2003-12-30 11:41:43 +00:00
|
|
|
/* $NetBSD: if_gre.h,v 1.13 2003/11/10 08:51:52 wiz Exp $ */
|
2002-09-06 17:12:50 +00:00
|
|
|
/* $FreeBSD$ */
|
|
|
|
|
|
2005-01-07 01:45:51 +00:00
|
|
|
/*-
|
2002-09-06 17:12:50 +00:00
|
|
|
* Copyright (c) 1998 The NetBSD Foundation, Inc.
|
|
|
|
|
* All rights reserved
|
|
|
|
|
*
|
|
|
|
|
* This code is derived from software contributed to The NetBSD Foundation
|
|
|
|
|
* by Heiko W.Rupp <hwr@pilhuhn.de>
|
|
|
|
|
*
|
|
|
|
|
* 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.
|
2004-01-26 12:21:59 +00:00
|
|
|
*
|
2002-09-06 17:12:50 +00:00
|
|
|
* THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. 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 FOUNDATION 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.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef _NET_IF_GRE_H
|
|
|
|
|
#define _NET_IF_GRE_H
|
|
|
|
|
|
|
|
|
|
#include <sys/ioccom.h>
|
2002-09-09 08:25:00 +00:00
|
|
|
#ifdef _KERNEL
|
2002-09-06 17:12:50 +00:00
|
|
|
#include <sys/queue.h>
|
|
|
|
|
|
2004-01-26 12:33:56 +00:00
|
|
|
/*
|
|
|
|
|
* Version of the WCCP, need to be configured manually since
|
|
|
|
|
* header for version 2 is the same but IP payload is prepended
|
|
|
|
|
* with additional 4-bytes field.
|
|
|
|
|
*/
|
|
|
|
|
typedef enum {
|
|
|
|
|
WCCP_V1 = 0,
|
|
|
|
|
WCCP_V2
|
|
|
|
|
} wccp_ver_t;
|
|
|
|
|
|
2002-09-06 17:12:50 +00:00
|
|
|
struct gre_softc {
|
2005-06-10 16:49:24 +00:00
|
|
|
struct ifnet *sc_ifp;
|
2002-09-06 17:12:50 +00:00
|
|
|
LIST_ENTRY(gre_softc) sc_list;
|
|
|
|
|
int gre_unit;
|
|
|
|
|
int gre_flags;
|
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
|
|
|
u_int gre_fibnum; /* use this fib for envelopes */
|
2002-09-06 17:12:50 +00:00
|
|
|
struct in_addr g_src; /* source address of gre packets */
|
|
|
|
|
struct in_addr g_dst; /* destination address of gre packets */
|
|
|
|
|
struct route route; /* routing entry that determines, where a
|
|
|
|
|
encapsulated packet should go */
|
|
|
|
|
u_char g_proto; /* protocol of encapsulator */
|
|
|
|
|
|
|
|
|
|
const struct encaptab *encap; /* encapsulation cookie */
|
|
|
|
|
|
2008-06-20 17:26:34 +00:00
|
|
|
uint32_t key; /* key included in outgoing GRE packets */
|
|
|
|
|
/* zero means none */
|
|
|
|
|
|
2004-01-26 12:33:56 +00:00
|
|
|
wccp_ver_t wccp_ver; /* version of the WCCP */
|
2004-01-26 12:21:59 +00:00
|
|
|
};
|
2005-06-10 16:49:24 +00:00
|
|
|
#define GRE2IFP(sc) ((sc)->sc_ifp)
|
2002-09-06 17:12:50 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
struct gre_h {
|
|
|
|
|
u_int16_t flags; /* GRE flags */
|
2004-01-26 12:21:59 +00:00
|
|
|
u_int16_t ptype; /* protocol type of payload typically
|
2002-09-06 17:12:50 +00:00
|
|
|
Ether protocol type*/
|
2008-06-20 17:26:34 +00:00
|
|
|
uint32_t options[0]; /* optional options */
|
2004-01-26 12:21:59 +00:00
|
|
|
/*
|
|
|
|
|
* from here on: fields are optional, presence indicated by flags
|
2002-09-06 17:12:50 +00:00
|
|
|
*
|
|
|
|
|
u_int_16 checksum checksum (one-complements of GRE header
|
|
|
|
|
and payload
|
|
|
|
|
Present if (ck_pres | rt_pres == 1).
|
|
|
|
|
Valid if (ck_pres == 1).
|
|
|
|
|
u_int_16 offset offset from start of routing filed to
|
|
|
|
|
first octet of active SRE (see below).
|
|
|
|
|
Present if (ck_pres | rt_pres == 1).
|
|
|
|
|
Valid if (rt_pres == 1).
|
|
|
|
|
u_int_32 key inserted by encapsulator e.g. for
|
|
|
|
|
authentication
|
|
|
|
|
Present if (key_pres ==1 ).
|
|
|
|
|
u_int_32 seq_num Sequence number to allow for packet order
|
|
|
|
|
Present if (seq_pres ==1 ).
