2022-09-03 05:47:59 +03:00
|
|
|
/* $NetBSD: if_faith.c,v 1.63 2022/09/03 02:47:59 thorpej Exp $ */
|
2001-05-08 14:15:13 +04:00
|
|
|
/* $KAME: if_faith.c,v 1.21 2001/02/20 07:59:26 itojun Exp $ */
|
1999-12-02 10:18:44 +03:00
|
|
|
|
1999-06-28 10:36:47 +04:00
|
|
|
/*
|
|
|
|
* 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.
|
2003-08-07 20:26:28 +04:00
|
|
|
* 3. Neither the name of the University nor the names of its contributors
|
1999-06-28 10:36:47 +04:00
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
/*
|
2001-05-08 14:15:13 +04:00
|
|
|
* derived from
|
1999-06-28 10:36:47 +04:00
|
|
|
* @(#)if_loop.c 8.1 (Berkeley) 6/10/93
|
|
|
|
* Id: if_loop.c,v 1.22 1996/06/19 16:24:10 wollman Exp
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
2006-02-01 01:27:15 +03:00
|
|
|
* IPv6-to-IPv4 TCP relay capturing interface
|
1999-06-28 10:36:47 +04:00
|
|
|
*/
|
2001-11-13 02:49:33 +03:00
|
|
|
|
|
|
|
#include <sys/cdefs.h>
|
2022-09-03 05:47:59 +03:00
|
|
|
__KERNEL_RCSID(0, "$NetBSD: if_faith.c,v 1.63 2022/09/03 02:47:59 thorpej Exp $");
|
2001-11-13 02:49:33 +03:00
|
|
|
|
2016-08-07 20:38:33 +03:00
|
|
|
#ifdef _KERNEL_OPT
|
1999-06-28 10:36:47 +04:00
|
|
|
#include "opt_inet.h"
|
2016-08-07 20:38:33 +03:00
|
|
|
#endif
|
1999-06-28 10:36:47 +04:00
|
|
|
|
2001-11-15 10:01:27 +03:00
|
|
|
#include <sys/param.h>
|
1999-06-28 10:36:47 +04:00
|
|
|
#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>
|
2000-07-05 00:02:46 +04:00
|
|
|
#include <sys/queue.h>
|
2016-08-07 20:38:33 +03:00
|
|
|
#include <sys/device.h>
|
|
|
|
#include <sys/module.h>
|
|
|
|
#include <sys/atomic.h>
|
2000-07-05 00:02:46 +04:00
|
|
|
|
2007-10-19 15:59:34 +04:00
|
|
|
#include <sys/cpu.h>
|
1999-06-28 10:36:47 +04:00
|
|
|
|
|
|
|
#include <net/if.h>
|
|
|
|
#include <net/if_types.h>
|
|
|
|
#include <net/route.h>
|
|
|
|
#include <net/bpf.h>
|
2001-05-08 14:15:13 +04:00
|
|
|
#include <net/if_faith.h>
|
1999-06-28 10:36:47 +04:00
|
|
|
|
|
|
|
#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>
|
2000-02-06 15:49:37 +03:00
|
|
|
#include <netinet/ip6.h>
|
2001-05-08 14:15:13 +04:00
|
|
|
#include <netinet6/ip6_var.h>
|
1999-06-28 10:36:47 +04:00
|
|
|
#endif
|
|
|
|
|
2015-08-20 17:40:16 +03:00
|
|
|
#include "ioconf.h"
|
|
|
|
|
2007-03-04 08:59:00 +03:00
|
|
|
static int faithioctl(struct ifnet *, u_long, void *);
|
KNF: de-__P, bzero -> memset, bcmp -> memcmp. Remove extraneous
parentheses in return statements.
Cosmetic: don't open-code TAILQ_FOREACH().
Cosmetic: change types of variables to avoid oodles of casts: in
in6_src.c, avoid casts by changing several route_in6 pointers
to struct route pointers. Remove unnecessary casts to caddr_t
elsewhere.
Pave the way for eliminating address family-specific route caches:
soon, struct route will not embed a sockaddr, but it will hold
a reference to an external sockaddr, instead. We will set the
destination sockaddr using rtcache_setdst(). (I created a stub
for it, but it isn't used anywhere, yet.) rtcache_free() will
free the sockaddr. I have extracted from rtcache_free() a helper
subroutine, rtcache_clear(). rtcache_clear() will "forget" a
cached route, but it will not forget the destination by releasing
the sockaddr. I use rtcache_clear() instead of rtcache_free()
in rtcache_update(), because rtcache_update() is not supposed
to forget the destination.
