freebsd-dev/sys/netinet/in_var.h
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

330 lines
12 KiB
C

/*-
* Copyright (c) 1985, 1986, 1993
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)in_var.h 8.2 (Berkeley) 1/9/95
* $FreeBSD$
*/
#ifndef _NETINET_IN_VAR_H_
#define _NETINET_IN_VAR_H_
#include <sys/queue.h>
#include <sys/fnv_hash.h>
/*
* Interface address, Internet version. One of these structures
* is allocated for each Internet address on an interface.
* The ifaddr structure contains the protocol-independent part
* of the structure and is assumed to be first.
*/
struct in_ifaddr {
struct ifaddr ia_ifa; /* protocol-independent info */
#define ia_ifp ia_ifa.ifa_ifp
#define ia_flags ia_ifa.ifa_flags
/* ia_{,sub}net{,mask} in host order */
u_long ia_net; /* network number of interface */
u_long ia_netmask; /* mask of net part */
u_long ia_subnet; /* subnet number, including net */
u_long ia_subnetmask; /* mask of subnet part */
struct in_addr ia_netbroadcast; /* to recognize net broadcasts */
LIST_ENTRY(in_ifaddr) ia_hash; /* entry in bucket of inet addresses */
TAILQ_ENTRY(in_ifaddr) ia_link; /* list of internet addresses */
struct sockaddr_in ia_addr; /* reserve space for interface name */
struct sockaddr_in ia_dstaddr; /* reserve space for broadcast addr */
#define ia_broadaddr ia_dstaddr
struct sockaddr_in ia_sockmask; /* reserve space for general netmask */
};
struct in_aliasreq {
char ifra_name[IFNAMSIZ]; /* if name, e.g. "en0" */
struct sockaddr_in ifra_addr;
struct sockaddr_in ifra_broadaddr;
#define ifra_dstaddr ifra_broadaddr
struct sockaddr_in ifra_mask;
};
/*
* Given a pointer to an in_ifaddr (ifaddr),
* return a pointer to the addr as a sockaddr_in.
*/
#define IA_SIN(ia) (&(((struct in_ifaddr *)(ia))->ia_addr))
#define IA_DSTSIN(ia) (&(((struct in_ifaddr *)(ia))->ia_dstaddr))
#define IN_LNAOF(in, ifa) \
((ntohl((in).s_addr) & ~((struct in_ifaddr *)(ifa)->ia_subnetmask))
#ifdef _KERNEL
extern u_char inetctlerrmap[];
/*
* Hash table for IP addresses.
*/
extern LIST_HEAD(in_ifaddrhashhead, in_ifaddr) *in_ifaddrhashtbl;
extern TAILQ_HEAD(in_ifaddrhead, in_ifaddr) in_ifaddrhead;
extern u_long in_ifaddrhmask; /* mask for hash table */
#define INADDR_NHASH_LOG2 9
#define INADDR_NHASH (1 << INADDR_NHASH_LOG2)
#define INADDR_HASHVAL(x) fnv_32_buf((&(x)), sizeof(x), FNV1_32_INIT)
#define INADDR_HASH(x) \
(&in_ifaddrhashtbl[INADDR_HASHVAL(x) & in_ifaddrhmask])
/*
* Macro for finding the internet address structure (in_ifaddr)
* corresponding to one of our IP addresses (in_addr).
*/
#define INADDR_TO_IFADDR(addr, ia) \
/* struct in_addr addr; */ \
/* struct in_ifaddr *ia; */ \
do { \
\
LIST_FOREACH(ia, INADDR_HASH((addr).s_addr), ia_hash) \
if (IA_SIN(ia)->sin_addr.s_addr == (addr).s_addr) \
break; \
} while (0)
/*
* Macro for finding the interface (ifnet structure) corresponding to one
* of our IP addresses.
*/
#define INADDR_TO_IFP(addr, ifp) \
/* struct in_addr addr; */ \
/* struct ifnet *ifp; */ \
{ \
struct in_ifaddr *ia; \
\
INADDR_TO_IFADDR(addr, ia); \
(ifp) = (ia == NULL) ? NULL : ia->ia_ifp; \
}
/*
* Macro for finding the internet address structure (in_ifaddr) corresponding
* to a given interface (ifnet structure).
