freebsd-skq/sys/net/if_disc.c

245 lines
5.9 KiB
C
Raw Normal View History

/*-
* 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.
*
* From: @(#)if_loop.c 8.1 (Berkeley) 6/10/93
1999-08-28 01:08:13 +00:00
* $FreeBSD$
*/
/*
* 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_var.h>
#include <net/if_clone.h>
#include <net/if_types.h>
#include <net/route.h>
#include <net/bpf.h>
2014-10-05 19:46:52 +00:00
#include <net/vnet.h>
#include "opt_inet.h"
#include "opt_inet6.h"
#ifdef TINY_DSMTU
#define DSMTU (1024+512)
#else
#define DSMTU 65532
#endif
struct disc_softc {
struct ifnet *sc_ifp;
};
static int discoutput(struct ifnet *, struct mbuf *,
const struct sockaddr *, struct route *);
static int discioctl(struct ifnet *, u_long, caddr_t);
static int disc_clone_create(struct if_clone *, int, caddr_t);
static void disc_clone_destroy(struct ifnet *);
static const char discname[] = "disc";
static MALLOC_DEFINE(M_DISC, discname, "Discard interface");
2014-10-05 19:46:52 +00:00
static VNET_DEFINE(struct if_clone *, disc_cloner);
#define V_disc_cloner VNET(disc_cloner)
static int
disc_clone_create(struct if_clone *ifc, int unit, caddr_t params)
{
struct ifnet *ifp;
struct disc_softc *sc;
sc = malloc(sizeof(struct disc_softc), M_DISC, M_WAITOK | M_ZERO);
ifp = sc->sc_ifp = if_alloc(IFT_LOOP);
if (ifp == NULL) {
free(sc, M_DISC);
return (ENOSPC);
}
ifp->if_softc = sc;
if_initname(ifp, discname, unit);
ifp->if_mtu = DSMTU;
/*
* IFF_LOOPBACK should not be removed from disc's flags because
* it controls what PF-specific routes are magically added when
* a network address is assigned to the interface. Things just
* won't work as intended w/o such routes because the output
* interface selection for a packet is totally route-driven.
* A valid alternative to IFF_LOOPBACK can be IFF_BROADCAST or
* IFF_POINTOPOINT, but it would result in different properties
* of the interface.
*/
ifp->if_flags = IFF_LOOPBACK | IFF_MULTICAST;
2005-11-11 11:17:57 +00:00
ifp->if_drv_flags = IFF_DRV_RUNNING;
ifp->if_ioctl = discioctl;
ifp->if_output = discoutput;
ifp->if_hdrlen = 0;
ifp->if_addrlen = 0;
1999-11-12 19:30:08 +00:00
ifp->if_snd.ifq_maxlen = 20;
if_attach(ifp);
bpfattach(ifp, DLT_NULL, sizeof(u_int32_t));
return (0);
}
static void
disc_clone_destroy(struct ifnet *ifp)
{
struct disc_softc *sc;
sc = ifp->if_softc;
bpfdetach(ifp);
if_detach(ifp);
if_free(ifp);
free(sc, M_DISC);
}
2014-10-05 19:46:52 +00:00
static void
vnet_disc_init(const void *unused __unused)
{
V_disc_cloner = if_clone_simple(discname, disc_clone_create,
disc_clone_destroy, 0);
}
Get closer to a VIMAGE network stack teardown from top to bottom rather than removing the network interfaces first. This change is rather larger and convoluted as the ordering requirements cannot be separated. Move the pfil(9) framework to SI_SUB_PROTO_PFIL, move Firewalls and related modules to their own SI_SUB_PROTO_FIREWALL. Move initialization of "physical" interfaces to SI_SUB_DRIVERS, move virtual (cloned) interfaces to SI_SUB_PSEUDO. Move Multicast to SI_SUB_PROTO_MC. Re-work parts of multicast initialisation and teardown, not taking the huge amount of memory into account if used as a module yet. For interface teardown we try to do as many of them as we can on SI_SUB_INIT_IF, but for some this makes no sense, e.g., when tunnelling over a higher layer protocol such as IP. In that case the interface has to go along (or before) the higher layer protocol is shutdown. Kernel hhooks need to go last on teardown