Constify:
1 Introduce const accessor for route->ro_dst, rtcache_getdst().
2 Constify the 'dst' argument to ifnet->if_output(). This
led me to constify a lot of code called by output routines.
3 Constify the sockaddr argument to protosw->pr_ctlinput. This
led me to constify a lot of code called by ctlinput routines.
4 Introduce const macros for converting from a generic sockaddr
to family-specific sockaddrs, e.g., sockaddr_in: satocsin6,
satocsin, et cetera.
2007-02-18 01:34:07 +03:00
|
|
|
static int faithoutput(struct ifnet *, struct mbuf *,
|
2016-04-28 03:16:56 +03:00
|
|
|
const struct sockaddr *, const struct rtentry *);
|
2008-10-24 21:07:33 +04:00
|
|
|
static void faithrtrequest(int, struct rtentry *,
|
|
|
|
const struct rt_addrinfo *);
|
1999-06-28 10:36:47 +04:00
|
|
|
|
2005-12-12 02:05:24 +03:00
|
|
|
static int faith_clone_create(struct if_clone *, int);
|
|
|
|
static int faith_clone_destroy(struct ifnet *);
|
2000-07-05 00:02:46 +04:00
|
|
|
|
2005-12-12 02:05:24 +03:00
|
|
|
static struct if_clone faith_cloner =
|
2000-07-05 00:02:46 +04:00
|
|
|
IF_CLONE_INITIALIZER("faith", faith_clone_create, faith_clone_destroy);
|
1999-06-28 10:36:47 +04:00
|
|
|
|
|
|
|
#define FAITHMTU 1500
|
|
|
|
|
2016-08-07 20:38:33 +03:00
|
|
|
static u_int faith_count;
|
|
|
|
|
1999-06-28 10:36:47 +04:00
|
|
|
/* ARGSUSED */
|
|
|
|
void
|
2006-11-16 04:32:37 +03:00
|
|
|
faithattach(int count)
|
1999-06-28 10:36:47 +04:00
|
|
|
{
|
2000-07-05 00:02:46 +04:00
|
|
|
|
2016-08-07 20:38:33 +03:00
|
|
|
/*
|
|
|
|
* Nothing to do here, initialization is handled by the
|
|
|
|
* module initialization code in faithinit() below).
|
|
|
|
*/
|
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
|
|
|
faithinit(void)
|
|
|
|
{
|
2000-07-05 00:02:46 +04:00
|
|
|
if_clone_attach(&faith_cloner);
|
|
|
|
}
|
|
|
|
|
2016-08-07 20:38:33 +03:00
|
|
|
static int
|
|
|
|
faithdetach(void)
|
|
|
|
{
|
|
|
|
int error = 0;
|
|
|
|
|
|
|
|
if (faith_count != 0)
|
|
|
|
error = EBUSY;
|
|
|
|
|
|
|
|
if (error == 0)
|
|
|
|
if_clone_detach(&faith_cloner);
|
|
|
|
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2005-12-12 02:05:24 +03:00
|
|
|
static int
|
|
|
|
faith_clone_create(struct if_clone *ifc, int unit)
|
2000-07-05 00:02:46 +04:00
|
|
|
{
|
2006-10-09 14:46:00 +04:00
|
|
|
struct ifnet *ifp;
|
2000-07-05 00:02:46 +04:00
|
|
|
|
2008-06-15 22:40:55 +04:00
|
|
|
ifp = if_alloc(IFT_FAITH);
|
2000-07-05 00:02:46 +04:00
|
|
|
|
2008-06-15 20:37:21 +04:00
|
|
|
if_initname(ifp, ifc->ifc_name, unit);
|
2000-07-05 00:02:46 +04:00
|
|
|
|
2006-10-09 14:46:00 +04:00
|
|
|
ifp->if_mtu = FAITHMTU;
|
2000-07-05 00:02:46 +04:00
|
|
|
/* Change to BROADCAST experimentaly to announce its prefix. */
|
2006-10-09 14:46:00 +04:00
|
|
|
ifp->if_flags = /* IFF_LOOPBACK */ IFF_BROADCAST | IFF_MULTICAST;
|
|
|
|
ifp->if_ioctl = faithioctl;
|
|
|
|
ifp->if_output = faithoutput;
|
|
|
|
ifp->if_type = IFT_FAITH;
|
|
|
|
ifp->if_hdrlen = 0;
|
|
|
|
ifp->if_addrlen = 0;
|
|
|
|
ifp->if_dlt = DLT_NULL;
|
if_attach and if_initialize cannot fail, don't test return value
These were originally made failable back in 2017 when if_initialize
allocated a softint in every interface for link state changes, so
that it could fail gracefully instead of panicking:
https://mail-index.NetBSD.org/source-changes/2017/10/23/msg089053.html
However, this spawned many seldom- or never-tested error branches,
which are risky to have around. And that softint in every interface
has since been replaced by a single global workqueue, because link
state changes require thread context but not low latency or high
throughput:
https://mail-index.NetBSD.org/source-changes/2020/02/06/msg113759.html
So there is no longer any reason for if_initialize to fail. (The
subroutine if_stats_init can't fail because percpu_alloc can't fail
either.)
