aboutsummaryrefslogtreecommitdiffstats
path: root/net/dccp/timer.c
blob: 3af067354bd4ec531ab61f2b22cf4ecd01028552 (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
/*
 *  net/dccp/timer.c
 *
 *  An implementation of the DCCP protocol
 *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
 *
 *	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.
 */

#include <linux/dccp.h>
#include <linux/skbuff.h>

#include "dccp.h"

/* sysctl variables governing numbers of retransmission attempts */
int  sysctl_dccp_request_retries	__read_mostly = TCP_SYN_RETRIES;
int  sysctl_dccp_retries1		__read_mostly = TCP_RETR1;
int  sysctl_dccp_retries2		__read_mostly = TCP_RETR2;

static void dccp_write_err(struct sock *sk)
{
	sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
	sk->sk_error_report(sk);

	dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
	dccp_done(sk);
	DCCP_INC_STATS_BH(DCCP_MIB_ABORTONTIMEOUT);
}

/* A write timeout has occurred. Process the after effects. */
static int dccp_write_timeout(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	int retry_until;

	if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) {
		if (icsk->icsk_retransmits != 0)
			dst_negative_advice(&sk->sk_dst_cache);
		retry_until = icsk->icsk_syn_retries ?
			    : sysctl_dccp_request_retries;
	} else {
		if (icsk->icsk_retransmits >= sysctl_dccp_retries1) {
			/* NOTE. draft-ietf-tcpimpl-pmtud-01.txt requires pmtu
			   black hole detection. :-(

			   It is place to make it. It is not made. I do not want
			   to make it. It is disguisting. It does not work in any
			   case. Let me to cite the same draft, which requires for
			   us to implement this:

   "The one security concern raised by this memo is that ICMP black holes
   are often caused by over-zealous security administrators who block
   all ICMP messages.  It is vitally important that those who design and
   deploy security systems understand the impact of strict filtering on
   upper-layer protocols.  The safest web site in the world is worthless
   if most TCP implementations cannot transfer data from it.  It would
   be far nicer to have all of the black holes fixed rather than fixing
   all of the TCP implementations."

			   Golden words :-).
		   */

			dst_negative_advice(&sk->sk_dst_cache);
		}

		retry_until = sysctl_dccp_retries2;
		/*
		 * FIXME: see tcp_write_timout and tcp_out_of_resources
		 */
	}

	if (icsk->icsk_retransmits >= retry_until) {
		/* Has it gone just too far? */
		dccp_write_err(sk);
		return 1;
	}
	return 0;
}

/*
 *	The DCCP retransmit timer.
 */
static void dccp_retransmit_timer(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	/* retransmit timer is used for feature negotiation throughout
	 * connection.  In this case, no packet is re-transmitted, but rather an
	 * ack is generated and pending changes are placed into its options.
	 */
	if (sk->sk_send_head == NULL) {
		dccp_pr_debug("feat negotiation retransmit timeout %p\n", sk);
		if (sk->sk_state == DCCP_OPEN)
			dccp_send_ack(sk);
		goto backoff;
	}

	/*
	 * sk->sk_send_head has to have one skb with
	 * DCCP_SKB_CB(skb)->dccpd_type set to one of the retransmittable DCCP
	 * packet types. The only packets eligible for retransmission are:
	 *	-- Requests in client-REQUEST  state (sec. 8.1.1)
	 *	-- Acks     in client-PARTOPEN state (sec. 8.1.5)
	 *	-- CloseReq in server-CLOSEREQ state (sec. 8.3)
	 *	-- Close    in   node-CLOSING  state (sec. 8.3)                */
	BUG_TRAP(sk->sk_send_head != NULL);

	/*
	 * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was
	 * sent, no need to retransmit, this sock is dead.
	 */
	if (dccp_write_timeout(sk))
		goto out;

	/*
	 * We want to know the number of packets retransmitted, not the
	 * total number of retransmissions of clones of original packets.
	 */
	if (icsk->icsk_retransmits == 0)
		DCCP_INC_STATS_BH(DCCP_MIB_TIMEOUTS);

	if (dccp_retransmit_skb(sk, sk->sk_send_head) < 0) {
		/*
		 * Retransmission failed because of local congestion,
		 * do not backoff.
		 */
		if (icsk->icsk_retransmits == 0)
			icsk->icsk_retransmits = 1;
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  min(icsk->icsk_rto,
					      TCP_RESOURCE_PROBE_INTERVAL),
					  DCCP_RTO_MAX);
		goto out;
	}

backoff:
	icsk->icsk_backoff++;
	icsk->icsk_retransmits++;

	icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX);
	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto,
				  DCCP_RTO_MAX);
	if (icsk->icsk_retransmits > sysctl_dccp_retries1)
		__sk_dst_reset(sk);
out:;
}

static void dccp_write_timer(unsigned long data)
{
	struct sock *sk = (struct sock *)data;
	struct inet_connection_sock *icsk = inet_csk(sk);
	int event = 0;

