summaryrefslogtreecommitdiffstats
path: root/net/dccp/minisocks.c
blob: 9e1de5919ee5c114e09e83433a656f6a7bbd5fc8 (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
/*
 *  net/dccp/minisocks.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/config.h>
#include <linux/dccp.h>
#include <linux/skbuff.h>
#include <linux/timer.h>

#include <net/sock.h>
#include <net/xfrm.h>
#include <net/inet_timewait_sock.h>

#include "ackvec.h"
#include "ccid.h"
#include "dccp.h"
#include "feat.h"

struct inet_timewait_death_row dccp_death_row = {
	.sysctl_max_tw_buckets = NR_FILE * 2,
	.period		= DCCP_TIMEWAIT_LEN / INET_TWDR_TWKILL_SLOTS,
	.death_lock	= SPIN_LOCK_UNLOCKED,
	.hashinfo	= &dccp_hashinfo,
	.tw_timer	= TIMER_INITIALIZER(inet_twdr_hangman, 0,
					    (unsigned long)&dccp_death_row),
	.twkill_work	= __WORK_INITIALIZER(dccp_death_row.twkill_work,
					     inet_twdr_twkill_work,
					     &dccp_death_row),
/* Short-time timewait calendar */

	.twcal_hand	= -1,
	.twcal_timer	= TIMER_INITIALIZER(inet_twdr_twcal_tick, 0,
					    (unsigned long)&dccp_death_row),
};

EXPORT_SYMBOL_GPL(dccp_death_row);

void dccp_time_wait(struct sock *sk, int state, int timeo)
{
	struct inet_timewait_sock *tw = NULL;

	if (dccp_death_row.tw_count < dccp_death_row.sysctl_max_tw_buckets)
		tw = inet_twsk_alloc(sk, state);

	if (tw != NULL) {
		const struct inet_connection_sock *icsk = inet_csk(sk);
		const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
		if (tw->tw_family == PF_INET6) {
			const struct ipv6_pinfo *np = inet6_sk(sk);
			struct inet6_timewait_sock *tw6;

			tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
			tw6 = inet6_twsk((struct sock *)tw);
			ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr);
			ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr);
			tw->tw_ipv6only = np->ipv6only;
		}
#endif
		/* Linkage updates. */
		__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);

		/* Get the TIME_WAIT timeout firing. */
		if (timeo < rto)
			timeo = rto;

		tw->tw_timeout = DCCP_TIMEWAIT_LEN;
		if (state == DCCP_TIME_WAIT)
			timeo = DCCP_TIMEWAIT_LEN;

		inet_twsk_schedule(tw, &dccp_death_row, timeo,
				   DCCP_TIMEWAIT_LEN);
		inet_twsk_put(tw);
	} else {
		/* Sorry, if we're out of memory, just CLOSE this
		 * socket up.  We've got bigger problems than
		 * non-graceful socket closings.
		 */
		LIMIT_NETDEBUG(KERN_INFO "DCCP: time wait bucket "
					 "table overflow\n");
	}

	dccp_done(sk);
}

struct sock *dccp_create_openreq_child(struct sock *sk,
				       const struct request_sock *req,
				       const struct sk_buff *skb)
{
	/*
	 * Step 3: Process LISTEN state
	 *
	 * // Generate a new socket and switch to that socket
	 * Set S := new socket for this port pair
	 */
	struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC);

	if (newsk != NULL) {
		const struct dccp_request_sock *dreq = dccp_rsk(req);
		struct inet_connection_sock *newicsk = inet_csk(sk);
		struct dccp_sock *newdp = dccp_sk(newsk);

		newdp->dccps_role	   = DCCP_ROLE_SERVER;
		newdp->dccps_hc_rx_ackvec  = NULL;
		newdp->dccps_service_list  = NULL;
		newdp->dccps_service	   = dreq->dreq_service;
		newicsk->icsk_rto	   = DCCP_TIMEOUT_INIT;
		do_gettimeofday(&newdp->dccps_epoch);

		if (dccp_feat_clone(sk, newsk))
			goto out_free;

		if (newdp->dccps_options.dccpo_send_ack_vector) {
			newdp->dccps_hc_rx_ackvec =
						dccp_ackvec_alloc(GFP_ATOMIC);
			/*
			 * XXX: We're using the same CCIDs set on the parent,
			 * i.e. sk_clone copied the master sock and left the
			 * CCID pointers for this child, that is why we do the
			 * __ccid_get calls.
			 */
			if (unlikely(newdp->dccps_hc_rx_ackvec == NULL))
				goto out_free;
		}

		if (unlikely(ccid_hc_rx_init(newdp->dccps_hc_rx_ccid,
					     newsk) != 0 ||
			     ccid_hc_tx_init(newdp->dccps_hc_tx_ccid,
				     	     newsk) != 0)) {
			dccp_ackvec_free(newdp->dccps_hc_rx_ackvec);
			ccid_hc_rx_exit(newdp->dccps_hc_rx_ccid, newsk);
			ccid_hc_tx_exit(newdp->dccps_hc_tx_ccid, newsk);
out_free:
			/* It is still raw copy of parent, so invalidate
			 * destructor and make plain sk_free() */
			newsk->sk_destruct = NULL;
			sk_free(newsk);
			return NULL;
		}