as they may be used at various higher layers and we cannot remove them before we cleaned up the higher layers. For interface teardown there are multiple paths: (a) a cloned interface is destroyed (inside a VIMAGE or in the base system), (b) any interface is moved from a virtual network stack to a different network stack ("vmove"), or (c) a virtual network stack is being shut down. All code paths go through if_detach_internal() where we, depending on the vmove flag or the vnet state, make a decision on how much to shut down; in case we are destroying a VNET the individual protocol layers will cleanup their own parts thus we cannot do so again for each interface as we end up with, e.g., double-frees, destroying locks twice or acquiring already destroyed locks. When calling into protocol cleanups we equally have to tell them whether they need to detach upper layer protocols ("ulp") or not (e.g., in6_ifdetach()). Provide or enahnce helper functions to do proper cleanup at a protocol rather than at an interface level. Approved by: re (hrs) Obtained from: projects/vnet Reviewed by: gnn, jhb Sponsored by: The FreeBSD Foundation MFC after: 2 weeks Differential Revision: https://reviews.freebsd.org/D6747
2016-06-21 13:48:49 +00:00
VNET_SYSINIT(vnet_disc_init, SI_SUB_PSEUDO, SI_ORDER_ANY,
2014-10-05 19:46:52 +00:00
vnet_disc_init, NULL);
static void
vnet_disc_uninit(const void *unused __unused)
{
if_clone_detach(V_disc_cloner);
}
Get closer to a VIMAGE network stack teardown from top to bottom rather than removing the network interfaces first. This change is rather larger and convoluted as the ordering requirements cannot be separated. Move the pfil(9) framework to SI_SUB_PROTO_PFIL, move Firewalls and related modules to their own SI_SUB_PROTO_FIREWALL. Move initialization of "physical" interfaces to SI_SUB_DRIVERS, move virtual (cloned) interfaces to SI_SUB_PSEUDO. Move Multicast to SI_SUB_PROTO_MC. Re-work parts of multicast initialisation and teardown, not taking the huge amount of memory into account if used as a module yet. For interface teardown we try to do as many of them as we can on SI_SUB_INIT_IF, but for some this makes no sense, e.g., when tunnelling over a higher layer protocol such as IP. In that case the interface has to go along (or before) the higher layer protocol is shutdown. Kernel hhooks need to go last on teardown as they may be used at various higher layers and we cannot remove them before we cleaned up the higher layers. For interface teardown there are multiple paths: (a) a cloned interface is destroyed (inside a VIMAGE or in the base system), (b) any interface is moved from a virtual network stack to a different network stack ("vmove"), or (c) a virtual network stack is being shut down. All code paths go through if_detach_internal() where we, depending on the vmove flag or the vnet state, make a decision on how much to shut down; in case we are destroying a VNET the individual protocol layers will cleanup their own parts thus we cannot do so again for each interface as we end up with, e.g., double-frees, destroying locks twice or acquiring already destroyed locks. When calling into protocol cleanups we equally have to tell them whether they need to detach upper layer protocols ("ulp") or not (e.g., in6_ifdetach()). Provide or enahnce helper functions to do proper cleanup at a protocol rather than at an interface level. Approved by: re (hrs) Obtained from: projects/vnet Reviewed by: gnn, jhb Sponsored by: The FreeBSD Foundation MFC after: 2 weeks Differential Revision: https://reviews.freebsd.org/D6747
