summaryrefslogtreecommitdiffstats
path: root/freebsd/sys/kern/uipc_mbuf2.c
blob: a2e4e3957691deb191652e449bdd1c2398e0735e (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
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
#include <machine/rtems-bsd-kernel-space.h>

/*	$KAME: uipc_mbuf2.c,v 1.31 2001/11/28 11:08:53 itojun Exp $	*/
/*	$NetBSD: uipc_mbuf.c,v 1.40 1999/04/01 00:23:25 thorpej Exp $	*/

/*-
 * Copyright (C) 1999 WIDE Project.
 * 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.
 * 3. Neither the name of the project 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 PROJECT 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 PROJECT 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.
 */
/*-
 * Copyright (c) 1982, 1986, 1988, 1991, 1993
 *	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.
 *
 *	@(#)uipc_mbuf.c	8.4 (Berkeley) 2/14/95
 */

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

/*#define PULLDOWN_DEBUG*/

#include <rtems/bsd/sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <rtems/bsd/sys/lock.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/mutex.h>

#include <security/mac/mac_framework.h>

static MALLOC_DEFINE(M_PACKET_TAGS, MBUF_TAG_MEM_NAME,
    "packet-attached information");

/* can't call it m_dup(), as freebsd[34] uses m_dup() with different arg */
static struct mbuf *m_dup1(struct mbuf *, int, int, int);

/*
 * ensure that [off, off + len) is contiguous on the mbuf chain "m".
 * packet chain before "off" is kept untouched.
 * if offp == NULL, the target will start at <retval, 0> on resulting chain.
 * if offp != NULL, the target will start at <retval, *offp> on resulting chain.
 *
 * on error return (NULL return value), original "m" will be freed.
 *
 * XXX: M_TRAILINGSPACE/M_LEADINGSPACE only permitted on writable ext_buf.
 */
struct mbuf *
m_pulldown(struct mbuf *m, int off, int len, int *offp)
{
	struct mbuf *n, *o;
	int hlen, tlen, olen;
	int writable;

	/* check invalid arguments. */
	if (m == NULL)
		panic("m == NULL in m_pulldown()");
	if (len > MCLBYTES) {
		m_freem(m);
		return NULL;	/* impossible */
	}

#ifdef PULLDOWN_DEBUG
    {
	struct mbuf *t;
	printf("before:");
	for (t = m; t; t = t->m_next)
		printf(" %d", t->m_len);
	printf("\n");
    }
#endif
	n = m;
	while (n != NULL && off > 0) {
		if (n->m_len > off)
			break;
		off -= n->m_len;
		n = n->m_next;
	}
	/* be sure to point non-empty mbuf */
	while (n != NULL && n->m_len == 0)
		n = n->m_next;
	if (!n) {
		m_freem(m);
		return NULL;	/* mbuf chain too short */
	}

	/*
	 * XXX: This code is flawed because it considers a "writable" mbuf
	 *      data region to require all of the following:
	 *	  (i) mbuf _has_ to have M_EXT set; if it is just a regular
	 *	      mbuf, it is still not considered "writable."
	 *	  (ii) since mbuf has M_EXT, the ext_type _has_ to be
	 *	       EXT_CLUSTER. Anything else makes it non-writable.
	 *	  (iii) M_WRITABLE() must evaluate true.
	 *      Ideally, the requirement should only be (iii).
	 *
	 * If we're writable, we're sure we're writable, because the ref. count
	 * cannot increase from 1, as that would require posession of mbuf
	 * n by someone else (which is impossible). However, if we're _not_
	 * writable, we may eventually become writable )if the ref. count drops
	 * to 1), but we'll fail to notice it unless we re-evaluate
	 * M_WRITABLE(). For now, we only evaluate once at the beginning and
	 * live with this.
	 */
	/*
	 * XXX: This is dumb. If we're just a regular mbuf with no M_EXT,
	 *      then we're not "writable," according to this code.
	 */
	writable = 0;
	if ((n->m_flags & M_EXT) == 0 ||
	    (n->m_ext.ext_type == EXT_CLUSTER && M_WRITABLE(n)))
		writable = 1;

	/*
	 * the target data is on <n, off>.
	 * if we got enough data on the mbuf "n", we're done.
	 */
	if ((off == 0 || offp) && len <= n->m_len - off && writable)
		goto ok;

