1384 lines · 41.7 KB · C
RawDownload
/* 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>#include <uapi/linux/mptcp.h>#include <net/genetlink.h>#include <net/rstreason.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_RM_ADDR	BIT(7)#define OPTION_MPTCP_FASTCLOSE	BIT(8)#define OPTION_MPTCP_PRIO	BIT(9)#define OPTION_MPTCP_RST	BIT(10)#define OPTION_MPTCP_DSS	BIT(11)#define OPTION_MPTCP_FAIL	BIT(12) #define OPTION_MPTCP_CSUMREQD	BIT(13) #define OPTIONS_MPTCP_MPC	(OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | \				 OPTION_MPTCP_MPC_ACK)#define OPTIONS_MPTCP_MPJ	(OPTION_MPTCP_MPJ_SYN | OPTION_MPTCP_MPJ_SYNACK | \				 OPTION_MPTCP_MPJ_ACK)#define OPTIONS_MPTCP_DSS	(OPTION_MPTCP_DSS | OPTION_MPTCP_CSUMREQD) /* 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#define MPTCPOPT_RST		8 /* 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_PORT_ALIGN	2#define TCPOLEN_MPTCP_RM_ADDR_BASE	3#define TCPOLEN_MPTCP_PRIO		3#define TCPOLEN_MPTCP_PRIO_ALIGN	4#define TCPOLEN_MPTCP_FASTCLOSE		12#define TCPOLEN_MPTCP_RST		4#define TCPOLEN_MPTCP_FAIL		12 #define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM	(TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA) /* MPTCP MP_JOIN flags */#define MPTCPOPT_BACKUP		BIT(0)#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_DENY_JOIN_ID0	BIT(5)#define MPTCP_CAP_HMAC_SHA256	BIT(0)#define MPTCP_CAP_FLAG_MASK	(0x1F) /* 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) /* MPTCP MP_PRIO flags */#define MPTCP_PRIO_BKUP		BIT(0) /* MPTCP TCPRST flags */#define MPTCP_RST_TRANSIENT	BIT(0) /* MPTCP socket atomic flags */#define MPTCP_WORK_RTX		1#define MPTCP_FALLBACK_DONE	2#define MPTCP_WORK_CLOSE_SUBFLOW 3#define MPTCP_RTX_ENABLED	4 /* MPTCP socket release cb flags */#define MPTCP_PUSH_PENDING	1#define MPTCP_CLEAN_UNA		2#define MPTCP_ERROR_REPORT	3#define MPTCP_RETRANSMIT	4#define MPTCP_FLUSH_JOIN_LIST	5#define MPTCP_SYNC_STATE	6#define MPTCP_SYNC_SNDBUF	7 struct mptcp_skb_cb {	u64 map_seq;	u64 end_seq;	u32 offset;	u8  has_rxtstamp;	u8  cant_coalesce;}; #define MPTCP_SKB_CB(__skb)	((struct mptcp_skb_cb *)&((__skb)->cb[0])) 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;	__sum16	csum;	struct_group(status,		u16 suboptions;		u16 use_map:1,		    dsn64:1,		    data_fin:1,		    use_ack:1,		    ack64:1,		    mpc_map:1,		    reset_reason:4,		    reset_transient:1,		    echo:1,		    backup:1,		    deny_join_id0:1,		    __unused:2;	);	u8	join_id;	u32	token;	u32	nonce;	u64	thmac;	u8	hmac[MPTCPOPT_HMAC_LEN];	struct mptcp_addr_info addr;	struct mptcp_rm_list rm_list;	u64	ahmac;	u64	fail_seq;}; 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);} 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,	MPTCP_PM_ALREADY_ESTABLISHED,	/* persistent status, set after ESTABLISHED event */	MPTCP_PM_MPC_ENDPOINT_ACCOUNTED, /* persistent status, set after MPC local address is					  * accounted int id_avail_bitmap					  */	MPTCP_PM_DESTROYING,		/* To fence out PM list allocs */}; enum mptcp_pm_type {	MPTCP_PM_TYPE_KERNEL = 0,	MPTCP_PM_TYPE_USERSPACE, 	__MPTCP_PM_TYPE_NR,	__MPTCP_PM_TYPE_MAX = __MPTCP_PM_TYPE_NR - 1,}; /* Status bits below MPTCP_PM_ALREADY_ESTABLISHED need pm worker actions */#define MPTCP_PM_WORK_MASK ((1 << MPTCP_PM_ALREADY_ESTABLISHED) - 1) enum mptcp_addr_signal_status {	MPTCP_ADD_ADDR_SIGNAL,	MPTCP_ADD_ADDR_ECHO,	MPTCP_RM_ADDR_SIGNAL,}; /* max value of mptcp_addr_info.id */#define MPTCP_PM_MAX_ADDR_ID		U8_MAX struct mptcp_pm_data {	struct mptcp_addr_info local;	struct