aboutsummaryrefslogtreecommitdiffstats
path: root/sys/netinet/tcp_reass.c
blob: f5248106e9b78e42a09d8a3c1e92e8f04ef4d5e3 (plain) (blame)
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
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
/*-
 * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994, 1995
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)tcp_input.c	8.12 (Berkeley) 5/24/95
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_tcpdebug.h"

#include <sys/param.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/systm.h>

#include <vm/uma.h>

#include <net/if.h>
#include <net/route.h>
#include <net/vnet.h>

#include <netinet/in.h>
#include <netinet/in_pcb.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>
#include <netinet/ip6.h>
#include <netinet6/in6_pcb.h>
#include <netinet6/ip6_var.h>
#include <netinet6/nd6.h>
#include <netinet/tcp.h>
#include <netinet/tcp_fsm.h>
#include <netinet/tcp_seq.h>
#include <netinet/tcp_timer.h>
#include <netinet/tcp_var.h>
#include <netinet6/tcp6_var.h>
#include <netinet/tcpip.h>
#ifdef TCPDEBUG
#include <netinet/tcp_debug.h>
#endif /* TCPDEBUG */

static int tcp_reass_sysctl_maxseg(SYSCTL_HANDLER_ARGS);
static int tcp_reass_sysctl_qsize(SYSCTL_HANDLER_ARGS);

SYSCTL_NODE(_net_inet_tcp, OID_AUTO, reass, CTLFLAG_RW, 0,
    "TCP Segment Reassembly Queue");

static VNET_DEFINE(int, tcp_reass_maxseg) = 0;
#define	V_tcp_reass_maxseg		VNET(tcp_reass_maxseg)
SYSCTL_VNET_PROC(_net_inet_tcp_reass, OID_AUTO, maxsegments,
    CTLTYPE_INT | CTLFLAG_RDTUN,
    &VNET_NAME(tcp_reass_maxseg), 0, &tcp_reass_sysctl_maxseg, "I",
    "Global maximum number of TCP Segments in Reassembly Queue");

static VNET_DEFINE(int, tcp_reass_qsize) = 0;
#define	V_tcp_reass_qsize		VNET(tcp_reass_qsize)
SYSCTL_VNET_PROC(_net_inet_tcp_reass, OID_AUTO, cursegments,
    CTLTYPE_INT | CTLFLAG_RD,
    &VNET_NAME(tcp_reass_qsize), 0, &tcp_reass_sysctl_qsize, "I",
    "Global number of TCP Segments currently in Reassembly Queue");

static VNET_DEFINE(int, tcp_reass_overflows) = 0;
#define	V_tcp_reass_overflows		VNET(tcp_reass_overflows)
SYSCTL_VNET_INT(_net_inet_tcp_reass, OID_AUTO, overflows,
    CTLTYPE_INT | CTLFLAG_RD,
    &VNET_NAME(tcp_reass_overflows), 0,
    "Global number of TCP Segment Reassembly Queue Overflows");

static VNET_DEFINE(uma_zone_t, tcp_reass_zone);
#define	V_tcp_reass_zone		VNET(tcp_reass_zone)

/* Initialize TCP reassembly queue */
static void
tcp_reass_zone_change(void *tag)
{

	V_tcp_reass_maxseg = nmbclusters / 16;
	uma_zone_set_max(V_tcp_reass_zone, V_tcp_reass_maxseg);
}

void
tcp_reass_init(void)
{

	V_tcp_reass_maxseg = nmbclusters / 16;
	TUNABLE_INT_FETCH("net.inet.tcp.reass.maxsegments",
	    &V_tcp_reass_maxseg);
	V_tcp_reass_zone = uma_zcreate("tcpreass", sizeof (struct tseg_qent),
	    NULL, NULL, NULL, NULL, UMA_ALIGN_PTR, UMA_ZONE_NOFREE);
	uma_zone_set_max(V_tcp_reass_zone, V_tcp_reass_maxseg);
	EVENTHANDLER_REGISTER(nmbclusters_change,
	    tcp_reass_zone_change, NULL, EVENTHANDLER_PRI_ANY);
}