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk)) {
		/* Try again later */
		sk_reset_timer(sk, &icsk->icsk_retransmit_timer,
			       jiffies + (HZ / 20));
		goto out;
	}

	if (sk->sk_state == DCCP_CLOSED || !icsk->icsk_pending)
		goto out;

	if (time_after(icsk->icsk_timeout, jiffies)) {
		sk_reset_timer(sk, &icsk->icsk_retransmit_timer,
			       icsk->icsk_timeout);
		goto out;
	}

	event = icsk->icsk_pending;
	icsk->icsk_pending = 0;

	switch (event) {
	case ICSK_TIME_RETRANS:
		dccp_retransmit_timer(sk);
		break;
	}
out:
	bh_unlock_sock(sk);
	sock_put(sk);
}

/*
 *	Timer for listening sockets
 */
static void dccp_response_timer(struct sock *sk)
{
	inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL, DCCP_TIMEOUT_INIT,
				   DCCP_RTO_MAX);
}

static void dccp_keepalive_timer(unsigned long data)
{
	struct sock *sk = (struct sock *)data;

	/* Only process if socket is not in use. */
	bh_lock_sock(sk);
	if (sock_owned_by_user(sk)) {
		/* Try again later. */
		inet_csk_reset_keepalive_timer(sk, HZ / 20);
		goto out;
	}

	if (sk->sk_state == DCCP_LISTEN) {
		dccp_response_timer(sk);
		goto out;
	}
out:
	bh_unlock_sock(sk);
	sock_put(sk);
}

/* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */
static void dccp_delack_timer(unsigned long data)
{
	struct sock *sk = (struct sock *)data;
	struct inet_connection_sock *icsk = inet_csk(sk);

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk)) {
		/* Try again later. */
		icsk->icsk_ack.blocked = 1;
		NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOCKED);
		sk_reset_timer(sk, &icsk->icsk_delack_timer,
			       jiffies + TCP_DELACK_MIN);
		goto out;
	}

	if (sk->sk_state == DCCP_CLOSED ||
	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
		goto out;
	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
		sk_reset_timer(sk, &icsk->icsk_delack_timer,
			       icsk->icsk_ack.timeout);
		goto out;
	}

	icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;

	if (inet_csk_ack_scheduled(sk)) {
		if (!icsk->icsk_ack.pingpong) {
			/* Delayed ACK missed: inflate ATO. */
			icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1,
						 icsk->icsk_rto);
		} else {
			/* Delayed ACK missed: leave pingpong mode and
			 * deflate ATO.
			 */
			icsk->icsk_ack.pingpong = 0;
			icsk->icsk_ack.ato = TCP_ATO_MIN;
		}
		dccp_send_ack(sk);
		NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKS);
	}
out:
	bh_unlock_sock(sk);
	sock_put(sk);
}

/* Transmit-delay timer: used by the CCIDs to delay actual send time */
static void dccp_write_xmit_timer(unsigned long data)
{
	struct sock *sk = (struct sock *)data;
	struct dccp_sock *dp = dccp_sk(sk);

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk))
		sk_reset_timer(sk, &dp->dccps_xmit_timer, jiffies+1);
	else
		dccp_write_xmit(sk, 0);
	bh_unlock_sock(sk);
	sock_put(sk);
}

static void dccp_init_write_xmit_timer(struct sock *sk)
{
	struct dccp_sock *dp = dccp_sk(sk);

	init_timer(&dp->dccps_xmit_timer);
	dp->dccps_xmit_timer.data = (unsigned long)sk;
	dp->dccps_xmit_timer.function = dccp_write_xmit_timer;
}

void dccp_init_xmit_timers(struct sock *sk)
{
	dccp_init_write_xmit_timer(sk);
	inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer,
				  &dccp_keepalive_timer);
}

static ktime_t dccp_timestamp_seed;
/**
 * dccp_timestamp  -  10s of microseconds time source
 * Returns the number of 10s of microseconds since loading DCCP. This is native
 * DCCP time difference format (RFC 4340, sec. 13).
 * Please note: This will wrap around about circa every 11.9 hours.
 */
u32 dccp_timestamp(void)
{
	s64 delta = ktime_us_delta(ktime_get_real(), dccp_timestamp_seed);

	do_div(delta, 10);
	return delta;
}
EXPORT_SYMBOL_GPL(dccp_timestamp);

void __init dccp_timestamping_init(void)
{
	dccp_timestamp_seed = ktime_get_real();
}