xref: /linux/include/net/tcp.h (revision 55fbedcec622a943cb09a969aef1ddcba87ee40a)

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Definitions for the TCP module.
 *
 * Version:	@(#)tcp.h	1.0.5	05/23/93
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 */
#ifndef _TCP_H
#define _TCP_H

#define FASTRETRANS_DEBUG 1

#include <linux/list.h>
#include <linux/tcp.h>
#include <linux/bug.h>
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/percpu.h>
#include <linux/skbuff.h>
#include <linux/kref.h>
#include <linux/ktime.h>
#include <linux/indirect_call_wrapper.h>
#include <linux/bits.h>

#include <net/inet_connection_sock.h>
#include <net/inet_timewait_sock.h>
#include <net/inet_hashtables.h>
#include <net/checksum.h>
#include <net/request_sock.h>
#include <net/sock_reuseport.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/tcp_states.h>
#include <net/tcp_ao.h>
#include <net/inet_ecn.h>
#include <net/dst.h>
#include <net/mptcp.h>
#include <net/xfrm.h>
#include <net/secure_seq.h>

#include <linux/seq_file.h>
#include <linux/memcontrol.h>
#include <linux/bpf-cgroup.h>
#include <linux/siphash.h>

extern struct inet_hashinfo tcp_hashinfo;

DECLARE_PER_CPU(unsigned int, tcp_orphan_count);
int tcp_orphan_count_sum(void);

static inline void tcp_orphan_count_inc(void)
{
	this_cpu_inc(tcp_orphan_count);
}

static inline void tcp_orphan_count_dec(void)
{
	this_cpu_dec(tcp_orphan_count);
}

void tcp_time_wait(struct sock *sk, int state, int timeo);

#define MAX_TCP_HEADER	L1_CACHE_ALIGN(128 + MAX_HEADER)
#define MAX_TCP_OPTION_SPACE 40
#define TCP_MIN_SND_MSS		48
#define TCP_MIN_GSO_SIZE	(TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)

/*
 * Never offer a window over 32767 without using window scaling. Some
 * poor stacks do signed 16bit maths!
 */
#define MAX_TCP_WINDOW		32767U

/* Minimal accepted MSS. It is (60+60+8) - (20+20). */
#define TCP_MIN_MSS		88U

/* The initial MTU to use for probing */
#define TCP_BASE_MSS		1024

/* probing interval, default to 10 minutes as per RFC4821 */
#define TCP_PROBE_INTERVAL	600

/* Specify interval when tcp mtu probing will stop */
#define TCP_PROBE_THRESHOLD	8

/* After receiving this amount of duplicate ACKs fast retransmit starts. */
#define TCP_FASTRETRANS_THRESH 3

/* Maximal number of ACKs sent quickly to accelerate slow-start. */
#define TCP_MAX_QUICKACKS	16U

/* Maximal number of window scale according to RFC1323 */
#define TCP_MAX_WSCALE		14U

/* Default sending frequency of accurate ECN option per RTT */
#define TCP_ACCECN_OPTION_BEACON	3

/* urg_data states */
#define TCP_URG_VALID	0x0100
#define TCP_URG_NOTYET	0x0200
#define TCP_URG_READ	0x0400

#define TCP_RETR1	3	/*
				 * This is how many retries it does before it
				 * tries to figure out if the gateway is
				 * down. Minimal RFC value is 3; it corresponds
				 * to ~3sec-8min depending on RTO.
				 */

#define TCP_RETR2	15	/*
				 * This should take at least
				 * 90 minutes to time out.
				 * RFC1122 says that the limit is 100 sec.
				 * 15 is ~13-30min depending on RTO.
				 */

#define TCP_SYN_RETRIES	 6	/* This is how many retries are done
				 * when active opening a connection.
				 * RFC1122 says the minimum retry MUST
				 * be at least 180secs.  Nevertheless
				 * this value is corresponding to
				 * 63secs of retransmission with the
				 * current initial RTO.
				 */

#define TCP_SYNACK_RETRIES 5	/* This is how may retries are done
				 * when passive opening a connection.
				 * This is corresponding to 31secs of
				 * retransmission with the current
				 * initial RTO.
				 */

#define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT
				  * state, about 60 seconds	*/
#define TCP_FIN_TIMEOUT	TCP_TIMEWAIT_LEN
                                 /* BSD style FIN_WAIT2 deadlock breaker.
				  * It used to be 3min, new value is 60sec,
				  * to combine FIN-WAIT-2 timeout with
				  * TIME-WAIT timer.
				  */
#define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */

#define TCP_DELACK_MAX	((unsigned)(HZ/5))	/* maximal time to delay before sending an ACK */
static_assert((1 << ATO_BITS) > TCP_DELACK_MAX);

#if HZ >= 100
#define TCP_DELACK_MIN	((unsigned)(HZ/25))	/* minimal time to delay before sending an ACK */
#define TCP_ATO_MIN	((unsigned)(HZ/25))
#else
#define TCP_DELACK_MIN	4U
#define TCP_ATO_MIN	4U
#endif
#define TCP_RTO_MAX_SEC 120
#define TCP_RTO_MAX	((unsigned)(TCP_RTO_MAX_SEC * HZ))
#define TCP_RTO_MIN	((unsigned)(HZ / 5))
#define TCP_TIMEOUT_MIN	(2U) /* Min timeout for TCP timers in jiffies */

#define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */

#define TCP_TIMEOUT_INIT ((unsigned)(1*HZ))	/* RFC6298 2.1 initial RTO value	*/
#define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ))	/* RFC 1122 initial RTO value, now
						 * used as a fallback RTO for the
						 * initial data transmission if no
						 * valid RTT sample has been acquired,
						 * most likely due to retrans in 3WHS.
						 */

#define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes
					                 * for local resources.
					                 */
#define TCP_KEEPALIVE_TIME	(120*60*HZ)	/* two hours */
#define TCP_KEEPALIVE_PROBES	9		/* Max of 9 keepalive probes	*/
#define TCP_KEEPALIVE_INTVL	(75*HZ)

#define MAX_TCP_KEEPIDLE	32767
#define MAX_TCP_KEEPINTVL	32767
#define MAX_TCP_KEEPCNT		127
#define MAX_TCP_SYNCNT		127

/* Ensure that TCP PAWS checks are relaxed after ~2147 seconds
 * to avoid overflows. This assumes a clock smaller than 1 Mhz.
 * Default clock is 1 Khz, tcp_usec_ts uses 1 Mhz.
 */
#define TCP_PAWS_WRAP (INT_MAX / USEC_PER_SEC)

#define TCP_PAWS_MSL	60		/* Per-host timestamps are invalidated
					 * after this time. It should be equal
					 * (or greater than) TCP_TIMEWAIT_LEN
					 * to provide reliability equal to one
					 * provided by timewait state.
					 */
#define TCP_PAWS_WINDOW	1		/* Replay window for per-host
					 * timestamps. It must be less than
					 * minimal timewait lifetime.
					 */
/*
 *	TCP option
 */

#define TCPOPT_NOP		1	/* Padding */
#define TCPOPT_EOL		0	/* End of options */
#define TCPOPT_MSS		2	/* Segment size negotiating */
#define TCPOPT_WINDOW		3	/* Window scaling */
#define TCPOPT_SACK_PERM        4       /* SACK Permitted */
#define TCPOPT_SACK             5       /* SACK Block */
#define TCPOPT_TIMESTAMP	8	/* Better RTT estimations/PAWS */
#define TCPOPT_MD5SIG		19	/* MD5 Signature (RFC2385) */
#define TCPOPT_AO		29	/* Authentication Option (RFC5925) */
#define TCPOPT_MPTCP		30	/* Multipath TCP (RFC6824) */
#define TCPOPT_FASTOPEN		34	/* Fast open (RFC7413) */
#define TCPOPT_ACCECN0		172	/* 0xAC: Accurate ECN Order 0 */
#define TCPOPT_ACCECN1		174	/* 0xAE: Accurate ECN Order 1 */
#define TCPOPT_EXP		254	/* Experimental */
/* Magic number to be after the option value for sharing TCP
 * experimental options. See draft-ietf-tcpm-experimental-options-00.txt
 */
#define TCPOPT_FASTOPEN_MAGIC	0xF989
#define TCPOPT_SMC_MAGIC	0xE2D4C3D9

/*
 *     TCP option lengths
 */

#define TCPOLEN_MSS            4
#define TCPOLEN_WINDOW         3
#define TCPOLEN_SACK_PERM      2
#define TCPOLEN_TIMESTAMP      10
#define TCPOLEN_MD5SIG         18
#define TCPOLEN_FASTOPEN_BASE  2
#define TCPOLEN_ACCECN_BASE    2
#define TCPOLEN_EXP_FASTOPEN_BASE  4
#define TCPOLEN_EXP_SMC_BASE   6

/* But this is what stacks really send out. */
#define TCPOLEN_TSTAMP_ALIGNED		12
#define TCPOLEN_WSCALE_ALIGNED		4
#define TCPOLEN_SACKPERM_ALIGNED	4
#define TCPOLEN_SACK_BASE		2
#define TCPOLEN_SACK_BASE_ALIGNED	4
#define TCPOLEN_SACK_PERBLOCK		8
#define TCPOLEN_MD5SIG_ALIGNED		20
#define TCPOLEN_MSS_ALIGNED		4
#define TCPOLEN_EXP_SMC_BASE_ALIGNED	8
#define TCPOLEN_ACCECN_PERFIELD		3

/* Maximum number of byte counters in AccECN option + size */
#define TCP_ACCECN_NUMFIELDS		3
#define TCP_ACCECN_MAXSIZE		(TCPOLEN_ACCECN_BASE + \
					 TCPOLEN_ACCECN_PERFIELD * \
					 TCP_ACCECN_NUMFIELDS)
#define TCP_ACCECN_SAFETY_SHIFT		1 /* SAFETY_FACTOR in accecn draft */

/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF		1	/* Nagle's algo is disabled */
#define TCP_NAGLE_CORK		2	/* Socket is corked	    */
#define TCP_NAGLE_PUSH		4	/* Cork is overridden for already queued data */

/* TCP thin-stream limits */
#define TCP_THIN_LINEAR_RETRIES 6       /* After 6 linear retries, do exp. backoff */

/* TCP initial congestion window as per rfc6928 */
#define TCP_INIT_CWND		10

/* Bit Flags for sysctl_tcp_fastopen */
#define	TFO_CLIENT_ENABLE	1
#define	TFO_SERVER_ENABLE	2
#define	TFO_CLIENT_NO_COOKIE	4	/* Data in SYN w/o cookie option */

/* Accept SYN data w/o any cookie option */
#define	TFO_SERVER_COOKIE_NOT_REQD	0x200

/* Force enable TFO on all listeners, i.e., not requiring the
 * TCP_FASTOPEN socket option.
 */
#define	TFO_SERVER_WO_SOCKOPT1	0x400


/* sysctl variables for tcp */
extern int sysctl_tcp_max_orphans;
extern long sysctl_tcp_mem[3];

#define TCP_RACK_LOSS_DETECTION  0x1 /* Use RACK to detect losses */
#define TCP_RACK_STATIC_REO_WND  0x2 /* Use static RACK reo wnd */
#define TCP_RACK_NO_DUPTHRESH    0x4 /* Do not use DUPACK threshold in RACK */

DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc);

extern struct percpu_counter tcp_sockets_allocated;
extern unsigned long tcp_memory_pressure;

/* optimized version of sk_under_memory_pressure() for TCP sockets */
static inline bool tcp_under_memory_pressure(const struct sock *sk)
{
	if (mem_cgroup_sk_enabled(sk) &&
	    mem_cgroup_sk_under_memory_pressure(sk))
		return true;

	if (sk->sk_bypass_prot_mem)
		return false;

	return READ_ONCE(tcp_memory_pressure);
}
/*
 * The next routines deal with comparing 32 bit unsigned ints
 * and worry about wraparound (automatic with unsigned arithmetic).
 */

static inline bool before(__u32 seq1, __u32 seq2)
{
        return (__s32)(seq1-seq2) < 0;
}
#define after(seq2, seq1) 	before(seq1, seq2)

/* is s2<=s1<=s3 ? */
static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3)
{
	return seq3 - seq2 >= seq1 - seq2;
}

static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
{
	sk_wmem_queued_add(sk, -skb->truesize);
	if (!skb_zcopy_pure(skb))
		sk_mem_uncharge(sk, skb->truesize);
	else
		sk_mem_uncharge(sk, SKB_TRUESIZE(skb_end_offset(skb)));
	__kfree_skb(skb);
}

void sk_forced_mem_schedule(struct sock *sk, int size);

bool tcp_check_oom(const struct sock *sk, int shift);


extern struct proto tcp_prot;

#define TCP_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.tcp_statistics, field)
#define __TCP_INC_STATS(net, field)	__SNMP_INC_STATS((net)->mib.tcp_statistics, field)
#define TCP_DEC_STATS(net, field)	SNMP_DEC_STATS((net)->mib.tcp_statistics, field)
#define TCP_ADD_STATS(net, field, val)	SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val)

