NetBSD/sys/net/if_loop.c
dyoung de87fe677d *** Summary ***
When a link-layer address changes (e.g., ifconfig ex0 link
02🇩🇪ad:be:ef:02 active), send a gratuitous ARP and/or a Neighbor
Advertisement to update the network-/link-layer address bindings
on our LAN peers.

Refuse a change of ethernet address to the address 00:00:00:00:00:00
or to any multicast/broadcast address.  (Thanks matt@.)

Reorder ifnet ioctl operations so that driver ioctls may inherit
the functions of their "class"---ether_ioctl(), fddi_ioctl(), et
cetera---and the class ioctls may inherit from the generic ioctl,
ifioctl_common(), but both driver- and class-ioctls may override
the generic behavior.  Make network drivers share more code.

Distinguish a "factory" link-layer address from others for the
purposes of both protecting that address from deletion and computing
EUI64.

Return consistent, appropriate error codes from network drivers.

Improve readability.  KNF.

*** Details ***

In if_attach(), always initialize the interface ioctl routine,
ifnet->if_ioctl, if the driver has not already initialized it.
Delete if_ioctl == NULL tests everywhere else, because it cannot
happen.

In the ioctl routines of network interfaces, inherit common ioctl
behaviors by calling either ifioctl_common() or whichever ioctl
routine is appropriate for the class of interface---e.g., ether_ioctl()
for ethernets.

Stop (ab)using SIOCSIFADDR and start to use SIOCINITIFADDR.  In
the user->kernel interface, SIOCSIFADDR's argument was an ifreq,
but on the protocol->ifnet interface, SIOCSIFADDR's argument was
an ifaddr.  That was confusing, and it would work against me as I
make it possible for a network interface to overload most ioctls.
On the protocol->ifnet interface, replace SIOCSIFADDR with
SIOCINITIFADDR.  In ifioctl(), return EPERM if userland tries to
invoke SIOCINITIFADDR.

In ifioctl(), give the interface the first shot at handling most
interface ioctls, and give the protocol the second shot, instead
of the other way around. Finally, let compatibility code (COMPAT_OSOCK)
take a shot.

Pull device initialization out of switch statements under
SIOCINITIFADDR.  For example, pull ..._init() out of any switch
statement that looks like this:

        switch (...->sa_family) {
        case ...:
                ..._init();
                ...
                break;
        ...
        default:
                ..._init();
                ...
                break;
        }

Rewrite many if-else clauses that handle all permutations of IFF_UP
and IFF_RUNNING to use a switch statement,

        switch (x & (IFF_UP|IFF_RUNNING)) {
        case 0:
                ...
                break;
        case IFF_RUNNING:
                ...
                break;
        case IFF_UP:
                ...
                break;
        case IFF_UP|IFF_RUNNING:
                ...
                break;
        }

unifdef lots of code containing #ifdef FreeBSD, #ifdef NetBSD, and
#ifdef SIOCSIFMTU, especially in fwip(4) and in ndis(4).

In ipw(4), remove an if_set_sadl() call that is out of place.

In nfe(4), reuse the jumbo MTU logic in ether_ioctl().

Let ethernets register a callback for setting h/w state such as
promiscuous mode and the multicast filter in accord with a change
in the if_flags: ether_set_ifflags_cb() registers a callback that
returns ENETRESET if the caller should reset the ethernet by calling
if_init(), 0 on success, != 0 on failure.  Pull common code from
ex(4), gem(4), nfe(4), sip(4), tlp(4), vge(4) into ether_ioctl(),
and register if_flags callbacks for those drivers.

Return ENOTTY instead of EINVAL for inappropriate ioctls.  In
zyd(4), use ENXIO instead of ENOTTY to indicate that the device is
not any longer attached.

Add to if_set_sadl() a boolean 'factory' argument that indicates
whether a link-layer address was assigned by the factory or some
other source.  In a comment, recommend using the factory address
for generating an EUI64, and update in6_get_hw_ifid() to prefer a
factory address to any other link-layer address.

Add a routing message, RTM_LLINFO_UPD, that tells protocols to
update the binding of network-layer addresses to link-layer addresses.
Implement this message in IPv4 and IPv6 by sending a gratuitous
ARP or a neighbor advertisement, respectively.  Generate RTM_LLINFO_UPD
messages on a change of an interface's link-layer address.

In ether_ioctl(), do not let SIOCALIFADDR set a link-layer address
that is broadcast/multicast or equal to 00:00:00:00:00:00.

Make ether_ioctl() call ifioctl_common() to handle ioctls that it
does not understand.

In gif(4), initialize if_softc and use it, instead of assuming that
the gif_softc and ifp overlap.

Let ifioctl_common() handle SIOCGIFADDR.

Sprinkle rtcache_invariants(), which checks on DIAGNOSTIC kernels
that certain invariants on a struct route are satisfied.

