NetBSD/sys/net/if_stf.c

748 lines
18 KiB
C
Raw Normal View History

/* $NetBSD: if_stf.c,v 1.105 2018/06/26 06:48:02 msaitoh Exp $ */
2007-03-29 20:51:21 +04:00
/* $KAME: if_stf.c,v 1.62 2001/06/07 22:32:16 itojun Exp $ */
/*
* Copyright (C) 2000 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.
*/
/*
* 6to4 interface, based on RFC3056.
*
* 6to4 interface is NOT capable of link-layer (I mean, IPv4) multicasting.
* There is no address mapping defined from IPv6 multicast address to IPv4
* address. Therefore, we do not have IFF_MULTICAST on the interface.
*
* Due to the lack of address mapping for link-local addresses, we cannot
* throw packets toward link-local addresses (fe80::x). Also, we cannot throw
* packets to link-local multicast addresses (ff02::x).
*
* Here are interesting symptoms due to the lack of link-local address:
*
* Unicast routing exchange:
2000-04-21 06:40:53 +04:00
* - RIPng: Impossible. Uses link-local multicast packet toward ff02::9,
* and link-local addresses as nexthop.
* - OSPFv6: Impossible. OSPFv6 assumes that there's link-local address
* assigned to the link, and makes use of them. Also, HELLO packets use
* link-local multicast addresses (ff02::5 and ff02::6).
* - BGP4+: Maybe. You can only use global address as nexthop, and global
* address as TCP endpoint address.
*
* Multicast routing protocols:
* - PIM: Hello packet cannot be used to discover adjacent PIM routers.
* Adjacent PIM routers must be configured manually (is it really spec-wise
* correct thing to do?).
*
* ICMPv6:
* - Redirects cannot be used due to the lack of link-local address.
*
2005-02-27 01:45:09 +03:00
* stf interface does not have, and will not need, a link-local address.
* It seems to have no real benefit and does not help the above symptoms much.
* Even if we assign link-locals to interface, we cannot really
* use link-local unicast/multicast on top of 6to4 cloud (since there's no
* encapsulation defined for link-local address), and the above analysis does
* not change. RFC3056 does not mandate the assignment of link-local address
* either.
*
* 6to4 interface has security issues. Refer to
* http://playground.iijlab.net/i-d/draft-itojun-ipv6-transition-abuse-00.txt
* for details. The code tries to filter out some of malicious packets.
* Note that there is no way to be 100% secure.
*/
2001-11-13 02:49:33 +03:00
#include <sys/cdefs.h>
__KERNEL_RCSID(0, "$NetBSD: if_stf.c,v 1.105 2018/06/26 06:48:02 msaitoh Exp $");
2001-11-13 02:49:33 +03:00
2015-08-25 01:21:26 +03:00
#ifdef _KERNEL_OPT
#include "opt_inet.h"
#include "stf.h"
2015-08-25 01:21:26 +03:00
#endif
#ifndef INET6
#error "pseudo-device stf requires options INET6"
#endif
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/socket.h>
#include <sys/sockio.h>
#include <sys/mbuf.h>
#include <sys/errno.h>
#include <sys/ioctl.h>
#include <sys/proc.h>
#include <sys/queue.h>
#include <sys/syslog.h>
#include <sys/device.h>
#include <sys/module.h>
2006-05-15 01:19:33 +04:00
#include <sys/cpu.h>
#include <net/if.h>
#include <net/route.h>
#include <net/netisr.h>
#include <net/if_types.h>
#include <net/if_stf.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/in_var.h>
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet6/in6_var.h>
#include <netinet/ip_ecn.h>
#include <netinet/ip_encap.h>
#include <net/bpf.h>
#include "ioconf.h"
#define IN6_IS_ADDR_6TO4(x) (ntohs((x)->s6_addr16[0]) == 0x2002)
#define GET_V4(x) ((const struct in_addr *)(&(x)->s6_addr16[1]))
struct stf_softc {
struct ifnet sc_if; /* common area */
Eliminate address family-specific route caches (struct route, struct route_in6, struct route_iso), replacing all caches with a struct route. The principle benefit of this change is that all of the protocol families can benefit from route cache-invalidation, which is necessary for correct routing. Route-cache invalidation fixes an ancient PR, kern/3508, at long last; it fixes various other PRs, also. Discussions with and ideas from Joerg Sonnenberger influenced this work tremendously. Of course, all design oversights and bugs are mine. DETAILS 1 I added to each address family a pool of sockaddrs. I have introduced routines for allocating, copying, and duplicating, and freeing sockaddrs: struct sockaddr *sockaddr_alloc(sa_family_t af, int flags); struct sockaddr *sockaddr_copy(struct sockaddr *dst, const struct sockaddr *src); struct sockaddr *sockaddr_dup(const struct sockaddr *src, int flags); void sockaddr_free(struct sockaddr *sa); sockaddr_alloc() returns either a sockaddr from the pool belonging to the specified family, or NULL if the pool is exhausted. The returned sockaddr has the right size for that family; sa_family and sa_len fields are initialized to the family and sockaddr length---e.g., sa_family = AF_INET and sa_len = sizeof(struct sockaddr_in). sockaddr_free() puts the given sockaddr back into its family's pool. sockaddr_dup() and sockaddr_copy() work analogously to strdup() and strcpy(), respectively. sockaddr_copy() KASSERTs that the family of the destination and source sockaddrs are alike. The 'flags' argumet for sockaddr_alloc() and sockaddr_dup() is passed directly to pool_get(9). 2 I added routines for initializing sockaddrs in each address family, sockaddr_in_init(), sockaddr_in6_init(), sockaddr_iso_init(), etc. They are fairly self-explanatory. 3 structs route_in6 and route_iso are no more. All protocol families use struct route. I have changed the route cache, 'struct route', so that it does not contain storage space for a sockaddr. Instead, struct route points to a sockaddr coming from the pool the sockaddr belongs to. I added a new method to struct route, rtcache_setdst(), for setting the cache destination: int rtcache_setdst(struct route *, const struct sockaddr *); rtcache_setdst() returns 0 on success, or ENOMEM if no memory is available to create the sockaddr storage. It is now possible for rtcache_getdst() to return NULL if, say, rtcache_setdst() failed. I check the return value for NULL everywhere in the kernel. 4 Each routing domain (struct domain) has a list of live route caches, dom_rtcache. rtflushall(sa_family_t af) looks up the domain indicated by 'af', walks the domain's list of route caches and invalidates each one.
2007-05-03 00:40:22 +04:00
struct route sc_ro;
const struct encaptab *encap_cookie;
LIST_ENTRY(stf_softc) sc_list;
};
static LIST_HEAD(, stf_softc) stf_softc_list;
static int stf_clone_create(struct if_clone *, int);
static int stf_clone_destroy(struct ifnet *);
struct if_clone stf_cloner =
IF_CLONE_INITIALIZER("stf", stf_clone_create, stf_clone_destroy);
static int ip_stf_ttl = STF_TTL;
extern struct domain inetdomain;
static const struct encapsw in_stf_encapsw =
{
2016-01-28 03:28:11 +03:00
.encapsw4 = {
.pr_input = in_stf_input,
.pr_ctlinput = NULL,
}
};
static int stf_encapcheck(struct mbuf *, int, int, void *);
static struct in6_ifaddr *stf_getsrcifa6(struct ifnet *);
static int stf_output(struct ifnet *, struct mbuf *, const struct sockaddr *,
const struct rtentry *);
static int isrfc1918addr(const struct in_addr *);
static int stf_checkaddr4(struct stf_softc *, const struct in_addr *,
struct ifnet *);
static int stf_checkaddr6(struct stf_softc *, const struct in6_addr *,
struct ifnet *);
static void stf_rtrequest(int, struct rtentry *, const struct rt_addrinfo *);
static int stf_ioctl(struct ifnet *, u_long, void *);
/* ARGSUSED */
void
stfattach(int count)
{
/*
* Nothing to do here, initialization is handled by the
* module initialization code in stfinit() below).
*/
}
static void
stfinit(void)
{
LIST_INIT(&stf_softc_list);
if_clone_attach(&stf_cloner);
}
static int
stfdetach(void)
{
int error = 0;
if (!LIST_EMPTY(&stf_softc_list))
error = EBUSY;
if (error == 0)
if_clone_detach(&stf_cloner);
return error;
}
static int
stf_clone_create(struct if_clone *ifc, int unit)
{
struct stf_softc *sc;
int error;
sc = malloc(sizeof(struct stf_softc), M_DEVBUF, M_WAIT|M_ZERO);
if_initname(&sc->sc_if, ifc->ifc_name, unit);
error = encap_lock_enter();
if (error) {
free(sc, M_DEVBUF);
return error;
}
if (LIST_FIRST(&stf_softc_list) != NULL) {
/* Only one stf interface is allowed. */
encap_lock_exit();
free(sc, M_DEVBUF);
return EEXIST;
}
sc->encap_cookie = encap_attach_func(AF_INET, IPPROTO_IPV6,
stf_encapcheck, &in_stf_encapsw, sc);
encap_lock_exit();
if (sc->encap_cookie == NULL) {
printf("%s: unable to attach encap\n", if_name(&sc->sc_if));
free(sc, M_DEVBUF);
return EIO; /* XXX */
}
sc->sc_if.if_mtu = STF_MTU;
sc->sc_if.if_flags = 0;
sc->sc_if.if_ioctl = stf_ioctl;
sc->sc_if.if_output = stf_output;
sc->sc_if.if_type = IFT_STF;
2000-12-18 22:44:33 +03:00