/*
 * TCP splice context
 */
struct tcp_splice_state {
	struct pipe_inode_info *pipe;
	size_t len;
	unsigned int flags;
};

void tcp_tsq_work_init(void);

int tcp_v4_err(struct sk_buff *skb, u32);

void tcp_shutdown(struct sock *sk, int how);

int tcp_v4_rcv(struct sk_buff *skb);

void tcp_remove_empty_skb(struct sock *sk);
int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size);
int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
			 size_t size, struct ubuf_info *uarg);
void tcp_splice_eof(struct socket *sock);
int tcp_send_mss(struct sock *sk, int *size_goal, int flags);
int tcp_wmem_schedule(struct sock *sk, int copy);
void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle,
	      int size_goal);

void tcp_release_cb(struct sock *sk);

static inline bool tcp_release_cb_cond(struct sock *sk)
{
#ifdef CONFIG_INET
	if (likely(sk->sk_prot->release_cb == tcp_release_cb)) {
		if (unlikely(smp_load_acquire(&sk->sk_tsq_flags) & TCP_DEFERRED_ALL))
			tcp_release_cb(sk);
		return true;
	}
#endif
	return false;
}

void tcp_write_timer_handler(struct sock *sk);
void tcp_delack_timer_handler(struct sock *sk);
int tcp_ioctl(struct sock *sk, int cmd, int *karg);
enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb);
void tcp_rcv_established(struct sock *sk, struct sk_buff *skb);
void tcp_rcvbuf_grow(struct sock *sk, u32 newval);
void tcp_rcv_space_adjust(struct sock *sk);
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
void tcp_twsk_destructor(struct sock *sk);
void tcp_twsk_purge(struct list_head *net_exit_list);
int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
			 unsigned int offset, size_t len);
ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
			struct pipe_inode_info *pipe, size_t len,
			unsigned int flags);
struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp,
				     bool force_schedule);

static inline void tcp_dec_quickack_mode(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (icsk->icsk_ack.quick) {
		/* How many ACKs S/ACKing new data have we sent? */
		const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0;

		if (pkts >= icsk->icsk_ack.quick) {
			icsk->icsk_ack.quick = 0;
			/* Leaving quickack mode we deflate ATO. */
			icsk->icsk_ack.ato   = TCP_ATO_MIN;
		} else
			icsk->icsk_ack.quick -= pkts;
	}
}

#define	TCP_ECN_MODE_RFC3168	BIT(0)
#define	TCP_ECN_QUEUE_CWR	BIT(1)
#define	TCP_ECN_DEMAND_CWR	BIT(2)
#define	TCP_ECN_SEEN		BIT(3)
#define	TCP_ECN_MODE_ACCECN	BIT(4)

#define	TCP_ECN_DISABLED	0
#define	TCP_ECN_MODE_PENDING	(TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN)
#define	TCP_ECN_MODE_ANY	(TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN)

static inline bool tcp_ecn_mode_any(const struct tcp_sock *tp)
{
	return tp->ecn_flags & TCP_ECN_MODE_ANY;
}

static inline bool tcp_ecn_mode_rfc3168(const struct tcp_sock *tp)
{
	return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_RFC3168;
}

static inline bool tcp_ecn_mode_accecn(const struct tcp_sock *tp)
{
	return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_ACCECN;
}

static inline bool tcp_ecn_disabled(const struct tcp_sock *tp)
{
	return !tcp_ecn_mode_any(tp);
}

static inline bool tcp_ecn_mode_pending(const struct tcp_sock *tp)
{
	return (tp->ecn_flags & TCP_ECN_MODE_PENDING) == TCP_ECN_MODE_PENDING;
}

static inline void tcp_ecn_mode_set(struct tcp_sock *tp, u8 mode)
{
	tp->ecn_flags &= ~TCP_ECN_MODE_ANY;
	tp->ecn_flags |= mode;
}

enum tcp_tw_status {
	TCP_TW_SUCCESS = 0,
	TCP_TW_RST = 1,
	TCP_TW_ACK = 2,
	TCP_TW_SYN = 3,
	TCP_TW_ACK_OOW = 4
};


enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
					      struct sk_buff *skb,
					      const struct tcphdr *th,
					      u32 *tw_isn,
					      enum skb_drop_reason *drop_reason);
struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
			   struct request_sock *req, bool fastopen,
			   bool *lost_race, enum skb_drop_reason *drop_reason);
enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
				       struct sk_buff *skb);
void tcp_enter_loss(struct sock *sk);
void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag);
void tcp_clear_retrans(struct tcp_sock *tp);
void tcp_update_pacing_rate(struct sock *sk);
void tcp_set_rto(struct sock *sk);
void tcp_update_metrics(struct sock *sk);
void tcp_init_metrics(struct sock *sk);
void tcp_metrics_init(void);
bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
void __tcp_close(struct sock *sk, long timeout);
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
__poll_t tcp_poll(struct file *file, struct socket *sock,
		      struct poll_table_struct *wait);
int do_tcp_getsockopt(struct sock *sk, int level,
		      int optname, sockptr_t optval, sockptr_t optlen);
int tcp_getsockopt(struct sock *sk, int level, int optname,
		   char __user *optval, int __user *optlen);
bool tcp_bpf_bypass_getsockopt(int level, int optname);
int do_tcp_setsockopt(struct sock *sk, int level, int optname,
		      sockptr_t optval, unsigned int optlen);
int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
		   unsigned int optlen);
void tcp_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
void tcp_set_keepalive(struct sock *sk, int val);
void tcp_syn_ack_timeout(const struct request_sock *req);
int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
		int flags);
int __tcp_set_rcvlowat(struct sock *sk, int val, bool wakeup);
int tcp_set_rcvlowat(struct sock *sk, int val);
void tcp_set_rcvbuf(struct sock *sk, int val);
int tcp_set_window_clamp(struct sock *sk, int val);

static inline void
tcp_update_recv_tstamps(struct sk_buff *skb,
			struct scm_timestamping_internal *tss)
{
	tss->ts[0] = skb->tstamp;
	tss->ts[2] = skb_hwtstamps(skb)->hwtstamp;
}

void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
			struct scm_timestamping_internal *tss);
void tcp_data_ready(struct sock *sk);
#ifdef CONFIG_MMU
int tcp_mmap(struct file *file, struct socket *sock,
	     struct vm_area_struct *vma);
#endif
void tcp_parse_options(const struct net *net, const struct sk_buff *skb,
		       struct tcp_options_received *opt_rx,
		       int estab, struct tcp_fastopen_cookie *foc);

/*
 *	BPF SKB-less helpers
 */
u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
			 struct tcphdr *th, u32 *cookie);
u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
			 struct tcphdr *th, u32 *cookie);
u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss);
u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
			  const struct tcp_request_sock_ops *af_ops,
			  struct sock *sk, struct tcphdr *th);
/*
 *	TCP v4 functions exported for the inet6 API
 */

void tcp_v4_mtu_reduced(struct sock *sk);
void tcp_req_err(struct sock *sk, u32 seq, bool abort);
void tcp_ld_RTO_revert(struct sock *sk, u32 seq);
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
struct sock *tcp_create_openreq_child(const struct sock *sk,
				      struct request_sock *req,
				      struct sk_buff *skb);
void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst);
struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
				  struct request_sock *req,
				  struct dst_entry *dst,
				  struct request_sock *req_unhash,
				  bool *own_req,
				  void (*opt_child_init)(struct sock *newsk,
							 const struct sock *sk));
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
int tcp_connect(struct sock *sk);
enum tcp_synack_type {
	TCP_SYNACK_NORMAL,
	TCP_SYNACK_FASTOPEN,
	TCP_SYNACK_COOKIE,
	TCP_SYNACK_RETRANS,
};
struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
				struct request_sock *req,
				struct tcp_fastopen_cookie *foc,
				enum tcp_synack_type synack_type,
				struct sk_buff *syn_skb);
int tcp_disconnect(struct sock *sk, int flags);

void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size);
void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);

/* From syncookies.c */
struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
				 struct request_sock *req,
				 struct dst_entry *dst);
int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th);
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
					    struct sock *sk, struct sk_buff *skb,
					    struct tcp_options_received *tcp_opt,
					    int mss, u32 tsoff);

#if IS_ENABLED(CONFIG_BPF)
struct bpf_tcp_req_attrs {
	u32 rcv_tsval;
	u32 rcv_tsecr;
	u16 mss;
	u8 rcv_wscale;
	u8 snd_wscale;
	u8 ecn_ok;
	u8 wscale_ok;
	u8 sack_ok;
	u8 tstamp_ok;
	u8 usec_ts_ok;
	u8 reserved[3];
};
#endif

#ifdef CONFIG_SYN_COOKIES

/* Syncookies use a monotonic timer which increments every 60 seconds.
 * This counter is used both as a hash input and partially encoded into
 * the cookie value.  A cookie is only validated further if the delta
 * between the current counter value and the encoded one is less than this,
 * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if
 * the counter advances immediately after a cookie is generated).
 */
#define MAX_SYNCOOKIE_AGE	2
#define TCP_SYNCOOKIE_PERIOD	(60 * HZ)
#define TCP_SYNCOOKIE_VALID	(MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD)

/* syncookies: remember time of last synqueue overflow
 * But do not dirty this field too often (once per second is enough)
 * It is racy as we do not hold a lock, but race is very minor.
 */
static inline void tcp_synq_overflow(const struct sock *sk)
{
	unsigned int last_overflow;
	unsigned int now = jiffies;

	if (sk->sk_reuseport) {
		struct sock_reuseport *reuse;

		reuse = rcu_dereference(sk->sk_reuseport_cb);
		if (likely(reuse)) {
			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
			if (!time_between32(now, last_overflow,
					    last_overflow + HZ))
				WRITE_ONCE(reuse->synq_overflow_ts, now);
			return;
		}
	}

	last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);
	if (!time_between32(now, last_overflow, last_overflow + HZ))
		WRITE_ONCE(tcp_sk_rw(sk)->rx_opt.ts_recent_stamp, now);
}

/* syncookies: no recent synqueue overflow on this listening socket? */
static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
{
	unsigned int last_overflow;
	unsigned int now = jiffies;

	if (sk->sk_reuseport) {
		struct sock_reuseport *reuse;

		reuse = rcu_dereference(sk->sk_reuseport_cb);
		if (likely(reuse)) {
			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
			return !time_between32(now, last_overflow - HZ,
					       last_overflow +
					       TCP_SYNCOOKIE_VALID);
		}
	}

	last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);

	/* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID,
	 * then we're under synflood. However, we have to use
	 * 'last_overflow - HZ' as lower bound. That's because a concurrent
	 * tcp_synq_overflow() could update .ts_recent_stamp after we read
	 * jiffies but before we store .ts_recent_stamp into last_overflow,
	 * which could lead to rejecting a valid syncookie.
	 */
	return !time_between32(now, last_overflow - HZ,
			       last_overflow + TCP_SYNCOOKIE_VALID);
}

static inline u32 tcp_cookie_time(void)
{
	u64 val = get_jiffies_64();

	do_div(val, TCP_SYNCOOKIE_PERIOD);
	return val;
}

/* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */
static inline u64 tcp_ns_to_ts(bool usec_ts, u64 val)
{
	if (usec_ts)
		return div_u64(val, NSEC_PER_USEC);

	return div_u64(val, NSEC_PER_MSEC);
}

u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
			      u16 *mssp);
__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss);
u64 cookie_init_timestamp(struct request_sock *req, u64 now);
bool cookie_timestamp_decode(const struct net *net,
			     struct tcp_options_received *opt);

static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *dst)
{
	return READ_ONCE(net->ipv4.sysctl_tcp_ecn) ||
		dst_feature(dst, RTAX_FEATURE_ECN);
}

#if IS_ENABLED(CONFIG_BPF)
static inline bool cookie_bpf_ok(struct sk_buff *skb)
{
	return skb->sk;
}

struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb);
#else
static inline bool cookie_bpf_ok(struct sk_buff *skb)
{
	return false;
}

static inline struct request_sock *cookie_bpf_check(struct net *net, struct sock *sk,
						    struct sk_buff *skb)
{
	return NULL;
}
#endif

/* From net/ipv6/syncookies.c */
int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th);
struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);

u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
			      const struct tcphdr *th, u16 *mssp);
__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss);
#endif
/* tcp_output.c */

void tcp_skb_entail(struct sock *sk, struct sk_buff *skb);
void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb);
void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
			       int nonagle);
int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
void tcp_retransmit_timer(struct sock *sk);
void tcp_xmit_retransmit_queue(struct sock *);
void tcp_simple_retransmit(struct sock *);
void tcp_enter_recovery(struct sock *sk, bool ece_ack);
int tcp_trim_head(struct sock *, struct sk_buff *, u32);
enum tcp_queue {
	TCP_FRAG_IN_WRITE_QUEUE,
	TCP_FRAG_IN_RTX_QUEUE,
};
int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
		 struct sk_buff *skb, u32 len,
		 unsigned int mss_now, gfp_t gfp);

void tcp_send_probe0(struct sock *);
int tcp_write_wakeup(struct sock *, int mib);
void tcp_send_fin(struct sock *sk);
void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason);
int tcp_send_synack(struct sock *);
void tcp_push_one(struct sock *, unsigned int mss_now);
void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags);
void tcp_send_ack(struct sock *sk);
void tcp_send_delayed_ack(struct sock *sk);
void tcp_send_loss_probe(struct sock *sk);
bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto);
void tcp_skb_collapse_tstamp(struct sk_buff *skb,
			     const struct sk_buff *next_skb);

