inet_connection_sock.h 10.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * NET		Generic infrastructure for INET connection oriented protocols.
 *
 *		Definitions for inet_connection_sock 
 *
 * Authors:	Many people, see the TCP sources
 *
 * 		From code originally in TCP
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */
#ifndef _INET_CONNECTION_SOCK_H
#define _INET_CONNECTION_SOCK_H

18
#include <linux/compiler.h>
19
#include <linux/string.h>
20
#include <linux/timer.h>
A
Al Viro 已提交
21
#include <linux/poll.h>
22 23

#include <net/inet_sock.h>
24 25
#include <net/request_sock.h>

26 27 28 29 30
#define INET_CSK_DEBUG 1

/* Cancel timers, when they are not required. */
#undef INET_CSK_CLEAR_TIMERS

31
struct inet_bind_bucket;
32
struct tcp_congestion_ops;
33

34 35 36 37 38
/*
 * Pointers to address related TCP functions
 * (i.e. things that depend on the address family)
 */
struct inet_connection_sock_af_ops {
39
	int	    (*queue_xmit)(struct sk_buff *skb, int ipfragok);
40 41 42 43 44 45 46 47
	void	    (*send_check)(struct sock *sk, 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 request_sock *req,
				      struct dst_entry *dst);
	int	    (*remember_stamp)(struct sock *sk);
48 49
	u16	    net_header_len;
	u16	    sockaddr_len;
50
	int	    (*setsockopt)(struct sock *sk, int level, int optname, 
51
				  char __user *optval, unsigned int optlen);
52 53
	int	    (*getsockopt)(struct sock *sk, int level, int optname, 
				  char __user *optval, int __user *optlen);
A
Alexey Dobriyan 已提交
54
#ifdef CONFIG_COMPAT
55 56
	int	    (*compat_setsockopt)(struct sock *sk,
				int level, int optname,
57
				char __user *optval, unsigned int optlen);
58 59 60
	int	    (*compat_getsockopt)(struct sock *sk,
				int level, int optname,
				char __user *optval, int __user *optlen);
A
Alexey Dobriyan 已提交
61
#endif
62
	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
63 64
	int	    (*bind_conflict)(const struct sock *sk,
				     const struct inet_bind_bucket *tb);
65 66
};

67 68 69 70 71 72 73
/** inet_connection_sock - INET connection oriented sock
 *
 * @icsk_accept_queue:	   FIFO of established children 
 * @icsk_bind_hash:	   Bind node
 * @icsk_timeout:	   Timeout
 * @icsk_retransmit_timer: Resend (no ack)
 * @icsk_rto:		   Retransmit timeout
74
 * @icsk_pmtu_cookie	   Last pmtu seen by socket
75
 * @icsk_ca_ops		   Pluggable congestion control hook
76
 * @icsk_af_ops		   Operations which are AF_INET{4,6} specific
77
 * @icsk_ca_state:	   Congestion control state
78 79 80 81
 * @icsk_retransmits:	   Number of unrecovered [RTO] timeouts
 * @icsk_pending:	   Scheduled timer event
 * @icsk_backoff:	   Backoff
 * @icsk_syn_retries:      Number of allowed SYN (or equivalent) retries
82
 * @icsk_probes_out:	   unanswered 0 window probes
83
 * @icsk_ext_hdr_len:	   Network protocol overhead (IP/IPv6 options)
84
 * @icsk_ack:		   Delayed ACK control data
J
John Heffner 已提交
85
 * @icsk_mtup;		   MTU probing control data
86 87 88 89 90 91 92 93 94 95
 */
struct inet_connection_sock {
	/* inet_sock has to be the first member! */
	struct inet_sock	  icsk_inet;
	struct request_sock_queue icsk_accept_queue;
	struct inet_bind_bucket	  *icsk_bind_hash;
	unsigned long		  icsk_timeout;
 	struct timer_list	  icsk_retransmit_timer;
 	struct timer_list	  icsk_delack_timer;
	__u32			  icsk_rto;
96
	__u32			  icsk_pmtu_cookie;
97 98
	const struct tcp_congestion_ops *icsk_ca_ops;
	const struct inet_connection_sock_af_ops *icsk_af_ops;
99
	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
100
	__u8			  icsk_ca_state;
101 102 103 104
	__u8			  icsk_retransmits;
	__u8			  icsk_pending;
	__u8			  icsk_backoff;
	__u8			  icsk_syn_retries;
105
	__u8			  icsk_probes_out;
106
	__u16			  icsk_ext_hdr_len;
107 108 109 110 111 112 113 114 115 116 117
	struct {
		__u8		  pending;	 /* ACK is pending			   */
		__u8		  quick;	 /* Scheduled number of quick acks	   */
		__u8		  pingpong;	 /* The session is interactive		   */
		__u8		  blocked;	 /* Delayed ACK was blocked by socket lock */
		__u32		  ato;		 /* Predicted tick of soft clock	   */
		unsigned long	  timeout;	 /* Currently scheduled timeout		   */
		__u32		  lrcvtime;	 /* timestamp of last received data packet */
		__u16		  last_seg_size; /* Size of last incoming segment	   */
		__u16		  rcv_mss;	 /* MSS used for delayed ACK decisions	   */ 
	} icsk_ack;
J
John Heffner 已提交
118 119 120 121 122 123 124 125 126 127
	struct {
		int		  enabled;