*/
#define IFP_TO_IA(ifp, ia) \
/* struct ifnet *ifp; */ \
/* struct in_ifaddr *ia; */ \
{ \
for ((ia) = TAILQ_FIRST(&in_ifaddrhead); \
(ia) != NULL && (ia)->ia_ifp != (ifp); \
(ia) = TAILQ_NEXT((ia), ia_link)) \
continue; \
}
#endif
/*
* This information should be part of the ifnet structure but we don't wish
* to change that - as it might break a number of things
*/
struct router_info {
struct ifnet *rti_ifp;
int rti_type; /* type of router which is querier on this interface */
int rti_time; /* # of slow timeouts since last old query */
SLIST_ENTRY(router_info) rti_list;
#ifdef notyet
int rti_timev1; /* IGMPv1 querier present */
int rti_timev2; /* IGMPv2 querier present */
int rti_timer; /* report to general query */
int rti_qrv; /* querier robustness */
#endif
};
/*
* Internet multicast address structure. There is one of these for each IP
* multicast group to which this host belongs on a given network interface.
* For every entry on the interface's if_multiaddrs list which represents
* an IP multicast group, there is one of these structures. They are also
* kept on a system-wide list to make it easier to keep our legacy IGMP code
* compatible with the rest of the world (see IN_FIRST_MULTI et al, below).
*/
struct in_multi {
LIST_ENTRY(in_multi) inm_link; /* queue macro glue */
struct in_addr inm_addr; /* IP multicast address, convenience */
struct ifnet *inm_ifp; /* back pointer to ifnet */
struct ifmultiaddr *inm_ifma; /* back pointer to ifmultiaddr */
u_int inm_timer; /* IGMP membership report timer */
u_int inm_state; /* state of the membership */
struct router_info *inm_rti; /* router info*/
u_int inm_refcount; /* reference count */
#ifdef notyet /* IGMPv3 source-specific multicast fields */
TAILQ_HEAD(, in_msfentry) inm_msf; /* all active source filters */
TAILQ_HEAD(, in_msfentry) inm_msf_record; /* recorded sources */
TAILQ_HEAD(, in_msfentry) inm_msf_exclude; /* exclude sources */
TAILQ_HEAD(, in_msfentry) inm_msf_include; /* include sources */
/* XXX: should this lot go to the router_info structure? */
/* XXX: can/should these be callouts? */
/* IGMP protocol timers */
int32_t inm_ti_curstate; /* current state timer */
int32_t inm_ti_statechg; /* state change timer */
/* IGMP report timers */
uint16_t inm_rpt_statechg; /* state change report timer */
uint16_t inm_rpt_toxx; /* fmode change report timer */
/* IGMP protocol state */
uint16_t inm_fmode; /* filter mode */
uint32_t inm_recsrc_count; /* # of recorded sources */
uint16_t inm_exclude_sock_count; /* # of exclude-mode sockets */
uint16_t inm_gass_count; /* # of g-a-s queries */
#endif
};
#ifdef notyet
/*
* Internet multicast source filter list. This list is used to store
* IP multicast source addresses for each membership on an interface.
* TODO: Allocate these structures using UMA.
* TODO: Find an easier way of linking the struct into two lists at once.
*/
struct in_msfentry {
TAILQ_ENTRY(in_msfentry) isf_link; /* next filter in all-list */
TAILQ_ENTRY(in_msfentry) isf_next; /* next filter in queue */
struct in_addr isf_addr; /* the address of this source */
uint16_t isf_refcount; /* reference count */
uint16_t isf_reporttag; /* what to report to the IGMP router */
uint16_t isf_rexmit; /* retransmission state/count */
};
#endif
#ifdef _KERNEL
#ifdef SYSCTL_DECL
SYSCTL_DECL(_net_inet);
SYSCTL_DECL(_net_inet_ip);
SYSCTL_DECL(_net_inet_raw);
#endif
extern LIST_HEAD(in_multihead, in_multi) in_multihead;
/*
* Lock macros for IPv4 layer multicast address lists. IPv4 lock goes
* before link layer multicast locks in the lock order. In most cases,
* consumers of IN_*_MULTI() macros should acquire the locks before
* calling them; users of the in_{add,del}multi() functions should not.
