freebsd-dev/sys/netinet/if_atm.c
Julian Elischer 8b07e49a00 Add code to allow the system to handle multiple routing tables.
This particular implementation is designed to be fully backwards compatible
and to be MFC-able to 7.x (and 6.x)

Currently the only protocol that can make use of the multiple tables is IPv4
Similar functionality exists in OpenBSD and Linux.

From my notes:

-----

  One thing where FreeBSD has been falling behind, and which by chance I
  have some time to work on is "policy based routing", which allows
  different
  packet streams to be routed by more than just the destination address.

  Constraints:
  ------------

  I want to make some form of this available in the 6.x tree
  (and by extension 7.x) , but FreeBSD in general needs it so I might as
  well do it in -current and back port the portions I need.

  One of the ways that this can be done is to have the ability to
  instantiate multiple kernel routing tables (which I will now
  refer to as "Forwarding Information Bases" or "FIBs" for political
  correctness reasons). Which FIB a particular packet uses to make
  the next hop decision can be decided by a number of mechanisms.
  The policies these mechanisms implement are the "Policies" referred
  to in "Policy based routing".

  One of the constraints I have if I try to back port this work to
  6.x is that it must be implemented as a EXTENSION to the existing
  ABIs in 6.x so that third party applications do not need to be
  recompiled in timespan of the branch.

  This first version will not have some of the bells and whistles that
  will come with later versions. It will, for example, be limited to 16
  tables in the first commit.
  Implementation method, Compatible version. (part 1)
  -------------------------------
  For this reason I have implemented a "sufficient subset" of a
  multiple routing table solution in Perforce, and back-ported it
  to 6.x. (also in Perforce though not  always caught up with what I
  have done in -current/P4). The subset allows a number of FIBs
  to be defined at compile time (8 is sufficient for my purposes in 6.x)
  and implements the changes needed to allow IPV4 to use them. I have not
  done the changes for ipv6 simply because I do not need it, and I do not
  have enough knowledge of ipv6 (e.g. neighbor discovery) needed to do it.

  Other protocol families are left untouched and should there be
  users with proprietary protocol families, they should continue to work
  and be oblivious to the existence of the extra FIBs.

  To understand how this is done, one must know that the current FIB
  code starts everything off with a single dimensional array of
  pointers to FIB head structures (One per protocol family), each of
  which in turn points to the trie of routes available to that family.

  The basic change in the ABI compatible version of the change is to
  extent that array to be a 2 dimensional array, so that
  instead of protocol family X looking at rt_tables[X] for the
  table it needs, it looks at rt_tables[Y][X] when for all
  protocol families except ipv4 Y is always 0.
  Code that is unaware of the change always just sees the first row
  of the table, which of course looks just like the one dimensional
  array that existed before.

  The entry points rtrequest(), rtalloc(), rtalloc1(), rtalloc_ign()
  are all maintained, but refer only to the first row of the array,
  so that existing callers in proprietary protocols can continue to
  do the "right thing".
  Some new entry points are added, for the exclusive use of ipv4 code
  called in_rtrequest(), in_rtalloc(), in_rtalloc1() and in_rtalloc_ign(),
  which have an extra argument which refers the code to the correct row.

  In addition, there are some new entry points (currently called
  rtalloc_fib() and friends) that check the Address family being
  looked up and call either rtalloc() (and friends) if the protocol
  is not IPv4 forcing the action to row 0 or to the appropriate row
  if it IS IPv4 (and that info is available). These are for calling
  from code that is not specific to any particular protocol. The way
  these are implemented would change in the non ABI preserving code
  to be added later.

  One feature of the first version of the code is that for ipv4,
  the interface routes show up automatically on all the FIBs, so
  that no matter what FIB you select you always have the basic
  direct attached hosts available to you. (rtinit() does this
  automatically).

  You CAN delete an interface route from one FIB should you want
  to but by default it's there. ARP information is also available
  in each FIB. It's assumed that the same machine would have the
  same MAC address, regardless of which FIB you are using to get
  to it.

