path: root/net/mptcp/protocol.h

/* SPDX-License-Identifier: GPL-2.0 */
/* Multipath TCP
 *
 * Copyright (c) 2017 - 2019, Intel Corporation.
 */

#ifndef __MPTCP_PROTOCOL_H
#define __MPTCP_PROTOCOL_H

#include <linux/random.h>
#include <net/tcp.h>
#include <net/inet_connection_sock.h>

#define MPTCP_SUPPORTED_VERSION	1

/* MPTCP option bits */
#define OPTION_MPTCP_MPC_SYN	BIT(0)
#define OPTION_MPTCP_MPC_SYNACK	BIT(1)
#define OPTION_MPTCP_MPC_ACK	BIT(2)
#define OPTION_MPTCP_MPJ_SYN	BIT(3)
#define OPTION_MPTCP_MPJ_SYNACK	BIT(4)
#define OPTION_MPTCP_MPJ_ACK	BIT(5)
#define OPTION_MPTCP_ADD_ADDR	BIT(6)
#define OPTION_MPTCP_ADD_ADDR6	BIT(7)
#define OPTION_MPTCP_RM_ADDR	BIT(8)

/* MPTCP option subtypes */
#define MPTCPOPT_MP_CAPABLE	0
#define MPTCPOPT_MP_JOIN	1
#define MPTCPOPT_DSS		2
#define MPTCPOPT_ADD_ADDR	3
#define MPTCPOPT_RM_ADDR	4
#define MPTCPOPT_MP_PRIO	5
#define MPTCPOPT_MP_FAIL	6
#define MPTCPOPT_MP_FASTCLOSE	7

/* MPTCP suboption lengths */
#define TCPOLEN_MPTCP_MPC_SYN		4
#define TCPOLEN_MPTCP_MPC_SYNACK	12
#define TCPOLEN_MPTCP_MPC_ACK		20
#define TCPOLEN_MPTCP_MPC_ACK_DATA	22
#define TCPOLEN_MPTCP_MPJ_SYN		12
#define TCPOLEN_MPTCP_MPJ_SYNACK	16
#define TCPOLEN_MPTCP_MPJ_ACK		24
#define TCPOLEN_MPTCP_DSS_BASE		4
#define TCPOLEN_MPTCP_DSS_ACK32		4
#define TCPOLEN_MPTCP_DSS_ACK64		8
#define TCPOLEN_MPTCP_DSS_MAP32		10
#define TCPOLEN_MPTCP_DSS_MAP64		14
#define TCPOLEN_MPTCP_DSS_CHECKSUM	2
#define TCPOLEN_MPTCP_ADD_ADDR		16
#define TCPOLEN_MPTCP_ADD_ADDR_PORT	18
#define TCPOLEN_MPTCP_ADD_ADDR_BASE	8
#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT	10
#define TCPOLEN_MPTCP_ADD_ADDR6		28
#define TCPOLEN_MPTCP_ADD_ADDR6_PORT	30
#define TCPOLEN_MPTCP_ADD_ADDR6_BASE	20
#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT	22
#define TCPOLEN_MPTCP_PORT_LEN		2
#define TCPOLEN_MPTCP_RM_ADDR_BASE	4

/* MPTCP MP_JOIN flags */
#define MPTCPOPT_BACKUP		BIT(0)
#define MPTCPOPT_HMAC_LEN	20
#define MPTCPOPT_THMAC_LEN	8

/* MPTCP MP_CAPABLE flags */
#define MPTCP_VERSION_MASK	(0x0F)
#define MPTCP_CAP_CHECKSUM_REQD	BIT(7)
#define MPTCP_CAP_EXTENSIBILITY	BIT(6)
#define MPTCP_CAP_HMAC_SHA256	BIT(0)
#define MPTCP_CAP_FLAG_MASK	(0x3F)

/* MPTCP DSS flags */
#define MPTCP_DSS_DATA_FIN	BIT(4)
#define MPTCP_DSS_DSN64		BIT(3)
#define MPTCP_DSS_HAS_MAP	BIT(2)
#define MPTCP_DSS_ACK64		BIT(1)
#define MPTCP_DSS_HAS_ACK	BIT(0)
#define MPTCP_DSS_FLAG_MASK	(0x1F)

/* MPTCP ADD_ADDR flags */
#define MPTCP_ADDR_ECHO		BIT(0)
#define MPTCP_ADDR_IPVERSION_4	4
#define MPTCP_ADDR_IPVERSION_6	6

/* MPTCP socket flags */
#define MPTCP_DATA_READY	0
#define MPTCP_NOSPACE		1
#define MPTCP_WORK_RTX		2
#define MPTCP_WORK_EOF		3
#define MPTCP_FALLBACK_DONE	4
#define MPTCP_WORK_CLOSE_SUBFLOW 5
#define MPTCP_PUSH_PENDING	6
#define MPTCP_CLEAN_UNA		7

static inline bool before64(__u64 seq1, __u64 seq2)
{
	return (__s64)(seq1 - seq2) < 0;
}

