tcp.h

Linux Kernel 2.6.9 for OMAP1710

					 * binary search.
					 */
#define BICTCP_FUNC_OF_MIN_INCR 11	/*
					 * log(B/Smin)/log(B/(B-1))+1,
					 * Smin:min increment
					 * B:log factor
					 */
#define BICTCP_B		4	 /*
					  * In binary search,
					  * go to point (max+min)/N
					  */

/*
 *	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 */

/*
 *     TCP option lengths
 */

#define TCPOLEN_MSS            4
#define TCPOLEN_WINDOW         3
#define TCPOLEN_SACK_PERM      2
#define TCPOLEN_TIMESTAMP      10

/* 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 TCP_TIME_RETRANS	1	/* Retransmit timer */
#define TCP_TIME_DACK		2	/* Delayed ack timer */
#define TCP_TIME_PROBE0		3	/* Zero window probe timer */
#define TCP_TIME_KEEPOPEN	4	/* Keepalive timer */

/* 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 overriden for already queued data */

/* sysctl variables for tcp */
extern int sysctl_max_syn_backlog;
extern int sysctl_tcp_timestamps;
extern int sysctl_tcp_window_scaling;
extern int sysctl_tcp_sack;
extern int sysctl_tcp_fin_timeout;
extern int sysctl_tcp_tw_recycle;
extern int sysctl_tcp_keepalive_time;
extern int sysctl_tcp_keepalive_probes;
extern int sysctl_tcp_keepalive_intvl;
extern int sysctl_tcp_syn_retries;
extern int sysctl_tcp_synack_retries;
extern int sysctl_tcp_retries1;
extern int sysctl_tcp_retries2;
extern int sysctl_tcp_orphan_retries;
extern int sysctl_tcp_syncookies;
extern int sysctl_tcp_retrans_collapse;
extern int sysctl_tcp_stdurg;
extern int sysctl_tcp_rfc1337;
extern int sysctl_tcp_abort_on_overflow;
extern int sysctl_tcp_max_orphans;
extern int sysctl_tcp_max_tw_buckets;
extern int sysctl_tcp_fack;
extern int sysctl_tcp_reordering;
extern int sysctl_tcp_ecn;
extern int sysctl_tcp_dsack;
extern int sysctl_tcp_mem[3];
extern int sysctl_tcp_wmem[3];
extern int sysctl_tcp_rmem[3];
extern int sysctl_tcp_app_win;
extern int sysctl_tcp_adv_win_scale;
extern int sysctl_tcp_tw_reuse;
extern int sysctl_tcp_frto;
extern int sysctl_tcp_low_latency;
extern int sysctl_tcp_westwood;
extern int sysctl_tcp_vegas_cong_avoid;
extern int sysctl_tcp_vegas_alpha;
extern int sysctl_tcp_vegas_beta;
extern int sysctl_tcp_vegas_gamma;
extern int sysctl_tcp_nometrics_save;
extern int sysctl_tcp_bic;
extern int sysctl_tcp_bic_fast_convergence;
extern int sysctl_tcp_bic_low_window;
extern int sysctl_tcp_moderate_rcvbuf;
extern int sysctl_tcp_tso_win_divisor;

extern atomic_t tcp_memory_allocated;
extern atomic_t tcp_sockets_allocated;
extern int tcp_memory_pressure;

struct open_request;

struct or_calltable {
	int  family;
	int  (*rtx_syn_ack)	(struct sock *sk, struct open_request *req, struct dst_entry*);
	void (*send_ack)	(struct sk_buff *skb, struct open_request *req);
	void (*destructor)	(struct open_request *req);
	void (*send_reset)	(struct sk_buff *skb);
};

struct tcp_v4_open_req {
	__u32			loc_addr;
	__u32			rmt_addr;
	struct ip_options	*opt;
};

#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
struct tcp_v6_open_req {
	struct in6_addr		loc_addr;
	struct in6_addr		rmt_addr;
	struct sk_buff		*pktopts;
	int			iif;
};
#endif