There is a snag: the softint_establish in if_percpuq_create could
fail, potentially leading to bad consequences later on trying to use
the softint. This change doesn't introduce any new bugs because of
the snag -- if_percpuq_attach was already broken. However, the snag
can be better addressed without spawning error branches, either by
using a single softint or making softints less scarce.
(Separate commit will change the signatures of if_attach and
if_initialize to return void, scheduled to ride whatever is the next
convenient kernel bump.)
Patch and testing on amd64 and evbmips64-eb by maya@; commit message
soliloquy, and compile-testing on evbppc/i386/earmv7hf, by me.
2021-06-16 03:21:17 +03:00
|
|
|
if_attach(ifp);
|
2006-10-09 14:46:00 +04:00
|
|
|
if_alloc_sadl(ifp);
|
2010-04-05 11:19:28 +04:00
|
|
|
bpf_attach(ifp, DLT_NULL, sizeof(u_int));
|
2016-08-07 20:38:33 +03:00
|
|
|
atomic_inc_uint(&faith_count);
|
2000-07-05 00:02:46 +04:00
|
|
|
return (0);
|
|
|
|
}
|
|
|
|
|
2004-12-04 21:31:43 +03:00
|
|
|
int
|
2005-12-12 02:05:24 +03:00
|
|
|
faith_clone_destroy(struct ifnet *ifp)
|
2000-07-05 00:02:46 +04:00
|
|
|
{
|
|
|
|
|
2010-04-05 11:19:28 +04:00
|
|
|
bpf_detach(ifp);
|
2000-07-05 00:02:46 +04:00
|
|
|
if_detach(ifp);
|
2014-07-29 05:35:44 +04:00
|
|
|
if_free(ifp);
|
2004-12-04 21:31:43 +03:00
|
|
|
|
2016-08-07 20:38:33 +03:00
|
|
|
atomic_dec_uint(&faith_count);
|
2004-12-04 21:31:43 +03:00
|
|
|
return (0);
|
1999-06-28 10:36:47 +04:00
|
|
|
}
|
|
|
|
|
KNF: de-__P, bzero -> memset, bcmp -> memcmp. Remove extraneous
parentheses in return statements.
Cosmetic: don't open-code TAILQ_FOREACH().
Cosmetic: change types of variables to avoid oodles of casts: in
in6_src.c, avoid casts by changing several route_in6 pointers
to struct route pointers. Remove unnecessary casts to caddr_t
elsewhere.
Pave the way for eliminating address family-specific route caches:
soon, struct route will not embed a sockaddr, but it will hold
a reference to an external sockaddr, instead. We will set the
destination sockaddr using rtcache_setdst(). (I created a stub
for it, but it isn't used anywhere, yet.) rtcache_free() will
free the sockaddr. I have extracted from rtcache_free() a helper
subroutine, rtcache_clear(). rtcache_clear() will "forget" a
cached route, but it will not forget the destination by releasing
the sockaddr. I use rtcache_clear() instead of rtcache_free()
in rtcache_update(), because rtcache_update() is not supposed
to forget the destination.
