freebsd-nq/sys/net/if_disc.c
Sam Leffler d1dd20be6e Locking for updates to routing table entries. Each rtentry gets a mutex
that covers updates to the contents.  Note this is separate from holding
a reference and/or locking the routing table itself.

Other/related changes:

o rtredirect loses the final parameter by which an rtentry reference
  may be returned; this was never used and added unwarranted complexity
  for locking.
o minor style cleanups to routing code (e.g. ansi-fy function decls)
o remove the logic to bump the refcnt on the parent of cloned routes,
  we assume the parent will remain as long as the clone; doing this avoids
  a circularity in locking during delete
o convert some timeouts to MPSAFE callouts

Notes:

1. rt_mtx in struct rtentry is guarded by #ifdef _KERNEL as user-level
   applications cannot/do-no know about mutex's.  Doing this requires
   that the mutex be the last element in the structure.  A better solution
   is to introduce an externalized version of struct rtentry but this is
   a major task because of the intertwining of rtentry and other data
   structures that are visible to user applications.
2. There are known LOR's that are expected to go away with forthcoming
   work to eliminate many held references.  If not these will be resolved
   prior to release.
3. ATM changes are untested.

Sponsored by:	FreeBSD Foundation
Obtained from:	BSD/OS (partly)
2003-10-04 03:44:50 +00:00

257 lines
6.1 KiB
C

/*
* Copyright (c) 1982, 1986, 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.
*
* From: @(#)if_loop.c 8.1 (Berkeley) 6/10/93
* $FreeBSD$
*/
/*
* Discard interface driver for protocol testing and timing.
* (Based on the loopback.)
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/module.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/sockio.h>
#include <net/if.h>
#include <net/if_types.h>
#include <net/route.h>
#include <net/bpf.h>
#include "opt_inet.h"
#include "opt_inet6.h"
#ifdef TINY_DSMTU
#define DSMTU (1024+512)
#else
#define DSMTU 65532
#endif
#define DISCNAME "disc"
struct disc_softc {
struct ifnet sc_if; /* must be first */
LIST_ENTRY(disc_softc) sc_list;
};
static int discoutput(struct ifnet *, struct mbuf *,
struct sockaddr *, struct rtentry *);
static void discrtrequest(int, struct rtentry *, struct rt_addrinfo *);
static int discioctl(struct ifnet *, u_long, caddr_t);
static int disc_clone_create(struct if_clone *, int);
static void disc_clone_destroy(struct ifnet *);
static MALLOC_DEFINE(M_DISC, DISCNAME, "Discard interface");
static LIST_HEAD(, disc_softc) disc_softc_list;
static struct if_clone disc_cloner = IF_CLONE_INITIALIZER(DISCNAME,
disc_clone_create, disc_clone_destroy, 0, IF_MAXUNIT);
static int
disc_clone_create(struct if_clone *ifc, int unit)
{
struct ifnet *ifp;
struct disc_softc *sc;
sc = malloc(sizeof(struct disc_softc), M_DISC, M_WAITOK);
bzero(sc, sizeof(struct disc_softc));
ifp = &sc->sc_if;
ifp->if_softc = sc;
ifp->if_name = DISCNAME;
ifp->if_unit = unit;
ifp->if_mtu = DSMTU;
ifp->if_flags = IFF_LOOPBACK | IFF_MULTICAST;
ifp->if_ioctl = discioctl;
ifp->if_output = discoutput;
ifp->if_type = IFT_LOOP;
ifp->if_hdrlen = 0;
ifp->if_addrlen = 0;
ifp->if_snd.ifq_maxlen = 20;
if_attach(ifp);
bpfattach(ifp, DLT_NULL, sizeof(u_int));
LIST_INSERT_HEAD(&disc_softc_list, sc, sc_list);
return (0);
}
static void
disc_clone_destroy(struct ifnet *ifp)
{
struct disc_softc *sc;
sc = ifp->if_softc;
LIST_REMOVE(sc, sc_list);
bpfdetach(ifp);
if_detach(ifp);
free(sc, M_DISC);
}
static int
disc_modevent(module_t mod, int type, void *data)
{
switch (type) {
case MOD_LOAD:
LIST_INIT(&disc_softc_list);
if_clone_attach(&disc_cloner);
break;
case MOD_UNLOAD:
if_clone_detach(&disc_cloner);
while (!LIST_EMPTY(&disc_softc_list))
disc_clone_destroy(
&LIST_FIRST(&disc_softc_list)->sc_if);
break;
}
return 0;
}
static moduledata_t disc_mod = {
"if_disc",
disc_modevent,
NULL
};
DECLARE_MODULE(if_disc, disc_mod, SI_SUB_PSEUDO, SI_ORDER_ANY);
static int
discoutput(struct ifnet *ifp, struct mbuf *m, struct sockaddr *dst,
struct rtentry *rt)
{
M_ASSERTPKTHDR(m);
/* BPF write needs to be handled specially */
if (dst->sa_family == AF_UNSPEC) {
dst->sa_family = *(mtod(m, int *));
m->m_len -= sizeof(int);
m->m_pkthdr.len -= sizeof(int);
m->m_data += sizeof(int);
}
if (ifp->if_bpf) {
/*
* We need to prepend the address family as
* a four byte field. Cons up a dummy header
* to pacify bpf. This is safe because bpf
* will only read from the mbuf (i.e., it won't
* try to free it or keep a pointer a to it).
*/
struct mbuf m0;
u_int af = dst->sa_family;
m0.m_next = m;
m0.m_len = 4;
m0.m_data = (char *)&af;
BPF_MTAP(ifp, &m0);
}
m->m_pkthdr.rcvif = ifp;
ifp->if_opackets++;
ifp->if_obytes += m->m_pkthdr.len;
m_freem(m);
return 0;
}
/* ARGSUSED */
static void
discrtrequest(int cmd, struct rtentry *rt, struct rt_addrinfo *info)
{
RT_LOCK_ASSERT(rt);
if (rt)
rt->rt_rmx.rmx_mtu = DSMTU;
}
/*
* Process an ioctl request.
*/
static int
discioctl(struct ifnet *ifp, u_long cmd, caddr_t data)
{
struct ifaddr *ifa;
struct ifreq *ifr = (struct ifreq *)data;
int error = 0;
switch (cmd) {
case SIOCSIFADDR:
ifp->if_flags |= IFF_UP;
ifa = (struct ifaddr *)data;
if (ifa != 0)
ifa->ifa_rtrequest = discrtrequest;
/*
* Everything else is done at a higher level.
*/
break;
case SIOCADDMULTI:
case SIOCDELMULTI:
if (ifr == 0) {
error = EAFNOSUPPORT; /* XXX */
break;
}
switch (ifr->ifr_addr.sa_family) {
#ifdef INET
case AF_INET:
break;
#endif
#ifdef INET6
case AF_INET6:
break;
#endif
default:
error = EAFNOSUPPORT;
break;
}
break;
case SIOCSIFMTU:
ifp->if_mtu = ifr->ifr_mtu;
break;
default:
error = EINVAL;
}
return (error);
}