/* this structure is too big */
struct open_request {
	struct open_request	*dl_next; /* Must be first member! */
	__u32			rcv_isn;
	__u32			snt_isn;
	__u16			rmt_port;
	__u16			mss;
	__u8			retrans;
	__u8			__pad;
	__u16	snd_wscale : 4, 
		rcv_wscale : 4, 
		tstamp_ok : 1,
		sack_ok : 1,
		wscale_ok : 1,
		ecn_ok : 1,
		acked : 1;
	/* The following two fields can be easily recomputed I think -AK */
	__u32			window_clamp;	/* window clamp at creation time */
	__u32			rcv_wnd;	/* rcv_wnd offered first time */
	__u32			ts_recent;
	unsigned long		expires;
	struct or_calltable	*class;
	struct sock		*sk;
	union {
		struct tcp_v4_open_req v4_req;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
		struct tcp_v6_open_req v6_req;
#endif
	} af;
};

/* SLAB cache for open requests. */
extern kmem_cache_t *tcp_openreq_cachep;

#define tcp_openreq_alloc()		kmem_cache_alloc(tcp_openreq_cachep, SLAB_ATOMIC)
#define tcp_openreq_fastfree(req)	kmem_cache_free(tcp_openreq_cachep, req)

static inline void tcp_openreq_free(struct open_request *req)
{
	req->class->destructor(req);
	tcp_openreq_fastfree(req);
}

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#define TCP_INET_FAMILY(fam) ((fam) == AF_INET)
#else
#define TCP_INET_FAMILY(fam) 1
#endif

/*
 *	Pointers to address related TCP functions
 *	(i.e. things that depend on the address family)
 */

struct tcp_func {
	int			(*queue_xmit)		(struct sk_buff *skb,
							 int ipfragok);

	void			(*send_check)		(struct sock *sk,
							 struct tcphdr *th,
							 int len,
							 struct sk_buff *skb);

	int			(*rebuild_header)	(struct sock *sk);

	int			(*conn_request)		(struct sock *sk,
							 struct sk_buff *skb);

	struct sock *		(*syn_recv_sock)	(struct sock *sk,
							 struct sk_buff *skb,
							 struct open_request *req,
							 struct dst_entry *dst);
    
	int			(*remember_stamp)	(struct sock *sk);

	__u16			net_header_len;

	int			(*setsockopt)		(struct sock *sk, 
							 int level, 
							 int optname, 
							 char __user *optval, 
							 int optlen);

	int			(*getsockopt)		(struct sock *sk, 
							 int level, 
							 int optname, 
							 char __user *optval, 
							 int __user *optlen);


	void			(*addr2sockaddr)	(struct sock *sk,
							 struct sockaddr *);

	int sockaddr_len;
};

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

static inline int before(__u32 seq1, __u32 seq2)
{
        return (__s32)(seq1-seq2) < 0;
}

static inline int after(__u32 seq1, __u32 seq2)
{
	return (__s32)(seq2-seq1) < 0;
}


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


extern struct proto tcp_prot;

DECLARE_SNMP_STAT(struct tcp_mib, tcp_statistics);
#define TCP_INC_STATS(field)		SNMP_INC_STATS(tcp_statistics, field)
#define TCP_INC_STATS_BH(field)		SNMP_INC_STATS_BH(tcp_statistics, field)
#define TCP_INC_STATS_USER(field) 	SNMP_INC_STATS_USER(tcp_statistics, field)
#define TCP_DEC_STATS(field)		SNMP_DEC_STATS(tcp_statistics, field)
#define TCP_ADD_STATS_BH(field, val)	SNMP_ADD_STATS_BH(tcp_statistics, field, val)
#define TCP_ADD_STATS_USER(field, val)	SNMP_ADD_STATS_USER(tcp_statistics, field, val)

extern void			tcp_put_port(struct sock *sk);
extern void			tcp_inherit_port(struct sock *sk, struct sock *child);

extern void			tcp_v4_err(struct sk_buff *skb, u32);