Constify:
1 Introduce const accessor for route->ro_dst, rtcache_getdst().
2 Constify the 'dst' argument to ifnet->if_output(). This
led me to constify a lot of code called by output routines.
3 Constify the sockaddr argument to protosw->pr_ctlinput. This
led me to constify a lot of code called by ctlinput routines.
4 Introduce const macros for converting from a generic sockaddr
to family-specific sockaddrs, e.g., sockaddr_in: satocsin6,
satocsin, et cetera.
2007-02-18 01:34:07 +03:00
|
|
|
static int
|
|
|
|
faithoutput(struct ifnet *ifp, struct mbuf *m, const struct sockaddr *dst,
|
2016-04-28 03:16:56 +03:00
|
|
|
const struct rtentry *rt)
|
1999-06-28 10:36:47 +04:00
|
|
|
{
|
2014-06-06 03:48:16 +04:00
|
|
|
pktqueue_t *pktq;
|
|
|
|
size_t pktlen;
|
|
|
|
int s, error;
|
KNF: de-__P, bzero -> memset, bcmp -> memcmp. Remove extraneous
parentheses in return statements.
Cosmetic: don't open-code TAILQ_FOREACH().
Cosmetic: change types of variables to avoid oodles of casts: in
in6_src.c, avoid casts by changing several route_in6 pointers
to struct route pointers. Remove unnecessary casts to caddr_t
elsewhere.
Pave the way for eliminating address family-specific route caches:
soon, struct route will not embed a sockaddr, but it will hold
a reference to an external sockaddr, instead. We will set the
destination sockaddr using rtcache_setdst(). (I created a stub
for it, but it isn't used anywhere, yet.) rtcache_free() will
free the sockaddr. I have extracted from rtcache_free() a helper
subroutine, rtcache_clear(). rtcache_clear() will "forget" a
cached route, but it will not forget the destination by releasing
the sockaddr. I use rtcache_clear() instead of rtcache_free()
in rtcache_update(), because rtcache_update() is not supposed
to forget the destination.
Constify:
1 Introduce const accessor for route->ro_dst, rtcache_getdst().
2 Constify the 'dst' argument to ifnet->if_output(). This
led me to constify a lot of code called by output routines.
3 Constify the sockaddr argument to protosw->pr_ctlinput. This
led me to constify a lot of code called by ctlinput routines.
4 Introduce const macros for converting from a generic sockaddr
to family-specific sockaddrs, e.g., sockaddr_in: satocsin6,
satocsin, et cetera.
2007-02-18 01:34:07 +03:00
|
|
|
uint32_t af;
|
1999-06-28 10:36:47 +04:00
|
|
|
|
|
|
|
if ((m->m_flags & M_PKTHDR) == 0)
|
|
|
|
panic("faithoutput no HDR");
|
KNF: de-__P, bzero -> memset, bcmp -> memcmp. Remove extraneous
parentheses in return statements.
Cosmetic: don't open-code TAILQ_FOREACH().
Cosmetic: change types of variables to avoid oodles of casts: in
in6_src.c, avoid casts by changing several route_in6 pointers
to struct route pointers. Remove unnecessary casts to caddr_t
elsewhere.
Pave the way for eliminating address family-specific route caches:
soon, struct route will not embed a sockaddr, but it will hold
a reference to an external sockaddr, instead. We will set the
destination sockaddr using rtcache_setdst(). (I created a stub
for it, but it isn't used anywhere, yet.) rtcache_free() will
free the sockaddr. I have extracted from rtcache_free() a helper
subroutine, rtcache_clear(). rtcache_clear() will "forget" a
cached route, but it will not forget the destination by releasing
the sockaddr. I use rtcache_clear() instead of rtcache_free()
in rtcache_update(), because rtcache_update() is not supposed
to forget the destination.
Constify:
1 Introduce const accessor for route->ro_dst, rtcache_getdst().
2 Constify the 'dst' argument to ifnet->if_output(). This
led me to constify a lot of code called by output routines.
3 Constify the sockaddr argument to protosw->pr_ctlinput. This
led me to constify a lot of code called by ctlinput routines.
4 Introduce const macros for converting from a generic sockaddr
to family-specific sockaddrs, e.g., sockaddr_in: satocsin6,
satocsin, et cetera.