|
|
|
|
|
struct gre_sre[] routing Routing fileds (see below)
|
|
|
|
|
Present if (rt_pres == 1)
|
|
|
|
|
*/
|
2002-09-23 06:25:08 +00:00
|
|
|
} __packed;
|
2002-09-06 17:12:50 +00:00
|
|
|
|
|
|
|
|
struct greip {
|
|
|
|
|
struct ip gi_i;
|
|
|
|
|
struct gre_h gi_g;
|
2002-09-23 06:25:08 +00:00
|
|
|
} __packed;
|
2002-09-06 17:12:50 +00:00
|
|
|
|
|
|
|
|
#define gi_pr gi_i.ip_p
|
|
|
|
|
#define gi_len gi_i.ip_len
|
|
|
|
|
#define gi_src gi_i.ip_src
|
|
|
|
|
#define gi_dst gi_i.ip_dst
|
|
|
|
|
#define gi_ptype gi_g.ptype
|
|
|
|
|
#define gi_flags gi_g.flags
|
2008-06-20 17:26:34 +00:00
|
|
|
#define gi_options gi_g.options
|
2002-09-06 17:12:50 +00:00
|
|
|
|
|
|
|
|
#define GRE_CP 0x8000 /* Checksum Present */
|
|
|
|
|
#define GRE_RP 0x4000 /* Routing Present */
|
|
|
|
|
#define GRE_KP 0x2000 /* Key Present */
|
|
|
|
|
#define GRE_SP 0x1000 /* Sequence Present */
|
|
|
|
|
#define GRE_SS 0x0800 /* Strict Source Route */
|
|
|
|
|
|
2002-12-07 14:22:05 +00:00
|
|
|
/*
|
|
|
|
|
* CISCO uses special type for GRE tunnel created as part of WCCP
|
|
|
|
|
* connection, while in fact those packets are just IPv4 encapsulated
|
|
|
|
|
* into GRE.
|
|
|
|
|
*/
|
|
|
|
|
#define WCCP_PROTOCOL_TYPE 0x883E
|
|
|
|
|
|
2002-09-06 17:12:50 +00:00
|
|
|
/*
|
|
|
|
|
* gre_sre defines a Source route Entry. These are needed if packets
|
|
|
|
|
* should be routed over more than one tunnel hop by hop
|
|
|
|
|
*/
|
|
|
|
|
struct gre_sre {
|
2003-12-30 11:41:43 +00:00
|
|
|
u_int16_t sre_family; /* address family */
|
2002-09-06 17:12:50 +00:00
|
|
|
u_char sre_offset; /* offset to first octet of active entry */
|
2004-01-26 12:21:59 +00:00
|
|
|
u_char sre_length; /* number of octets in the SRE.
|
2002-09-06 17:12:50 +00:00
|
|
|
sre_lengthl==0 -> last entry. */
|
|
|
|
|
u_char *sre_rtinfo; /* the routing information */
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct greioctl {
|
|
|
|
|
int unit;
|
|
|
|
|
struct in_addr addr;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/* for mobile encaps */
|
|
|
|
|
|
|
|
|
|
struct mobile_h {
|
|
|
|
|
u_int16_t proto; /* protocol and S-bit */
|
|
|
|
|
u_int16_t hcrc; /* header checksum */
|
|
|
|
|
u_int32_t odst; /* original destination address */
|
|
|
|
|
u_int32_t osrc; /* original source addr, if S-bit set */
|
2002-09-23 06:25:08 +00:00
|
|
|
} __packed;
|
2002-09-06 17:12:50 +00:00
|
|
|
|
|
|
|
|
struct mobip_h {
|
|
|
|
|
struct ip mi;
|
|
|
|
|
struct mobile_h mh;
|
2002-09-23 06:25:08 +00:00
|
|
|
} __packed;
|
2002-09-06 17:12:50 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
#define MOB_H_SIZ_S (sizeof(struct mobile_h) - sizeof(u_int32_t))
|
|
|
|
|
#define MOB_H_SIZ_L (sizeof(struct mobile_h))
|
|
|
|
|
#define MOB_H_SBIT 0x0080
|
|
|
|
|
|
|
|
|
|
#define GRE_TTL 30
|
|
|
|
|
|
2002-09-09 08:25:00 +00:00
|
|
|
#endif /* _KERNEL */
|
|
|
|
|
|
2004-01-26 12:21:59 +00:00
|
|
|
/*
|
|
|
|
|
* ioctls needed to manipulate the interface
|
2002-09-06 17:12:50 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define GRESADDRS _IOW('i', 101, struct ifreq)
|
2004-01-26 12:21:59 +00:00
|
|
|
#define GRESADDRD _IOW('i', 102, struct ifreq)
|
2002-09-06 17:12:50 +00:00
|
|
|
#define GREGADDRS _IOWR('i', 103, struct ifreq)
|
|
|
|
|
#define GREGADDRD _IOWR('i', 104, struct ifreq)
|
|
|
|
|
#define GRESPROTO _IOW('i' , 105, struct ifreq)
|
|
|
|
|
#define GREGPROTO _IOWR('i', 106, struct ifreq)
|
2008-06-20 17:26:34 +00:00
|
|
|
#define GREGKEY _IOWR('i', 107, struct ifreq)
|
|
|
|
|
#define GRESKEY _IOW('i', 108, struct ifreq)
|
2002-09-06 17:12:50 +00:00
|
|
|
|
|
|
|
|
#ifdef _KERNEL
|
|
|
|
|
LIST_HEAD(gre_softc_head, gre_softc);
|
2004-03-22 16:04:43 +00:00
|
|
|
extern struct mtx gre_mtx;
|
2002-09-06 17:12:50 +00:00
|
|
|
extern struct gre_softc_head gre_softc_list;
|
|
|
|
|
|
2003-12-30 11:41:43 +00:00
|
|
|
u_int16_t gre_in_cksum(u_int16_t *, u_int);
|
2002-09-06 17:12:50 +00:00
|
|
|
#endif /* _KERNEL */
|
|
|
|
|
|
|
|
|
|
#endif
|