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

extern int			tcp_v4_rcv(struct sk_buff *skb);

extern int			tcp_v4_remember_stamp(struct sock *sk);

extern int		    	tcp_v4_tw_remember_stamp(struct tcp_tw_bucket *tw);

extern int			tcp_sendmsg(struct kiocb *iocb, struct sock *sk,
					    struct msghdr *msg, size_t size);
extern ssize_t			tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags);

extern int			tcp_ioctl(struct sock *sk, 
					  int cmd, 
					  unsigned long arg);

extern int			tcp_rcv_state_process(struct sock *sk, 
						      struct sk_buff *skb,
						      struct tcphdr *th,
						      unsigned len);

extern int			tcp_rcv_established(struct sock *sk, 
						    struct sk_buff *skb,
						    struct tcphdr *th, 
						    unsigned len);

extern void			tcp_rcv_space_adjust(struct sock *sk);

enum tcp_ack_state_t
{
	TCP_ACK_SCHED = 1,
	TCP_ACK_TIMER = 2,
	TCP_ACK_PUSHED= 4
};

static inline void tcp_schedule_ack(struct tcp_opt *tp)
{
	tp->ack.pending |= TCP_ACK_SCHED;
}

static inline int tcp_ack_scheduled(struct tcp_opt *tp)
{
	return tp->ack.pending&TCP_ACK_SCHED;
}

static __inline__ void tcp_dec_quickack_mode(struct tcp_opt *tp)
{
	if (tp->ack.quick && --tp->ack.quick == 0) {
		/* Leaving quickack mode we deflate ATO. */
		tp->ack.ato = TCP_ATO_MIN;
	}
}

extern void tcp_enter_quickack_mode(struct tcp_opt *tp);

static __inline__ void tcp_delack_init(struct tcp_opt *tp)
{
	memset(&tp->ack, 0, sizeof(tp->ack));
}

static inline void tcp_clear_options(struct tcp_opt *tp)
{
 	tp->tstamp_ok = tp->sack_ok = tp->wscale_ok = tp->snd_wscale = 0;
}

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


extern enum tcp_tw_status	tcp_timewait_state_process(struct tcp_tw_bucket *tw,
							   struct sk_buff *skb,
							   struct tcphdr *th,
							   unsigned len);

extern struct sock *		tcp_check_req(struct sock *sk,struct sk_buff *skb,
					      struct open_request *req,
					      struct open_request **prev);
extern int			tcp_child_process(struct sock *parent,
						  struct sock *child,
						  struct sk_buff *skb);
extern void			tcp_enter_frto(struct sock *sk);
extern void			tcp_enter_loss(struct sock *sk, int how);
extern void			tcp_clear_retrans(struct tcp_opt *tp);
extern void			tcp_update_metrics(struct sock *sk);

extern void			tcp_close(struct sock *sk, 
					  long timeout);
extern struct sock *		tcp_accept(struct sock *sk, int flags, int *err);
extern unsigned int		tcp_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait);

extern int			tcp_getsockopt(struct sock *sk, int level, 
					       int optname,
					       char __user *optval, 
					       int __user *optlen);
extern int			tcp_setsockopt(struct sock *sk, int level, 
					       int optname, char __user *optval, 
					       int optlen);
extern void			tcp_set_keepalive(struct sock *sk, int val);
extern int			tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
					    struct msghdr *msg,
					    size_t len, int nonblock, 
					    int flags, int *addr_len);

extern int			tcp_listen_start(struct sock *sk);

extern void			tcp_parse_options(struct sk_buff *skb,
						  struct tcp_opt *tp,
						  int estab);