In agr(4), rewrite agr_ioctl_filter() to be a bit more explicit
about the ioctls that we do not allow on an agr(4) member interface.

bzero -> memset.  Delete unnecessary casts to void *.  Use
sockaddr_in_init() and sockaddr_in6_init().  Compare pointers with
NULL instead of "testing truth".  Replace some instances of (type
*)0 with NULL.  Change some K&R prototypes to ANSI C, and join
lines.
2008-11-07 00:20:01 +00:00

467 lines
10 KiB
C

/* $NetBSD: if_loop.c,v 1.70 2008/11/07 00:20:13 dyoung Exp $ */
/*
* Copyright (C) 1995, 1996, 1997, and 1998 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, 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. 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
*/
/*
* Loopback interface driver for protocol testing and timing.
*/
#include <sys/cdefs.h>
__KERNEL_RCSID(0, "$NetBSD: if_loop.c,v 1.70 2008/11/07 00:20:13 dyoung Exp $");
#include "opt_inet.h"
#include "opt_atalk.h"
#include "opt_iso.h"
#include "opt_ipx.h"
#include "opt_mbuftrace.h"
#include "bpfilter.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/errno.h>
#include <sys/ioctl.h>
#include <sys/time.h>
#include <sys/cpu.h>
#include <net/if.h>
#include <net/if_types.h>
#include <net/netisr.h>
#include <net/route.h>
#ifdef INET
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#endif
#ifdef INET6
#ifndef INET
#include <netinet/in.h>
#endif
#include <netinet6/in6_var.h>
#include <netinet/ip6.h>
#endif
#ifdef IPX
#include <netipx/ipx.h>
#include <netipx/ipx_if.h>
#endif
#ifdef ISO
#include <netiso/iso.h>
#include <netiso/iso_var.h>
#endif
#ifdef NETATALK
#include <netatalk/at.h>
#include <netatalk/at_var.h>
#endif
#if NBPFILTER > 0
#include <net/bpf.h>
#endif
#if defined(LARGE_LOMTU)
#define LOMTU (131072 + MHLEN + MLEN)
#define LOMTU_MAX LOMTU
#else
#define LOMTU (32768 + MHLEN + MLEN)
#define LOMTU_MAX (65536 + MHLEN + MLEN)
#endif
#ifdef ALTQ
static void lostart(struct ifnet *);
#endif
static int loop_clone_create(struct if_clone *, int);
static int loop_clone_destroy(struct ifnet *);
static struct if_clone loop_cloner =
IF_CLONE_INITIALIZER("lo", loop_clone_create, loop_clone_destroy);
void
loopattach(int n)
{
(void)loop_clone_create(&loop_cloner, 0); /* lo0 always exists */
if_clone_attach(&loop_cloner);
}
static int
loop_clone_create(struct if_clone *ifc, int unit)
{
struct ifnet *ifp;
ifp = if_alloc(IFT_LOOP);
if_initname(ifp, ifc->ifc_name, unit);
ifp->if_mtu = LOMTU;
ifp->if_flags = IFF_LOOPBACK | IFF_MULTICAST | IFF_RUNNING;
ifp->if_ioctl = loioctl;
ifp->if_output = looutput;
#ifdef ALTQ
ifp->if_start = lostart;
#endif
ifp->if_type = IFT_LOOP;
ifp->if_hdrlen = 0;
ifp->if_addrlen = 0;
ifp->if_dlt = DLT_NULL;
IFQ_SET_READY(&ifp->if_snd);
if (unit == 0)
lo0ifp = ifp;
if_attach(ifp);
if_alloc_sadl(ifp);
#if NBPFILTER > 0
bpfattach(ifp, DLT_NULL, sizeof(u_int));
#endif
#ifdef MBUFTRACE
ifp->if_mowner = malloc(sizeof(struct mowner), M_DEVBUF,
M_WAITOK | M_ZERO);
strlcpy(ifp->if_mowner->mo_name, ifp->if_xname,
sizeof(ifp->if_mowner->mo_name));
MOWNER_ATTACH(ifp->if_mowner);
#endif
return (0);
}
static int
loop_clone_destroy(struct ifnet *ifp)
{
if (ifp == lo0ifp)
return (EPERM);
#ifdef MBUFTRACE
MOWNER_DETACH(ifp->if_mowner);
free(ifp->if_mowner, M_DEVBUF);
#endif
#if NBPFILTER > 0
bpfdetach(ifp);
#endif
if_detach(ifp);
free(ifp, M_DEVBUF);
return (0);
}
int
looutput(struct ifnet *ifp, struct mbuf *m, const struct sockaddr *dst,
struct rtentry *rt)
{
int s, isr;
struct ifqueue *ifq = NULL;
MCLAIM(m, ifp->if_mowner);
if ((m->m_flags & M_PKTHDR) == 0)
panic("looutput: no header mbuf");
#if NBPFILTER > 0
if (ifp->if_bpf && (ifp->if_flags & IFF_LOOPBACK))