2016-06-21 13:48:49 +00:00
VNET_SYSUNINIT(vnet_disc_uninit, SI_SUB_INIT_IF, SI_ORDER_ANY,
2014-10-05 19:46:52 +00:00
vnet_disc_uninit, NULL);
static int
2004-07-06 03:07:50 +00:00
disc_modevent(module_t mod, int type, void *data)
{
2004-07-06 03:07:50 +00:00
switch (type) {
case MOD_LOAD:
case MOD_UNLOAD:
break;
default:
return (EOPNOTSUPP);
2004-07-06 03:07:50 +00:00
}
return (0);
}
2004-07-06 03:07:50 +00:00
static moduledata_t disc_mod = {
"if_disc",
disc_modevent,
NULL
2004-07-06 03:07:50 +00:00
};
DECLARE_MODULE(if_disc, disc_mod, SI_SUB_PSEUDO, SI_ORDER_ANY);
static int
discoutput(struct ifnet *ifp, struct mbuf *m, const struct sockaddr *dst,
struct route *ro)
{
u_int32_t af;
2004-07-06 03:07:50 +00:00
M_ASSERTPKTHDR(m);
2004-07-06 03:07:50 +00:00
/* BPF writes need to be handled specially. */
if (dst->sa_family == AF_UNSPEC)
bcopy(dst->sa_data, &af, sizeof(af));
else
af = dst->sa_family;
if (bpf_peers_present(ifp->if_bpf))
bpf_mtap2(ifp->if_bpf, &af, sizeof(af), m);
m->m_pkthdr.rcvif = ifp;
if_inc_counter(ifp, IFCOUNTER_OPACKETS, 1);
if_inc_counter(ifp, IFCOUNTER_OBYTES, m->m_pkthdr.len);
m_freem(m);
2004-07-06 03:07:50 +00:00
return (0);
}
/*
* Process an ioctl request.
*/
static int
discioctl(struct ifnet *ifp, u_long cmd, caddr_t data)
{
struct ifreq *ifr = (struct ifreq *)data;
int error = 0;
switch (cmd) {
case SIOCSIFADDR:
ifp->if_flags |= IFF_UP;
Make checks for rt_mtu generic: Some virtual if drivers has (ab)used ifa ifa_rtrequest hook to enforce route MTU to be not bigger that interface MTU. While ifa_rtrequest hooking might be an option in some situation, it is not feasible to do MTU checks there: generic (or per-domain) routing code is perfectly capable of doing this. We currrently have 3 places where MTU is altered: 1) route addition. In this case domain overrides radix _addroute callback (in[6]_addroute) and all necessary checks/fixes are/can be done there. 2) route change (especially, GW change). In this case, there are no explicit per-domain calls, but one can override rte by setting ifa_rtrequest hook to domain handler (inet6 does this). 3) ifconfig ifaceX mtu YYYY In this case, we have no callbacks, but ip[6]_output performes runtime checks and decreases rt_mtu if necessary. Generally, the goals are to be able to handle all MTU changes in control plane, not in runtime part, and properly deal with increased interface MTU. This commit changes the following: * removes hooks setting MTU from drivers side * adds proper per-doman MTU checks for case 1) * adds generic MTU check for case 2) * The latter is done by using new dom_ifmtu callback since if_mtu denotes L3 interface MTU, e.g. maximum trasmitted _packet_ size. However, IPv6 mtu might be different from if_mtu one (e.g. default 1280) for some cases, so we need an abstract way to know maximum MTU size for given interface and domain. * moves rt_setmetrics() before MTU/ifa_rtrequest hooks since it copies user-supplied data which must be checked. * removes RT_LOCK_ASSERT() from other ifa_rtrequest hooks to be able to use this functions on new non-inserted rte. More changes will follow soon. MFC after: 1 month Sponsored by: Yandex LLC
2014-11-06 13:13:09 +00:00
/*
* Everything else is done at a higher level.
*/
break;
case SIOCADDMULTI:
case SIOCDELMULTI:
if (ifr == NULL) {
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;
}
2001-12-14 19:28:06 +00:00
return (error);
}