/* tcp_input.c */
void tcp_rearm_rto(struct sock *sk);
void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
void tcp_done_with_error(struct sock *sk, int err);
void tcp_reset(struct sock *sk, struct sk_buff *skb);
void tcp_fin(struct sock *sk);
void __tcp_check_space(struct sock *sk);

/* Mirror of SOCK_NOSPACE in tcp_sock, maintained by sk_set_nospace()
 * and sk_clear_nospace().
 *
 * MPTCP subflows share the parent socket, and thus its SOCK_NOSPACE bit.
 * Keep their mirror always set (see subflow_ulp_init()) so that they
 * always reach __tcp_check_space() and behave as before.
 */
static inline void tcp_set_nospace(struct sock *sk)
{
	if (sk_is_tcp(sk)) {
		/* pairs with smp_mb__before_atomic() in tcp_clear_nospace() */
		smp_mb__after_atomic();
		/* pairs with smp_mb() in tcp_check_space() */
		smp_store_mb(tcp_sk(sk)->tcp_nospace, 1);
	}
}

static inline void tcp_clear_nospace(struct sock *sk)
{
	if (sk_is_tcp(sk) && !sk_is_mptcp(sk)) {
		WRITE_ONCE(tcp_sk(sk)->tcp_nospace, 0);
		/* pairs with smp_mb__after_atomic() in tcp_set_nospace() */
		smp_mb__before_atomic();
	}
}

static inline void tcp_check_space(struct sock *sk)
{
	/* pairs with tcp_poll() */
	smp_mb();

	if (unlikely(READ_ONCE(tcp_sk(sk)->tcp_nospace)))
		__tcp_check_space(sk);
}

void tcp_sack_compress_send_ack(struct sock *sk);

static inline void tcp_cleanup_skb(struct sk_buff *skb)
{
	skb_dst_drop(skb);
	secpath_reset(skb);
}

static inline void tcp_add_receive_queue(struct sock *sk, struct sk_buff *skb)
{
	DEBUG_NET_WARN_ON_ONCE(skb_dst(skb));
	DEBUG_NET_WARN_ON_ONCE(secpath_exists(skb));
	__skb_queue_tail(&sk->sk_receive_queue, skb);
}

/* tcp_timer.c */
void tcp_init_xmit_timers(struct sock *);
static inline void tcp_clear_xmit_timers(struct sock *sk)
{
	if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1)
		__sock_put(sk);

	if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1)
		__sock_put(sk);

	inet_csk_clear_xmit_timers(sk);
}

unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
unsigned int tcp_current_mss(struct sock *sk);
u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when);

u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
		     int min_tso_segs);

/* Bound MSS / TSO packet size with the half of the window */
static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
{
	int cutoff;

	/* When peer uses tiny windows, there is no use in packetizing
	 * to sub-MSS pieces for the sake of SWS or making sure there
	 * are enough packets in the pipe for fast recovery.
	 *
	 * On the other hand, for extremely large MSS devices, handling
	 * smaller than MSS windows in this way does make sense.
	 */
	if (tp->max_window > TCP_MSS_DEFAULT)
		cutoff = (tp->max_window >> 1);
	else
		cutoff = tp->max_window;

	if (cutoff && pktsize > cutoff)
		return max_t(int, cutoff, 68U - tp->tcp_header_len);
	else
		return pktsize;
}

/* tcp.c */
void tcp_get_info(struct sock *, struct tcp_info *);
void tcp_rate_check_app_limited(struct sock *sk);

/* Read 'sendfile()'-style from a TCP socket */
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
		  sk_read_actor_t recv_actor);
int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc,
			sk_read_actor_t recv_actor, bool noack,
			u32 *copied_seq);
int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor);
struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off);
void tcp_read_done(struct sock *sk, size_t len);

void tcp_initialize_rcv_mss(struct sock *sk);

int tcp_mtu_to_mss(struct sock *sk, int pmtu);
int tcp_mss_to_mtu(struct sock *sk, int mss);
void tcp_mtup_init(struct sock *sk);

static inline unsigned int tcp_rto_max(const struct sock *sk)
{
	return READ_ONCE(inet_csk(sk)->icsk_rto_max);
}

static inline void tcp_bound_rto(struct sock *sk)
{
	inet_csk(sk)->icsk_rto = min(inet_csk(sk)->icsk_rto, tcp_rto_max(sk));
}

static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
{
	return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us);
}

static inline unsigned long tcp_reqsk_timeout(struct request_sock *req)
{
	u64 timeout = (u64)req->timeout << req->num_timeout;

	return (unsigned long)min_t(u64, timeout,
				    tcp_rto_max(req->rsk_listener));
}

u32 tcp_delack_max(const struct sock *sk);

/* Compute the actual rto_min value */
static inline u32 tcp_rto_min(const struct sock *sk)
{
	const struct dst_entry *dst = __sk_dst_get(sk);
	u32 rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min);

	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
		rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
	return rto_min;
}

static inline u32 tcp_rto_min_us(const struct sock *sk)
{
	return jiffies_to_usecs(tcp_rto_min(sk));
}

static inline bool tcp_ca_dst_locked(const struct dst_entry *dst)
{
	return dst_metric_locked(dst, RTAX_CC_ALGO);
}

/* Minimum RTT in usec. ~0 means not available. */
static inline u32 tcp_min_rtt(const struct tcp_sock *tp)
{
	return minmax_get(&tp->rtt_min);
}

/* Compute the actual receive window we are currently advertising.
 * Rcv_nxt can be after the window if our peer push more data
 * than the offered window.
 */
static inline u32 tcp_receive_window(const struct tcp_sock *tp)
{
	s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt;

	if (win < 0)
		win = 0;
	return (u32) win;
}

/* Compute the maximum receive window we ever advertised.
 * Rcv_nxt can be after the window if our peer push more data
 * than the offered window.
 */
static inline u32 tcp_max_receive_window(const struct tcp_sock *tp)
{
	s32 win = tp->rcv_mwnd_seq - tp->rcv_nxt;

	if (win < 0)
		win = 0;
	return (u32) win;
}

/* Check if we need to update the maximum receive window sequence number */
static inline void tcp_update_max_rcv_wnd_seq(struct tcp_sock *tp)
{
	u32 wre = tp->rcv_wup + tp->rcv_wnd;

	if (after(wre, tp->rcv_mwnd_seq))
		tp->rcv_mwnd_seq = wre;
}

/* Choose a new window, without checks for shrinking, and without
 * scaling applied to the result.  The caller does these things
 * if necessary.  This is a "raw" window selection.
 */
u32 __tcp_select_window(struct sock *sk);

void tcp_send_window_probe(struct sock *sk);

/* TCP uses 32bit jiffies to save some space.
 * Note that this is different from tcp_time_stamp, which
 * historically has been the same until linux-4.13.
 */
#define tcp_jiffies32 ((u32)jiffies)

/*
 * Deliver a 32bit value for TCP timestamp option (RFC 7323)
 * It is no longer tied to jiffies, but to 1 ms clock.
 * Note: double check if you want to use tcp_jiffies32 instead of this.
 */
#define TCP_TS_HZ	1000

static inline u64 tcp_clock_ns(void)
{
	return ktime_get_ns();
}

static inline u64 tcp_clock_us(void)
{
	return div_u64(tcp_clock_ns(), NSEC_PER_USEC);
}

static inline u64 tcp_clock_ms(void)
{
	return div_u64(tcp_clock_ns(), NSEC_PER_MSEC);
}

/* TCP Timestamp included in TS option (RFC 1323) can either use ms
 * or usec resolution. Each socket carries a flag to select one or other
 * resolution, as the route attribute could change anytime.
 * Each flow must stick to initial resolution.
 */
static inline u32 tcp_clock_ts(bool usec_ts)
{
	return usec_ts ? tcp_clock_us() : tcp_clock_ms();
}

static inline u32 tcp_time_stamp_ms(const struct tcp_sock *tp)
{
	return div_u64(tp->tcp_mstamp, USEC_PER_MSEC);
}

static inline u32 tcp_time_stamp_ts(const struct tcp_sock *tp)
{
	if (tp->tcp_usec_ts)
		return tp->tcp_mstamp;
	return tcp_time_stamp_ms(tp);
}

/* Refresh clocks of a TCP socket,
 * ensuring monotically increasing values.
 */
static inline void tcp_mstamp_refresh_inline(struct tcp_sock *tp)
{
	u64 val = tcp_clock_ns();

	tp->tcp_clock_cache = val;
	tp->tcp_mstamp = div_u64(val, NSEC_PER_USEC);
}
void tcp_mstamp_refresh(struct tcp_sock *tp);

static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0)
{
	return max_t(s64, t1 - t0, 0);
}

/* provide the departure time in us unit */
static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb)
{
	return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC);
}

/* Provide skb TSval in usec or ms unit */
static inline u32 tcp_skb_timestamp_ts(bool usec_ts, const struct sk_buff *skb)
{
	if (usec_ts)
		return tcp_skb_timestamp_us(skb);

	return div_u64(skb->skb_mstamp_ns, NSEC_PER_MSEC);
}

static inline u32 tcp_tw_tsval(const struct tcp_timewait_sock *tcptw)
{
	return tcp_clock_ts(tcptw->tw_sk.tw_usec_ts) + tcptw->tw_ts_offset;
}

static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq)
{
	return tcp_clock_ts(treq->req_usec_ts) + treq->ts_off;
}

#define tcp_flag_byte(th) (((u_int8_t *)th)[13])

#define TCPHDR_FIN	BIT(0)
#define TCPHDR_SYN	BIT(1)
#define TCPHDR_RST	BIT(2)
#define TCPHDR_PSH	BIT(3)
#define TCPHDR_ACK	BIT(4)
#define TCPHDR_URG	BIT(5)
#define TCPHDR_ECE	BIT(6)
#define TCPHDR_CWR	BIT(7)
#define TCPHDR_AE	BIT(8)
#define TCPHDR_FLAGS_MASK (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \
			   TCPHDR_PSH | TCPHDR_ACK | TCPHDR_URG | \
			   TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)
#define tcp_flags_ntohs(th) (ntohs(*(__be16 *)&tcp_flag_word(th)) & \
			    TCPHDR_FLAGS_MASK)

#define TCPHDR_ACE (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)
#define TCPHDR_SYN_ECN	(TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
#define TCPHDR_SYNACK_ACCECN (TCPHDR_SYN | TCPHDR_ACK | TCPHDR_CWR)

#define TCP_ACCECN_CEP_ACE_MASK 0x7
#define TCP_ACCECN_ACE_MAX_DELTA 6

/* To avoid/detect middlebox interference, not all counters start at 0.
 * See draft-ietf-tcpm-accurate-ecn for the latest values.
 */
#define TCP_ACCECN_CEP_INIT_OFFSET 5
#define TCP_ACCECN_E1B_INIT_OFFSET 1
#define TCP_ACCECN_E0B_INIT_OFFSET 1
#define TCP_ACCECN_CEB_INIT_OFFSET 0

/* State flags for sacked in struct tcp_skb_cb */
enum tcp_skb_cb_sacked_flags {
	TCPCB_SACKED_ACKED	= (1 << 0),	/* SKB ACK'd by a SACK block	*/
	TCPCB_SACKED_RETRANS	= (1 << 1),	/* SKB retransmitted		*/
	TCPCB_LOST		= (1 << 2),	/* SKB is lost			*/
	TCPCB_TAGBITS		= (TCPCB_SACKED_ACKED | TCPCB_SACKED_RETRANS |
				   TCPCB_LOST),	/* All tag bits			*/
	TCPCB_REPAIRED		= (1 << 4),	/* SKB repaired (no skb_mstamp_ns)	*/
	TCPCB_EVER_RETRANS	= (1 << 7),	/* Ever retransmitted frame	*/
	TCPCB_RETRANS		= (TCPCB_SACKED_RETRANS | TCPCB_EVER_RETRANS |
				   TCPCB_REPAIRED),
};

/* This is what the send packet queuing engine uses to pass
 * TCP per-packet control information to the transmission code.
 * We also store the host-order sequence numbers in here too.
 * This is 44 bytes if IPV6 is enabled.
 * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately.
 */
struct tcp_skb_cb {
	__u32		seq;		/* Starting sequence number	*/
	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
	union {
		/* Notes :
		 *	tcp_tw_isn is used in input path only
		 *	(isn chosen by tcp_timewait_state_process())
		 * 	  tcp_gso_segs/size are used in write queue only,
		 *	  cf tcp_skb_pcount()/tcp_skb_mss()
		 */
		u32		tcp_tw_isn;
		struct {
			u16	tcp_gso_segs;
			u16	tcp_gso_size;
		};
	};
	__u16		tcp_flags;	/* TCP header flags (tcp[12-13])*/