  This brings us as to how the correct FIB is selected for an outgoing
  IPV4 packet.

  Firstly, all packets have a FIB associated with them. if nothing
  has been done to change it, it will be FIB 0. The FIB is changed
  in the following ways.

  Packets fall into one of a number of classes.

  1/ locally generated packets, coming from a socket/PCB.
     Such packets select a FIB from a number associated with the
     socket/PCB. This in turn is inherited from the process,
     but can be changed by a socket option. The process in turn
     inherits it on fork. I have written a utility call setfib
     that acts a bit like nice..

         setfib -3 ping target.example.com # will use fib 3 for ping.

     It is an obvious extension to make it a property of a jail
     but I have not done so. It can be achieved by combining the setfib and
     jail commands.

  2/ packets received on an interface for forwarding.
     By default these packets would use table 0,
     (or possibly a number settable in a sysctl(not yet)).
     but prior to routing the firewall can inspect them (see below).
     (possibly in the future you may be able to associate a FIB
     with packets received on an interface..  An ifconfig arg, but not yet.)

  3/ packets inspected by a packet classifier, which can arbitrarily
     associate a fib with it on a packet by packet basis.
     A fib assigned to a packet by a packet classifier
     (such as ipfw) would over-ride a fib associated by
     a more default source. (such as cases 1 or 2).

  4/ a tcp listen socket associated with a fib will generate
     accept sockets that are associated with that same fib.

  5/ Packets generated in response to some other packet (e.g. reset
     or icmp packets). These should use the FIB associated with the
     packet being reponded to.

  6/ Packets generated during encapsulation.
     gif, tun and other tunnel interfaces will encapsulate using the FIB
     that was in effect withthe proces that set up the tunnel.
     thus setfib 1 ifconfig gif0 [tunnel instructions]
     will set the fib for the tunnel to use to be fib 1.

  Routing messages would be associated with their
  process, and thus select one FIB or another.
  messages from the kernel would be associated with the fib they
  refer to and would only be received by a routing socket associated
  with that fib. (not yet implemented)

  In addition Netstat has been edited to be able to cope with the
  fact that the array is now 2 dimensional. (It looks in system
  memory using libkvm (!)). Old versions of netstat see only the first FIB.

  In addition two sysctls are added to give:
  a) the number of FIBs compiled in (active)
  b) the default FIB of the calling process.

  Early testing experience:
  -------------------------

  Basically our (IronPort's) appliance does this functionality already
  using ipfw fwd but that method has some drawbacks.

  For example,
  It can't fully simulate a routing table because it can't influence the
  socket's choice of local address when a connect() is done.

  Testing during the generating of these changes has been
  remarkably smooth so far. Multiple tables have co-existed
  with no notable side effects, and packets have been routes
  accordingly.

  ipfw has grown 2 new keywords:

  setfib N ip from anay to any
  count ip from any to any fib N

  In pf there seems to be a requirement to be able to give symbolic names to the
  fibs but I do not have that capacity. I am not sure if it is required.

  SCTP has interestingly enough built in support for this, called VRFs
  in Cisco parlance. it will be interesting to see how that handles it
  when it suddenly actually does something.

  Where to next:
  --------------------

  After committing the ABI compatible version and MFCing it, I'd
  like to proceed in a forward direction in -current. this will
  result in some roto-tilling in the routing code.

  Firstly: the current code's idea of having a separate tree per
  protocol family, all of the same format, and pointed to by the
  1 dimensional array is a bit silly. Especially when one considers that
  there is code that makes assumptions about every protocol having the
  same internal structures there. Some protocols don't WANT that
  sort of structure. (for example the whole idea of a netmask is foreign
  to appletalk). This needs to be made opaque to the external code.

