subflows until the subflow

	 * is in TCP fallback, when socket options are passed through

	 * to the one remaining subflow.

	 */

	lock_sock(sk);

	ssk = __mptcp_tcp_fallback(msk);

	release_sock(sk);

	if (ssk)

		return tcp_getsockopt(ssk, level, optname, optval, option);



	return -EOPNOTSUPP;

}



void __mptcp_data_acked(struct sock *sk)

{

	if (!sock_owned_by_user(sk))
@@ -3375,7 +3246,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, 
		/* set ssk->sk_socket of accept()ed flows to mptcp socket.

		 * This is needed so NOSPACE flag can be set from tcp stack.

		 */

		__mptcp_flush_join_list(msk);

		mptcp_flush_join_list(msk);

		mptcp_for_each_subflow(msk, subflow) {

			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

net/mptcp/protocol.h

+16 −0
Original line number Diff line number Diff line
@@ -108,6 +108,7 @@ 
#define MPTCP_CLEAN_UNA		7

#define MPTCP_ERROR_REPORT	8

#define MPTCP_RETRANSMIT	9

#define MPTCP_WORK_SYNC_SETSOCKOPT 10



static inline bool before64(__u64 seq1, __u64 seq2)

{
@@ -255,6 +256,8 @@ struct mptcp_sock { 
		u64	time;	/* start time of measurement window */

		u64	rtt_us; /* last maximum rtt of subflows */

	} rcvq_space;



	u32 setsockopt_seq;

};



#define mptcp_lock_sock(___sk, cb) do {					\
@@ -413,6 +416,8 @@ struct mptcp_subflow_context { 
	long	delegated_status;

	struct	list_head delegated_node;   /* link into delegated_action, protected by local BH */



	u32 setsockopt_seq;



	struct	sock *tcp_sock;	    /* tcp sk backpointer */

	struct	sock *conn;	    /* parent mptcp_sock */

	const	struct inet_connection_sock_af_ops *icsk_af_ops;
@@ -571,6 +576,11 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk); 
void mptcp_data_ready(struct sock *sk, struct sock *ssk);

bool mptcp_finish_join(struct sock *sk);

bool mptcp_schedule_work(struct sock *sk);

int mptcp_setsockopt(struct sock *sk, int level, int optname,

		     sockptr_t optval, unsigned int optlen);

int mptcp_getsockopt(struct sock *sk, int level, int optname,

		     char __user *optval, int __user *option);



void __mptcp_check_push(struct sock *sk, struct sock *ssk);

void __mptcp_data_acked(struct sock *sk);

void __mptcp_error_report(struct sock *sk);
@@ -730,6 +740,12 @@ unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); 
unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk);

unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk);



int mptcp_setsockopt(struct sock *sk, int level, int optname,

		     sockptr_t optval, unsigned int optlen);



void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);

void mptcp_sockopt_sync_all(struct mptcp_sock *msk);



static inline struct mptcp_ext *mptcp_get_ext(const struct sk_buff *skb)

{

	return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);

net/mptcp/sockopt.c

0 → 100644
+756 −0

File added.

Preview size limit exceeded, changes collapsed.

net/mptcp/subflow.c

+5 −0
Original line number Diff line number Diff line
@@ -679,6 +679,9 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, 
			goto out;

		}



		/* ssk inherits options of listener sk */

		ctx->setsockopt_seq = listener->setsockopt_seq;



		if (ctx->mp_capable) {

			/* this can't race with mptcp_close(), as the msk is

			 * not yet exposted to user-space
@@ -694,6 +697,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, 
			 * created mptcp socket

			 */

			new_msk->sk_destruct = mptcp_sock_destruct;

			mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq;

			mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);

			mptcp_token_accept(subflow_req, mptcp_sk(new_msk));

			ctx->conn = new_msk;
@@ -1317,6 +1321,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, 
	mptcp_info2sockaddr(remote, &addr, ssk->sk_family);



	mptcp_add_pending_subflow(msk, subflow);

	mptcp_sockopt_sync(msk, ssk);

	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);

	if (err && err != -EINPROGRESS)

		goto failed_unlink;