		/* Range of MTUs to search */
		int		  search_high;
		int		  search_low;

		/* Information on the current probe. */
		int		  probe_size;
	} icsk_mtup;
128 129
	u32			  icsk_ca_priv[16];
#define ICSK_CA_PRIV_SIZE	(16 * sizeof(u32))
130 131
};

132 133 134 135 136
#define ICSK_TIME_RETRANS	1	/* Retransmit timer */
#define ICSK_TIME_DACK		2	/* Delayed ack timer */
#define ICSK_TIME_PROBE0	3	/* Zero window probe timer */
#define ICSK_TIME_KEEPOPEN	4	/* Keepalive timer */

137 138 139 140 141
static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
{
	return (struct inet_connection_sock *)sk;
}

142 143 144 145 146
static inline void *inet_csk_ca(const struct sock *sk)
{
	return (void *)inet_csk(sk)->icsk_ca_priv;
}

147 148
extern struct sock *inet_csk_clone(struct sock *sk,
				   const struct request_sock *req,
A
Al Viro 已提交
149
				   const gfp_t priority);
150

151 152 153
enum inet_csk_ack_state_t {
	ICSK_ACK_SCHED	= 1,
	ICSK_ACK_TIMER  = 2,
154 155
	ICSK_ACK_PUSHED = 4,
	ICSK_ACK_PUSHED2 = 8
156 157
};

158 159 160 161 162 163
extern void inet_csk_init_xmit_timers(struct sock *sk,
				      void (*retransmit_handler)(unsigned long),
				      void (*delack_handler)(unsigned long),
				      void (*keepalive_handler)(unsigned long));
extern void inet_csk_clear_xmit_timers(struct sock *sk);

164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202
static inline void inet_csk_schedule_ack(struct sock *sk)
{
	inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED;
}

static inline int inet_csk_ack_scheduled(const struct sock *sk)
{
	return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED;
}

static inline void inet_csk_delack_init(struct sock *sk)
{
	memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
}

extern void inet_csk_delete_keepalive_timer(struct sock *sk);
extern void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);

#ifdef INET_CSK_DEBUG
extern const char inet_csk_timer_bug_msg[];
#endif

static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	
	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
		icsk->icsk_pending = 0;
#ifdef INET_CSK_CLEAR_TIMERS
		sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
#endif
	} else if (what == ICSK_TIME_DACK) {
		icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
#ifdef INET_CSK_CLEAR_TIMERS
		sk_stop_timer(sk, &icsk->icsk_delack_timer);
#endif
	}
#ifdef INET_CSK_DEBUG
	else {
203
		pr_debug("%s", inet_csk_timer_bug_msg);
204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235
	}
#endif
}