sc->sc_if.if_dlt = DLT_NULL;
error = if_attach(&sc->sc_if);
if (error != 0) {
aprint_error("%s: if_initialize failed(%d)\n",
if_name(&sc->sc_if), error);
encap_lock_enter();
encap_detach(sc->encap_cookie);
encap_lock_exit();
free(sc, M_DEVBUF);
return error;
}
if_alloc_sadl(&sc->sc_if);
bpf_attach(&sc->sc_if, DLT_NULL, sizeof(u_int));
LIST_INSERT_HEAD(&stf_softc_list, sc, sc_list);
return 0;
}
static int
stf_clone_destroy(struct ifnet *ifp)
{
struct stf_softc *sc = (void *) ifp;
encap_lock_enter();
LIST_REMOVE(sc, sc_list);
encap_detach(sc->encap_cookie);
encap_lock_exit();
bpf_detach(ifp);
if_detach(ifp);
Eliminate address family-specific route caches (struct route, struct route_in6, struct route_iso), replacing all caches with a struct route. The principle benefit of this change is that all of the protocol families can benefit from route cache-invalidation, which is necessary for correct routing. Route-cache invalidation fixes an ancient PR, kern/3508, at long last; it fixes various other PRs, also. Discussions with and ideas from Joerg Sonnenberger influenced this work tremendously. Of course, all design oversights and bugs are mine. DETAILS 1 I added to each address family a pool of sockaddrs. I have introduced routines for allocating, copying, and duplicating, and freeing sockaddrs: struct sockaddr *sockaddr_alloc(sa_family_t af, int flags); struct sockaddr *sockaddr_copy(struct sockaddr *dst, const struct sockaddr *src); struct sockaddr *sockaddr_dup(const struct sockaddr *src, int flags); void sockaddr_free(struct sockaddr *sa); sockaddr_alloc() returns either a sockaddr from the pool belonging to the specified family, or NULL if the pool is exhausted. The returned sockaddr has the right size for that family; sa_family and sa_len fields are initialized to the family and sockaddr length---e.g., sa_family = AF_INET and sa_len = sizeof(struct sockaddr_in). sockaddr_free() puts the given sockaddr back into its family's pool. sockaddr_dup() and sockaddr_copy() work analogously to strdup() and strcpy(), respectively. sockaddr_copy() KASSERTs that the family of the destination and source sockaddrs are alike. The 'flags' argumet for sockaddr_alloc() and sockaddr_dup() is passed directly to pool_get(9). 2 I added routines for initializing sockaddrs in each address family, sockaddr_in_init(), sockaddr_in6_init(), sockaddr_iso_init(), etc. They are fairly self-explanatory. 3 structs route_in6 and route_iso are no more. All protocol families use struct route. I have changed the route cache, 'struct route', so that it does not contain storage space for a sockaddr. Instead, struct route points to a sockaddr coming from the pool the sockaddr belongs to. I added a new method to struct route, rtcache_setdst(), for setting the cache destination: int rtcache_setdst(struct route *, const struct sockaddr *); rtcache_setdst() returns 0 on success, or ENOMEM if no memory is available to create the sockaddr storage. It is now possible for rtcache_getdst() to return NULL if, say, rtcache_setdst() failed. I check the return value for NULL everywhere in the kernel. 4 Each routing domain (struct domain) has a list of live route caches, dom_rtcache. rtflushall(sa_family_t af) looks up the domain indicated by 'af', walks the domain's list of route caches and invalidates each one.
2007-05-03 00:40:22 +04:00
rtcache_free(&sc->sc_ro);
free(sc, M_DEVBUF);
return 0;
}
static int
stf_encapcheck(struct mbuf *m, int off, int proto, void *arg)
{
struct ip ip;
struct in6_ifaddr *ia6;
struct stf_softc *sc;
struct in_addr a, b;
sc = (struct stf_softc *)arg;
if (sc == NULL)
return 0;
if ((sc->sc_if.if_flags & IFF_UP) == 0)
return 0;
/* IFF_LINK0 means "no decapsulation" */
if ((sc->sc_if.if_flags & IFF_LINK0) != 0)
return 0;
if (proto != IPPROTO_IPV6)
return 0;
m_copydata(m, 0, sizeof(ip), (void *)&ip);
if (ip.ip_v != 4)
return 0;
ia6 = stf_getsrcifa6(&sc->sc_if);
if (ia6 == NULL)
return 0;
/*
* check if IPv4 dst matches the IPv4 address derived from the
* local 6to4 address.
* success on: dst = 10.1.1.1, ia6->ia_addr = 2002:0a01:0101:...
*/
2009-03-18 18:14:29 +03:00
if (memcmp(GET_V4(&ia6->ia_addr.sin6_addr), &ip.ip_dst,
sizeof(ip.ip_dst)) != 0)
return 0;
/*
* check if IPv4 src matches the IPv4 address derived from the
* local 6to4 address masked by prefixmask.