bpf_mtap_af(ifp->if_bpf, dst->sa_family, m);
#endif
m->m_pkthdr.rcvif = ifp;
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;
#ifdef ALTQ
/*
* ALTQ on the loopback interface is just for debugging. It's
* used only for loopback interfaces, not for a simplex interface.
*/
if ((ALTQ_IS_ENABLED(&ifp->if_snd) || TBR_IS_ENABLED(&ifp->if_snd)) &&
ifp->if_start == lostart) {
struct altq_pktattr pktattr;
int error;
/*
* If the queueing discipline needs packet classification,
* do it before prepending the link headers.
*/
IFQ_CLASSIFY(&ifp->if_snd, m, dst->sa_family, &pktattr);
M_PREPEND(m, sizeof(uint32_t), M_DONTWAIT);
if (m == NULL)
return (ENOBUFS);
*(mtod(m, uint32_t *)) = dst->sa_family;
s = splnet();
IFQ_ENQUEUE(&ifp->if_snd, m, &pktattr, error);
(*ifp->if_start)(ifp);
splx(s);
return (error);
}
#endif /* ALTQ */
m_tag_delete_nonpersistent(m);
switch (dst->sa_family) {
#ifdef INET
case AF_INET:
ifq = &ipintrq;
isr = NETISR_IP;
break;
#endif
#ifdef INET6
case AF_INET6:
m->m_flags |= M_LOOP;
ifq = &ip6intrq;
isr = NETISR_IPV6;
break;
#endif
#ifdef ISO
case AF_ISO:
ifq = &clnlintrq;
isr = NETISR_ISO;
break;
#endif
#ifdef IPX
case AF_IPX:
ifq = &ipxintrq;
isr = NETISR_IPX;
break;
#endif
#ifdef NETATALK
case AF_APPLETALK:
ifq = &atintrq2;
isr = NETISR_ATALK;
break;
#endif
default:
printf("%s: can't handle af%d\n", ifp->if_xname,
dst->sa_family);
m_freem(m);
return (EAFNOSUPPORT);
}
s = splnet();
if (IF_QFULL(ifq)) {
IF_DROP(ifq);
m_freem(m);
splx(s);
return (ENOBUFS);
}
IF_ENQUEUE(ifq, m);
schednetisr(isr);
ifp->if_ipackets++;
ifp->if_ibytes += m->m_pkthdr.len;
splx(s);
return (0);
}
#ifdef ALTQ
static void
lostart(struct ifnet *ifp)
{
struct ifqueue *ifq;
struct mbuf *m;
uint32_t af;
int s, isr;
for (;;) {
IFQ_DEQUEUE(&ifp->if_snd, m);
if (m == NULL)
return;
af = *(mtod(m, uint32_t *));
m_adj(m, sizeof(uint32_t));
switch (af) {
#ifdef INET
case AF_INET:
ifq = &ipintrq;
isr = NETISR_IP;
break;
#endif
#ifdef INET6
case AF_INET6:
m->m_flags |= M_LOOP;
ifq = &ip6intrq;
isr = NETISR_IPV6;
break;
#endif
#ifdef IPX
case AF_IPX:
ifq = &ipxintrq;
isr = NETISR_IPX;
break;
#endif
#ifdef ISO
case AF_ISO:
ifq = &clnlintrq;
isr = NETISR_ISO;
break;
#endif
#ifdef NETATALK
case AF_APPLETALK:
ifq = &atintrq2;
isr = NETISR_ATALK;
break;
#endif
default:
printf("%s: can't handle af%d\n", ifp->if_xname, af);
m_freem(m);
return;
}
s = splnet();
if (IF_QFULL(ifq)) {
IF_DROP(ifq);
splx(s);
m_freem(m);
return;
}
IF_ENQUEUE(ifq, m);
schednetisr(isr);
ifp->if_ipackets++;
ifp->if_ibytes += m->m_pkthdr.len;
splx(s);
}
}
#endif /* ALTQ */
/* ARGSUSED */
void
lortrequest(int cmd, struct rtentry *rt,
const struct rt_addrinfo *info)
{
if (rt)
rt->rt_rmx.rmx_mtu = lo0ifp->if_mtu;
}
/*
* Process an ioctl request.
*/
/* ARGSUSED */
int
loioctl(struct ifnet *ifp, u_long cmd, void *data)
{
struct ifaddr *ifa;
struct ifreq *ifr = data;
int error = 0;
switch (cmd) {
case SIOCINITIFADDR:
ifp->if_flags |= IFF_UP;
ifa = (struct ifaddr *)data;
if (ifa != NULL /*&& ifa->ifa_addr->sa_family == AF_ISO*/)
ifa->ifa_rtrequest = lortrequest;
/*
* Everything else is done at a higher level.
*/
break;
case SIOCSIFMTU:
if ((unsigned)ifr->ifr_mtu > LOMTU_MAX)
error = EINVAL;
else if ((error = ifioctl_common(ifp, cmd, data)) == ENETRESET){
/* XXX update rt mtu for AF_ISO? */
error = 0;
}
break;
case SIOCADDMULTI:
case SIOCDELMULTI:
if (ifr == NULL) {
error = EAFNOSUPPORT; /* XXX */
break;
}
switch (ifreq_getaddr(cmd, ifr)->sa_family) {
#ifdef INET
case AF_INET:
break;
#endif
#ifdef INET6
case AF_INET6:
break;
#endif
default:
error = EAFNOSUPPORT;
break;
}
break;
default:
error = ifioctl_common(ifp, cmd, data);
}
return (error);
}