mptcp_addr_info remote;	struct list_head anno_list;	struct list_head userspace_pm_local_addr_list; 	spinlock_t	lock;		/*protects the whole PM data */ 	struct_group(reset, 	u8		addr_signal;	bool		server_side;	bool		work_pending;	bool		accept_addr;	bool		accept_subflow;	bool		remote_deny_join_id0;	u8		add_addr_signaled;	u8		add_addr_accepted;	u8		local_addr_used;	u8		pm_type;	u8		extra_subflows;	u8		status; 	); 	DECLARE_BITMAP(id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);	struct mptcp_rm_list rm_list_tx;	struct mptcp_rm_list rm_list_rx;}; struct mptcp_pm_local {	struct mptcp_addr_info	addr;	u32			flags;	int			ifindex;}; struct mptcp_pm_addr_entry {	struct list_head	list;	struct mptcp_addr_info	addr;	u32			flags;	int			ifindex;	struct socket		*lsk;}; struct mptcp_data_frag {	struct list_head list;	u64 data_seq;	u16 data_len;	u16 offset;	u8 overhead;	u8 eor;			/* currently using 1 bit */	u16 already_sent;	struct page *page;}; /* Arbitrary compromise between as low as possible to react timely to subflow * close event and as big as possible to avoid being fouled by biased large * samples due to peer sending data on a different subflow WRT to the incoming * ack. */#define MPTCP_RTT_SAMPLES	5 /* MPTCP connection sock */struct mptcp_sock {	/* inet_connection_sock must be the first member */	struct inet_connection_sock sk;	u64		local_key;		/* protected by the first subflow socket lock						 * lockless access read						 */	u64		remote_key;		/* same as above */	u64		write_seq;	u64		bytes_sent;	u64		snd_nxt;	u64		bytes_received;	u64		ack_seq;	atomic64_t	rcv_wnd_sent;	u64		rcv_data_fin_seq;	u64		bytes_retrans;	u64		bytes_consumed;	int		snd_burst;	int		old_wspace;	u64		recovery_snd_nxt;	/* in recovery mode accept up to this seq;						 * recovery related fields are under data_lock						 * protection						 */	u64		bytes_acked;	u64		snd_una;	u64		wnd_end;	u32		last_data_sent;	u32		last_data_recv;	u32		last_ack_recv;	unsigned long	timer_ival;	u32		token;	unsigned long	flags;	unsigned long	cb_flags;	bool		recovery;		/* closing subflow write queue reinjected */	bool		can_ack;	bool		fully_established;	bool		rcv_data_fin;	bool		snd_data_fin_enable;	bool		rcv_fastclose;	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */	bool		csum_enabled;	bool		allow_infinite_fallback;	u8		pending_state; /* A subflow asked to set this sk_state,					* protected by the msk data lock					*/	u8		mpc_endpoint_id;	u8		recvmsg_inq:1,			cork:1,			nodelay:1,			fastopening:1,			in_accept_queue:1,			free_first:1,			rcvspace_init:1,			fastclosing:1;	u32		notsent_lowat;	int		keepalive_cnt;	int		keepalive_idle;	int		keepalive_intvl;	int		maxseg;	struct work_struct work;	struct sk_buff  *ooo_last_skb;	struct rb_root  out_of_order_queue;	struct list_head conn_list;	struct list_head rtx_queue;	struct mptcp_data_frag *first_pending;	struct list_head join_list;	struct sock	*first; /* The mptcp ops can safely dereference, using suitable				 * ONCE annotation, the subflow outside the socket				 * lock as such sock is freed after close().				 */	struct mptcp_pm_data	pm;	struct mptcp_sched_ops	*sched; 	/* Most recent rtt_us observed by in use incoming subflows. */	struct {		u32	samples[MPTCP_RTT_SAMPLES];		u32	next_sample;	} rcv_rtt_est; 	struct {		int	space;	/* bytes copied in last measurement window */		int	copied; /* bytes copied in this measurement window */		u64	time;	/* start time of measurement window */	} rcvq_space;	u8		scaling_ratio;	bool		allow_subflows; 	u32		subflow_id;	u32		setsockopt_seq;	char		ca_name[TCP_CA_NAME_MAX]; 	spinlock_t	fallback_lock;	/* protects fallback,					 * allow_infinite_fallback and					 * allow_join					 */ 	struct list_head backlog_list;	/* protected by the data lock */	u32		backlog_len;	u32		backlog_unaccounted;}; #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)#define mptcp_for_each_subflow_safe(__msk, __subflow, __tmp)			\	list_for_each_entry_safe(__subflow, __tmp, &((__msk)->conn_list), node)#define mptcp_next_subflow(__msk, __subflow)				\	list_next_entry_circular(__subflow, &((__msk)->conn_list), node) extern struct genl_family mptcp_genl_family; static inline void msk_owned_by_me(const struct mptcp_sock *msk){	sock_owned_by_me((const struct sock *)msk);} #ifdef CONFIG_DEBUG_NET/* MPTCP-specific: we might (indirectly) call this helper with the wrong sk */#undef tcp_sk#define tcp_sk(ptr) ({								\	typeof(ptr) _ptr = (ptr);						\	WARN_ON(_ptr->sk_protocol != IPPROTO_TCP);				\	container_of_const(_ptr, struct tcp_sock, inet_conn.icsk_inet.sk);	\})#define mptcp_sk(ptr) ({						\	typeof(ptr) _ptr = (ptr);					\	WARN_ON(_ptr->sk_protocol != IPPROTO_MPTCP);			\	container_of_const(_ptr, struct mptcp_sock, sk.icsk_inet.sk);	\}) #else /* !CONFIG_DEBUG_NET */#define mptcp_sk(ptr) container_of_const(ptr, struct mptcp_sock, sk.icsk_inet.sk)#endif static inline int mptcp_win_from_space(const struct sock *sk, int space){	return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space);} static inline int mptcp_space_from_win(const struct sock *sk, int win){	return __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, win);} static inline int __mptcp_space(const struct sock *sk){	return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) -				    READ_ONCE(mptcp_sk(sk)->backlog_len) -				    sk_rmem_alloc_get(sk));} static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk){	const struct mptcp_sock *msk = mptcp_sk(sk); 	return msk->first_pending;} static inline void mptcp_init_rtt_est(struct mptcp_sock *msk){	int i; 	for (i = 0; i < MPTCP_RTT_SAMPLES; ++i)		msk->rcv_rtt_est.samples[i] = U32_MAX;	msk->rcv_rtt_est.next_sample = 0;	msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO;} static inline u32 mptcp_rtt_us_est(const struct mptcp_sock *msk){	u32 rtt_us = READ_ONCE(msk->rcv_rtt_est.samples[0]);	int i; 	/* Lockless access of collected samples. */	for (i = 1; i < MPTCP_RTT_SAMPLES; ++i)		rtt_us = min(rtt_us, READ_ONCE(msk->rcv_rtt_est.samples[i]));	return rtt_us;} 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) ? NULL :						     list_next_entry(cur, list);} static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk){	const struct mptcp_sock *msk = mptcp_sk(sk); 	if (!msk->first_pending)		return NULL; 	if (WARN_ON_ONCE(list_empty(&msk->rtx_queue)))		return NULL; 	return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);} static inline struct mptcp_data_frag *mptcp_rtx_head(struct sock *sk){	struct mptcp_sock *msk = mptcp_sk(sk); 	if (msk->snd_una == msk->snd_nxt)		return NULL; 	return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list);} struct csum_pseudo_header {	__be64 data_seq;	__be32 subflow_seq;	__be16 data_len;	__sum16 csum;

Lines 1–500 of 1384.

Keyboard shortcuts

General

Show keyboard shortcuts
?
Focus the current search
/

Issues and pull requests

Open filters
f

Issues, pull requests and Inbox

Select next item
j↓
Select previous item
k↑
Open selected item
Enter
Dismiss filters or clear selection
Esc

Repository code

Go to file
t