2007-02-18 01:34:07 +03:00
|
|
|
af = dst->sa_family;
|
1999-06-28 10:36:47 +04:00
|
|
|
/* BPF write needs to be handled specially */
|
KNF: de-__P, bzero -> memset, bcmp -> memcmp. Remove extraneous
parentheses in return statements.
Cosmetic: don't open-code TAILQ_FOREACH().
Cosmetic: change types of variables to avoid oodles of casts: in
in6_src.c, avoid casts by changing several route_in6 pointers
to struct route pointers. Remove unnecessary casts to caddr_t
elsewhere.
Pave the way for eliminating address family-specific route caches:
soon, struct route will not embed a sockaddr, but it will hold
a reference to an external sockaddr, instead. We will set the
destination sockaddr using rtcache_setdst(). (I created a stub
for it, but it isn't used anywhere, yet.) rtcache_free() will
free the sockaddr. I have extracted from rtcache_free() a helper
subroutine, rtcache_clear(). rtcache_clear() will "forget" a
cached route, but it will not forget the destination by releasing
the sockaddr. I use rtcache_clear() instead of rtcache_free()
in rtcache_update(), because rtcache_update() is not supposed
to forget the destination.
Constify:
1 Introduce const accessor for route->ro_dst, rtcache_getdst().
2 Constify the 'dst' argument to ifnet->if_output(). This
led me to constify a lot of code called by output routines.
3 Constify the sockaddr argument to protosw->pr_ctlinput. This
led me to constify a lot of code called by ctlinput routines.
4 Introduce const macros for converting from a generic sockaddr
to family-specific sockaddrs, e.g., sockaddr_in: satocsin6,
satocsin, et cetera.
2007-02-18 01:34:07 +03:00
|
|
|
if (af == AF_UNSPEC) {
|
|
|
|
af = *(mtod(m, int *));
|
|
|
|
m_adj(m, sizeof(int));
|
1999-06-28 10:36:47 +04:00
|
|
|
}
|
|
|
|
|
2018-06-26 09:47:57 +03:00
|
|
|
bpf_mtap_af(ifp, af, m, BPF_D_OUT);
|
1999-06-28 10:36:47 +04:00
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
2014-06-06 03:48:16 +04:00
|
|
|
pktlen = m->m_pkthdr.len;
|
2020-01-29 07:11:35 +03:00
|
|
|
if_statadd2(ifp, if_opackets, 1, if_obytes, pktlen);
|
KNF: de-__P, bzero -> memset, bcmp -> memcmp. Remove extraneous
parentheses in return statements.
Cosmetic: don't open-code TAILQ_FOREACH().
Cosmetic: change types of variables to avoid oodles of casts: in
in6_src.c, avoid casts by changing several route_in6 pointers
to struct route pointers. Remove unnecessary casts to caddr_t
elsewhere.
Pave the way for eliminating address family-specific route caches:
soon, struct route will not embed a sockaddr, but it will hold
a reference to an external sockaddr, instead. We will set the
destination sockaddr using rtcache_setdst(). (I created a stub
for it, but it isn't used anywhere, yet.) rtcache_free() will
free the sockaddr. I have extracted from rtcache_free() a helper
subroutine, rtcache_clear(). rtcache_clear() will "forget" a
cached route, but it will not forget the destination by releasing
the sockaddr. I use rtcache_clear() instead of rtcache_free()
in rtcache_update(), because rtcache_update() is not supposed
to forget the destination.
Constify:
1 Introduce const accessor for route->ro_dst, rtcache_getdst().
2 Constify the 'dst' argument to ifnet->if_output(). This
led me to constify a lot of code called by output routines.
3 Constify the sockaddr argument to protosw->pr_ctlinput. This
led me to constify a lot of code called by ctlinput routines.
4 Introduce const macros for converting from a generic sockaddr
to family-specific sockaddrs, e.g., sockaddr_in: satocsin6,
satocsin, et cetera.
