summaryrefslogtreecommitdiffstats
path: root/include/net/inet_connection_sock.h
blob: 481fe1c9044cfd8b49585139e24df16b0716debf (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
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
203
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
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
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
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
/*
 * 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

#include <linux/compiler.h>
#include <linux/string.h>
#include <linux/timer.h>
#include <linux/poll.h>

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

#define INET_CSK_DEBUG 1

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

struct inet_bind_bucket;
struct tcp_congestion_ops;

/*
 * Pointers to address related TCP functions
 * (i.e. things that depend on the address family)
 */
struct inet_connection_sock_af_ops {
	int	    (*queue_xmit)(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
	void	    (*send_check)(struct sock *sk, struct sk_buff *skb);
	int	    (*rebuild_header)(struct sock *sk);
	void	    (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb);
	int	    (*conn_request)(struct sock *sk, struct sk_buff *skb);
	struct sock *(*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);
	u16	    net_header_len;
	u16	    net_frag_header_len;
	u16	    sockaddr_len;
	int	    (*setsockopt)(struct sock *sk, int level, int optname, 
				  char __user *optval, unsigned int optlen);
	int	    (*getsockopt)(struct sock *sk, int level, int optname, 
				  char __user *optval, int __user *optlen);
#ifdef CONFIG_COMPAT
	int	    (*compat_setsockopt)(struct sock *sk,
				int level, int optname,
				char __user *optval, unsigned int optlen);
	int	    (*compat_getsockopt)(struct sock *sk,
				int level, int optname,
				char __user *optval, int __user *optlen);
#endif
	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
	int	    (*bind_conflict)(const struct sock *sk,
				     const struct inet_bind_bucket *tb, bool relax);
	void	    (*mtu_reduced)(struct sock *sk);
};

/** 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
 * @icsk_pmtu_cookie	   Last pmtu seen by socket
 * @icsk_ca_ops		   Pluggable congestion control hook
 * @icsk_af_ops		   Operations which are AF_INET{4,6} specific
 * @icsk_ca_state:	   Congestion control state
 * @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
 * @icsk_probes_out:	   unanswered 0 window probes
 * @icsk_ext_hdr_len:	   Network protocol overhead (IP/IPv6 options)
 * @icsk_ack:		   Delayed ACK control data
 * @icsk_mtup;		   MTU probing control data
 */
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;
	__u32			  icsk_pmtu_cookie;
	const struct tcp_congestion_ops *icsk_ca_ops;
	const struct inet_connection_sock_af_ops *icsk_af_ops;
	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
	__u8			  icsk_ca_state:6,
				  icsk_ca_setsockopt:1,
				  icsk_ca_dst_locked:1;
	__u8			  icsk_retransmits;
	__u8			  icsk_pending;
	__u8			  icsk_backoff;
	__u8			  icsk_syn_retries;
	__u8			  icsk_probes_out;
	__u16			  icsk_ext_hdr_len;
	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;
	struct {
		int		  enabled;

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

		/* Information on the current probe. */
		int		  probe_size;

		u32		  probe_timestamp;
	} icsk_mtup;
	u32			  icsk_user_timeout;

	u64			  icsk_ca_priv[64 / sizeof(u64)];
#define ICSK_CA_PRIV_SIZE      (8 * sizeof(u64))
};

#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_EARLY_RETRANS 4	/* Early retransmit timer */
#define ICSK_TIME_LOSS_PROBE	5	/* Tail loss probe timer */

static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
{
	return (struct inet_connection_sock *)sk;
}

static inline void *inet_csk_ca(const struct sock *sk)
{
	return (void *)inet_csk(sk)->icsk_ca_priv;
}

struct sock *inet_csk_clone_lock(const struct sock *sk,
				 const struct request_sock *req,
				 const gfp_t priority);

enum inet_csk_ack_state_t {
	ICSK_ACK_SCHED	= 1,
	ICSK_ACK_TIMER  = 2,
	ICSK_ACK_PUSHED = 4,
	ICSK_ACK_PUSHED2 = 8
};

void inet_csk_init_xmit_timers(struct sock *sk,
			       void (*retransmit_handler)(unsigned long),
			       void (*delack_handler)(unsigned long),
			       void (*keepalive_handler)(unsigned long));
void inet_csk_clear_xmit_timers(struct sock *sk);

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));
}

void inet_csk_delete_keepalive_timer(struct sock *sk);
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 {
		pr_debug("%s", inet_csk_timer_bug_msg);
	}
#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 ||
	    what == ICSK_TIME_EARLY_RETRANS || what ==  ICSK_TIME_LOSS_PROBE) {
		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 {
		pr_debug("%s", inet_csk_timer_bug_msg);
	}
#endif
}

static inline unsigned long
inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
		     unsigned long max_when)
{
        u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff;

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

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

int inet_csk_bind_conflict(const struct sock *sk,
			   const struct inet_bind_bucket *tb, bool relax);
int inet_csk_get_port(struct sock *sk, unsigned short snum);

struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4,
				     const struct request_sock *req);
struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
					    struct sock *newsk,
					    const struct request_sock *req);

void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
			      struct sock *child);
void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
				   unsigned long timeout);
struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
					 struct request_sock *req,
					 bool own_req);

static inline void inet_csk_reqsk_queue_added(struct sock *sk)
{
	reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue);
}

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 inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog;
}

void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);

void inet_csk_destroy_sock(struct sock *sk);
void inet_csk_prepare_forced_close(struct sock *sk);

/*
 * 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;
}

int inet_csk_listen_start(struct sock *sk, int backlog);
void inet_csk_listen_stop(struct sock *sk);

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

int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
			       char __user *optval, int __user *optlen);
int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
			       char __user *optval, unsigned int optlen);

struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
#endif /* _INET_CONNECTION_SOCK_H */
OpenPOWER on IntegriCloud