* success on: src = 10.1.1.1, ia6->ia_addr = 2002:0a00:.../24
* fail on: src = 10.1.1.1, ia6->ia_addr = 2002:0b00:.../24
*/
2001-07-18 20:43:09 +04:00
memset(&a, 0, sizeof(a));
a.s_addr = GET_V4(&ia6->ia_addr.sin6_addr)->s_addr;
a.s_addr &= GET_V4(&ia6->ia_prefixmask.sin6_addr)->s_addr;
b = ip.ip_src;
b.s_addr &= GET_V4(&ia6->ia_prefixmask.sin6_addr)->s_addr;
if (a.s_addr != b.s_addr)
return 0;
/* stf interface makes single side match only */
return 32;
}
static struct in6_ifaddr *
stf_getsrcifa6(struct ifnet *ifp)
{
struct ifaddr *ifa;
struct in_ifaddr *ia4;
struct sockaddr_in6 *sin6;
struct in_addr in;
int s;
s = pserialize_read_enter();
IFADDR_READER_FOREACH(ifa, ifp) {
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
sin6 = (struct sockaddr_in6 *)ifa->ifa_addr;
if (!IN6_IS_ADDR_6TO4(&sin6->sin6_addr))
continue;
memcpy(&in, GET_V4(&sin6->sin6_addr), sizeof(in));
ia4 = in_get_ia(in);
if (ia4 == NULL)
continue;
pserialize_read_exit(s);
/* TODO NOMPSAFE */
return (struct in6_ifaddr *)ifa;
}
pserialize_read_exit(s);
return NULL;
}
static int
stf_output(struct ifnet *ifp, struct mbuf *m, const struct sockaddr *dst,
const struct rtentry *rt0)
{
struct rtentry *rt;
struct stf_softc *sc;
const struct sockaddr_in6 *dst6;
const struct in_addr *in4;
uint8_t tos;
struct ip *ip;
struct ip6_hdr *ip6;
struct in6_ifaddr *ia6;
Eliminate address family-specific route caches (struct route, struct route_in6, struct route_iso), replacing all caches with a struct route. The principle benefit of this change is that all of the protocol families can benefit from route cache-invalidation, which is necessary for correct routing. Route-cache invalidation fixes an ancient PR, kern/3508, at long last; it fixes various other PRs, also. Discussions with and ideas from Joerg Sonnenberger influenced this work tremendously. Of course, all design oversights and bugs are mine. DETAILS 1 I added to each address family a pool of sockaddrs. I have introduced routines for allocating, copying, and duplicating, and freeing sockaddrs: struct sockaddr *sockaddr_alloc(sa_family_t af, int flags); struct sockaddr *sockaddr_copy(struct sockaddr *dst, const struct sockaddr *src); struct sockaddr *sockaddr_dup(const struct sockaddr *src, int flags); void sockaddr_free(struct sockaddr *sa); sockaddr_alloc() returns either a sockaddr from the pool belonging to the specified family, or NULL if the pool is exhausted. The returned sockaddr has the right size for that family; sa_family and sa_len fields are initialized to the family and sockaddr length---e.g., sa_family = AF_INET and sa_len = sizeof(struct sockaddr_in). sockaddr_free() puts the given sockaddr back into its family's pool. sockaddr_dup() and sockaddr_copy() work analogously to strdup() and strcpy(), respectively. sockaddr_copy() KASSERTs that the family of the destination and source sockaddrs are alike. The 'flags' argumet for sockaddr_alloc() and sockaddr_dup() is passed directly to pool_get(9). 2 I added routines for initializing sockaddrs in each address family, sockaddr_in_init(), sockaddr_in6_init(), sockaddr_iso_init(), etc. They are fairly self-explanatory. 3 structs route_in6 and route_iso are no more. All protocol families use struct route. I have changed the route cache, 'struct route', so that it does not contain storage space for a sockaddr. Instead, struct route points to a sockaddr coming from the pool the sockaddr belongs to. I added a new method to struct route, rtcache_setdst(), for setting the cache destination: int rtcache_setdst(struct route *, const struct sockaddr *); rtcache_setdst() returns 0 on success, or ENOMEM if no memory is available to create the sockaddr storage. It is now possible for rtcache_getdst() to return NULL if, say, rtcache_setdst() failed. I check the return value for NULL everywhere in the kernel. 4 Each routing domain (struct domain) has a list of live route caches, dom_rtcache. rtflushall(sa_family_t af) looks up the domain indicated by 'af', walks the domain's list of route caches and invalidates each one.
2007-05-03 00:40:22 +04:00
union {
struct sockaddr dst;
struct sockaddr_in dst4;
} u;
sc = (struct stf_softc*)ifp;
dst6 = (const struct sockaddr_in6 *)dst;
/* just in case */
if ((ifp->if_flags & IFF_UP) == 0) {
m_freem(m);
return ENETDOWN;
}
/*
* If we don't have an ip4 address that match my inner ip6 address,
* we shouldn't generate output. Without this check, we'll end up
* using wrong IPv4 source.