	__u8		sacked;		/* State flags for SACK.	*/
	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
#define TSTAMP_ACK_SK	0x1
#define TSTAMP_ACK_BPF	0x2
	__u8		txstamp_ack:2,	/* Record TX timestamp for ack? */
			eor:1,		/* Is skb MSG_EOR marked? */
			has_rxtstamp:1,	/* SKB has a RX timestamp	*/
			unused:4;
	__u32		ack_seq;	/* Sequence number ACK'd	*/
	union {
		struct {
#define TCPCB_DELIVERED_CE_MASK ((1U<<20) - 1)
			/* There is space for up to 24 bytes */
			__u32 is_app_limited:1, /* cwnd not fully used? */
			      delivered_ce:20,
			      unused:11;
			/* pkts S/ACKed so far upon tx of skb, incl retrans: */
			__u32 delivered;
			/* start of send pipeline phase */
			u64 first_tx_mstamp;
			/* when we reached the "delivered" count */
			u64 delivered_mstamp;
		} tx;   /* only used for outgoing skbs */
		union {
			struct inet_skb_parm	h4;
#if IS_ENABLED(CONFIG_IPV6)
			struct inet6_skb_parm	h6;
#endif
		} header;	/* For incoming skbs */
	};
};

#define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))

extern const struct inet_connection_sock_af_ops ipv4_specific;

#if IS_ENABLED(CONFIG_IPV6)
/* This is the variant of inet6_iif() that must be used by TCP,
 * as TCP moves IP6CB into a different location in skb->cb[]
 */
static inline int tcp_v6_iif(const struct sk_buff *skb)
{
	return TCP_SKB_CB(skb)->header.h6.iif;
}

static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb)
{
	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);

	return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
}

/* TCP_SKB_CB reference means this can not be used from early demux */
static inline int tcp_v6_sdif(const struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
	if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags))
		return TCP_SKB_CB(skb)->header.h6.iif;
#endif
	return 0;
}

extern const struct inet_connection_sock_af_ops ipv6_specific;

INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb));

#endif

/* TCP_SKB_CB reference means this can not be used from early demux */
static inline int tcp_v4_sdif(struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
	if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
		return TCP_SKB_CB(skb)->header.h4.iif;
#endif
	return 0;
}

/* Due to TSO, an SKB can be composed of multiple actual
 * packets.  To keep these tracked properly, we use this.
 */
static inline int tcp_skb_pcount(const struct sk_buff *skb)
{
	return TCP_SKB_CB(skb)->tcp_gso_segs;
}

static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs)
{
	TCP_SKB_CB(skb)->tcp_gso_segs = segs;
}

static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs)
{
	TCP_SKB_CB(skb)->tcp_gso_segs += segs;
}

/* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */
static inline int tcp_skb_mss(const struct sk_buff *skb)
{
	return TCP_SKB_CB(skb)->tcp_gso_size;
}

static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb)
{
	return likely(!TCP_SKB_CB(skb)->eor);
}

static inline bool tcp_skb_can_collapse(const struct sk_buff *to,
					const struct sk_buff *from)
{
	return likely(tcp_skb_can_collapse_to(to) &&
		      mptcp_skb_can_collapse(to, from) &&
		      !skb_cmp_decrypted(to, from) &&
		      skb_pure_zcopy_same(to, from) &&
		      skb_frags_readable(to) == skb_frags_readable(from));
}

static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to,
					   const struct sk_buff *from)
{
	return likely(mptcp_skb_can_collapse(to, from) &&
		      !skb_cmp_decrypted(to, from));
}

/* Events passed to congestion control interface */
enum tcp_ca_event {
	CA_EVENT_TX_START,	/* first transmit when no packets in flight */
	CA_EVENT_CWND_RESTART,	/* congestion window restart */
	CA_EVENT_COMPLETE_CWR,	/* end of congestion recovery */
	CA_EVENT_LOSS,		/* loss timeout */
	CA_EVENT_ECN_NO_CE,	/* ECT set, but not CE marked */
	CA_EVENT_ECN_IS_CE,	/* received CE marked IP packet */
};

/* Information about inbound ACK, passed to cong_ops->in_ack_event() */
enum tcp_ca_ack_event_flags {
	CA_ACK_SLOWPATH		= (1 << 0),	/* In slow path processing */
	CA_ACK_WIN_UPDATE	= (1 << 1),	/* ACK updated window */
	CA_ACK_ECE		= (1 << 2),	/* ECE bit is set on ack */
};

/*
 * Interface for adding new TCP congestion control handlers
 */
#define TCP_CA_NAME_MAX	16
#define TCP_CA_MAX	128
#define TCP_CA_BUF_MAX	(TCP_CA_NAME_MAX*TCP_CA_MAX)

#define TCP_CA_UNSPEC	0

/* Algorithm can be set on socket without CAP_NET_ADMIN privileges */
#define TCP_CONG_NON_RESTRICTED		BIT(0)
/* Requires ECN/ECT set on all packets */
#define TCP_CONG_NEEDS_ECN		BIT(1)
/* Require successfully negotiated AccECN capability */
#define TCP_CONG_NEEDS_ACCECN		BIT(2)
/* Use ECT(1) instead of ECT(0) while the CA is uninitialized */
#define TCP_CONG_ECT_1_NEGOTIATION	BIT(3)
/* Cannot fallback to RFC3168 during AccECN negotiation */
#define TCP_CONG_NO_FALLBACK_RFC3168	BIT(4)
#define TCP_CONG_MASK  (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \
			TCP_CONG_NEEDS_ACCECN | TCP_CONG_ECT_1_NEGOTIATION | \
			TCP_CONG_NO_FALLBACK_RFC3168)

union tcp_cc_info;

struct ack_sample {
	u32 pkts_acked;
	s32 rtt_us;
	u32 in_flight;
};

/* A rate sample measures the number of (original/retransmitted) data
 * packets delivered "delivered" over an interval of time "interval_us".
 * The tcp_rate.c code fills in the rate sample, and congestion
 * control modules that define a cong_control function to run at the end
 * of ACK processing can optionally chose to consult this sample when
 * setting cwnd and pacing rate.
 * A sample is invalid if "delivered" or "interval_us" is negative.
 */
struct rate_sample {
	u64  prior_mstamp; /* starting timestamp for interval */
	u32  prior_delivered;	/* tp->delivered at "prior_mstamp" */
	u32  prior_delivered_ce;/* tp->delivered_ce at "prior_mstamp" */
	s32  delivered;		/* number of packets delivered over interval */
	s32  delivered_ce;	/* number of packets delivered w/ CE marks*/
	long interval_us;	/* time for tp->delivered to incr "delivered" */
	u32 snd_interval_us;	/* snd interval for delivered packets */
	u32 rcv_interval_us;	/* rcv interval for delivered packets */
	long rtt_us;		/* RTT of last (S)ACKed packet (or -1) */
	int  losses;		/* number of packets marked lost upon ACK */
	u32  acked_sacked;	/* number of packets newly (S)ACKed upon ACK */
	u32  prior_in_flight;	/* in flight before this ACK */
	u32  last_end_seq;	/* end_seq of most recently ACKed packet */
	bool is_app_limited;	/* is sample from packet with bubble in pipe? */
	bool is_retrans;	/* is sample from retransmission? */
	bool is_ack_delayed;	/* is this (likely) a delayed ACK? */
};

struct tcp_congestion_ops {
/* fast path fields are put first to fill one cache line */

	/* A congestion control (CC) must provide one of either:
	 *
	 * (a) a cong_avoid function, if the CC wants to use the core TCP
	 *     stack's default functionality to implement a "classic"
	 *     (Reno/CUBIC-style) response to packet loss, RFC3168 ECN,
	 *     idle periods, pacing rate computations, etc.
	 *
	 * (b) a cong_control function, if the CC wants custom behavior and
	 *      complete control of all congestion control behaviors.
	 */
	/* (a) "classic" response: calculate new cwnd.
	 */
	void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked);
	/* (b) "custom" response: call when packets are delivered to update
	 * cwnd and pacing rate, after all the ca_state processing.
	 */
	void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs);

	/* return slow start threshold (required) */
	u32 (*ssthresh)(struct sock *sk);

	/* call before changing ca_state (optional) */
	void (*set_state)(struct sock *sk, u8 new_state);

	/* call when cwnd event occurs (optional) */
	void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);

	/* call when CA_EVENT_TX_START cwnd event occurs (optional) */
	void (*cwnd_event_tx_start)(struct sock *sk);

	/* call when ack arrives (optional) */
	void (*in_ack_event)(struct sock *sk, u32 flags);

	/* hook for packet ack accounting (optional) */
	void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);

	/* Override tcp_tso_autosize() (optional)
	 *
	 * If provided, this callback supplies the TSO segment target count
	 * instead of using tcp_tso_autosize(). The returned value is
	 * subsequently clamped to [1, sk->sk_gso_max_segs] by the caller.
	 *
	 * For the kernel callback path, mss_now originates from
	 * tcp_current_mss() and should never be zero.
	 */
	u32 (*tso_segs)(struct sock *sk, u32 mss_now);

	/* new value of cwnd after loss (required) */
	u32  (*undo_cwnd)(struct sock *sk);
	/* returns the multiplier used in tcp_sndbuf_expand (optional) */
	u32 (*sndbuf_expand)(struct sock *sk);

/* control/slow paths put last */
	/* get info for inet_diag (optional) */
	size_t (*get_info)(struct sock *sk, u32 ext, int *attr,
			   union tcp_cc_info *info);

	char 			name[TCP_CA_NAME_MAX];
	struct module		*owner;
	struct list_head	list;
	u32			key;
	u32			flags;

	/* initialize private data (optional) */
	void (*init)(struct sock *sk);
	/* cleanup private data  (optional) */
	void (*release)(struct sock *sk);
} ____cacheline_aligned_in_smp;

int tcp_register_congestion_control(struct tcp_congestion_ops *type);
void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
int tcp_update_congestion_control(struct tcp_congestion_ops *type,
				  struct tcp_congestion_ops *old_type);
int tcp_validate_congestion_control(struct tcp_congestion_ops *ca);

void tcp_assign_congestion_control(struct sock *sk);
void tcp_init_congestion_control(struct sock *sk);
void tcp_cleanup_congestion_control(struct sock *sk);
int tcp_set_default_congestion_control(struct net *net, const char *name);
void tcp_get_default_congestion_control(struct net *net, char *name);
void tcp_get_available_congestion_control(char *buf, size_t len);
void tcp_get_allowed_congestion_control(char *buf, size_t len);
int tcp_set_allowed_congestion_control(char *allowed);
int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
			       bool cap_net_admin);
u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);

u32 tcp_reno_ssthresh(struct sock *sk);
u32 tcp_reno_undo_cwnd(struct sock *sk);
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
extern struct tcp_congestion_ops tcp_reno;

struct tcp_congestion_ops *tcp_ca_find(const char *name);
struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca);
#ifdef CONFIG_INET
char *tcp_ca_get_name_by_key(u32 key, char *buffer);
#else
static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer)
{
	return NULL;
}
#endif

static inline bool tcp_ca_needs_ecn(const struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);

	return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
}

static inline bool tcp_ca_needs_accecn(const struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);

	return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ACCECN;
}

static inline bool tcp_ca_ect_1_negotiation(const struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);

	return icsk->icsk_ca_ops->flags & TCP_CONG_ECT_1_NEGOTIATION;
}

static inline bool tcp_ca_no_fallback_rfc3168(const struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);

	return icsk->icsk_ca_ops->flags & TCP_CONG_NO_FALLBACK_RFC3168;
}

static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);

	if (event == CA_EVENT_TX_START) {
		if (icsk->icsk_ca_ops->cwnd_event_tx_start)
			icsk->icsk_ca_ops->cwnd_event_tx_start(sk);
		return;
	}
	if (icsk->icsk_ca_ops->cwnd_event)
		icsk->icsk_ca_ops->cwnd_event(sk, event);
}

/* From tcp_cong.c */
void tcp_set_ca_state(struct sock *sk, const u8 ca_state);


static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
{
	return t1 > t2 || (t1 == t2 && after(seq1, seq2));
}

/* These functions determine how the current flow behaves in respect of SACK
 * handling. SACK is negotiated with the peer, and therefore it can vary
 * between different flows.
 *
 * tcp_is_sack - SACK enabled
 * tcp_is_reno - No SACK
 */
static inline int tcp_is_sack(const struct tcp_sock *tp)
{
	return likely(tp->rx_opt.sack_ok);
}

static inline bool tcp_is_reno(const struct tcp_sock *tp)
{
	return !tcp_is_sack(tp);
}

static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
{
	return tp->sacked_out + tp->lost_out;
}

/* This determines how many packets are "in the network" to the best
 * of our knowledge.  In many cases it is conservative, but where
 * detailed information is available from the receiver (via SACK
 * blocks etc.) we can make more aggressive calculations.
 *
 * Use this for decisions involving congestion control, use just
 * tp->packets_out to determine if the send queue is empty or not.
 *
 * Read this equation as:
 *
 *	"Packets sent once on transmission queue" MINUS
 *	"Packets left network, but not honestly ACKed yet" PLUS
 *	"Packets fast retransmitted"
 */
static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
{
	return tp->packets_out - tcp_left_out(tp) + tp->retrans_out;
}

#define TCP_INFINITE_SSTHRESH	0x7fffffff

static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp)
{
	return tp->snd_cwnd;
}

static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val)
{
	WARN_ON_ONCE((int)val <= 0);
	WRITE_ONCE(tp->snd_cwnd, val);
}

static inline bool tcp_in_slow_start(const struct tcp_sock *tp)
{
	return tcp_snd_cwnd(tp) < tp->snd_ssthresh;
}

static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp)
{
	return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH;
}

static inline bool tcp_in_cwnd_reduction(const struct sock *sk)
{
	return (TCPF_CA_CWR | TCPF_CA_Recovery) &
	       (1 << inet_csk(sk)->icsk_ca_state);
}

/* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd.
 * The exception is cwnd reduction phase, when cwnd is decreasing towards
 * ssthresh.
 */
static inline __u32 tcp_current_ssthresh(const struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_in_cwnd_reduction(sk))
		return tp->snd_ssthresh;
	else
		return max(tp->snd_ssthresh,
			   ((tcp_snd_cwnd(tp) >> 1) +
			    (tcp_snd_cwnd(tp) >> 2)));
}

/* Use define here intentionally to get WARN_ON location shown at the caller */
#define tcp_verify_left_out(tp)	WARN_ON(tcp_left_out(tp) > tp->packets_out)

void tcp_enter_cwr(struct sock *sk);
__u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst);

/* The maximum number of MSS of available cwnd for which TSO defers
 * sending if not using sysctl_tcp_tso_win_divisor.
 */
static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp)
{
	return 3;
}

/* Returns end sequence number of the receiver's advertised window */
static inline u32 tcp_wnd_end(const struct tcp_sock *tp)
{
	return tp->snd_una + tp->snd_wnd;
}

/* We follow the spirit of RFC2861 to validate cwnd but implement a more
 * flexible approach. The RFC suggests cwnd should not be raised unless
 * it was fully used previously. And that's exactly what we do in
 * congestion avoidance mode. But in slow start we allow cwnd to grow
 * as long as the application has used half the cwnd.
 * Example :
 *    cwnd is 10 (IW10), but application sends 9 frames.
 *    We allow cwnd to reach 18 when all frames are ACKed.
 * This check is safe because it's as aggressive as slow start which already
 * risks 100% overshoot. The advantage is that we discourage application to
 * either send more filler packets or data to artificially blow up the cwnd
 * usage, and allow application-limited process to probe bw more aggressively.
 */
static inline bool tcp_is_cwnd_limited(const struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	if (tp->is_cwnd_limited)
		return true;

	/* If in slow start, ensure cwnd grows to twice what was ACKed. */
	if (tcp_in_slow_start(tp))
		return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out;

	return false;
}

/* BBR congestion control needs pacing.
 * Same remark for SO_MAX_PACING_RATE.
 * sch_fq packet scheduler is efficiently handling pacing,
 * but is not always installed/used.
 * Return true if TCP stack should pace packets itself.
 */
static inline bool tcp_needs_internal_pacing(const struct sock *sk)
{
	return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
}

/* Estimates in how many jiffies next packet for this flow can be sent.
 * Scheduling a retransmit timer too early would be silly.
 */
static inline unsigned long tcp_pacing_delay(const struct sock *sk)
{
	s64 delay = tcp_sk(sk)->tcp_wstamp_ns - tcp_sk(sk)->tcp_clock_cache;

	return delay > 0 ? nsecs_to_jiffies(delay) : 0;
}

static inline void tcp_reset_xmit_timer(struct sock *sk,
					const int what,
					unsigned long when,
					bool pace_delay)
{
	if (pace_delay)
		when += tcp_pacing_delay(sk);
	inet_csk_reset_xmit_timer(sk, what, when,
				  tcp_rto_max(sk));
}

/* Something is really bad, we could not queue an additional packet,
 * because qdisc is full or receiver sent a 0 window, or we are paced.
 * We do not want to add fuel to the fire, or abort too early,
 * so make sure the timer we arm now is at least 200ms in the future,
 * regardless of current icsk_rto value (as it could be ~2ms)
 */
static inline unsigned long tcp_probe0_base(const struct sock *sk)
{
	return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN);
}

/* Variant of inet_csk_rto_backoff() used for zero window probes */
static inline unsigned long tcp_probe0_when(const struct sock *sk,
					    unsigned long max_when)
{
	u8 backoff = min_t(u8, ilog2(TCP_RTO_MAX / TCP_RTO_MIN) + 1,
			   inet_csk(sk)->icsk_backoff);
	u64 when = (u64)tcp_probe0_base(sk) << backoff;

	return (unsigned long)min_t(u64, when, max_when);
}

static inline void tcp_check_probe_timer(struct sock *sk)
{
	if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending)
		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
				     tcp_probe0_base(sk), true);
}

static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
{
	tp->snd_wl1 = seq;
}

static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq)
{
	tp->snd_wl1 = seq;
}

/*
 * Calculate(/check) TCP checksum
 */
static inline __sum16 tcp_v4_check(int len, __be32 saddr,
				   __be32 daddr, __wsum base)
{
	return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_TCP, base);
}

static inline bool tcp_checksum_complete(struct sk_buff *skb)
{
	return !skb_csum_unnecessary(skb) &&
		__skb_checksum_complete(skb);
}

enum skb_drop_reason tcp_add_backlog(struct sock *sk, struct sk_buff *skb);

static inline enum skb_drop_reason
tcp_filter(struct sock *sk, struct sk_buff *skb)
{
	const struct tcphdr *th = (const struct tcphdr *)skb->data;

	return sk_filter_trim_cap(sk, skb, __tcp_hdrlen(th));
}

void tcp_set_state(struct sock *sk, int state);
void tcp_done(struct sock *sk);
int tcp_abort(struct sock *sk, int err);

static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
{
	rx_opt->dsack = 0;
	rx_opt->num_sacks = 0;
}

void tcp_cwnd_restart(struct sock *sk, s32 delta);

static inline void tcp_slow_start_after_idle_check(struct sock *sk)
{
	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
	struct tcp_sock *tp = tcp_sk(sk);
	s32 delta;

	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) ||
	    tp->packets_out || ca_ops->cong_control)
		return;
	delta = tcp_jiffies32 - tp->lsndtime;
	if (delta > inet_csk(sk)->icsk_rto)
		tcp_cwnd_restart(sk, delta);
}

/* Determine a window scaling and initial window to offer. */
void tcp_select_initial_window(const struct sock *sk, int __space,
			       __u32 mss, __u32 *rcv_wnd,
			       __u32 *window_clamp, int wscale_ok,
			       __u8 *rcv_wscale, __u32 init_rcv_wnd);

static inline int __tcp_win_from_space(u8 scaling_ratio, int space)
{
	s64 scaled_space = (s64)space * scaling_ratio;

	return scaled_space >> TCP_RMEM_TO_WIN_SCALE;
}

static inline int tcp_win_from_space(const struct sock *sk, int space)
{
	return __tcp_win_from_space(tcp_sk(sk)->scaling_ratio, space);
}

/* inverse of __tcp_win_from_space() */
static inline int __tcp_space_from_win(u8 scaling_ratio, int win)
{
	u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE;

	do_div(val, scaling_ratio);
	return val;
}

static inline int tcp_space_from_win(const struct sock *sk, int win)
{
	return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win);
}

/* Assume a 50% default for skb->len/skb->truesize ratio.
 * This may be adjusted later in tcp_measure_rcv_mss().
 */
#define TCP_DEFAULT_SCALING_RATIO (1 << (TCP_RMEM_TO_WIN_SCALE - 1))

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 */
static inline int tcp_space(const struct sock *sk)
{
	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) -
				  READ_ONCE(sk->sk_backlog.len) -
				  atomic_read(&sk->sk_rmem_alloc));
}

static inline int tcp_full_space(const struct sock *sk)
{
	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
}

static inline u32 tcp_dst_advmss(const struct dst_entry *dst)
{
	return max_t(u32, dst_metric_advmss(dst), TCP_MIN_MSS);
}

static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh)
{
	int unused_mem = sk_unused_reserved_mem(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh);
	if (unused_mem)
		tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh,
					 tcp_win_from_space(sk, unused_mem));
}

static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
{
	__tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss);
}

void tcp_cleanup_rbuf(struct sock *sk, int copied);
void __tcp_cleanup_rbuf(struct sock *sk, int copied);


/* We provision sk_rcvbuf around 200% of sk_rcvlowat.
 * If 87.5 % (7/8) of the space has been consumed, we want to override
 * SO_RCVLOWAT constraint, since we are receiving skbs with too small
 * len/truesize ratio.
 */
static inline bool tcp_rmem_pressure(const struct sock *sk)
{
	int rcvbuf, threshold;

	if (tcp_under_memory_pressure(sk))
		return true;

	rcvbuf = READ_ONCE(sk->sk_rcvbuf);
	threshold = rcvbuf - (rcvbuf >> 3);

	return atomic_read(&sk->sk_rmem_alloc) > threshold;
}

static inline bool tcp_epollin_ready(const struct sock *sk, int target)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);

	if (avail <= 0)
		return false;

	return (avail >= target) || tcp_rmem_pressure(sk) ||
	       (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss);
}

extern void tcp_openreq_init_rwin(struct request_sock *req,
				  const struct sock *sk_listener,
				  const struct dst_entry *dst);

void tcp_enter_memory_pressure(struct sock *sk);
void tcp_leave_memory_pressure(struct sock *sk);

static inline int keepalive_intvl_when(const struct tcp_sock *tp)
{
	struct net *net = sock_net((struct sock *)tp);
	int val;

	/* Paired with WRITE_ONCE() in tcp_sock_set_keepintvl()
	 * and do_tcp_setsockopt().
	 */
	val = READ_ONCE(tp->keepalive_intvl);

	return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl);
}

static inline int keepalive_time_when(const struct tcp_sock *tp)
{
	struct net *net = sock_net((struct sock *)tp);
	int val;

	/* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */
	val = READ_ONCE(tp->keepalive_time);

	return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time);
}

static inline int keepalive_probes(const struct tcp_sock *tp)
{
	struct net *net = sock_net((struct sock *)tp);
	int val;

	/* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt()
	 * and do_tcp_setsockopt().
	 */
	val = READ_ONCE(tp->keepalive_probes);

	return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes);
}

static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
{
	const struct inet_connection_sock *icsk = &tp->inet_conn;

	return min_t(u32, tcp_jiffies32 - icsk->icsk_ack.lrcvtime,
			  tcp_jiffies32 - tp->rcv_tstamp);
}

static inline int tcp_fin_time(const struct sock *sk)
{
	int fin_timeout = tcp_sk(sk)->linger2 ? :
		READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout);
	const int rto = inet_csk(sk)->icsk_rto;

	if (fin_timeout < (rto << 2) - (rto >> 1))
		fin_timeout = (rto << 2) - (rto >> 1);

	return fin_timeout;
}

static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt,
				  int paws_win)
{
	if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
		return true;
	if (unlikely(!time_before32(ktime_get_seconds(),
				    rx_opt->ts_recent_stamp + TCP_PAWS_WRAP)))
		return true;
	/*
	 * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0,
	 * then following tcp messages have valid values. Ignore 0 value,
	 * or else 'negative' tsval might forbid us to accept their packets.
	 */
	if (!rx_opt->ts_recent)
		return true;
	return false;
}

static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt,
				   int rst)
{
	if (tcp_paws_check(rx_opt, 0))
		return false;

	/* RST segments are not recommended to carry timestamp,
	   and, if they do, it is recommended to ignore PAWS because
	   "their cleanup function should take precedence over timestamps."
	   Certainly, it is mistake. It is necessary to understand the reasons
	   of this constraint to relax it: if peer reboots, clock may go
	   out-of-sync and half-open connections will not be reset.
	   Actually, the problem would be not existing if all
	   the implementations followed draft about maintaining clock
	   via reboots. Linux-2.2 DOES NOT!