  My suggested first change is to add routing method pointers to the
  'domain' structure, along with information pointing the data.
  instead of having an array of pointers to uniform structures,
  there would be an array pointing to the 'domain' structures
  for each protocol address domain (protocol family),
  and the methods this reached would be called. The methods would have
  an argument that gives FIB number, but the protocol would be free
  to ignore it.

  When the ABI can be changed it raises the possibilty of the
  addition of a fib entry into the "struct route". Currently,
  the structure contains the sockaddr of the desination, and the resulting
  fib entry. To make this work fully, one could add a fib number
  so that given an address and a fib, one can find the third element, the
  fib entry.

  Interaction with the ARP layer/ LL layer would need to be
  revisited as well. Qing Li has been working on this already.

  This work was sponsored by Ironport Systems/Cisco

Reviewed by:    several including rwatson, bz and mlair (parts each)
Obtained from:  Ironport systems/Cisco
2008-05-09 23:03:00 +00:00

371 lines
10 KiB
C

/* $NetBSD: if_atm.c,v 1.6 1996/10/13 02:03:01 christos Exp $ */
/*-
*
* Copyright (c) 1996 Charles D. Cranor and Washington University.
* 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. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by Charles D. Cranor and
* Washington University.
* 4. The name of the author may not be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 AUTHOR 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.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
/*
* IP <=> ATM address resolution.
*/
#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_natm.h"
#if defined(INET) || defined(INET6)
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/queue.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/sockio.h>
#include <sys/syslog.h>
#include <net/if.h>
#include <net/if_dl.h>
#include <net/route.h>
#include <net/if_atm.h>
#include <netinet/in.h>
#include <netinet/if_atm.h>
#ifdef NATM
#include <netnatm/natm.h>
#endif
#define SDL(s) ((struct sockaddr_dl *)s)
#define GET3BYTE(V, A, L) do { \
(V) = ((A)[0] << 16) | ((A)[1] << 8) | (A)[2]; \
(A) += 3; \
(L) -= 3; \
} while (0)
#define GET2BYTE(V, A, L) do { \
(V) = ((A)[0] << 8) | (A)[1]; \
(A) += 2; \
(L) -= 2; \
} while (0)
#define GET1BYTE(V, A, L) do { \
(V) = *(A)++; \
(L)--; \
} while (0)
/*
* atm_rtrequest: handle ATM rt request (in support of generic code)
* inputs: "req" = request code
* "rt" = route entry
* "info" = rt_addrinfo
*/
void
atm_rtrequest(int req, struct rtentry *rt, struct rt_addrinfo *info)
{
struct sockaddr *gate = rt->rt_gateway;
struct atmio_openvcc op;
struct atmio_closevcc cl;
u_char *addr;
u_int alen;
#ifdef NATM
struct sockaddr_in *sin;
struct natmpcb *npcb = NULL;
#endif
static struct sockaddr_dl null_sdl = {sizeof(null_sdl), AF_LINK};
if (rt->rt_flags & RTF_GATEWAY) /* link level requests only */
return;
switch (req) {
case RTM_RESOLVE: /* resolve: only happens when cloning */