2007-02-18 01:34:07 +03:00
|
|
|
switch (af) {
|
1999-12-13 18:17:17 +03:00
|
|
|
#ifdef INET
|
|
|
|
case AF_INET:
|
2014-06-06 03:48:16 +04:00
|
|
|
pktq = ip_pktq;
|
1999-12-13 18:17:17 +03:00
|
|
|
break;
|
|
|
|
#endif
|
1999-06-28 10:36:47 +04:00
|
|
|
#ifdef INET6
|
|
|
|
case AF_INET6:
|
2014-06-06 03:48:16 +04:00
|
|
|
pktq = ip6_pktq;
|
1999-06-28 10:36:47 +04:00
|
|
|
break;
|
|
|
|
#endif
|
|
|
|
default:
|
|
|
|
m_freem(m);
|
|
|
|
return EAFNOSUPPORT;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* XXX do we need more sanity checks? */
|
2014-06-06 03:48:16 +04:00
|
|
|
KASSERT(pktq != NULL);
|
2016-06-10 16:27:10 +03:00
|
|
|
m_set_rcvif(m, ifp);
|
2014-06-06 03:48:16 +04:00
|
|
|
|
2001-04-14 03:29:55 +04:00
|
|
|
s = splnet();
|
2014-06-06 03:48:16 +04:00
|
|
|
if (__predict_true(pktq_enqueue(pktq, m, 0))) {
|
2020-01-29 07:11:35 +03:00
|
|
|
if_statadd2(ifp, if_ipackets, 1, if_ibytes, pktlen);
|
2014-06-06 03:48:16 +04:00
|
|
|
error = 0;
|
|
|
|
} else {
|
1999-06-28 10:36:47 +04:00
|
|
|
m_freem(m);
|
2014-06-06 03:48:16 +04:00
|
|
|
error = ENOBUFS;
|
1999-06-28 10:36:47 +04:00
|
|
|
}
|
|
|
|
splx(s);
|
2014-06-06 03:48:16 +04:00
|
|
|
|
|
|
|
return error;
|
1999-06-28 10:36:47 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
/* ARGSUSED */
|
|
|
|
static void
|
2006-11-16 04:32:37 +03:00
|
|
|
faithrtrequest(int cmd, struct rtentry *rt,
|
2008-10-24 21:07:33 +04:00
|
|
|
const struct rt_addrinfo *info)
|
1999-06-28 10:36:47 +04:00
|
|
|
{
|
2002-06-05 02:11:15 +04:00
|
|
|
if (rt)
|
1999-06-28 10:36:47 +04:00
|
|
|
rt->rt_rmx.rmx_mtu = rt->rt_ifp->if_mtu; /* for ISO */
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Process an ioctl request.
|
|
|
|
*/
|
|
|
|
/* ARGSUSED */
|
|
|
|
static int
|
2007-03-04 08:59:00 +03:00
|
|
|
faithioctl(struct ifnet *ifp, u_long cmd, void *data)
|
1999-06-28 10:36:47 +04:00
|
|
|
{
|
2000-03-30 13:45:33 +04:00
|
|
|
struct ifaddr *ifa;
|
|
|
|
struct ifreq *ifr = (struct ifreq *)data;
|
|
|
|
int error = 0;
|
1999-06-28 10:36:47 +04:00
|
|
|
|
|
|
|
switch (cmd) {
|
|
|
|
|
*** Summary ***
When a link-layer address changes (e.g., ifconfig ex0 link
02:de: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 03:20:01 +03:00
|
|
|
case SIOCINITIFADDR:
|
1999-06-28 10:36:47 +04:00
|
|
|
ifa = (struct ifaddr *)data;
|
|
|
|
ifa->ifa_rtrequest = faithrtrequest;
|
2017-12-06 10:40:16 +03:00
|
|
|
ifp->if_flags |= IFF_UP | IFF_RUNNING;
|
1999-06-28 10:36:47 +04:00
|
|
|
/*
|
|
|
|
* 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) {
|
1999-12-13 18:17:17 +03:00
|
|
|
#ifdef INET
|
|
|
|
case AF_INET:
|
|
|
|
break;
|
|
|
|
#endif
|
1999-06-28 10:36:47 +04:00
|
|
|
#ifdef INET6
|
|
|
|
case AF_INET6:
|
|
|
|
break;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
default:
|
|
|
|
error = EAFNOSUPPORT;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
*** Summary ***
When a link-layer address changes (e.g., ifconfig ex0 link
02:de: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 03:20:01 +03:00
|
|
|
default:
|
2008-02-07 04:21:52 +03:00
|
|
|
if ((error = ifioctl_common(ifp, cmd, data)) == ENETRESET)
|
|
|
|
error = 0;
|
1999-06-28 10:36:47 +04:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
return (error);
|
|
|
|
}
|
2001-05-08 14:15:13 +04:00
|
|
|
|
2006-01-31 20:15:20 +03:00
|
|
|
#ifdef INET6
|
2001-05-08 14:15:13 +04:00
|
|
|
/*
|
|
|
|
* XXX could be slow
|
|
|
|
* XXX could be layer violation to call sys/net from sys/netinet6
|
|
|
|
*/
|
|
|
|
int
|
2005-12-12 02:05:24 +03:00
|
|
|
faithprefix(struct in6_addr *in6)
|
2001-05-08 14:15:13 +04:00
|
|
|
{
|
|
|
|
struct rtentry *rt;
|
|
|
|
