path: root/net/mptcp/pm_kernel.c

// SPDX-License-Identifier: GPL-2.0
/* Multipath TCP
 *
 * Copyright (c) 2025, Matthieu Baerts.
 */

#define pr_fmt(fmt) "MPTCP: " fmt

#include <net/netns/generic.h>

#include "protocol.h"
#include "mib.h"
#include "mptcp_pm_gen.h"

static int pm_nl_pernet_id;

struct pm_nl_pernet {
	/* protects pernet updates */
	spinlock_t		lock;
	struct list_head	endp_list;
	u8			endpoints;
	u8			endp_signal_max;
	u8			endp_subflow_max;
	u8			endp_laminar_max;
	u8			limit_add_addr_accepted;
	u8			limit_extra_subflows;
	u8			next_id;
	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
};

#define MPTCP_PM_ADDR_MAX	8

static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net)
{
	return net_generic(net, pm_nl_pernet_id);
}

static struct pm_nl_pernet *
pm_nl_get_pernet_from_msk(const struct mptcp_sock *msk)
{
	return pm_nl_get_pernet(sock_net((struct sock *)msk));
}

static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info)
{
	return pm_nl_get_pernet(genl_info_net(info));
}

u8 mptcp_pm_get_endp_signal_max(const struct mptcp_sock *msk)
{
	const struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	return READ_ONCE(pernet->endp_signal_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_signal_max);

u8 mptcp_pm_get_endp_subflow_max(const struct mptcp_sock *msk)
{
	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	return READ_ONCE(pernet->endp_subflow_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_subflow_max);

u8 mptcp_pm_get_endp_laminar_max(const struct mptcp_sock *msk)
{
	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	return READ_ONCE(pernet->endp_laminar_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_laminar_max);

u8 mptcp_pm_get_limit_add_addr_accepted(const struct mptcp_sock *msk)
{
	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	return READ_ONCE(pernet->limit_add_addr_accepted);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_limit_add_addr_accepted);

u8 mptcp_pm_get_limit_extra_subflows(const struct mptcp_sock *msk)
{
	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	return READ_ONCE(pernet->limit_extra_subflows);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_limit_extra_subflows);

static bool lookup_subflow_by_daddr(const struct list_head *list,
				    const struct mptcp_addr_info *daddr)
{
	struct mptcp_subflow_context *subflow;
	struct mptcp_addr_info cur;

	list_for_each_entry(subflow, list, node) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		if (!((1 << inet_sk_state_load(ssk)) &
		      (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV)))
			continue;

		mptcp_remote_address((struct sock_common *)ssk, &cur);
		if (mptcp_addresses_equal(&cur, daddr, daddr->port))
			return true;
	}

	return false;
}

static bool
select_local_address(const struct pm_nl_pernet *pernet,
		     const struct mptcp_sock *msk,
		     struct mptcp_pm_local *new_local)
{
	struct mptcp_pm_addr_entry *entry;
	bool found = false;

	msk_owned_by_me(msk);

	rcu_read_lock();
	list_for_each_entry_rcu(entry, &pernet->endp_list, list) {
		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
			continue;

		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
			continue;

		new_local->addr = entry->addr;
		new_local->flags = entry->flags;
		new_local->ifindex = entry->ifindex;
		found = true;
		break;
	}
	rcu_read_unlock();

	return found;
}

static bool
select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
		      struct mptcp_pm_local *new_local)
{
	struct mptcp_pm_addr_entry *entry;
	bool found = false;

	rcu_read_lock();
	/* do not keep any additional per socket state, just signal
	 * the address list in order.
	 * Note: removal from the local address list during the msk life-cycle
	 * can lead to additional addresses not being announced.
	 */
	list_for_each_entry_rcu(entry, &pernet->endp_list, list) {
		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
			continue;

		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
			continue;

		new_local->addr = entry->addr;
		new_local->flags = entry->flags;
		new_local->ifindex = entry->ifindex;
		found = true;
		break;
	}
	rcu_read_unlock();

	return found;
}

static unsigned int
fill_remote_addr(struct mptcp_sock *msk, struct mptcp_addr_info *local,
		 struct mptcp_addr_info *addrs)
{
	bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
	struct mptcp_addr_info remote = { 0 };
	struct sock *sk = (struct sock *)msk;

	if (deny_id0)
		return 0;

	mptcp_remote_address((struct sock_common *)sk, &remote);

	if (!mptcp_pm_addr_families_match(sk, local, &remote))
		return 0;

	msk->pm.extra_subflows++;
	*addrs = remote;

	return 1;
}

static unsigned int
fill_remote_addresses_fullmesh(struct mptcp_sock *msk,
			       struct mptcp_addr_info *local,
			       struct mptcp_addr_info *addrs)
{
	u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
	bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
	DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
	struct sock *sk = (struct sock *)msk, *ssk;
	struct mptcp_subflow_context *subflow;
	int i = 0;

	/* Forbid creation of new subflows matching existing ones, possibly
	 * already created by incoming ADD_ADDR
	 */
	bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
	mptcp_for_each_subflow(msk, subflow)
		if (READ_ONCE(subflow->local_id) == local->id)
			__set_bit(subflow->remote_id, unavail_id);

	mptcp_for_each_subflow(msk, subflow) {
		ssk = mptcp_subflow_tcp_sock(subflow);
		mptcp_remote_address((struct sock_common *)ssk, &addrs[i]);
		addrs[i].id = READ_ONCE(subflow->remote_id);
		if (de