printf("atm_rtrequest: RTM_RESOLVE request detected?\n");
break;
case RTM_ADD:
/*
* route added by a command (e.g. ifconfig, route, arp...).
*
* first check to see if this is not a host route, in which
* case we are being called via "ifconfig" to set the address.
*/
if ((rt->rt_flags & RTF_HOST) == 0) {
rt_setgate(rt,rt_key(rt),(struct sockaddr *)&null_sdl);
gate = rt->rt_gateway;
SDL(gate)->sdl_type = rt->rt_ifp->if_type;
SDL(gate)->sdl_index = rt->rt_ifp->if_index;
break;
}
if ((rt->rt_flags & RTF_CLONING) != 0) {
printf("atm_rtrequest: cloning route detected?\n");
break;
}
if (gate->sa_family != AF_LINK ||
gate->sa_len < sizeof(null_sdl)) {
log(LOG_DEBUG, "atm_rtrequest: bad gateway value");
break;
}
KASSERT(rt->rt_ifp->if_ioctl != NULL,
("atm_rtrequest: null ioctl"));
/*
* Parse and verify the link level address as
* an open request
*/
#ifdef NATM
NATM_LOCK();
#endif
bzero(&op, sizeof(op));
addr = LLADDR(SDL(gate));
alen = SDL(gate)->sdl_alen;
if (alen < 4) {
printf("%s: bad link-level address\n", __func__);
goto failed;
}
if (alen == 4) {
/* old type address */
GET1BYTE(op.param.flags, addr, alen);
GET1BYTE(op.param.vpi, addr, alen);
GET2BYTE(op.param.vci, addr, alen);
op.param.traffic = ATMIO_TRAFFIC_UBR;
op.param.aal = (op.param.flags & ATM_PH_AAL5) ?
ATMIO_AAL_5 : ATMIO_AAL_0;
} else {
/* new address */
op.param.aal = ATMIO_AAL_5;
GET1BYTE(op.param.flags, addr, alen);
op.param.flags &= ATM_PH_LLCSNAP;
GET1BYTE(op.param.vpi, addr, alen);
GET2BYTE(op.param.vci, addr, alen);
GET1BYTE(op.param.traffic, addr, alen);
switch (op.param.traffic) {
case ATMIO_TRAFFIC_UBR:
if (alen >= 3)
GET3BYTE(op.param.tparam.pcr,
addr, alen);
break;
case ATMIO_TRAFFIC_CBR:
if (alen < 3)
goto bad_param;
GET3BYTE(op.param.tparam.pcr, addr, alen);
break;
case ATMIO_TRAFFIC_VBR:
if (alen < 3 * 3)
goto bad_param;
GET3BYTE(op.param.tparam.pcr, addr, alen);
GET3BYTE(op.param.tparam.scr, addr, alen);
GET3BYTE(op.param.tparam.mbs, addr, alen);
break;
case ATMIO_TRAFFIC_ABR:
if (alen < 4 * 3 + 2 + 1 * 2 + 3)
goto bad_param;
GET3BYTE(op.param.tparam.pcr, addr, alen);
GET3BYTE(op.param.tparam.mcr, addr, alen);
GET3BYTE(op.param.tparam.icr, addr, alen);
GET3BYTE(op.param.tparam.tbe, addr, alen);
GET1BYTE(op.param.tparam.nrm, addr, alen);
GET1BYTE(op.param.tparam.trm, addr, alen);
GET2BYTE(op.param.tparam.adtf, addr, alen);
GET1BYTE(op.param.tparam.rif, addr, alen);
GET1BYTE(op.param.tparam.rdf, addr, alen);
GET1BYTE(op.param.tparam.cdf, addr, alen);
break;
default:
bad_param:
printf("%s: bad traffic params\n", __func__);
goto failed;
}
}
op.param.rmtu = op.param.tmtu = rt->rt_ifp->if_mtu;
#ifdef NATM
/*
* let native ATM know we are using this VCI/VPI
* (i.e. reserve it)
*/
sin = (struct sockaddr_in *) rt_key(rt);
if (sin->sin_family != AF_INET)
goto failed;
npcb = npcb_add(NULL, rt->rt_ifp, op.param.vci, op.param.vpi);
if (npcb == NULL)
goto failed;
npcb->npcb_flags |= NPCB_IP;
npcb->ipaddr.s_addr = sin->sin_addr.s_addr;
/* XXX: move npcb to llinfo when ATM ARP is ready */
rt->rt_llinfo = (caddr_t) npcb;
