16d878cc99
(1) bpf peer attaches to interface netif0
(2) Packet is received by netif0
(3) ifp->if_bpf pointer is checked and handed off to bpf
(4) bpf peer detaches from netif0 resulting in ifp->if_bpf being
initialized to NULL.
(5) ifp->if_bpf is dereferenced by bpf machinery
(6) Kaboom
This race condition likely explains the various different kernel panics
reported around sending SIGINT to tcpdump or dhclient processes. But really
this race can result in kernel panics anywhere you have frequent bpf attach
and detach operations with high packet per second load.
Summary of changes:
- Remove the bpf interface's "driverp" member
- When we attach bpf interfaces, we now set the ifp->if_bpf member to the
bpf interface structure. Once this is done, ifp->if_bpf should never be
NULL. [1]
- Introduce bpf_peers_present function, an inline operation which will do
a lockless read bpf peer list associated with the interface. It should
be noted that the bpf code will pickup the bpf_interface lock before adding
or removing bpf peers. This should serialize the access to the bpf descriptor
list, removing the race.
- Expose the bpf_if structure in bpf.h so that the bpf_peers_present function
can use it. This also removes the struct bpf_if; hack that was there.
- Adjust all consumers of the raw if_bpf structure to use bpf_peers_present
Now what happens is:
(1) Packet is received by netif0
(2) Check to see if bpf descriptor list is empty
(3) Pickup the bpf interface lock
(4) Hand packet off to process
From the attach/detach side:
(1) Pickup the bpf interface lock
(2) Add/remove from bpf descriptor list
Now that we are storing the bpf interface structure with the ifnet, there is
is no need to walk the bpf interface list to locate the correct bpf interface.
We now simply look up the interface, and initialize the pointer. This has a
nice side effect of changing a bpf interface attach operation from O(N) (where
N is the number of bpf interfaces), to O(1).
[1] From now on, we can no longer check ifp->if_bpf to tell us whether or
not we have any bpf peers that might be interested in receiving packets.
In collaboration with: sam@
MFC after: 1 month
398 lines
8.6 KiB
C
398 lines
8.6 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.
|
|
* 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.
|
|
*
|
|
* @(#)if_loop.c 8.2 (Berkeley) 1/9/95
|
|
* $FreeBSD$
|
|
*/
|
|
|
|
/*
|
|
* Loopback interface driver for protocol testing and timing.
|
|
*/
|
|
|
|
#include "opt_atalk.h"
|
|
#include "opt_inet.h"
|
|
#include "opt_inet6.h"
|
|
#include "opt_ipx.h"
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/systm.h>
|
|
#include <sys/kernel.h>
|
|
#include <sys/malloc.h>
|
|
#include <sys/mbuf.h>
|
|
#include <sys/module.h>
|
|
#include <machine/bus.h>
|
|
#include <sys/rman.h>
|
|
#include <sys/socket.h>
|
|
#include <sys/sockio.h>
|
|
#include <sys/sysctl.h>
|
|
|
|
#include <net/if.h>
|
|
#include <net/if_clone.h>
|
|
#include <net/if_types.h>
|
|
#include <net/netisr.h>
|
|
#include <net/route.h>
|
|
#include <net/bpf.h>
|
|
#include <net/bpfdesc.h>
|
|
|
|
#ifdef INET
|
|
#include <netinet/in.h>
|
|
#include <netinet/in_var.h>
|
|
#endif
|
|
|
|
#ifdef IPX
|
|
#include <netipx/ipx.h>
|
|
#include <netipx/ipx_if.h>
|
|
#endif
|
|
|
|
#ifdef INET6
|
|
#ifndef INET
|
|
#include <netinet/in.h>
|
|
#endif
|
|
#include <netinet6/in6_var.h>
|
|
#include <netinet/ip6.h>
|
|
#endif
|
|
|
|
#ifdef NETATALK
|
|
#include <netatalk/at.h>
|
|
#include <netatalk/at_var.h>
|
|
#endif
|
|
|
|
#ifdef TINY_LOMTU
|
|
#define LOMTU (1024+512)
|
|
#elif defined(LARGE_LOMTU)
|
|
#define LOMTU 131072
|
|
#else
|
|
#define LOMTU 16384
|
|
#endif
|
|
|
|
#define LONAME "lo"
|
|
|
|
struct lo_softc {
|
|
struct ifnet *sc_ifp;