#ifdef VIMAGE
void
tcp_reass_destroy(void)
{

	uma_zdestroy(V_tcp_reass_zone);
}
#endif

void
tcp_reass_flush(struct tcpcb *tp)
{
	struct tseg_qent *qe;

	INP_WLOCK_ASSERT(tp->t_inpcb);

	while ((qe = LIST_FIRST(&tp->t_segq)) != NULL) {
		LIST_REMOVE(qe, tqe_q);
		m_freem(qe->tqe_m);
		uma_zfree(V_tcp_reass_zone, qe);
		tp->t_segqlen--;
	}

	KASSERT((tp->t_segqlen == 0),
	    ("TCP reass queue %p segment count is %d instead of 0 after flush.",
	    tp, tp->t_segqlen));
}

static int
tcp_reass_sysctl_maxseg(SYSCTL_HANDLER_ARGS)
{
	V_tcp_reass_maxseg = uma_zone_get_max(V_tcp_reass_zone);
	return (sysctl_handle_int(oidp, arg1, arg2, req));
}

static int
tcp_reass_sysctl_qsize(SYSCTL_HANDLER_ARGS)
{
	V_tcp_reass_qsize = uma_zone_get_cur(V_tcp_reass_zone);
	return (sysctl_handle_int(oidp, arg1, arg2, req));
}

int
tcp_reass(struct tcpcb *tp, struct tcphdr *th, int *tlenp, struct mbuf *m)
{
	struct tseg_qent *q;
	struct tseg_qent *p = NULL;
	struct tseg_qent *nq;
	struct tseg_qent *te = NULL;
	struct socket *so = tp->t_inpcb->inp_socket;
	char *s = NULL;
	int flags;
	struct tseg_qent tqs;

	INP_WLOCK_ASSERT(tp->t_inpcb);

	/*
	 * XXX: tcp_reass() is rather inefficient with its data structures
	 * and should be rewritten (see NetBSD for optimizations).
	 */

	/*
	 * Call with th==NULL after become established to
	 * force pre-ESTABLISHED data up to user socket.
	 */
	if (th == NULL)
		goto present;

	/*
	 * Limit the number of segments that can be queued to reduce the
	 * potential for mbuf exhaustion. For best performance, we want to be
	 * able to queue a full window's worth of segments. The size of the
	 * socket receive buffer determines our advertised window and grows
	 * automatically when socket buffer autotuning is enabled. Use it as the
	 * basis for our queue limit.
	 * Always let the missing segment through which caused this queue.
	 * NB: Access to the socket buffer is left intentionally unlocked as we
	 * can tolerate stale information here.
	 *
	 * XXXLAS: Using sbspace(so->so_rcv) instead of so->so_rcv.sb_hiwat
	 * should work but causes packets to be dropped when they shouldn't.
	 * Investigate why and re-evaluate the below limit after the behaviour
	 * is understood.
	 */
	if (th->th_seq != tp->rcv_nxt &&
	    tp->t_segqlen >= (so->so_rcv.sb_hiwat / tp->t_maxseg) + 1) {
		V_tcp_reass_overflows++;
		TCPSTAT_INC(tcps_rcvmemdrop);
		m_freem(m);
		*tlenp = 0;
		if ((s = tcp_log_addrs(&tp->t_inpcb->inp_inc, th, NULL, NULL))) {
			log(LOG_DEBUG, "%s; %s: queue limit reached, "
			    "segment dropped\n", s, __func__);
			free(s, M_TCPLOG);
		}
		return (0);
	}

	/*
	 * Allocate a new queue entry. If we can't, or hit the zone limit
	 * just drop the pkt.
	 *
	 * Use a temporary structure on the stack for the missing segment
	 * when the zone is exhausted. Otherwise we may get stuck.
	 */
	te = uma_zalloc(V_tcp_reass_zone, M_NOWAIT);
	if (te == NULL) {
		if (th->th_seq != tp->rcv_nxt) {
			TCPSTAT_INC(tcps_rcvmemdrop);
			m_freem(m);
			*tlenp = 0;
			if ((s = tcp_log_addrs(&tp->t_inpcb->inp_inc, th, NULL,
			    NULL))) {
				log(LOG_DEBUG, "%s; %s: global zone limit "
				    "reached, segment dropped\n", s, __func__);
				free(s, M_TCPLOG);
			}
			return (0);
		} else {
			bzero(&tqs, sizeof(struct tseg_qent));
			te = &tqs;
			if ((s = tcp_log_addrs(&tp->t_inpcb->inp_inc, th, NULL,
			    NULL))) {
				log(LOG_DEBUG,
				    "%s; %s: global zone limit reached, using "
				    "stack for missing segment\n", s, __func__);
				free(s, M_TCPLOG);
			}
		}
	}
	tp->t_segqlen++;