struct sockaddr_in6 sin6;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (ip6_keepfaith == 0)
|
|
|
|
return 0;
|
|
|
|
|
2001-07-18 20:43:09 +04:00
|
|
|
memset(&sin6, 0, sizeof(sin6));
|
2001-05-08 14:15:13 +04:00
|
|
|
sin6.sin6_family = AF_INET6;
|
|
|
|
sin6.sin6_len = sizeof(struct sockaddr_in6);
|
|
|
|
sin6.sin6_addr = *in6;
|
|
|
|
rt = rtalloc1((struct sockaddr *)&sin6, 0);
|
|
|
|
if (rt && rt->rt_ifp && rt->rt_ifp->if_type == IFT_FAITH &&
|
|
|
|
(rt->rt_ifp->if_flags & IFF_UP) != 0)
|
|
|
|
ret = 1;
|
|
|
|
else
|
|
|
|
ret = 0;
|
|
|
|
if (rt)
|
Make the routing table and rtcaches MP-safe
See the following descriptions for details.
Proposed on tech-kern and tech-net
Overview
--------
We protect the routing table with a rwock and protect
rtcaches with another rwlock. Each rtentry is protected
from being freed or updated via reference counting and psref.
Global rwlocks
--------------
There are two rwlocks; one for the routing table (rt_lock) and
the other for rtcaches (rtcache_lock). rtcache_lock covers
all existing rtcaches; there may have room for optimizations
(future work).
The locking order is rtcache_lock first and rt_lock is next.
rtentry references
------------------
References to an rtentry is managed with reference counting
and psref. Either of the two mechanisms is used depending on
where a rtentry is obtained. Reference counting is used when
we obtain a rtentry from the routing table directly via
rtalloc1 and rtrequest{,1} while psref is used when we obtain
a rtentry from a rtcache via rtcache_* APIs. In both cases,
a caller can sleep/block with holding an obtained rtentry.
The reasons why we use two different mechanisms are (i) only
using reference counting hurts the performance due to atomic
instructions (rtcache case) (ii) ease of implementation;
applying psref to APIs such rtaloc1 and rtrequest{,1} requires
additional works (adding a local variable and an argument).
We will finally migrate to use only psref but we can do it
when we have a lockless routing table alternative.
Reference counting for rtentry
------------------------------
rt_refcnt now doesn't count permanent references such as for
rt_timers and rtcaches, instead it is used only for temporal
references when obtaining a rtentry via rtalloc1 and rtrequest{,1}.
We can do so because destroying a rtentry always involves
removing references of rt_timers and rtcaches to the rtentry
and we don't need to track such references. This also makes
it easy to wait for readers to release references on deleting
or updating a rtentry, i.e., we can simply wait until the
reference counter is 0 or 1. (If there are permanent references
the counter can be arbitrary.)
rt_ref increments a reference counter of a rtentry and rt_unref
decrements it. rt_ref is called inside APIs (rtalloc1 and
rtrequest{,1} so users don't need to care about it while
users must call rt_unref to an obtained rtentry after using it.
rtfree is removed and we use rt_unref and rt_free instead.
rt_unref now just decrements the counter of a given rtentry
and rt_free just tries to destroy a given rtentry.
See the next section for destructions of rtentries by rt_free.
Destructions of rtentries
-------------------------
We destroy a rtentry only when we call rtrequst{,1}(RTM_DELETE);
the original implementation can destroy in any rtfree where it's
the last reference. If we use reference counting or psref, it's
easy to understand if the place that a rtentry is destroyed is
fixed.
rt_free waits for references to a given rtentry to be released
before actually destroying the rtentry. rt_free uses a condition
variable (cv_wait) (and psref_target_destroy for psref) to wait.