|
|
LIST_ENTRY(lo_softc) sc_next;
|
|
};
|
|
|
|
int loioctl(struct ifnet *, u_long, caddr_t);
|
|
static void lortrequest(int, struct rtentry *, struct rt_addrinfo *);
|
|
int looutput(struct ifnet *ifp, struct mbuf *m,
|
|
struct sockaddr *dst, struct rtentry *rt);
|
|
static int lo_clone_create(struct if_clone *, int);
|
|
static void lo_clone_destroy(struct ifnet *);
|
|
|
|
struct ifnet *loif = NULL; /* Used externally */
|
|
|
|
static MALLOC_DEFINE(M_LO, LONAME, "Loopback Interface");
|
|
|
|
static struct mtx lo_mtx;
|
|
static LIST_HEAD(lo_list, lo_softc) lo_list;
|
|
|
|
IFC_SIMPLE_DECLARE(lo, 1);
|
|
|
|
static void
|
|
lo_clone_destroy(ifp)
|
|
struct ifnet *ifp;
|
|
{
|
|
struct lo_softc *sc;
|
|
|
|
sc = ifp->if_softc;
|
|
|
|
/* XXX: destroying lo0 will lead to panics. */
|
|
KASSERT(loif != ifp, ("%s: destroying lo0", __func__));
|
|
|
|
mtx_lock(&lo_mtx);
|
|
LIST_REMOVE(sc, sc_next);
|
|
mtx_unlock(&lo_mtx);
|
|
bpfdetach(ifp);
|
|
if_detach(ifp);
|
|
if_free(ifp);
|
|
free(sc, M_LO);
|
|
}
|
|
|
|
static int
|
|
lo_clone_create(ifc, unit)
|
|
struct if_clone *ifc;
|
|
int unit;
|
|
{
|
|
struct ifnet *ifp;
|
|
struct lo_softc *sc;
|
|
|
|
MALLOC(sc, struct lo_softc *, sizeof(*sc), M_LO, M_WAITOK | M_ZERO);
|
|
ifp = sc->sc_ifp = if_alloc(IFT_LOOP);
|
|
if (ifp == NULL) {
|
|
free(sc, M_LO);
|
|
return (ENOSPC);
|
|
}
|
|
|
|
if_initname(ifp, ifc->ifc_name, unit);
|
|
ifp->if_mtu = LOMTU;
|
|
ifp->if_flags = IFF_LOOPBACK | IFF_MULTICAST;
|
|
ifp->if_ioctl = loioctl;
|
|
ifp->if_output = looutput;
|
|
ifp->if_snd.ifq_maxlen = ifqmaxlen;
|
|
ifp->if_softc = sc;
|
|
if_attach(ifp);
|
|
bpfattach(ifp, DLT_NULL, sizeof(u_int32_t));
|
|
mtx_lock(&lo_mtx);
|
|
LIST_INSERT_HEAD(&lo_list, sc, sc_next);
|
|
mtx_unlock(&lo_mtx);
|
|
if (loif == NULL)
|
|
loif = ifp;
|
|
|
|
return (0);
|
|
}
|
|
|
|
static int
|
|
loop_modevent(module_t mod, int type, void *data)
|
|
{
|
|
switch (type) {
|
|
case MOD_LOAD:
|
|
mtx_init(&lo_mtx, "lo_mtx", NULL, MTX_DEF);
|
|
LIST_INIT(&lo_list);
|
|
if_clone_attach(&lo_cloner);
|
|
break;
|
|
case MOD_UNLOAD:
|
|
printf("loop module unload - not possible for this module type\n");
|
|
return EINVAL;
|
|
default:
|
|
return EOPNOTSUPP;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static moduledata_t loop_mod = {
|
|
"loop",
|
|
loop_modevent,
|
|
0
|
|
};
|
|
|
|
DECLARE_MODULE(loop, loop_mod, SI_SUB_PROTO_IFATTACHDOMAIN, SI_ORDER_ANY);
|
|
|
|
int
|
|
looutput(ifp, m, dst, rt)
|
|
struct ifnet *ifp;
|
|
register struct mbuf *m;
|
|
struct sockaddr *dst;
|
|
register struct rtentry *rt;
|
|
{
|
|
u_int32_t af;
|
|
|
|
M_ASSERTPKTHDR(m); /* check if we have the packet header */
|
|
|
|
if (rt && rt->rt_flags & (RTF_REJECT|RTF_BLACKHOLE)) {
|
|
m_freem(m);
|
|
return (rt->rt_flags & RTF_BLACKHOLE ? 0 :
|
|
rt->rt_flags & RTF_HOST ? EHOSTUNREACH : ENETUNREACH);
|
|
}
|
|
|
|
ifp->if_opackets++;
|
|
ifp->if_obytes += m->m_pkthdr.len;
|
|
|
|
/* BPF writes need to be handled specially. */
|
|
if (dst->sa_family == AF_UNSPEC) {
|
|
bcopy(dst->sa_data, &af, sizeof(af));
|
|
dst->sa_family = af;
|
|
}
|
|
|
|
#if 1 /* XXX */
|
|
switch (dst->sa_family) {
|
|
case AF_INET:
|
|
case AF_INET6:
|
|
case AF_IPX:
|
|
case AF_APPLETALK:
|
|
break;
|
|
default:
|
|
printf("looutput: af=%d unexpected\n", dst->sa_family);
|
|
m_freem(m);
|
|
return (EAFNOSUPPORT);
|
|
}
|
|
#endif
|
|
return(if_simloop(ifp, m, dst->sa_family, 0));
|
|
}
|
|
|
|
/*
|
|
* if_simloop()
|
|
*
|
|
* This function is to support software emulation of hardware loopback,
|
|
* i.e., for interfaces with the IFF_SIMPLEX attribute. Since they can't
|
|
* hear their own broadcasts, we create a copy of the packet that we
|
|
* would normally receive via a hardware loopback.