*/
ia6 = stf_getsrcifa6(ifp);
if (ia6 == NULL) {
m_freem(m);
ifp->if_oerrors++;
return ENETDOWN;
}
if (m->m_len < sizeof(*ip6)) {
m = m_pullup(m, sizeof(*ip6));
if (m == NULL) {
ifp->if_oerrors++;
return ENOBUFS;
}
}
ip6 = mtod(m, struct ip6_hdr *);
tos = (ntohl(ip6->ip6_flow) >> 20) & 0xff;
/*
* Pickup the right outer dst addr from the list of candidates.
* ip6_dst has priority as it may be able to give us shorter IPv4 hops.
*/
if (IN6_IS_ADDR_6TO4(&ip6->ip6_dst))
in4 = GET_V4(&ip6->ip6_dst);
else if (IN6_IS_ADDR_6TO4(&dst6->sin6_addr))
in4 = GET_V4(&dst6->sin6_addr);
else {
m_freem(m);
ifp->if_oerrors++;
return ENETUNREACH;
}
bpf_mtap_af(ifp, AF_INET6, m, BPF_D_OUT);
M_PREPEND(m, sizeof(struct ip), M_DONTWAIT);
if (m && m->m_len < sizeof(struct ip))
m = m_pullup(m, sizeof(struct ip));
if (m == NULL) {
ifp->if_oerrors++;
return ENOBUFS;
}
ip = mtod(m, struct ip *);
2001-07-18 20:43:09 +04:00
memset(ip, 0, sizeof(*ip));
bcopy(GET_V4(&((struct sockaddr_in6 *)&ia6->ia_addr)->sin6_addr),
&ip->ip_src, sizeof(ip->ip_src));
memcpy(&ip->ip_dst, in4, sizeof(ip->ip_dst));
ip->ip_p = IPPROTO_IPV6;
ip->ip_ttl = ip_stf_ttl;
ip->ip_len = htons(m->m_pkthdr.len);
if (ifp->if_flags & IFF_LINK1)
ip_ecn_ingress(ECN_ALLOWED, &ip->ip_tos, &tos);
else
ip_ecn_ingress(ECN_NOCARE, &ip->ip_tos, &tos);
Eliminate address family-specific route caches (struct route, struct route_in6, struct route_iso), replacing all caches with a struct route. The principle benefit of this change is that all of the protocol families can benefit from route cache-invalidation, which is necessary for correct routing. Route-cache invalidation fixes an ancient PR, kern/3508, at long last; it fixes various other PRs, also. Discussions with and ideas from Joerg Sonnenberger influenced this work tremendously. Of course, all design oversights and bugs are mine. DETAILS 1 I added to each address family a pool of sockaddrs. I have introduced routines for allocating, copying, and duplicating, and freeing sockaddrs: struct sockaddr *sockaddr_alloc(sa_family_t af, int flags); struct sockaddr *sockaddr_copy(struct sockaddr *dst, const struct sockaddr *src); struct sockaddr *sockaddr_dup(const struct sockaddr *src, int flags); void sockaddr_free(struct sockaddr *sa); sockaddr_alloc() returns either a sockaddr from the pool belonging to the specified family, or NULL if the pool is exhausted. The returned sockaddr has the right size for that family; sa_family and sa_len fields are initialized to the family and sockaddr length---e.g., sa_family = AF_INET and sa_len = sizeof(struct sockaddr_in). sockaddr_free() puts the given sockaddr back into its family's pool. sockaddr_dup() and sockaddr_copy() work analogously to strdup() and strcpy(), respectively. sockaddr_copy() KASSERTs that the family of the destination and source sockaddrs are alike. The 'flags' argumet for sockaddr_alloc() and sockaddr_dup() is passed directly to pool_get(9). 2 I added routines for initializing sockaddrs in each address family, sockaddr_in_init(), sockaddr_in6_init(), sockaddr_iso_init(), etc. They are fairly self-explanatory. 3 structs route_in6 and route_iso are no more. All protocol families use struct route. I have changed the route cache, 'struct route', so that it does not contain storage space for a sockaddr. Instead, struct route points to a sockaddr coming from the pool the sockaddr belongs to. I added a new method to struct route, rtcache_setdst(), for setting the cache destination: int rtcache_setdst(struct route *, const struct sockaddr *); rtcache_setdst() returns 0 on success, or ENOMEM if no memory is available to create the sockaddr storage. It is now possible for rtcache_getdst() to return NULL if, say, rtcache_setdst() failed. I check the return value for NULL everywhere in the kernel. 4 Each routing domain (struct domain) has a list of live route caches, dom_rtcache. rtflushall(sa_family_t af) looks up the domain indicated by 'af', walks the domain's list of route caches and invalidates each one.