	/*
	 * when len <= n->m_len - off and off != 0, it is a special case.
	 * len bytes from <n, off> sits in single mbuf, but the caller does
	 * not like the starting position (off).
	 * chop the current mbuf into two pieces, set off to 0.
	 */
	if (len <= n->m_len - off) {
		o = m_dup1(n, off, n->m_len - off, M_DONTWAIT);
		if (o == NULL) {
			m_freem(m);
			return NULL;	/* ENOBUFS */
		}
		n->m_len = off;
		o->m_next = n->m_next;
		n->m_next = o;
		n = n->m_next;
		off = 0;
		goto ok;
	}

	/*
	 * we need to take hlen from <n, off> and tlen from <n->m_next, 0>,
	 * and construct contiguous mbuf with m_len == len.
	 * note that hlen + tlen == len, and tlen > 0.
	 */
	hlen = n->m_len - off;
	tlen = len - hlen;

	/*
	 * ensure that we have enough trailing data on mbuf chain.
	 * if not, we can do nothing about the chain.
	 */
	olen = 0;
	for (o = n->m_next; o != NULL; o = o->m_next)
		olen += o->m_len;
	if (hlen + olen < len) {
		m_freem(m);
		return NULL;	/* mbuf chain too short */
	}

	/*
	 * easy cases first.
	 * we need to use m_copydata() to get data from <n->m_next, 0>.
	 */
	if ((off == 0 || offp) && M_TRAILINGSPACE(n) >= tlen
	 && writable) {
		m_copydata(n->m_next, 0, tlen, mtod(n, caddr_t) + n->m_len);
		n->m_len += tlen;
		m_adj(n->m_next, tlen);
		goto ok;
	}
	if ((off == 0 || offp) && M_LEADINGSPACE(n->m_next) >= hlen
	 && writable) {
		n->m_next->m_data -= hlen;
		n->m_next->m_len += hlen;
		bcopy(mtod(n, caddr_t) + off, mtod(n->m_next, caddr_t), hlen);
		n->m_len -= hlen;
		n = n->m_next;
		off = 0;
		goto ok;
	}

	/*
	 * now, we need to do the hard way.  don't m_copy as there's no room
	 * on both end.
	 */
	if (len > MLEN)
		o = m_getcl(M_DONTWAIT, m->m_type, 0);
	else
		o = m_get(M_DONTWAIT, m->m_type);
	if (!o) {
		m_freem(m);
		return NULL;	/* ENOBUFS */
	}
	/* get hlen from <n, off> into <o, 0> */
	o->m_len = hlen;
	bcopy(mtod(n, caddr_t) + off, mtod(o, caddr_t), hlen);
	n->m_len -= hlen;
	/* get tlen from <n->m_next, 0> into <o, hlen> */
	m_copydata(n->m_next, 0, tlen, mtod(o, caddr_t) + o->m_len);
	o->m_len += tlen;
	m_adj(n->m_next, tlen);
	o->m_next = n->m_next;
	n->m_next = o;
	n = o;
	off = 0;

ok:
#ifdef PULLDOWN_DEBUG
    {
	struct mbuf *t;
	printf("after:");
	for (t = m; t; t = t->m_next)
		printf("%c%d", t == n ? '*' : ' ', t->m_len);
	printf(" (off=%d)\n", off);
    }
#endif
	if (offp)
		*offp = off;
	return n;
}

static struct mbuf *
m_dup1(struct mbuf *m, int off, int len, int wait)
{
	struct mbuf *n;
	int copyhdr;

	if (len > MCLBYTES)
		return NULL;
	if (off == 0 && (m->m_flags & M_PKTHDR) != 0)
		copyhdr = 1;
	else
		copyhdr = 0;
	if (len >= MINCLSIZE) {
		if (copyhdr == 1)
			n = m_getcl(wait, m->m_type, M_PKTHDR);
		else
			n = m_getcl(wait, m->m_type, 0);
	} else {
		if (copyhdr == 1)
			n = m_gethdr(wait, m->m_type);
		else
			n = m_get(wait, m->m_type);
	}
	if (!n)
		return NULL; /* ENOBUFS */

	if (copyhdr && !m_dup_pkthdr(n, m, wait)) {
		m_free(n);
		return NULL;
	}
	m_copydata(m, off, len, mtod(n, caddr_t));
	n->m_len = len;
	return n;
}

/* Free a packet tag. */
void
m_tag_free_default(struct m_tag *t)
{
#ifdef MAC
	if (t->m_tag_id == PACKET_TAG_MACLABEL)
		mac_mbuf_tag_destroy(t);
#endif
	free(t, M_PACKET_TAGS);
}