rt->rt_flags |= RTF_LLINFO;
#endif
/*
* let the lower level know this circuit is active
*/
op.rxhand = NULL;
op.param.flags |= ATMIO_FLAG_ASYNC;
if (rt->rt_ifp->if_ioctl(rt->rt_ifp, SIOCATMOPENVCC,
(caddr_t)&op) != 0) {
printf("atm: couldn't add VC\n");
goto failed;
}
SDL(gate)->sdl_type = rt->rt_ifp->if_type;
SDL(gate)->sdl_index = rt->rt_ifp->if_index;
#ifdef NATM
NATM_UNLOCK();
#endif
break;
failed:
#ifdef NATM
if (npcb) {
npcb_free(npcb, NPCB_DESTROY);
rt->rt_llinfo = NULL;
rt->rt_flags &= ~RTF_LLINFO;
}
NATM_UNLOCK();
#endif
/* mark as invalid. We cannot RTM_DELETE the route from
* here, because the recursive call to rtrequest1 does
* not really work. */
rt->rt_flags |= RTF_REJECT;
break;
case RTM_DELETE:
#ifdef NATM
/*
* tell native ATM we are done with this VC
*/
if (rt->rt_flags & RTF_LLINFO) {
NATM_LOCK();
npcb_free((struct natmpcb *)rt->rt_llinfo,
NPCB_DESTROY);
rt->rt_llinfo = NULL;
rt->rt_flags &= ~RTF_LLINFO;
NATM_UNLOCK();
}
#endif
/*
* tell the lower layer to disable this circuit
*/
bzero(&op, sizeof(op));
addr = LLADDR(SDL(gate));
addr++;
cl.vpi = *addr++;
cl.vci = *addr++ << 8;
cl.vci |= *addr++;
(void)rt->rt_ifp->if_ioctl(rt->rt_ifp, SIOCATMCLOSEVCC,
(caddr_t)&cl);
break;
}
}
/*
* atmresolve:
* inputs:
* [1] "rt" = the link level route to use (or null if need to look one up)
* [2] "m" = mbuf containing the data to be sent
* [3] "dst" = sockaddr_in (IP) address of dest.
* output:
* [4] "desten" = ATM pseudo header which we will fill in VPI/VCI info
* return:
* 0 == resolve FAILED; note that "m" gets m_freem'd in this case
* 1 == resolve OK; desten contains result
*
* XXX: will need more work if we wish to support ATMARP in the kernel,
* but this is enough for PVCs entered via the "route" command.
*/
int
atmresolve(struct rtentry *rt, struct mbuf *m, struct sockaddr *dst,
struct atm_pseudohdr *desten)
{
struct sockaddr_dl *sdl;
if (m->m_flags & (M_BCAST | M_MCAST)) {
log(LOG_INFO,
"atmresolve: BCAST/MCAST packet detected/dumped\n");
goto bad;
}
if (rt == NULL) {
rt = RTALLOC1(dst, 0); /* link level on table 0 XXX MRT */
if (rt == NULL)
goto bad; /* failed */
RT_REMREF(rt); /* don't keep LL references */
if ((rt->rt_flags & RTF_GATEWAY) != 0 ||
(rt->rt_flags & RTF_LLINFO) == 0 ||
/* XXX: are we using LLINFO? */
rt->rt_gateway->sa_family != AF_LINK) {
RT_UNLOCK(rt);
goto bad;
}
RT_UNLOCK(rt);
}
/*
* note that rt_gateway is a sockaddr_dl which contains the
* atm_pseudohdr data structure for this route. we currently
* don't need any rt_llinfo info (but will if we want to support
* ATM ARP [c.f. if_ether.c]).
*/
sdl = SDL(rt->rt_gateway);
/*
* Check the address family and length is valid, the address
* is resolved; otherwise, try to resolve.
*/
if (sdl->sdl_family == AF_LINK && sdl->sdl_alen >= sizeof(*desten)) {
bcopy(LLADDR(sdl), desten, sizeof(*desten));
return (1); /* ok, go for it! */
}
/*
* we got an entry, but it doesn't have valid link address
* info in it (it is prob. the interface route, which has
* sdl_alen == 0). dump packet. (fall through to "bad").
*/
bad:
m_freem(m);
return (0);
}
#endif /* INET */