Unfortunately rtrequst{,1}(RTM_DELETE) can be called in softint
that we cannot use cv_wait. In that case, we have to defer the
destruction to a workqueue.
rtentry#rt_cv, rtentry#rt_psref and global variables
(see rt_free_global) are added to conduct the procedure.
Updates of rtentries
--------------------
One difficulty to use refcnt/psref instead of rwlock for rtentry
is updates of rtentries. We need an additional mechanism to
prevent readers from seeing inconsistency of a rtentry being
updated.
We introduce RTF_UPDATING flag to rtentries that are updating.
While the flag is set to a rtentry, users cannot acquire the
rtentry. By doing so, we avoid users to see inconsistent
rtentries.
There are two options when a user tries to acquire a rtentry
with the RTF_UPDATING flag; if a user runs in softint context
the user fails to acquire a rtentry (NULL is returned).
Otherwise a user waits until the update completes by waiting
on cv.
The procedure of a updater is simpler to destruction of
a rtentry. Wait on cv (and psref) and after all readers left,
proceed with the update.
Global variables (see rt_update_global) are added to conduct
the procedure.
Currently we apply the mechanism to only RTM_CHANGE in
rtsock.c. We would have to apply other codes. See
"Known issues" section.
psref for rtentry
-----------------
When we obtain a rtentry from a rtcache via rtcache_* APIs,
psref is used to reference to the rtentry.
rtcache_ref acquires a reference to a rtentry with psref
and rtcache_unref releases the reference after using it.
rtcache_ref is called inside rtcache_* APIs and users don't
need to take care of it while users must call rtcache_unref
to release the reference.
struct psref and int bound that is needed for psref is
embedded into struct route. By doing so we don't need to
add local variables and additional argument to APIs.
However this adds another constraint to psref other than
reference counting one's; holding a reference of an rtentry
via a rtcache is allowed by just one caller at the same time.
So we must not acquire a rtentry via a rtcache twice and
avoid a recursive use of a rtcache. And also a rtcache must
be arranged to be used by a LWP/softint at the same time
somehow. For IP forwarding case, we have per-CPU rtcaches
used in softint so the constraint is guaranteed. For a h
rtcache of a PCB case, the constraint is guaranteed by the
solock of each PCB. Any other cases (pf, ipf, stf and ipsec)
are currently guaranteed by only the existence of the global
locks (softnet_lock and/or KERNEL_LOCK). If we've found the
cases that we cannot guarantee the constraint, we would need
to introduce other rtcache APIs that use simple reference
counting.
psref of rtcache is created with IPL_SOFTNET and so rtcache
shouldn't used at an IPL higher than IPL_SOFTNET.
Note that rtcache_free is used to invalidate a given rtcache.
We don't need another care by my change; just keep them as
they are.
Performance impact
------------------
When NET_MPSAFE is disabled the performance drop is 3% while
when it's enabled the drop is increased to 11%. The difference
comes from that currently we don't take any global locks and
don't use psref if NET_MPSAFE is disabled.
We can optimize the performance of the case of NET_MPSAFE
on by reducing lookups of rtcache that uses psref;
currently we do two lookups but we should be able to trim
one of two. This is a future work.
Known issues
------------
There are two known issues to be solved; one is that
a caller of rtrequest(RTM_ADD) may change rtentry (see rtinit).
We need to prevent new references during the update. Or
we may be able to remove the code (perhaps, need more
investigations).
The other is rtredirect that updates a rtentry. We need
to apply our update mechanism, however it's not easy because
rtredirect is called in softint and we cannot apply our
mechanism simply. One solution is to defer rtredirect to
a workqueue but it requires some code restructuring.
2016-12-12 06:55:57 +03:00
|
|
|
rt_unref(rt);
|
2001-05-08 14:15:13 +04:00
|
|
|
return ret;
|
|
|
|
}
|
2006-01-31 20:15:20 +03:00
|
|
|
#endif
|
2016-08-07 20:38:33 +03:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Module infrastructure
|
|
|
|
*/
|
|
|
|
#include "if_module.h"
|
|
|
|
|
2019-04-27 09:18:15 +03:00
|
|
|
IF_MODULE(MODULE_CLASS_DRIVER, faith, NULL)
|