/* Get a packet tag structure along with specified data following. */
struct m_tag *
m_tag_alloc(u_int32_t cookie, int type, int len, int wait)
{
	struct m_tag *t;

	MBUF_CHECKSLEEP(wait);
	if (len < 0)
		return NULL;
	t = malloc(len + sizeof(struct m_tag), M_PACKET_TAGS, wait);
	if (t == NULL)
		return NULL;
	m_tag_setup(t, cookie, type, len);
	t->m_tag_free = m_tag_free_default;
	return t;
}

/* Unlink and free a packet tag. */
void
m_tag_delete(struct mbuf *m, struct m_tag *t)
{

	KASSERT(m && t, ("m_tag_delete: null argument, m %p t %p", m, t));
	m_tag_unlink(m, t);
	m_tag_free(t);
}

/* Unlink and free a packet tag chain, starting from given tag. */
void
m_tag_delete_chain(struct mbuf *m, struct m_tag *t)
{
	struct m_tag *p, *q;

	KASSERT(m, ("m_tag_delete_chain: null mbuf"));
	if (t != NULL)
		p = t;
	else
		p = SLIST_FIRST(&m->m_pkthdr.tags);
	if (p == NULL)
		return;
	while ((q = SLIST_NEXT(p, m_tag_link)) != NULL)
		m_tag_delete(m, q);
	m_tag_delete(m, p);
}

/*
 * Strip off all tags that would normally vanish when
 * passing through a network interface.  Only persistent
 * tags will exist after this; these are expected to remain
 * so long as the mbuf chain exists, regardless of the
 * path the mbufs take.
 */
void
m_tag_delete_nonpersistent(struct mbuf *m)
{
	struct m_tag *p, *q;

	SLIST_FOREACH_SAFE(p, &m->m_pkthdr.tags, m_tag_link, q)
		if ((p->m_tag_id & MTAG_PERSISTENT) == 0)
			m_tag_delete(m, p);
}

/* Find a tag, starting from a given position. */
struct m_tag *
m_tag_locate(struct mbuf *m, u_int32_t cookie, int type, struct m_tag *t)
{
	struct m_tag *p;

	KASSERT(m, ("m_tag_locate: null mbuf"));
	if (t == NULL)
		p = SLIST_FIRST(&m->m_pkthdr.tags);
	else
		p = SLIST_NEXT(t, m_tag_link);
	while (p != NULL) {
		if (p->m_tag_cookie == cookie && p->m_tag_id == type)
			return p;
		p = SLIST_NEXT(p, m_tag_link);
	}
	return NULL;
}

/* Copy a single tag. */
struct m_tag *
m_tag_copy(struct m_tag *t, int how)
{
	struct m_tag *p;

	MBUF_CHECKSLEEP(how);
	KASSERT(t, ("m_tag_copy: null tag"));
	p = m_tag_alloc(t->m_tag_cookie, t->m_tag_id, t->m_tag_len, how);
	if (p == NULL)
		return (NULL);
#ifdef MAC
	/*
	 * XXXMAC: we should probably pass off the initialization, and
	 * copying here?  can we hide that PACKET_TAG_MACLABEL is
	 * special from the mbuf code?
	 */
	if (t->m_tag_id == PACKET_TAG_MACLABEL) {
		if (mac_mbuf_tag_init(p, how) != 0) {
			m_tag_free(p);
			return (NULL);
		}
		mac_mbuf_tag_copy(t, p);
	} else
#endif
		bcopy(t + 1, p + 1, t->m_tag_len); /* Copy the data */
	return p;
}

/*
 * Copy two tag chains. The destination mbuf (to) loses any attached
 * tags even if the operation fails. This should not be a problem, as
 * m_tag_copy_chain() is typically called with a newly-allocated
 * destination mbuf.
 */
int
m_tag_copy_chain(struct mbuf *to, struct mbuf *from, int how)
{
	struct m_tag *p, *t, *tprev = NULL;

	MBUF_CHECKSLEEP(how);
	KASSERT(to && from,
		("m_tag_copy_chain: null argument, to %p from %p", to, from));
	m_tag_delete_chain(to, NULL);
	SLIST_FOREACH(p, &from->m_pkthdr.tags, m_tag_link) {
		t = m_tag_copy(p, how);
		if (t == NULL) {
			m_tag_delete_chain(to, NULL);
			return 0;
		}
		if (tprev == NULL)
			SLIST_INSERT_HEAD(&to->m_pkthdr.tags, t, m_tag_link);
		else
			SLIST_INSERT_AFTER(tprev, t, m_tag_link);
		tprev = t;
	}
	return 1;
}