	   However, we can relax time bounds for RST segments to MSL.
	 */
	if (rst && !time_before32(ktime_get_seconds(),
				  rx_opt->ts_recent_stamp + TCP_PAWS_MSL))
		return false;
	return true;
}

static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
	u32 ace;

	/* mptcp hooks are only on the slow path */
	if (sk_is_mptcp((struct sock *)tp))
		return;

	ace = tcp_ecn_mode_accecn(tp) ?
	      ((tp->delivered_ce + TCP_ACCECN_CEP_INIT_OFFSET) &
	       TCP_ACCECN_CEP_ACE_MASK) : 0;

	tp->pred_flags = htonl((tp->tcp_header_len << 26) |
			       (ace << 22) |
			       ntohl(TCP_FLAG_ACK) |
			       snd_wnd);
}

static inline void tcp_fast_path_on(struct tcp_sock *tp)
{
	__tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
}

static inline void tcp_fast_path_check(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (RB_EMPTY_ROOT(&tp->out_of_order_queue) &&
	    tp->rcv_wnd &&
	    atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
	    !tp->urg_data)
		tcp_fast_path_on(tp);
}

bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
			  int mib_idx, u32 *last_oow_ack_time);
void tcp_reqsk_send_challenge_ack(struct sock *sk, struct sk_buff *skb,
				  struct request_sock *req);

static inline void tcp_mib_init(struct net *net)
{
	/* See RFC 2012 */
	TCP_ADD_STATS(net, TCP_MIB_RTOALGORITHM, 1);
	TCP_ADD_STATS(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ);
	TCP_ADD_STATS(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ);
	TCP_ADD_STATS(net, TCP_MIB_MAXCONN, -1);
}

/* from STCP */
static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
{
	tp->retransmit_skb_hint = NULL;
}

#define tcp_md5_addr tcp_ao_addr

/* - key database */
struct tcp_md5sig_key {
	struct hlist_node	node;
	u8			keylen;
	u8			family; /* AF_INET or AF_INET6 */
	u8			prefixlen;
	u8			flags;
	union tcp_md5_addr	addr;
	int			l3index; /* set if key added with L3 scope */
	u8			key[TCP_MD5SIG_MAXKEYLEN];
	struct rcu_head		rcu;
};

/* - sock block */
struct tcp_md5sig_info {
	struct hlist_head	head;
	struct rcu_head		rcu;
};

/* - pseudo header */
struct tcp4_pseudohdr {
	__be32		saddr;
	__be32		daddr;
	__u8		pad;
	__u8		protocol;
	__be16		len;
};

struct tcp6_pseudohdr {
	struct in6_addr	saddr;
	struct in6_addr daddr;
	__be32		len;
	__be32		protocol;	/* including padding */
};

void tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
			 const struct sock *sk, const struct sk_buff *skb);
int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
		   int family, u8 prefixlen, int l3index, u8 flags,
		   const u8 *newkey, u8 newkeylen);
int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr,
		     int family, u8 prefixlen, int l3index,
		     struct tcp_md5sig_key *key);

int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr,
		   int family, u8 prefixlen, int l3index, u8 flags);
void tcp_clear_md5_list(struct sock *sk);
struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
					 const struct sock *addr_sk);

#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
					   const union tcp_md5_addr *addr,
					   int family, bool any_l3index);
static inline struct tcp_md5sig_key *
tcp_md5_do_lookup(const struct sock *sk, int l3index,
		  const union tcp_md5_addr *addr, int family)
{
	if (!static_branch_unlikely(&tcp_md5_needed.key))
		return NULL;
	return __tcp_md5_do_lookup(sk, l3index, addr, family, false);
}

static inline struct tcp_md5sig_key *
tcp_md5_do_lookup_any_l3index(const struct sock *sk,
			      const union tcp_md5_addr *addr, int family)
{
	if (!static_branch_unlikely(&tcp_md5_needed.key))
		return NULL;
	return __tcp_md5_do_lookup(sk, 0, addr, family, true);
}

#define tcp_twsk_md5_key(twsk)	((twsk)->tw_md5_key)
void tcp_md5_destruct_sock(struct sock *sk);
#else
static inline struct tcp_md5sig_key *
tcp_md5_do_lookup(const struct sock *sk, int l3index,
		  const union tcp_md5_addr *addr, int family)
{
	return NULL;
}

static inline struct tcp_md5sig_key *
tcp_md5_do_lookup_any_l3index(const struct sock *sk,
			      const union tcp_md5_addr *addr, int family)
{
	return NULL;
}

#define tcp_twsk_md5_key(twsk)	NULL
static inline void tcp_md5_destruct_sock(struct sock *sk)
{
}
#endif

struct md5_ctx;
void tcp_md5_hash_skb_data(struct md5_ctx *ctx, const struct sk_buff *skb,
			   unsigned int header_len);
void tcp_md5_hash_key(struct md5_ctx *ctx, const struct tcp_md5sig_key *key);

/* From tcp_fastopen.c */
void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
			    struct tcp_fastopen_cookie *cookie);
void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
			    struct tcp_fastopen_cookie *cookie, bool syn_lost,
			    u16 try_exp);
struct tcp_fastopen_request {
	/* Fast Open cookie. Size 0 means a cookie request */
	struct tcp_fastopen_cookie	cookie;
	struct msghdr			*data;  /* data in MSG_FASTOPEN */
	size_t				size;
	int				copied;	/* queued in tcp_connect() */
	struct ubuf_info		*uarg;
};
void tcp_free_fastopen_req(struct tcp_sock *tp);
void tcp_fastopen_destroy_cipher(struct sock *sk);
void tcp_fastopen_ctx_destroy(struct net *net);
int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
			      void *primary_key, void *backup_key);
int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk,
			    u64 *key);
void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
			      struct request_sock *req,
			      struct tcp_fastopen_cookie *foc,
			      const struct dst_entry *dst);
void tcp_fastopen_init_key_once(struct net *net);
bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
			     struct tcp_fastopen_cookie *cookie);
bool tcp_fastopen_defer_connect(struct sock *sk, int *err);
#define TCP_FASTOPEN_KEY_LENGTH sizeof(siphash_key_t)
#define TCP_FASTOPEN_KEY_MAX 2
#define TCP_FASTOPEN_KEY_BUF_LENGTH \
	(TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX)

/* Fastopen key context */
struct tcp_fastopen_context {
	siphash_key_t	key[TCP_FASTOPEN_KEY_MAX];
	int		num;
	struct rcu_head	rcu;
};

void tcp_fastopen_active_disable(struct sock *sk);
bool tcp_fastopen_active_should_disable(struct sock *sk);
void tcp_fastopen_active_disable_ofo_check(struct sock *sk);
void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired);

/* Caller needs to wrap with rcu_read_(un)lock() */
static inline
struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk)
{
	struct tcp_fastopen_context *ctx;

	ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx);
	if (!ctx)
		ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx);
	return ctx;
}

static inline
bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc,
			       const struct tcp_fastopen_cookie *orig)
{
	if (orig->len == TCP_FASTOPEN_COOKIE_SIZE &&
	    orig->len == foc->len &&
	    !memcmp(orig->val, foc->val, foc->len))
		return true;
	return false;
}

static inline
int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx)
{
	return ctx->num;
}

/* Latencies incurred by various limits for a sender. They are
 * chronograph-like stats that are mutually exclusive.
 */
enum tcp_chrono {
	TCP_CHRONO_UNSPEC,
	TCP_CHRONO_BUSY, /* Actively sending data (non-empty write queue) */
	TCP_CHRONO_RWND_LIMITED, /* Stalled by insufficient receive window */
	TCP_CHRONO_SNDBUF_LIMITED, /* Stalled by insufficient send buffer */
	__TCP_CHRONO_MAX,
};

static inline void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new)
{
	const u32 now = tcp_jiffies32;
	enum tcp_chrono old = tp->chrono_type;

	/* Following WRITE_ONCE()s pair with READ_ONCE()s in
	 * tcp_get_info_chrono_stats().
	 */
	if (old > TCP_CHRONO_UNSPEC)
		WRITE_ONCE(tp->chrono_stat[old - 1],
			   tp->chrono_stat[old - 1] + now - tp->chrono_start);
	WRITE_ONCE(tp->chrono_start, now);
	WRITE_ONCE(tp->chrono_type, new);
}

static inline void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* If there are multiple conditions worthy of tracking in a
	 * chronograph then the highest priority enum takes precedence
	 * over the other conditions. So that if something "more interesting"
	 * starts happening, stop the previous chrono and start a new one.
	 */
	if (type > tp->chrono_type)
		tcp_chrono_set(tp, type);
}

void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type);

/* This helper is needed, because skb->tcp_tsorted_anchor uses
 * the same memory storage than skb->destructor/_skb_refdst
 */
static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb)
{
	skb->destructor = NULL;
	skb->_skb_refdst = 0UL;
}

#define tcp_skb_tsorted_save(skb) {		\
	unsigned long _save = skb->_skb_refdst;	\
	skb->_skb_refdst = 0UL;

#define tcp_skb_tsorted_restore(skb)		\
	skb->_skb_refdst = _save;		\
}

void tcp_write_queue_purge(struct sock *sk);

static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk)
{
	return skb_rb_first(&sk->tcp_rtx_queue);
}

static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
{
	return skb_rb_last(&sk->tcp_rtx_queue);
}

static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk)
{
	return skb_peek_tail(&sk->sk_write_queue);
}

#define tcp_for_write_queue_from_safe(skb, tmp, sk)			\
	skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp)

static inline struct sk_buff *tcp_send_head(const struct sock *sk)
{
	return skb_peek(&sk->sk_write_queue);
}

static inline bool tcp_skb_is_last(const struct sock *sk,
				   const struct sk_buff *skb)
{
	return skb_queue_is_last(&sk->sk_write_queue, skb);
}

/**
 * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue
 * @sk: socket
 *
 * Since the write queue can have a temporary empty skb in it,
 * we must not use "return skb_queue_empty(&sk->sk_write_queue)"
 */
static inline bool tcp_write_queue_empty(const struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	return tp->write_seq == tp->snd_nxt;
}

static inline bool tcp_rtx_queue_empty(const struct sock *sk)
{
	return RB_EMPTY_ROOT(&sk->tcp_rtx_queue);
}

static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk)
{
	return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk);
}

static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
{
	__skb_queue_tail(&sk->sk_write_queue, skb);

	/* Queue it, remembering where we must start sending. */
	if (sk->sk_write_queue.next == skb)
		tcp_chrono_start(sk, TCP_CHRONO_BUSY);
}

/* Insert new before skb on the write queue of sk.  */
static inline void tcp_insert_write_queue_before(struct sk_buff *new,
						  struct sk_buff *skb,
						  struct sock *sk)
{
	__skb_queue_before(&sk->sk_write_queue, skb, new);
}

static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk)
{
	tcp_skb_tsorted_anchor_cleanup(skb);
	__skb_unlink(skb, &sk->sk_write_queue);
}

void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb);

static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk)
{
	tcp_skb_tsorted_anchor_cleanup(skb);
	rb_erase(&skb->rbnode, &sk->tcp_rtx_queue);
}

static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk)
{
	list_del(&skb->tcp_tsorted_anchor);
	tcp_rtx_queue_unlink(skb, sk);
	tcp_wmem_free_skb(sk, skb);
}

static inline void tcp_write_collapse_fence(struct sock *sk)
{
	struct sk_buff *skb = tcp_write_queue_tail(sk) ?: tcp_rtx_queue_tail(sk);

	if (skb)
		TCP_SKB_CB(skb)->eor = 1;
}

static inline void tcp_push_pending_frames(struct sock *sk)
{
	if (tcp_send_head(sk)) {
		struct tcp_sock *tp = tcp_sk(sk);

		__tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle);
	}
}

/* Start sequence of the skb just after the highest skb with SACKed
 * bit, valid only if sacked_out > 0 or when the caller has ensured
 * validity by itself.
 */
static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp)
{
	if (!tp->sacked_out)
		return tp->snd_una;

	if (tp->highest_sack == NULL)
		return tp->snd_nxt;

	return TCP_SKB_CB(tp->highest_sack)->seq;
}

static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb)
{
	tcp_sk(sk)->highest_sack = skb_rb_next(skb);
}

static inline struct sk_buff *tcp_highest_sack(struct sock *sk)
{
	return tcp_sk(sk)->highest_sack;
}

static inline void tcp_highest_sack_reset(struct sock *sk)
{
	tcp_sk(sk)->highest_sack = tcp_rtx_queue_head(sk);
}

/* Called when old skb is about to be deleted and replaced by new skb */
static inline void tcp_highest_sack_replace(struct sock *sk,
					    struct sk_buff *old,
					    struct sk_buff *new)
{
	if (old == tcp_highest_sack(sk))
		tcp_sk(sk)->highest_sack = new;
}

/* This helper checks if socket has IP_TRANSPARENT set */
static inline bool inet_sk_transparent(const struct sock *sk)
{
	switch (sk->sk_state) {
	case TCP_TIME_WAIT:
		return inet_twsk(sk)->tw_transparent;
	case TCP_NEW_SYN_RECV:
		return inet_rsk(inet_reqsk(sk))->no_srccheck;
	}
	return inet_test_bit(TRANSPARENT, sk);
}

/* Determines whether this is a thin stream (which may suffer from
 * increased latency). Used to trigger latency-reducing mechanisms.
 */
static inline bool tcp_stream_is_thin(struct tcp_sock *tp)
{
	return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp);
}

/* /proc */
enum tcp_seq_states {
	TCP_SEQ_STATE_LISTENING,
	TCP_SEQ_STATE_ESTABLISHED,
};

void *tcp_seq_start(struct seq_file *seq, loff_t *pos);
void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos);
void tcp_seq_stop(struct seq_file *seq, void *v);

struct tcp_seq_afinfo {
	sa_family_t			family;
};

struct tcp_iter_state {
	struct seq_net_private	p;
	enum tcp_seq_states	state;
	struct sock		*syn_wait_sk;
	int			bucket, offset, sbucket, num;
	loff_t			last_pos;
};

extern struct request_sock_ops tcp_request_sock_ops;
extern struct request_sock_ops tcp6_request_sock_ops;

void tcp_v4_destroy_sock(struct sock *sk);

struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
				netdev_features_t features);
struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th);
struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
				struct tcphdr *th);
INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff));
INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb));
#ifdef CONFIG_INET
void tcp_gro_complete(struct sk_buff *skb);
#else
static inline void tcp_gro_complete(struct sk_buff *skb) { }
#endif

static inline void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr,
				       __be32 daddr)
{
	struct tcphdr *th = tcp_hdr(skb);

	th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0);
	skb->csum_start = skb_transport_header(skb) - skb->head;
	skb->csum_offset = offsetof(struct tcphdr, check);
}

static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
{
	struct net *net = sock_net((struct sock *)tp);
	u32 val;

	val = READ_ONCE(tp->notsent_lowat);

	return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
}

bool tcp_stream_memory_free(const struct sock *sk, int wake);

#ifdef CONFIG_PROC_FS
int tcp4_proc_init(void);
void tcp4_proc_exit(void);
#endif

int tcp_rtx_synack(const struct sock *sk, struct request_sock *req);
int tcp_conn_request(struct request_sock_ops *rsk_ops,
		     const struct tcp_request_sock_ops *af_ops,
		     struct sock *sk, struct sk_buff *skb);