		__ccid_get(newdp->dccps_hc_rx_ccid);
		__ccid_get(newdp->dccps_hc_tx_ccid);

		/*
		 * Step 3: Process LISTEN state
		 *
		 *	Choose S.ISS (initial seqno) or set from Init Cookie
		 *	Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init
		 *	Cookie
		 */

		/* See dccp_v4_conn_request */
		newdp->dccps_options.dccpo_sequence_window = req->rcv_wnd;

		newdp->dccps_gar = newdp->dccps_isr = dreq->dreq_isr;
		dccp_update_gsr(newsk, dreq->dreq_isr);

		newdp->dccps_iss = dreq->dreq_iss;
		dccp_update_gss(newsk, dreq->dreq_iss);

		/*
		 * SWL and AWL are initially adjusted so that they are not less than
		 * the initial Sequence Numbers received and sent, respectively:
		 *	SWL := max(GSR + 1 - floor(W/4), ISR),
		 *	AWL := max(GSS - W' + 1, ISS).
		 * These adjustments MUST be applied only at the beginning of the
		 * connection.
		 */
		dccp_set_seqno(&newdp->dccps_swl,
			       max48(newdp->dccps_swl, newdp->dccps_isr));
		dccp_set_seqno(&newdp->dccps_awl,
			       max48(newdp->dccps_awl, newdp->dccps_iss));

		dccp_init_xmit_timers(newsk);

		DCCP_INC_STATS_BH(DCCP_MIB_PASSIVEOPENS);
	}
	return newsk;
}

EXPORT_SYMBOL_GPL(dccp_create_openreq_child);

/* 
 * Process an incoming packet for RESPOND sockets represented
 * as an request_sock.
 */
struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
			    struct request_sock *req,
			    struct request_sock **prev)
{
	struct sock *child = NULL;

	/* Check for retransmitted REQUEST */
	if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
		if (after48(DCCP_SKB_CB(skb)->dccpd_seq,
			    dccp_rsk(req)->dreq_isr)) {
			struct dccp_request_sock *dreq = dccp_rsk(req);

			dccp_pr_debug("Retransmitted REQUEST\n");
			/* Send another RESPONSE packet */
			dccp_set_seqno(&dreq->dreq_iss, dreq->dreq_iss + 1);
			dccp_set_seqno(&dreq->dreq_isr,
				       DCCP_SKB_CB(skb)->dccpd_seq);
			req->rsk_ops->rtx_syn_ack(sk, req, NULL);
		}
		/* Network Duplicate, discard packet */
		return NULL;
	}

	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;

	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_ACK &&
	    dccp_hdr(skb)->dccph_type != DCCP_PKT_DATAACK)
		goto drop;

	/* Invalid ACK */
	if (DCCP_SKB_CB(skb)->dccpd_ack_seq != dccp_rsk(req)->dreq_iss) {
		dccp_pr_debug("Invalid ACK number: ack_seq=%llu, "
			      "dreq_iss=%llu\n",
			      (unsigned long long)
			      DCCP_SKB_CB(skb)->dccpd_ack_seq,
			      (unsigned long long)
			      dccp_rsk(req)->dreq_iss);
		goto drop;
	}

	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
	if (child == NULL)
		goto listen_overflow;

	/* FIXME: deal with options */

	inet_csk_reqsk_queue_unlink(sk, req, prev);
	inet_csk_reqsk_queue_removed(sk, req);
	inet_csk_reqsk_queue_add(sk, req, child);
out:
	return child;
listen_overflow:
	dccp_pr_debug("listen_overflow!\n");
	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
drop:
	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
		req->rsk_ops->send_reset(skb);

	inet_csk_reqsk_queue_drop(sk, req, prev);
	goto out;
}

EXPORT_SYMBOL_GPL(dccp_check_req);

/*
 *  Queue segment on the new socket if the new socket is active,
 *  otherwise we just shortcircuit this and continue with
 *  the new socket.
 */
int dccp_child_process(struct sock *parent, struct sock *child,
		       struct sk_buff *skb)
{
	int ret = 0;
	const int state = child->sk_state;

	if (!sock_owned_by_user(child)) {
		ret = dccp_rcv_state_process(child, skb, dccp_hdr(skb),
					     skb->len);

		/* Wakeup parent, send SIGIO */
		if (state == DCCP_RESPOND && child->sk_state != state)
			parent->sk_data_ready(parent, 0);
	} else {
		/* Alas, it is possible again, because we do lookup
		 * in main socket hash table and lock on listening
		 * socket does not protect us more.
		 */
		sk_add_backlog(child, skb);
	}

	bh_unlock_sock(child);
	sock_put(child);
	return ret;
}

EXPORT_SYMBOL_GPL(dccp_child_process);