/*
 *	TCP v4 functions exported for the inet6 API
 */

extern int		       	tcp_v4_rebuild_header(struct sock *sk);

extern int		       	tcp_v4_build_header(struct sock *sk, 
						    struct sk_buff *skb);

extern void		       	tcp_v4_send_check(struct sock *sk, 
						  struct tcphdr *th, int len, 
						  struct sk_buff *skb);

extern int			tcp_v4_conn_request(struct sock *sk,
						    struct sk_buff *skb);

extern struct sock *		tcp_create_openreq_child(struct sock *sk,
							 struct open_request *req,
							 struct sk_buff *skb);

extern struct sock *		tcp_v4_syn_recv_sock(struct sock *sk,
						     struct sk_buff *skb,
						     struct open_request *req,
							struct dst_entry *dst);

extern int			tcp_v4_do_rcv(struct sock *sk,
					      struct sk_buff *skb);

extern int			tcp_v4_connect(struct sock *sk,
					       struct sockaddr *uaddr,
					       int addr_len);

extern int			tcp_connect(struct sock *sk);

extern struct sk_buff *		tcp_make_synack(struct sock *sk,
						struct dst_entry *dst,
						struct open_request *req);

extern int			tcp_disconnect(struct sock *sk, int flags);

extern void			tcp_unhash(struct sock *sk);

extern int			tcp_v4_hash_connecting(struct sock *sk);


/* From syncookies.c */
extern struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, 
				    struct ip_options *opt);
extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, 
				     __u16 *mss);

/* tcp_output.c */

extern int tcp_write_xmit(struct sock *, int nonagle);
extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
extern void tcp_xmit_retransmit_queue(struct sock *);
extern void tcp_simple_retransmit(struct sock *);
extern int tcp_trim_head(struct sock *, struct sk_buff *, u32);

extern void tcp_send_probe0(struct sock *);
extern void tcp_send_partial(struct sock *);
extern int  tcp_write_wakeup(struct sock *);
extern void tcp_send_fin(struct sock *sk);
extern void tcp_send_active_reset(struct sock *sk, int priority);
extern int  tcp_send_synack(struct sock *);
extern void tcp_push_one(struct sock *, unsigned mss_now);
extern void tcp_send_ack(struct sock *sk);
extern void tcp_send_delayed_ack(struct sock *sk);

/* tcp_timer.c */
extern void tcp_init_xmit_timers(struct sock *);
extern void tcp_clear_xmit_timers(struct sock *);

extern void tcp_delete_keepalive_timer (struct sock *);
extern void tcp_reset_keepalive_timer (struct sock *, unsigned long);
extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
extern unsigned int tcp_current_mss(struct sock *sk, int large);

extern const char timer_bug_msg[];

/* tcp_diag.c */
extern void tcp_get_info(struct sock *, struct tcp_info *);

/* Read 'sendfile()'-style from a TCP socket */
typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
				unsigned int, size_t);
extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
			 sk_read_actor_t recv_actor);

static inline void tcp_clear_xmit_timer(struct sock *sk, int what)
{
	struct tcp_opt *tp = tcp_sk(sk);
	
	switch (what) {
	case TCP_TIME_RETRANS:
	case TCP_TIME_PROBE0:
		tp->pending = 0;

#ifdef TCP_CLEAR_TIMERS
		sk_stop_timer(sk, &tp->retransmit_timer);
#endif
		break;
	case TCP_TIME_DACK:
		tp->ack.blocked = 0;
		tp->ack.pending = 0;

#ifdef TCP_CLEAR_TIMERS
		sk_stop_timer(sk, &tp->delack_timer);
#endif
		break;
	default:
		printk(timer_bug_msg);
		return;
	};

}

/*
 *	Reset the retransmission timer
 */
static inline void tcp_reset_xmit_timer(struct sock *sk, int what, unsigned long when)
{
	struct tcp_opt *tp = tcp_sk(sk);

	if (when > TCP_RTO_MAX) {
#ifdef TCP_DEBUG
		printk(KERN_DEBUG "reset_xmit_timer sk=%p %d when=0x%lx, caller=%p\n", sk, what, when, current_text_addr());
#endif
		when = TCP_RTO_MAX;
	}

	switch (what) {
	case TCP_TIME_RETRANS:
	case TCP_TIME_PROBE0:
		tp->pending = what;
		tp->timeout = jiffies+when;
		sk_reset_timer(sk, &tp->retransmit_timer, tp->timeout);
		break;

	case TCP_TIME_DACK:
		tp->ack.pending |= TCP_ACK_TIMER;
		tp->ack.timeout = jiffies+when;