#define after64(seq2, seq1)	before64(seq1, seq2)

struct mptcp_options_received {
	u64	sndr_key;
	u64	rcvr_key;
	u64	data_ack;
	u64	data_seq;
	u32	subflow_seq;
	u16	data_len;
	u16	mp_capable : 1,
		mp_join : 1,
		dss : 1,
		add_addr : 1,
		rm_addr : 1,
		family : 4,
		echo : 1,
		backup : 1;
	u32	token;
	u32	nonce;
	u64	thmac;
	u8	hmac[20];
	u8	join_id;
	u8	use_map:1,
		dsn64:1,
		data_fin:1,
		use_ack:1,
		ack64:1,
		mpc_map:1,
		__unused:2;
	u8	addr_id;
	u8	rm_id;
	union {
		struct in_addr	addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
		struct in6_addr	addr6;
#endif
	};
	u64	ahmac;
	u16	port;
};

static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
{
	return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) |
		     ((nib & 0xF) << 8) | field);
}

struct mptcp_addr_info {
	sa_family_t		family;
	__be16			port;
	u8			id;
	u8			flags;
	int			ifindex;
	union {
		struct in_addr addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
		struct in6_addr addr6;
#endif
	};
};

enum mptcp_pm_status {
	MPTCP_PM_ADD_ADDR_RECEIVED,
	MPTCP_PM_ADD_ADDR_SEND_ACK,
	MPTCP_PM_RM_ADDR_RECEIVED,
	MPTCP_PM_ESTABLISHED,
	MPTCP_PM_SUBFLOW_ESTABLISHED,
};

enum mptcp_add_addr_status {
	MPTCP_ADD_ADDR_SIGNAL,
	MPTCP_ADD_ADDR_ECHO,
	MPTCP_ADD_ADDR_IPV6,
};

struct mptcp_pm_data {
	struct mptcp_addr_info local;
	struct mptcp_addr_info remote;
	struct list_head anno_list;

	spinlock_t	lock;		/*protects the whole PM data */

	u8		add_addr_signal;
	bool		rm_addr_signal;
	bool		server_side;
	bool		work_pending;
	bool		accept_addr;
	bool		accept_subflow;
	u8		add_addr_signaled;
	u8		add_addr_accepted;
	u8		local_addr_used;
	u8		subflows;
	u8		add_addr_signal_max;
	u8		add_addr_accept_max;
	u8		local_addr_max;
	u8		subflows_max;
	u8		status;
	u8		rm_id;
};

struct mptcp_data_frag {
	struct list_head list;
	u64 data_seq;
	u16 data_len;
	u16 offset;
	u16 overhead;
	u16 already_sent;
	struct page *page;
};

/* MPTCP connection sock */
struct mptcp_sock {
	/* inet_connection_sock must be the first member */
	struct inet_connection_sock sk;
	u64		local_key;
	u64		remote_key;
	u64		write_seq;
	u64		snd_nxt;
	u64		ack_seq;
	u64		rcv_wnd_sent;
	u64		rcv_data_fin_seq;
	int		wmem_reserved;
	struct sock	*last_snd;
	int		snd_burst;
	int		old_wspace;
	u64		snd_una;
	u64		wnd_end;
	unsigned long	timer_ival;
	u32		token;
	int		rmem_pending;
	int		rmem_released;
	unsigned long	flags;
	bool		can_ack;
	bool		fully_established;
	bool		rcv_data_fin;
	bool		snd_data_fin_enable;
	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
	spinlock_t	join_list_lock;
	struct sock	*ack_hint;
	struct work_struct work;
	struct sk_buff  *ooo_last_skb;
	struct rb_root  out_of_order_queue;
	struct sk_buff_head receive_queue;
	struct sk_buff_head skb_tx_cache;	/* this is wmem accounted */
	int		tx_pending_data;
	int		size_goal_cache;
	struct list_head conn_list;
	struct list_head rtx_queue;
	struct mptcp_data_frag *first_pending;
	struct list_head join_list;
	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
	struct sock	*first;
	struct mptcp_pm_data	pm;
	struct {
		u32	space;	/* bytes copied in last measurement window */
		u32	copied; /* bytes copied in this measurement window */
		u64	time;	/* start time of measurement window */
		u64	rtt_us; /* last maximum rtt of subflows */
	} rcvq_space;
};

#define mptcp_lock_sock(___sk, cb) do {					\
	struct sock *__sk = (___sk); /* silence macro reuse warning */	\
	might_sleep();							\
	spin_lock_bh(&__sk->sk_lock.slock);				\
	if (__sk->sk_lock.owned)					\
		__lock_sock(__sk);					\
	cb;								\
	__sk->sk_lock.owned = 1;					\
	spin_unlock(&__sk->sk_lock.slock);				\
	mutex_acquire(&__sk->sk_lock.dep_map, 0, 0, _RET_IP_);		\
	local_bh_enable();						\
} while (0)

#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
#define mptcp_data_unlock(sk) spin_unlock_bh(&(sk)->sk_lock.slock)

#define mptcp_for_each_subflow(__msk, __subflow)			\
	list_for_each_entry(__subflow, &((__msk)->conn_list), node)

static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
{
	return (struct mptcp_sock *)sk;
}

static inline int __mptcp_space(const struct sock *sk)
{
	return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_pending);
}

static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
{
	const struct mptcp_sock *msk = mptcp_sk(sk);

	return READ_ONCE(msk->first_pending);
}

static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct mptcp_data_frag *cur;

	cur = msk->first_pending;
	return list_is_last(&cur->list, &msk->rtx_queue) ?