2007-05-03 00:40:22 +04:00
sockaddr_in_init(&u.dst4, &ip->ip_dst, 0);
if ((rt = rtcache_lookup(&sc->sc_ro, &u.dst)) == NULL) {
Eliminate address family-specific route caches (struct route, struct route_in6, struct route_iso), replacing all caches with a struct route. The principle benefit of this change is that all of the protocol families can benefit from route cache-invalidation, which is necessary for correct routing. Route-cache invalidation fixes an ancient PR, kern/3508, at long last; it fixes various other PRs, also. Discussions with and ideas from Joerg Sonnenberger influenced this work tremendously. Of course, all design oversights and bugs are mine. DETAILS 1 I added to each address family a pool of sockaddrs. I have introduced routines for allocating, copying, and duplicating, and freeing sockaddrs: struct sockaddr *sockaddr_alloc(sa_family_t af, int flags); struct sockaddr *sockaddr_copy(struct sockaddr *dst, const struct sockaddr *src); struct sockaddr *sockaddr_dup(const struct sockaddr *src, int flags); void sockaddr_free(struct sockaddr *sa); sockaddr_alloc() returns either a sockaddr from the pool belonging to the specified family, or NULL if the pool is exhausted. The returned sockaddr has the right size for that family; sa_family and sa_len fields are initialized to the family and sockaddr length---e.g., sa_family = AF_INET and sa_len = sizeof(struct sockaddr_in). sockaddr_free() puts the given sockaddr back into its family's pool. sockaddr_dup() and sockaddr_copy() work analogously to strdup() and strcpy(), respectively. sockaddr_copy() KASSERTs that the family of the destination and source sockaddrs are alike. The 'flags' argumet for sockaddr_alloc() and sockaddr_dup() is passed directly to pool_get(9). 2 I added routines for initializing sockaddrs in each address family, sockaddr_in_init(), sockaddr_in6_init(), sockaddr_iso_init(), etc. They are fairly self-explanatory. 3 structs route_in6 and route_iso are no more. All protocol families use struct route. I have changed the route cache, 'struct route', so that it does not contain storage space for a sockaddr. Instead, struct route points to a sockaddr coming from the pool the sockaddr belongs to. I added a new method to struct route, rtcache_setdst(), for setting the cache destination: int rtcache_setdst(struct route *, const struct sockaddr *); rtcache_setdst() returns 0 on success, or ENOMEM if no memory is available to create the sockaddr storage. It is now possible for rtcache_getdst() to return NULL if, say, rtcache_setdst() failed. I check the return value for NULL everywhere in the kernel. 4 Each routing domain (struct domain) has a list of live route caches, dom_rtcache. rtflushall(sa_family_t af) looks up the domain indicated by 'af', walks the domain's list of route caches and invalidates each one.
2007-05-03 00:40:22 +04:00
m_freem(m);
ifp->if_oerrors++;
return ENETUNREACH;
}
/* If the route constitutes infinite encapsulation, punt. */
if (rt->rt_ifp == ifp) {
rtcache_unref(rt, &sc->sc_ro);
rtcache_free(&sc->sc_ro);
m_freem(m);
ifp->if_oerrors++;
return ENETUNREACH;
}
rtcache_unref(rt, &sc->sc_ro);
ifp->if_opackets++;
ifp->if_obytes += m->m_pkthdr.len - sizeof(struct ip);
Eliminate address family-specific route caches (struct route, struct route_in6, struct route_iso), replacing all caches with a struct route. The principle benefit of this change is that all of the protocol families can benefit from route cache-invalidation, which is necessary for correct routing. Route-cache invalidation fixes an ancient PR, kern/3508, at long last; it fixes various other PRs, also. Discussions with and ideas from Joerg Sonnenberger influenced this work tremendously. Of course, all design oversights and bugs are mine. DETAILS 1 I added to each address family a pool of sockaddrs. I have introduced routines for allocating, copying, and duplicating, and freeing sockaddrs: struct sockaddr *sockaddr_alloc(sa_family_t af, int flags); struct sockaddr *sockaddr_copy(struct sockaddr *dst, const struct sockaddr *src); struct sockaddr *sockaddr_dup(const struct sockaddr *src, int flags); void sockaddr_free(struct sockaddr *sa); sockaddr_alloc() returns either a sockaddr from the pool belonging to the specified family, or NULL if the pool is exhausted. The returned sockaddr has the right size for that family; sa_family and sa_len fields are initialized to the family and sockaddr length---e.g., sa_family = AF_INET and sa_len = sizeof(struct sockaddr_in). sockaddr_free() puts the given sockaddr back into its family's pool. sockaddr_dup() and sockaddr_copy() work analogously to strdup() and strcpy(), respectively. sockaddr_copy() KASSERTs that the family of the destination and source sockaddrs are alike. The 'flags' argumet for sockaddr_alloc() and sockaddr_dup() is passed directly to pool_get(9). 2 I added routines for initializing sockaddrs in each address family, sockaddr_in_init(), sockaddr_in6_init(), sockaddr_iso_init(), etc. They are fairly self-explanatory. 3 structs route_in6 and route_iso are no more. All protocol families use struct route. I have changed the route cache, 'struct route', so that it does not contain storage space for a sockaddr. Instead, struct route points to a sockaddr coming from the pool the sockaddr belongs to. I added a new method to struct route, rtcache_setdst(), for setting the cache destination: int rtcache_setdst(struct route *, const struct sockaddr *); rtcache_setdst() returns 0 on success, or ENOMEM if no memory is available to create the sockaddr storage. It is now possible for rtcache_getdst() to return NULL if, say, rtcache_setdst() failed. I check the return value for NULL everywhere in the kernel. 4 Each routing domain (struct domain) has a list of live route caches, dom_rtcache. rtflushall(sa_family_t af) looks up the domain indicated by 'af', walks the domain's list of route caches and invalidates each one.
