df0e25bf6c
that should be better. The old code counted references to mbuf clusters by using the offset of the cluster from the start of memory allocated for mbufs and clusters as an index into an array of chars, which did the reference counting. If the external storage was not a cluster then reference counting had to be done by the code using that external storage. NetBSD's system of linked lists of mbufs was cosidered, but Alfred felt it would have locking issues when the kernel was made more SMP friendly. The system implimented uses a pool of unions to track external storage. The union contains an int for counting the references and a pointer for forming a free list. The reference counts are incremented and decremented atomically and so should be SMP friendly. This system can track reference counts for any sort of external storage. Access to the reference counting stuff is now through macros defined in mbuf.h, so it should be easier to make changes to the system in the future. The possibility of storing the reference count in one of the referencing mbufs was considered, but was rejected 'cos it would often leave extra mbufs allocated. Storing the reference count in the cluster was also considered, but because the external storage may not be a cluster this isn't an option. The size of the pool of reference counters is available in the stats provided by "netstat -m". PR: 19866 Submitted by: Bosko Milekic <bmilekic@dsuper.net> Reviewed by: alfred (glanced at by others on -net)
333 lines
8.9 KiB
C
333 lines
8.9 KiB
C
/* $FreeBSD$ */
|
|
/* $KAME: uipc_mbuf2.c,v 1.15 2000/02/22 14:01:37 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.
|
|
* 3. All advertising materials mentioning features or use of this software
|
|
* must display the following acknowledgement:
|
|
* This product includes software developed by the University of
|
|
* California, Berkeley and its contributors.
|
|
* 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
|
|
*/
|
|
|
|
/*#define PULLDOWN_DEBUG*/
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/systm.h>
|
|
#include <sys/proc.h>
|
|
#include <sys/malloc.h>
|
|
#include <sys/mbuf.h>
|
|
|
|
/*
|
|
* 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 on shared cluster (sharedcluster)
|
|
*/
|
|
struct mbuf *
|
|
m_pulldown(m, off, len, offp)
|
|
struct mbuf *m;
|
|
int off, len;
|
|
int *offp;
|
|
{
|
|
struct mbuf *n, *o;
|
|
int hlen, tlen, olen;
|
|
int sharedcluster;
|
|
|
|
/* 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 */
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
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_copym(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 ((n->m_flags & M_EXT) == 0)
|
|
sharedcluster = 0;
|
|
else {
|
|
if (n->m_ext.ext_free)
|
|
sharedcluster = 1;
|
|
else if (MEXT_IS_REF(n))
|
|
sharedcluster = 1;
|
|
else
|
|
sharedcluster = 0;
|
|
}
|
|
if ((off == 0 || offp) && M_TRAILINGSPACE(n) >= tlen
|
|
&& !sharedcluster) {
|
|
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
|
|
&& !sharedcluster) {
|
|
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.
|
|
*/
|
|
MGET(o, M_DONTWAIT, m->m_type);
|
|
if (o == NULL) {
|
|
m_freem(m);
|
|
return NULL; /* ENOBUFS */
|
|
}
|
|
if (len > MHLEN) { /* use MHLEN just for safety */
|
|
MCLGET(o, M_DONTWAIT);
|
|
if ((o->m_flags & M_EXT) == 0) {
|
|
m_freem(m);
|
|
m_free(o);
|
|
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;
|
|
}
|
|
|
|
/*
|
|
* pkthdr.aux chain manipulation.
|
|
* we don't allow clusters at this moment.
|
|
*/
|
|
struct mbuf *
|
|
m_aux_add(m, af, type)
|
|
struct mbuf *m;
|
|
int af, type;
|
|
{
|
|
struct mbuf *n;
|
|
struct mauxtag *t;
|
|
|
|
if ((m->m_flags & M_PKTHDR) == 0)
|
|
return NULL;
|
|
|
|
n = m_aux_find(m, af, type);
|
|
if (n)
|
|
return n;
|
|
|
|
MGET(n, M_DONTWAIT, m->m_type);
|
|
if (n == NULL)
|
|
return NULL;
|
|
|
|
t = mtod(n, struct mauxtag *);
|
|
t->af = af;
|
|
t->type = type;
|
|
n->m_data += sizeof(struct mauxtag);
|
|
n->m_len = 0;
|
|
n->m_next = m->m_pkthdr.aux;
|
|
m->m_pkthdr.aux = n;
|
|
return n;
|
|
}
|
|
|
|
struct mbuf *
|
|
m_aux_find(m, af, type)
|
|
struct mbuf *m;
|
|
int af, type;
|
|
{
|
|
struct mbuf *n;
|
|
struct mauxtag *t;
|
|
|
|
if ((m->m_flags & M_PKTHDR) == 0)
|
|
return NULL;
|
|
|
|
for (n = m->m_pkthdr.aux; n; n = n->m_next) {
|
|
t = (struct mauxtag *)n->m_dat;
|
|
if (t->af == af && t->type == type)
|
|
return n;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
void
|
|
m_aux_delete(m, victim)
|
|
struct mbuf *m;
|
|
struct mbuf *victim;
|
|
{
|
|
struct mbuf *n, *prev, *next;
|
|
struct mauxtag *t;
|
|
|
|
if ((m->m_flags & M_PKTHDR) == 0)
|
|
return;
|
|
|
|
prev = NULL;
|
|
n = m->m_pkthdr.aux;
|
|
while (n) {
|
|
t = (struct mauxtag *)n->m_dat;
|
|
next = n->m_next;
|
|
if (n == victim) {
|
|
if (prev)
|
|
prev->m_next = n->m_next;
|
|
else
|
|
m->m_pkthdr.aux = n->m_next;
|
|
n->m_next = NULL;
|
|
m_free(n);
|
|
} else
|
|
prev = n;
|
|
n = next;
|
|
}
|
|
}
|