/*
 *	Reset the retransmission timer
 */
static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
					     unsigned long when,
					     const unsigned long max_when)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (when > max_when) {
#ifdef INET_CSK_DEBUG
		pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
			 sk, what, when, current_text_addr());
#endif
		when = max_when;
	}

	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
		icsk->icsk_pending = what;
		icsk->icsk_timeout = jiffies + when;
		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
	} else if (what == ICSK_TIME_DACK) {
		icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
		icsk->icsk_ack.timeout = jiffies + when;
		sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
	}
#ifdef INET_CSK_DEBUG
	else {
236
		pr_debug("%s", inet_csk_timer_bug_msg);
237 238 239 240 241 242
	}
#endif
}

extern struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);

243 244
extern struct request_sock *inet_csk_search_req(const struct sock *sk,
						struct request_sock ***prevp,
245
						const __be16 rport,
246 247
						const __be32 raddr,
						const __be32 laddr);
248 249
extern int inet_csk_bind_conflict(const struct sock *sk,
				  const struct inet_bind_bucket *tb);
250
extern int inet_csk_get_port(struct sock *sk, unsigned short snum);
251 252 253 254

extern struct dst_entry* inet_csk_route_req(struct sock *sk,
					    const struct request_sock *req);

255 256 257 258 259 260 261 262 263
static inline void inet_csk_reqsk_queue_add(struct sock *sk,
					    struct request_sock *req,
					    struct sock *child)
{
	reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child);
}

extern void inet_csk_reqsk_queue_hash_add(struct sock *sk,
					  struct request_sock *req,
264
					  unsigned long timeout);
265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310

static inline void inet_csk_reqsk_queue_removed(struct sock *sk,
						struct request_sock *req)
{
	if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0)
		inet_csk_delete_keepalive_timer(sk);
}

static inline void inet_csk_reqsk_queue_added(struct sock *sk,
					      const unsigned long timeout)
{
	if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0)
		inet_csk_reset_keepalive_timer(sk, timeout);
}

static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
{
	return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue);
}

static inline int inet_csk_reqsk_queue_young(const struct sock *sk)
{
	return reqsk_queue_len_young(&inet_csk(sk)->icsk_accept_queue);
}

static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
{
	return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue);
}

static inline void inet_csk_reqsk_queue_unlink(struct sock *sk,
					       struct request_sock *req,
					       struct request_sock **prev)
{
	reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev);
}

static inline void inet_csk_reqsk_queue_drop(struct sock *sk,
					     struct request_sock *req,
					     struct request_sock **prev)
{
	inet_csk_reqsk_queue_unlink(sk, req, prev);
	inet_csk_reqsk_queue_removed(sk, req);
	reqsk_free(req);
}

311 312 313 314 315 316
extern void inet_csk_reqsk_queue_prune(struct sock *parent,
				       const unsigned long interval,
				       const unsigned long timeout,
				       const unsigned long max_rto);

extern void inet_csk_destroy_sock(struct sock *sk);
317 318 319 320 321 322 323 324 325 326

/*
 * LISTEN is a special case for poll..
 */
static inline unsigned int inet_csk_listen_poll(const struct sock *sk)
{
	return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ?
			(POLLIN | POLLRDNORM) : 0;
}

327
extern int  inet_csk_listen_start(struct sock *sk, const int nr_table_entries);
328 329
extern void inet_csk_listen_stop(struct sock *sk);

330 331
extern void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);

332 333 334
extern int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
				      char __user *optval, int __user *optlen);
extern int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
335
				      char __user *optval, unsigned int optlen);
336
#endif /* _INET_CONNECTION_SOCK_H */