*/
extern struct mtx in_multi_mtx;
#define IN_MULTI_LOCK() mtx_lock(&in_multi_mtx)
#define IN_MULTI_UNLOCK() mtx_unlock(&in_multi_mtx)
#define IN_MULTI_LOCK_ASSERT() mtx_assert(&in_multi_mtx, MA_OWNED)
/*
* Structure used by macros below to remember position when stepping through
* all of the in_multi records.
*/
struct in_multistep {
struct in_multi *i_inm;
};
/*
* Macro for looking up the in_multi record for a given IP multicast address
* on a given interface. If no matching record is found, "inm" is set null.
*/
#define IN_LOOKUP_MULTI(addr, ifp, inm) \
/* struct in_addr addr; */ \
/* struct ifnet *ifp; */ \
/* struct in_multi *inm; */ \
do { \
struct ifmultiaddr *ifma; \
\
IN_MULTI_LOCK_ASSERT(); \
IF_ADDR_LOCK(ifp); \
TAILQ_FOREACH(ifma, &((ifp)->if_multiaddrs), ifma_link) { \
if (ifma->ifma_addr->sa_family == AF_INET \
&& ((struct sockaddr_in *)ifma->ifma_addr)->sin_addr.s_addr == \
(addr).s_addr) \
break; \
} \
(inm) = ifma ? ifma->ifma_protospec : 0; \
IF_ADDR_UNLOCK(ifp); \
} while(0)
/*
* Macro to step through all of the in_multi records, one at a time.
* The current position is remembered in "step", which the caller must
* provide. IN_FIRST_MULTI(), below, must be called to initialize "step"
* and get the first record. Both macros return a NULL "inm" when there
* are no remaining records.
*/
#define IN_NEXT_MULTI(step, inm) \
/* struct in_multistep step; */ \
/* struct in_multi *inm; */ \
do { \
IN_MULTI_LOCK_ASSERT(); \
if (((inm) = (step).i_inm) != NULL) \
(step).i_inm = LIST_NEXT((step).i_inm, inm_link); \
} while(0)
#define IN_FIRST_MULTI(step, inm) \
/* struct in_multistep step; */ \
/* struct in_multi *inm; */ \
do { \
IN_MULTI_LOCK_ASSERT(); \
(step).i_inm = LIST_FIRST(&in_multihead); \
IN_NEXT_MULTI((step), (inm)); \
} while(0)
struct rtentry;
struct route;
struct ip_moptions;
size_t imo_match_group(struct ip_moptions *, struct ifnet *,
struct sockaddr *);
struct in_msource *imo_match_source(struct ip_moptions *, size_t,
struct sockaddr *);
struct in_multi *in_addmulti(struct in_addr *, struct ifnet *);
void in_delmulti(struct in_multi *);
void in_delmulti_locked(struct in_multi *);
int in_control(struct socket *, u_long, caddr_t, struct ifnet *,
struct thread *);
void in_rtqdrain(void);
void ip_input(struct mbuf *);
int in_ifadown(struct ifaddr *ifa, int);
void in_ifscrub(struct ifnet *, struct in_ifaddr *);
struct mbuf *ip_fastforward(struct mbuf *);
/* XXX */
void in_rtalloc_ign(struct route *ro, u_long ignflags, u_int fibnum);
void in_rtalloc(struct route *ro, u_int fibnum);
struct rtentry *in_rtalloc1(struct sockaddr *, int, u_long, u_int);
void in_rtredirect(struct sockaddr *, struct sockaddr *,
struct sockaddr *, int, struct sockaddr *, u_int);
int in_rtrequest(int, struct sockaddr *,
struct sockaddr *, struct sockaddr *, int, struct rtentry **, u_int);
int in_rt_check(struct rtentry **, struct rtentry **, struct sockaddr *, u_int);
#if 0
int in_rt_getifa(struct rt_addrinfo *, u_int fibnum);
int in_rtioctl(u_long, caddr_t, u_int);
int in_rtrequest1(int, struct rt_addrinfo *, struct rtentry **, u_int);
#endif
#endif /* _KERNEL */
/* INET6 stuff */
#include <netinet6/in6_var.h>
#endif /* _NETINET_IN_VAR_H_ */