/* TCP af-specific functions */
struct tcp_sock_af_ops {
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key	*(*md5_lookup) (const struct sock *sk,
						const struct sock *addr_sk);
	void		(*calc_md5_hash)(char *location,
					 const struct tcp_md5sig_key *md5,
					 const struct sock *sk,
					 const struct sk_buff *skb);
	int		(*md5_parse)(struct sock *sk,
				     int optname,
				     sockptr_t optval,
				     int optlen);
#endif
#ifdef CONFIG_TCP_AO
	int (*ao_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen);
	struct tcp_ao_key *(*ao_lookup)(const struct sock *sk,
					struct sock *addr_sk,
					int sndid, int rcvid);
	void (*ao_calc_key_sk)(struct tcp_ao_key *mkt, u8 *key,
			       const struct sock *sk,
			       __be32 sisn, __be32 disn, bool send);
	int (*calc_ao_hash)(char *location, struct tcp_ao_key *ao,
			    const struct sock *sk, const struct sk_buff *skb,
			    const u8 *tkey, int hash_offset, u32 sne);
#endif
};

struct tcp_request_sock_ops {
	u16 mss_clamp;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk,
						 const struct sock *addr_sk);
	void		(*calc_md5_hash) (char *location,
					  const struct tcp_md5sig_key *md5,
					  const struct sock *sk,
					  const struct sk_buff *skb);
#endif
#ifdef CONFIG_TCP_AO
	struct tcp_ao_key *(*ao_lookup)(const struct sock *sk,
					struct request_sock *req,
					int sndid, int rcvid);
	void (*ao_calc_key)(struct tcp_ao_key *mkt, u8 *key, struct request_sock *sk);
	int (*ao_synack_hash)(char *ao_hash, struct tcp_ao_key *mkt,
			      struct request_sock *req, const struct sk_buff *skb,
			      int hash_offset, u32 sne);
#endif
#ifdef CONFIG_SYN_COOKIES
	__u32 (*cookie_init_seq)(const struct sk_buff *skb,
				 __u16 *mss);
#endif
	struct dst_entry *(*route_req)(const struct sock *sk,
				       struct sk_buff *skb,
				       struct flowi *fl,
				       struct request_sock *req,
				       u32 tw_isn);
	union tcp_seq_and_ts_off (*init_seq_and_ts_off)(
					const struct net *net,
					const struct sk_buff *skb);
	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
			   struct flowi *fl, struct request_sock *req,
			   struct tcp_fastopen_cookie *foc,
			   enum tcp_synack_type synack_type,
			   struct sk_buff *syn_skb);
};

extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops;
#if IS_ENABLED(CONFIG_IPV6)
extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops;
#endif

#ifdef CONFIG_SYN_COOKIES
static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
					 struct sk_buff *skb, __u16 *mss)
{
	return ops->cookie_init_seq(skb, mss);
}
#else
static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
					 struct sk_buff *skb, __u16 *mss)
{
	return 0;
}
#endif

#ifdef CONFIG_SYN_COOKIES
static inline void cookie_record_sent(const struct sock *sk)
{
	tcp_synq_overflow(sk);
	__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT);
}
#else
static inline void cookie_record_sent(const struct sock *sk)
{
}
#endif

struct tcp_key {
	union {
		struct {
			struct tcp_ao_key *ao_key;
			char *traffic_key;
			u32 sne;
			u8 rcv_next;
		};
		struct tcp_md5sig_key *md5_key;
	};
	enum {
		TCP_KEY_NONE = 0,
		TCP_KEY_MD5,
		TCP_KEY_AO,
	} type;
};

static inline void tcp_get_current_key(const struct sock *sk,
				       struct tcp_key *out)
{
#if defined(CONFIG_TCP_AO) || defined(CONFIG_TCP_MD5SIG)
	const struct tcp_sock *tp = tcp_sk(sk);
#endif

#ifdef CONFIG_TCP_AO
	if (static_branch_unlikely(&tcp_ao_needed.key)) {
		struct tcp_ao_info *ao;

		ao = rcu_dereference_protected(tp->ao_info,
					       lockdep_sock_is_held(sk));
		if (ao) {
			out->ao_key = READ_ONCE(ao->current_key);
			out->type = TCP_KEY_AO;
			return;
		}
	}
#endif
#ifdef CONFIG_TCP_MD5SIG
	if (static_branch_unlikely(&tcp_md5_needed.key) &&
	    rcu_access_pointer(tp->md5sig_info)) {
		out->md5_key = tp->af_specific->md5_lookup(sk, sk);
		if (out->md5_key) {
			out->type = TCP_KEY_MD5;
			return;
		}
	}
#endif
	out->type = TCP_KEY_NONE;
}

static inline bool tcp_key_is_md5(const struct tcp_key *key)
{
	if (static_branch_tcp_md5())
		return key->type == TCP_KEY_MD5;
	return false;
}

static inline bool tcp_key_is_ao(const struct tcp_key *key)
{
	if (static_branch_tcp_ao())
		return key->type == TCP_KEY_AO;
	return false;
}

int tcpv4_offload_init(void);

void tcp_v4_init(void);
void tcp_init(void);

/* tcp_recovery.c */
void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb);
void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced);
extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb,
				u32 reo_wnd);
extern bool tcp_rack_mark_lost(struct sock *sk);
extern void tcp_rack_reo_timeout(struct sock *sk);

/* tcp_plb.c */

/*
 * Scaling factor for fractions in PLB. For example, tcp_plb_update_state
 * expects cong_ratio which represents fraction of traffic that experienced
 * congestion over a single RTT. In order to avoid floating point operations,
 * this fraction should be mapped to (1 << TCP_PLB_SCALE) and passed in.
 */
#define TCP_PLB_SCALE 8

/* State for PLB (Protective Load Balancing) for a single TCP connection. */
struct tcp_plb_state {
	u8	consec_cong_rounds:5, /* consecutive congested rounds */
		unused:3;
	u32	pause_until; /* jiffies32 when PLB can resume rerouting */
};

static inline void tcp_plb_init(const struct sock *sk,
				struct tcp_plb_state *plb)
{
	plb->consec_cong_rounds = 0;
	plb->pause_until = 0;
}
void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb,
			  const int cong_ratio);
void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb);
void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb);

static inline void tcp_warn_once(const struct sock *sk, bool cond, const char *str)
{
	WARN_ONCE(cond,
		  "%scwn:%u out:%u sacked:%u lost:%u retrans:%u tlp_high_seq:%u sk_state:%u ca_state:%u advmss:%u mss_cache:%u pmtu:%u\n",
		  str,
		  tcp_snd_cwnd(tcp_sk(sk)),
		  tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out,
		  tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out,
		  tcp_sk(sk)->tlp_high_seq, sk->sk_state,
		  inet_csk(sk)->icsk_ca_state,
		  tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache,
		  inet_csk(sk)->icsk_pmtu_cookie);
}

/* At how many usecs into the future should the RTO fire? */
static inline s64 tcp_rto_delta_us(const struct sock *sk)
{
	const struct sk_buff *skb = tcp_rtx_queue_head(sk);
	u32 rto = inet_csk(sk)->icsk_rto;

	if (likely(skb)) {
		u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto);

		return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp;
	} else {
		tcp_warn_once(sk, 1, "rtx queue empty: ");
		return jiffies_to_usecs(rto);
	}

}

/*
 * Save and compile IPv4 options, return a pointer to it
 */
static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net,
							 struct sk_buff *skb)
{
	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
	struct ip_options_rcu *dopt = NULL;

	if (opt->optlen) {
		int opt_size = sizeof(*dopt) + opt->optlen;

		dopt = kmalloc(opt_size, GFP_ATOMIC);
		if (dopt && __ip_options_echo(net, &dopt->opt, skb, opt)) {
			kfree(dopt);
			dopt = NULL;
		}
	}
	return dopt;
}

/* locally generated TCP pure ACKs have skb->truesize == 2
 * (check tcp_send_ack() in net/ipv4/tcp_output.c )
 * This is much faster than dissecting the packet to find out.
 * (Think of GRE encapsulations, IPv4, IPv6, ...)
 */
static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb)
{
	return skb->truesize == 2;
}

static inline void skb_set_tcp_pure_ack(struct sk_buff *skb)
{
	skb->truesize = 2;
}

static inline int tcp_inq(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int answ;

	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		answ = 0;
	} else if (sock_flag(sk, SOCK_URGINLINE) ||
		   !tp->urg_data ||
		   before(tp->urg_seq, tp->copied_seq) ||
		   !before(tp->urg_seq, tp->rcv_nxt)) {

		answ = tp->rcv_nxt - tp->copied_seq;

		/* Subtract 1, if FIN was received */
		if (answ && sock_flag(sk, SOCK_DONE))
			answ--;
	} else {
		answ = tp->urg_seq - tp->copied_seq;
	}

	return answ;
}

int tcp_peek_len(struct socket *sock);

static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb)
{
	u16 segs_in;

	segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs);

	/* We update these fields while other threads might
	 * read them from tcp_get_info()
	 */
	WRITE_ONCE(tp->segs_in, tp->segs_in + segs_in);
	if (skb->len > tcp_hdrlen(skb))
		WRITE_ONCE(tp->data_segs_in, tp->data_segs_in + segs_in);
}

/*
 * TCP listen path runs lockless.
 * We forced "struct sock" to be const qualified to make sure
 * we don't modify one of its field by mistake.
 * Here, we increment sk_drops which is an atomic_t, so we can safely
 * make sock writable again.
 */
static inline void tcp_listendrop(const struct sock *sk)
{
	sk_drops_inc((struct sock *)sk);
	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
}

enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer);

/*
 * Interface for adding Upper Level Protocols over TCP
 */

#define TCP_ULP_NAME_MAX	16
#define TCP_ULP_MAX		128
#define TCP_ULP_BUF_MAX		(TCP_ULP_NAME_MAX*TCP_ULP_MAX)

struct tcp_ulp_ops {
	struct list_head	list;

	/* initialize ulp */
	int (*init)(struct sock *sk);
	/* update ulp */
	void (*update)(struct sock *sk, struct proto *p,
		       void (*write_space)(struct sock *sk));
	/* cleanup ulp */
	void (*release)(struct sock *sk);
	/* diagnostic */
	int (*get_info)(struct sock *sk, struct sk_buff *skb, bool net_admin);
	size_t (*get_info_size)(const struct sock *sk, bool net_admin);
	/* clone ulp */
	void (*clone)(const struct request_sock *req, struct sock *newsk,
		      const gfp_t priority);

	char		name[TCP_ULP_NAME_MAX];
	struct module	*owner;
};
int tcp_register_ulp(struct tcp_ulp_ops *type);
void tcp_unregister_ulp(struct tcp_ulp_ops *type);
int tcp_set_ulp(struct sock *sk, const char *name);
void tcp_get_available_ulp(char *buf, size_t len);
void tcp_cleanup_ulp(struct sock *sk);
void tcp_update_ulp(struct sock *sk, struct proto *p,
		    void (*write_space)(struct sock *sk));

#define MODULE_ALIAS_TCP_ULP(name)				\
	MODULE_INFO(alias, name);		\
	MODULE_INFO(alias, "tcp-ulp-" name)

#ifdef CONFIG_NET_SOCK_MSG
struct sk_msg;
struct sk_psock;

#ifdef CONFIG_BPF_SYSCALL
int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
#ifdef CONFIG_BPF_STREAM_PARSER
struct strparser;
int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc,
			   sk_read_actor_t recv_actor);
#endif /* CONFIG_BPF_STREAM_PARSER */
#endif /* CONFIG_BPF_SYSCALL */

#ifdef CONFIG_INET
void tcp_eat_skb(struct sock *sk, struct sk_buff *skb);
#else
static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb)
{
}
#endif

int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress,
			  struct sk_msg *msg, u32 bytes, int flags);
#endif /* CONFIG_NET_SOCK_MSG */

#if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG)
static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
{
}
#endif

#ifdef CONFIG_CGROUP_BPF
static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
				      struct sk_buff *skb,
				      unsigned int end_offset)
{
	skops->skb = skb;
	skops->skb_data_end = skb->data + end_offset;
}
#else
static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
				      struct sk_buff *skb,
				      unsigned int end_offset)
{
}
#endif

/* Call BPF_SOCK_OPS program that returns an int. If the return value
 * is < 0, then the BPF op failed (for example if the loaded BPF
 * program does not support the chosen operation or there is no BPF
 * program loaded).
 */
#ifdef CONFIG_BPF
static inline int __tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
{
	struct bpf_sock_ops_kern sock_ops;
	int ret;

	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
	if (sk_fullsock(sk)) {
		sock_ops.is_fullsock = 1;
		sock_ops.is_locked_tcp_sock = 1;
		sock_owned_by_me(sk);
	}

	sock_ops.sk = sk;
	sock_ops.op = op;
	if (nargs > 0)
		memcpy(sock_ops.args, args, nargs * sizeof(*args));

	ret = __BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
	if (ret == 0)
		ret = sock_ops.reply;
	else
		ret = -1;
	return ret;
}