	/*
	 * Find a segment which begins after this one does.
	 */
	LIST_FOREACH(q, &tp->t_segq, tqe_q) {
		if (SEQ_GT(q->tqe_th->th_seq, th->th_seq))
			break;
		p = q;
	}

	/*
	 * If there is a preceding segment, it may provide some of
	 * our data already.  If so, drop the data from the incoming
	 * segment.  If it provides all of our data, drop us.
	 */
	if (p != NULL) {
		int i;
		/* conversion to int (in i) handles seq wraparound */
		i = p->tqe_th->th_seq + p->tqe_len - th->th_seq;
		if (i > 0) {
			if (i >= *tlenp) {
				TCPSTAT_INC(tcps_rcvduppack);
				TCPSTAT_ADD(tcps_rcvdupbyte, *tlenp);
				m_freem(m);
				uma_zfree(V_tcp_reass_zone, te);
				tp->t_segqlen--;
				/*
				 * Try to present any queued data
				 * at the left window edge to the user.
				 * This is needed after the 3-WHS
				 * completes.
				 */
				goto present;	/* ??? */
			}
			m_adj(m, i);
			*tlenp -= i;
			th->th_seq += i;
		}
	}
 	tp->t_rcvoopack++;
	TCPSTAT_INC(tcps_rcvoopack);
	TCPSTAT_ADD(tcps_rcvoobyte, *tlenp);

	/*
	 * While we overlap succeeding segments trim them or,
	 * if they are completely covered, dequeue them.
	 */
	while (q) {
		int i = (th->th_seq + *tlenp) - q->tqe_th->th_seq;
		if (i <= 0)
			break;
		if (i < q->tqe_len) {
			q->tqe_th->th_seq += i;
			q->tqe_len -= i;
			m_adj(q->tqe_m, i);
			break;
		}

		nq = LIST_NEXT(q, tqe_q);
		LIST_REMOVE(q, tqe_q);
		m_freem(q->tqe_m);
		uma_zfree(V_tcp_reass_zone, q);
		tp->t_segqlen--;
		q = nq;
	}

	/* Insert the new segment queue entry into place. */
	te->tqe_m = m;
	te->tqe_th = th;
	te->tqe_len = *tlenp;

	if (p == NULL) {
		LIST_INSERT_HEAD(&tp->t_segq, te, tqe_q);
	} else {
		KASSERT(te != &tqs, ("%s: temporary stack based entry not "
		    "first element in queue", __func__));
		LIST_INSERT_AFTER(p, te, tqe_q);
	}

present:
	/*
	 * Present data to user, advancing rcv_nxt through
	 * completed sequence space.
	 */
	if (!TCPS_HAVEESTABLISHED(tp->t_state))
		return (0);
	q = LIST_FIRST(&tp->t_segq);
	if (!q || q->tqe_th->th_seq != tp->rcv_nxt)
		return (0);
	SOCKBUF_LOCK(&so->so_rcv);
	do {
		tp->rcv_nxt += q->tqe_len;
		flags = q->tqe_th->th_flags & TH_FIN;
		nq = LIST_NEXT(q, tqe_q);
		LIST_REMOVE(q, tqe_q);
		if (so->so_rcv.sb_state & SBS_CANTRCVMORE)
			m_freem(q->tqe_m);
		else
			sbappendstream_locked(&so->so_rcv, q->tqe_m);
		if (q != &tqs)
			uma_zfree(V_tcp_reass_zone, q);
		tp->t_segqlen--;
		q = nq;
	} while (q && q->tqe_th->th_seq == tp->rcv_nxt);
	ND6_HINT(tp);
	sorwakeup_locked(so);
	return (flags);
}