2007-05-03 00:40:22 +04:00
return ip_output(m, NULL, &sc->sc_ro, 0, NULL, NULL);
}
static int
isrfc1918addr(const struct in_addr *in)
{
/*
* returns 1 if private address range:
* 10.0.0.0/8 172.16.0.0/12 192.168.0.0/16
*/
if ((ntohl(in->s_addr) & 0xff000000) >> 24 == 10 ||
(ntohl(in->s_addr) & 0xfff00000) >> 16 == 172 * 256 + 16 ||
(ntohl(in->s_addr) & 0xffff0000) >> 16 == 192 * 256 + 168)
return 1;
return 0;
}
static int
stf_checkaddr4(struct stf_softc *sc, const struct in_addr *in,
struct ifnet *inifp /*incoming interface*/)
{
struct in_ifaddr *ia4;
/*
* reject packets with the following address:
* 224.0.0.0/4 0.0.0.0/8 127.0.0.0/8 255.0.0.0/8
*/
if (IN_MULTICAST(in->s_addr))
return -1;
switch ((ntohl(in->s_addr) & 0xff000000) >> 24) {
case 0: case 127: case 255:
return -1;
}
/*
* reject packets with private address range.
* (requirement from RFC3056 section 2 1st paragraph)
*/
if (isrfc1918addr(in))
return -1;
/*
* reject packet with IPv4 link-local (169.254.0.0/16),
* as suggested in draft-savola-v6ops-6to4-security-00.txt
*/
if (((ntohl(in->s_addr) & 0xff000000) >> 24) == 169 &&
((ntohl(in->s_addr) & 0x00ff0000) >> 16) == 254)
return -1;
/*
* reject packets with broadcast
*/
IN_ADDRLIST_READER_FOREACH(ia4) {
if ((ia4->ia_ifa.ifa_ifp->if_flags & IFF_BROADCAST) == 0)
continue;
if (in->s_addr == ia4->ia_broadaddr.sin_addr.s_addr)
return -1;
}
/*
* perform ingress filter
*/
if (sc && (sc->sc_if.if_flags & IFF_LINK2) == 0 && inifp) {
struct sockaddr_in sin;
struct rtentry *rt;
2001-07-18 20:43:09 +04:00
memset(&sin, 0, sizeof(sin));
sin.sin_family = AF_INET;
sin.sin_len = sizeof(struct sockaddr_in);
sin.sin_addr = *in;
rt = rtalloc1((struct sockaddr *)&sin, 0);
if (!rt || rt->rt_ifp != inifp) {
#if 0
log(LOG_WARNING, "%s: packet from 0x%x dropped "
"due to ingress filter\n", if_name(&sc->sc_if),
(uint32_t)ntohl(sin.sin_addr.s_addr));
#endif
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);
return -1;
}
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);
}
return 0;
}
static int
stf_checkaddr6(struct stf_softc *sc, const struct in6_addr *in6,
struct ifnet *inifp /*incoming interface*/)
{
/*
* check 6to4 addresses
*/
if (IN6_IS_ADDR_6TO4(in6))
return stf_checkaddr4(sc, GET_V4(in6), inifp);
/*
* reject anything that look suspicious. the test is implemented
* in ip6_input too, but we check here as well to
* (1) reject bad packets earlier, and
* (2) to be safe against future ip6_input change.