#define tcp_call_bpf(sk, op)						\
({									\
	int __ret = 0;							\
	if (cgroup_bpf_enabled(CGROUP_SOCK_OPS)) {			\
		__ret = __tcp_call_bpf(sk, op, 0, NULL);		\
	}								\
	__ret;								\
})

#define tcp_call_bpf_flag(sk, op, ...)					\
do {									\
	if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) &&			\
	    BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), op ## _FLAG)) {		\
		u32 __args[] = { __VA_ARGS__ };				\
		__tcp_call_bpf(sk, op, ARRAY_SIZE(__args), __args);	\
	}								\
} while (0)

static inline void tcp_clear_sock_ops_cb_flags(struct sock *sk)
{
	tcp_sk(sk)->bpf_sock_ops_cb_flags = 0;
	WRITE_ONCE(tcp_sk(sk)->bpf_tcp_ops_flags, 0);
}

#else
static inline int tcp_call_bpf(struct sock *sk, int op)
{
	return -EPERM;
}

#define tcp_call_bpf_flag(sk, op, ...) do { } while (0)

static inline void tcp_clear_sock_ops_cb_flags(struct sock *sk)
{
}

#endif

#if defined(CONFIG_BPF_JIT) && defined(CONFIG_CGROUP_BPF)

struct bpf_tcp_ops {
	/* Should return the initial SYN (active open) or SYN-ACK (passive open)
	 * retransmission timeout. Return the timeout in jiffies, or <= 0 for
	 * the kernel default.
	 *
	 * @req: request_sock on the passive (synack) path; NULL otherwise.
	 */
	int (*timeout_init)(struct sock *sk, struct request_sock *req);

	/* Should return the initial advertised receive window, in packets,
	 * or < 0 for the kernel default. @req as in timeout_init().
	 */
	int (*rwnd_init)(struct sock *sk, struct request_sock *req);

	/* Called when an active connection becomes established.
	 * @skb is the SYNACK that completed the 3WHS, or NULL for a
	 * TCP_REPAIR socket (tcp_finish_connect() with no skb).
	 */
	void (*active_established)(struct sock *sk, struct sk_buff *skb__nullable);

	/* Called when a passive connection becomes established.
	 * @skb is the ACK that completed the 3WHS.
	 */
	void (*passive_established)(struct sock *sk, struct sk_buff *skb);

	/* Called when the retransmission timer fires. */
	void (*rto)(struct sock *sk);

	/* Called on every RTT sample if BPF_TCP_OPS_FLAG_RTT is enabled.
	 * @mrtt: the measured RTT, in microseconds.
	 * @srtt: the updated smoothed RTT.
	 */
	void (*rtt)(struct sock *sk, long mrtt, u32 srtt);

	/* Called when the connection changes TCP state.
	 * @state: the new state (one of the TCP_* states).
	 */
	void (*set_state)(struct sock *sk, int state);

	/* Called when an skb is retransmitted.
	 * @skb: the retransmitted skb.
	 * @err: tcp_transmit_skb() return value (0 on success).
	 */
	void (*retrans)(struct sock *sk, struct sk_buff *skb, int err);

	/* Called right before an active connection is initialized. */
	void (*connect)(struct sock *sk);

	/* Called on listen(2), right after the socket enters TCP_LISTEN. */
	void (*listen)(struct sock *sk);

	/*
	 * Parse the TCP header options of an incoming skb received on an
	 * established connection. Use bpf_dynptr_from_skb()/bpf_skb_load_bytes()
	 * to access the options.
	 *
	 * Called if BPF_TCP_OPS_FLAG_PARSE_HDR_OPT_ALL is enabled, or if
	 * BPF_TCP_OPS_FLAG_PARSE_HDR_OPT_UNKNOWN is enabled and an unknown
	 * option is received.
	 */
	void (*parse_hdr)(struct sock *sk, struct sk_buff *skb);

	/*
	 * Reserve space in the outgoing TCP header for options to be written
	 * later by write_hdr_opt(). Call bpf_reserve_hdr_opt() to reserve bytes.
	 *
	 * Called if BPF_TCP_OPS_FLAG_WRITE_HDR_OPT is enabled.
	 *
	 * @skb: outgoing packet. NULL when called from tcp_current_mss()
	 *       (MSS sizing).
	 * @req: request_sock on the synack path; NULL otherwise.
	 * @syn_skb: incoming SYN on the synack path; NULL otherwise.
	 * @synack_type: TCP_SYNACK_COOKIE indicates a stateless syncookie.
	 * @remaining: pointer to the size of space still available; cast it
	 *             using bpf_rdonly_cast() before dereferencing.
	 */
	void (*hdr_opt_len)(struct sock *sk, struct sk_buff *skb,
			    struct request_sock *req, struct sk_buff *syn_skb,
			    enum tcp_synack_type synack_type,
			    unsigned int *remaining);

	/*
	 * Write header options into the space reserved earlier by hdr_opt_len().
	 * Use bpf_store_hdr_opt() to write; it appends within the reserved window
	 * shared with legacy SOCKOPS.
	 *
	 * Called if BPF_TCP_OPS_FLAG_WRITE_HDR_OPT is enabled.
	 *
	 * @skb: outgoing packet.
	 * @req: request_sock on the synack path; NULL otherwise.
	 * @syn_skb: incoming SYN on the synack path; NULL otherwise.
	 * @synack_type: TCP_SYNACK_COOKIE indicates a stateless syncookie.
	 * @opt_off: offset in the outgoing @skb's TCP header where the
	 *	     bpf_tcp_ops portion of the reserved window begins, i.e. after
	 *	     the kernel and legacy options.
	 */
	void (*write_hdr_opt)(struct sock *sk, struct sk_buff *skb,
			      struct request_sock *req, struct sk_buff *syn_skb,
			      enum tcp_synack_type synack_type,
			      u32 opt_off);

	/*
	 * Called when an incoming skb is enqueued to sk->sk_receive_queue
	 * if BPF_TCP_OPS_FLAG_RCVQ is enabled.
	 */
	void (*enqueue_rcvq)(struct sock *sk, struct sk_buff *skb);

	/*
	 * Called after data is dequeued from sk->sk_receive_queue
	 * if BPF_TCP_OPS_FLAG_RCVQ is enabled.
	 */
	void (*dequeue_rcvq)(struct sock *sk);
};

#define __bpf_tcp_ops_call(op, sk, ...)					\
do {									\
	const struct bpf_prog_array_item *item;				\
	const struct bpf_tcp_ops *tcp_ops;				\
	struct cgroup *cgrp;						\
									\
	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);			\
	rcu_read_lock_dont_migrate();					\
	bpf_cgroup_struct_ops_foreach(tcp_ops, item, cgrp,		\
				      CGROUP_TCP_SOCK_OPS) {		\
		if (tcp_ops->op)					\
			tcp_ops->op(sk, ##__VA_ARGS__);			\
	}								\
	rcu_read_unlock_migrate();					\
} while (0)

#define bpf_tcp_ops_call(op, sk, ...)					\
do {									\
	if (cgroup_bpf_enabled(CGROUP_TCP_SOCK_OPS))			\
		__bpf_tcp_ops_call(op, sk, ##__VA_ARGS__);		\
} while (0)

#define bpf_tcp_ops_call_flag(op, flag, sk, ...)			\
do {									\
	if (cgroup_bpf_enabled(CGROUP_TCP_SOCK_OPS) &&			\
	    BPF_TCP_OPS_TEST_FLAG(tcp_sk(sk), flag))			\
		__bpf_tcp_ops_call(op, sk, ##__VA_ARGS__);		\
} while (0)

#define bpf_tcp_ops_call_int(op, init_retval, sk, ...)			\
({									\
	int __retval = (init_retval);					\
	if (cgroup_bpf_enabled(CGROUP_TCP_SOCK_OPS)) {			\
		const struct bpf_prog_array_item *item;			\
		const struct bpf_tcp_ops *tcp_ops;			\
		struct bpf_tramp_run_ctx run_ctx;			\
		struct bpf_run_ctx *old_run_ctx;			\
		struct sock *__sk = sk_to_full_sk(sk);                  \
		struct request_sock *req = NULL;			\
		struct cgroup *cgrp;					\
									\
		if (__sk) {						\
			run_ctx.retval = (init_retval);			\
			cgrp = sock_cgroup_ptr(&__sk->sk_cgrp_data);	\
			if (!sk_fullsock(sk))				\
				req = (struct request_sock *)sk;	\
			rcu_read_lock_dont_migrate();			\
			old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);\
			bpf_cgroup_struct_ops_foreach(tcp_ops, item, cgrp, \
						      CGROUP_TCP_SOCK_OPS) { \
				if (tcp_ops->op)			\
					run_ctx.retval = tcp_ops->op(__sk, req, ##__VA_ARGS__); \
			}						\
			bpf_reset_run_ctx(old_run_ctx);			\
			rcu_read_unlock_migrate();			\
			__retval = run_ctx.retval;			\
		}							\
	}								\
	__retval;							\
})

#else
#define __bpf_tcp_ops_call(op, sk, ...)			do { } while (0)
#define bpf_tcp_ops_call(op, sk, ...)			do { } while (0)
#define bpf_tcp_ops_call_flag(op, flag, sk, ...)	do { } while (0)
#define bpf_tcp_ops_call_int(op, init_retval, sk, ...)	(init_retval)
#endif

static inline u32 tcp_timeout_init(struct sock *sk)
{
	int timeout;

	timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT);
	timeout = bpf_tcp_ops_call_int(timeout_init, timeout, sk);
	if (timeout <= 0)
		timeout = TCP_TIMEOUT_INIT;
	return min_t(int, timeout, TCP_RTO_MAX);
}

static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
{
	int rwnd;

	rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT);
	rwnd = bpf_tcp_ops_call_int(rwnd_init, rwnd, sk);
	if (rwnd < 0)
		rwnd = 0;
	return rwnd;
}

static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
{
	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);
}

static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt)
{
	tcp_call_bpf_flag(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt);
	bpf_tcp_ops_call_flag(rtt, RTT, sk, mrtt, srtt);
}

#if IS_ENABLED(CONFIG_SMC)
extern struct static_key_false tcp_have_smc;
#endif

#if IS_ENABLED(CONFIG_TLS_DEVICE)
void clean_acked_data_enable(struct tcp_sock *tp,
			     void (*cad)(struct sock *sk, u32 ack_seq));
void clean_acked_data_disable(struct tcp_sock *tp);
void clean_acked_data_flush(void);
#endif

DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled);
static inline void tcp_add_tx_delay(struct sk_buff *skb,
				    const struct tcp_sock *tp)
{
	if (static_branch_unlikely(&tcp_tx_delay_enabled))
		skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC;
}

/* Compute Earliest Departure Time for some control packets
 * like ACK or RST for TIME_WAIT or non ESTABLISHED sockets.
 */
static inline u64 tcp_transmit_time(const struct sock *sk)
{
	if (static_branch_unlikely(&tcp_tx_delay_enabled)) {
		u32 delay = (sk->sk_state == TCP_TIME_WAIT) ?
			tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay;

		return tcp_clock_ns() + (u64)delay * NSEC_PER_USEC;
	}
	return 0;
}

static inline int tcp_parse_auth_options(const struct tcphdr *th,
		const u8 **md5_hash, const struct tcp_ao_hdr **aoh)
{
	const u8 *md5_tmp, *ao_tmp;
	int ret;

	ret = tcp_do_parse_auth_options(th, &md5_tmp, &ao_tmp);
	if (ret)
		return ret;

	if (md5_hash)
		*md5_hash = md5_tmp;

	if (aoh) {
		if (!ao_tmp)
			*aoh = NULL;
		else
			*aoh = (struct tcp_ao_hdr *)(ao_tmp - 2);
	}

	return 0;
}

static inline bool tcp_ao_required(struct sock *sk, const void *saddr,
				   int family, int l3index, bool stat_inc)
{
#ifdef CONFIG_TCP_AO
	struct tcp_ao_info *ao_info;
	struct tcp_ao_key *ao_key;

	if (!static_branch_unlikely(&tcp_ao_needed.key))
		return false;

	ao_info = rcu_dereference_check(tcp_sk(sk)->ao_info,
					lockdep_sock_is_held(sk));
	if (!ao_info)
		return false;

	ao_key = tcp_ao_do_lookup(sk, l3index, saddr, family, -1, -1);
	if (ao_info->ao_required || ao_key) {
		if (stat_inc) {
			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOREQUIRED);
			atomic64_inc(&ao_info->counters.ao_required);
		}
		return true;
	}
#endif
	return false;
}

enum skb_drop_reason tcp_inbound_hash(struct sock *sk,
		const struct request_sock *req, const struct sk_buff *skb,
		const void *saddr, const void *daddr,
		int family, int dif, int sdif);

static inline int tcp_recv_should_stop(struct sock *sk)
{
	return READ_ONCE(sk->sk_err) ||
	       sk->sk_state == TCP_CLOSE ||
	       (sk->sk_shutdown & RCV_SHUTDOWN) ||
	       signal_pending(current);
}

INDIRECT_CALLABLE_DECLARE(union tcp_seq_and_ts_off
			  tcp_v4_init_seq_and_ts_off(const struct net *net,
						     const struct sk_buff *skb));
INDIRECT_CALLABLE_DECLARE(union tcp_seq_and_ts_off
			  tcp_v6_init_seq_and_ts_off(const struct net *net,
						     const struct sk_buff *skb));
#endif	/* _TCP_H */