|
|
*
|
|
* This function expects the packet to include the media header of length hlen.
|
|
*/
|
|
|
|
int
|
|
if_simloop(ifp, m, af, hlen)
|
|
struct ifnet *ifp;
|
|
struct mbuf *m;
|
|
int af;
|
|
int hlen;
|
|
{
|
|
int isr;
|
|
|
|
M_ASSERTPKTHDR(m);
|
|
m_tag_delete_nonpersistent(m);
|
|
m->m_pkthdr.rcvif = ifp;
|
|
|
|
/* Let BPF see incoming packet */
|
|
if (bpf_peers_present(ifp->if_bpf)) {
|
|
if (ifp->if_bpf->bif_dlt == DLT_NULL) {
|
|
u_int32_t af1 = af; /* XXX beware sizeof(af) != 4 */
|
|
/*
|
|
* We need to prepend the address family.
|
|
*/
|
|
bpf_mtap2(ifp->if_bpf, &af1, sizeof(af1), m);
|
|
} else
|
|
bpf_mtap(ifp->if_bpf, m);
|
|
}
|
|
|
|
/* Strip away media header */
|
|
if (hlen > 0) {
|
|
m_adj(m, hlen);
|
|
#if defined(__ia64__) || defined(__sparc64__)
|
|
/*
|
|
* Some archs do not like unaligned data, so
|
|
* we move data down in the first mbuf.
|
|
*/
|
|
if (mtod(m, vm_offset_t) & 3) {
|
|
KASSERT(hlen >= 3, ("if_simloop: hlen too small"));
|
|
bcopy(m->m_data,
|
|
(char *)(mtod(m, vm_offset_t)
|
|
- (mtod(m, vm_offset_t) & 3)),
|
|
m->m_len);
|
|
m->m_data -= (mtod(m,vm_offset_t) & 3);
|
|
}
|
|
#endif
|
|
}
|
|
|
|
/* Deliver to upper layer protocol */
|
|
switch (af) {
|
|
#ifdef INET
|
|
case AF_INET:
|
|
isr = NETISR_IP;
|
|
break;
|
|
#endif
|
|
#ifdef INET6
|
|
case AF_INET6:
|
|
m->m_flags |= M_LOOP;
|
|
isr = NETISR_IPV6;
|
|
break;
|
|
#endif
|
|
#ifdef IPX
|
|
case AF_IPX:
|
|
isr = NETISR_IPX;
|
|
break;
|
|
#endif
|
|
#ifdef NETATALK
|
|
case AF_APPLETALK:
|
|
isr = NETISR_ATALK2;
|
|
break;
|
|
#endif
|
|
default:
|
|
printf("if_simloop: can't handle af=%d\n", af);
|
|
m_freem(m);
|
|
return (EAFNOSUPPORT);
|
|
}
|
|
ifp->if_ipackets++;
|
|
ifp->if_ibytes += m->m_pkthdr.len;
|
|
netisr_queue(isr, m); /* mbuf is free'd on failure. */
|
|
return (0);
|
|
}
|
|
|
|
/* ARGSUSED */
|
|
static void
|
|
lortrequest(cmd, rt, info)
|
|
int cmd;
|
|
struct rtentry *rt;
|
|
struct rt_addrinfo *info;
|
|
{
|
|
RT_LOCK_ASSERT(rt);
|
|
rt->rt_rmx.rmx_mtu = rt->rt_ifp->if_mtu;
|
|
}
|
|
|
|
/*
|
|
* Process an ioctl request.
|
|
*/
|
|
/* ARGSUSED */
|
|
int
|
|
loioctl(ifp, cmd, data)
|
|
register struct ifnet *ifp;
|
|
u_long cmd;
|
|
caddr_t data;
|
|
{
|
|
register struct ifaddr *ifa;
|
|
register struct ifreq *ifr = (struct ifreq *)data;
|
|
register int error = 0;
|
|
|
|
switch (cmd) {
|
|
|
|
case SIOCSIFADDR:
|
|
ifp->if_flags |= IFF_UP;
|
|
ifp->if_drv_flags |= IFF_DRV_RUNNING;
|
|
ifa = (struct ifaddr *)data;
|
|
ifa->ifa_rtrequest = lortrequest;
|
|
/*
|
|
* 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;
|
|
|
|
case SIOCSIFFLAGS:
|
|
break;
|
|
|
|
default:
|
|
error = EINVAL;
|
|
}
|
|
return (error);
|
|
}
|