*/
if (IN6_IS_ADDR_V4COMPAT(in6) || IN6_IS_ADDR_V4MAPPED(in6))
return -1;
/*
* reject link-local and site-local unicast
* as suggested in draft-savola-v6ops-6to4-security-00.txt
*/
if (IN6_IS_ADDR_LINKLOCAL(in6) || IN6_IS_ADDR_SITELOCAL(in6))
return -1;
/*
* reject node-local and link-local multicast
* as suggested in draft-savola-v6ops-6to4-security-00.txt
*/
if (IN6_IS_ADDR_MC_NODELOCAL(in6) || IN6_IS_ADDR_MC_LINKLOCAL(in6))
return -1;
return 0;
}
2016-01-28 03:28:11 +03:00
void
in_stf_input(struct mbuf *m, int off, int proto, void *eparg)
{
int s;
struct stf_softc *sc = eparg;
struct ip *ip;
struct ip6_hdr *ip6;
uint8_t otos, itos;
struct ifnet *ifp;
size_t pktlen;
KASSERT(sc != NULL);
if (proto != IPPROTO_IPV6) {
m_freem(m);
2016-01-28 03:28:11 +03:00
return;
}
ip = mtod(m, struct ip *);
if ((sc->sc_if.if_flags & IFF_UP) == 0) {
m_freem(m);
2016-01-28 03:28:11 +03:00
return;
}
ifp = &sc->sc_if;
/*
* perform sanity check against outer src/dst.
* for source, perform ingress filter as well.
*/
if (stf_checkaddr4(sc, &ip->ip_dst, NULL) < 0 ||
stf_checkaddr4(sc, &ip->ip_src, m_get_rcvif_NOMPSAFE(m)) < 0) {
m_freem(m);
2016-01-28 03:28:11 +03:00
return;
}
otos = ip->ip_tos;
m_adj(m, off);
if (m->m_len < sizeof(*ip6)) {
m = m_pullup(m, sizeof(*ip6));
if (!m)
2016-01-28 03:28:11 +03:00
return;
}
ip6 = mtod(m, struct ip6_hdr *);
/*
* perform sanity check against inner src/dst.
* for source, perform ingress filter as well.
*/
if (stf_checkaddr6(sc, &ip6->ip6_dst, NULL) < 0 ||
stf_checkaddr6(sc, &ip6->ip6_src, m_get_rcvif_NOMPSAFE(m)) < 0) {
m_freem(m);
2016-01-28 03:28:11 +03:00
return;
}
itos = (ntohl(ip6->ip6_flow) >> 20) & 0xff;
if ((ifp->if_flags & IFF_LINK1) != 0)
ip_ecn_egress(ECN_ALLOWED, &otos, &itos);
else
ip_ecn_egress(ECN_NOCARE, &otos, &itos);
ip6->ip6_flow &= ~htonl(0xff << 20);
ip6->ip6_flow |= htonl((uint32_t)itos << 20);
pktlen = m->m_pkthdr.len;
m_set_rcvif(m, ifp);
2005-02-27 01:45:09 +03:00
bpf_mtap_af(ifp, AF_INET6, m, BPF_D_IN);
/*
* Put the packet to the network layer input queue according to the
* specified address family.
* See net/if_gif.c for possible issues with packet processing
* reorder due to extra queueing.
*/
s = splnet();
if (__predict_true(pktq_enqueue(ip6_pktq, m, 0))) {
ifp->if_ipackets++;
ifp->if_ibytes += pktlen;
} else {
m_freem(m);
}
splx(s);
2016-01-28 03:28:11 +03:00
return;
}
/* ARGSUSED */
static void
stf_rtrequest(int cmd, struct rtentry *rt,
const struct rt_addrinfo *info)
{
if (rt != NULL) {
struct stf_softc *sc;
sc = LIST_FIRST(&stf_softc_list);
rt->rt_rmx.rmx_mtu = (sc != NULL) ? sc->sc_if.if_mtu : STF_MTU;
}
}
static int
stf_ioctl(struct ifnet *ifp, u_long cmd, void *data)
{
struct ifaddr *ifa;
struct ifreq *ifr = data;
struct sockaddr_in6 *sin6;
int error;
error = 0;
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:
ifa = (struct ifaddr *)data;
if (ifa == NULL || ifa->ifa_addr->sa_family != AF_INET6) {
error = EAFNOSUPPORT;
break;
}
sin6 = (struct sockaddr_in6 *)ifa->ifa_addr;
if (IN6_IS_ADDR_6TO4(&sin6->sin6_addr) &&
!isrfc1918addr(GET_V4(&sin6->sin6_addr))) {
ifa->ifa_rtrequest = stf_rtrequest;
ifp->if_flags |= IFF_UP;
} else
error = EINVAL;
break;
case SIOCADDMULTI:
case SIOCDELMULTI:
if (ifr != NULL &&
ifreq_getaddr(cmd, ifr)->sa_family == AF_INET6)
;
else
error = EAFNOSUPPORT;
break;
case SIOCSIFMTU:
if (ifr->ifr_mtu < STF_MTU_MIN || ifr->ifr_mtu > STF_MTU_MAX)
return EINVAL;
else if ((error = ifioctl_common(ifp, cmd, data)) == ENETRESET)
error = 0;
break;
default:
*** 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
error = ifioctl_common(ifp, cmd, data);
break;
}
return error;
}
/*
* Module infrastructure
*/
#include "if_module.h"
IF_MODULE(MODULE_CLASS_DRIVER, stf, "")