d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
0762c37122
freebsd-dev/sys/netinet/ip_mroute.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

367 lines
14 KiB
C
Raw Blame History

/*-
* Copyright (c) 1989 Stephen Deering.
* Copyright (c) 1992, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Stephen Deering of Stanford University.
*
* 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.
*
* @(#)ip_mroute.h 8.1 (Berkeley) 6/10/93
* $FreeBSD$
*/
#ifndef _NETINET_IP_MROUTE_H_
#define _NETINET_IP_MROUTE_H_
/*
* Definitions for IP multicast forwarding.
*
* Written by David Waitzman, BBN Labs, August 1988.
* Modified by Steve Deering, Stanford, February 1989.
* Modified by Ajit Thyagarajan, PARC, August 1993.
* Modified by Ajit Thyagarajan, PARC, August 1994.
* Modified by Ahmed Helmy, SGI, June 1996.
* Modified by Pavlin Radoslavov, ICSI, October 2002.
*
* MROUTING Revision: 3.3.1.3
* and PIM-SMv2 and PIM-DM support, advanced API support,
* bandwidth metering and signaling.
*/
/*
* Multicast Routing set/getsockopt commands.
*/
#define MRT_INIT 100 /* initialize forwarder */
#define MRT_DONE 101 /* shut down forwarder */
#define MRT_ADD_VIF 102 /* create virtual interface */
#define MRT_DEL_VIF 103 /* delete virtual interface */
#define MRT_ADD_MFC 104 /* insert forwarding cache entry */
#define MRT_DEL_MFC 105 /* delete forwarding cache entry */
#define MRT_VERSION 106 /* get kernel version number */
#define MRT_ASSERT 107 /* enable assert processing */
#define MRT_PIM MRT_ASSERT /* enable PIM processing */
#define MRT_API_SUPPORT 109 /* supported MRT API */
#define MRT_API_CONFIG 110 /* config MRT API */
#define MRT_ADD_BW_UPCALL 111 /* create bandwidth monitor */
#define MRT_DEL_BW_UPCALL 112 /* delete bandwidth monitor */
#define GET_TIME(t) microtime(&t)
/*
* Types and macros for handling bitmaps with one bit per virtual interface.
*/
#define MAXVIFS 32
typedef u_long vifbitmap_t;
typedef u_short vifi_t; /* type of a vif index */
#define ALL_VIFS (vifi_t)-1
#define VIFM_SET(n, m) ((m) |= (1 << (n)))
#define VIFM_CLR(n, m) ((m) &= ~(1 << (n)))
#define VIFM_ISSET(n, m) ((m) & (1 << (n)))
#define VIFM_CLRALL(m) ((m) = 0x00000000)
#define VIFM_COPY(mfrom, mto) ((mto) = (mfrom))
#define VIFM_SAME(m1, m2) ((m1) == (m2))
/*
* Argument structure for MRT_ADD_VIF.
* (MRT_DEL_VIF takes a single vifi_t argument.)
*/
struct vifctl {
vifi_t vifc_vifi; /* the index of the vif to be added */
u_char vifc_flags; /* VIFF_ flags defined below */
u_char vifc_threshold; /* min ttl required to forward on vif */
u_int vifc_rate_limit; /* max rate */
struct in_addr vifc_lcl_addr; /* local interface address */
struct in_addr vifc_rmt_addr; /* remote address (tunnels only) */
};
#define VIFF_TUNNEL 0x1 /* no-op; retained for old source */
#define VIFF_SRCRT 0x2 /* no-op; retained for old source */
#define VIFF_REGISTER 0x4 /* used for PIM Register encap/decap */
/*
* Argument structure for MRT_ADD_MFC and MRT_DEL_MFC
* XXX if you change this, make sure to change struct mfcctl2 as well.
*/
struct mfcctl {
struct in_addr mfcc_origin; /* ip origin of mcasts */
struct in_addr mfcc_mcastgrp; /* multicast group associated*/
vifi_t mfcc_parent; /* incoming vif */
u_char mfcc_ttls[MAXVIFS]; /* forwarding ttls on vifs */
};
/*
* The new argument structure for MRT_ADD_MFC and MRT_DEL_MFC overlays
* and extends the old struct mfcctl.
*/
struct mfcctl2 {
/* the mfcctl fields */
struct in_addr mfcc_origin; /* ip origin of mcasts */
struct in_addr mfcc_mcastgrp; /* multicast group associated*/
vifi_t mfcc_parent; /* incoming vif */
u_char mfcc_ttls[MAXVIFS]; /* forwarding ttls on vifs */
/* extension fields */
uint8_t mfcc_flags[MAXVIFS]; /* the MRT_MFC_FLAGS_* flags */
struct in_addr mfcc_rp; /* the RP address */
};
/*
* The advanced-API flags.
*
* The MRT_MFC_FLAGS_XXX API flags are also used as flags
* for the mfcc_flags field.
*/
#define MRT_MFC_FLAGS_DISABLE_WRONGVIF (1 << 0) /* disable WRONGVIF signals */
#define MRT_MFC_FLAGS_BORDER_VIF (1 << 1) /* border vif */
#define MRT_MFC_RP (1 << 8) /* enable RP address */
#define MRT_MFC_BW_UPCALL (1 << 9) /* enable bw upcalls */
#define MRT_MFC_FLAGS_ALL (MRT_MFC_FLAGS_DISABLE_WRONGVIF | \
MRT_MFC_FLAGS_BORDER_VIF)
#define MRT_API_FLAGS_ALL (MRT_MFC_FLAGS_ALL | \
MRT_MFC_RP | \
MRT_MFC_BW_UPCALL)
/*
* Structure for installing or delivering an upcall if the
* measured bandwidth is above or below a threshold.
*
* User programs (e.g. daemons) may have a need to know when the
* bandwidth used by some data flow is above or below some threshold.
* This interface allows the userland to specify the threshold (in
* bytes and/or packets) and the measurement interval. Flows are
* all packet with the same source and destination IP address.
* At the moment the code is only used for multicast destinations
* but there is nothing that prevents its use for unicast.
*
* The measurement interval cannot be shorter than some Tmin (currently, 3s).
* The threshold is set in packets and/or bytes per_interval.
*
* Measurement works as follows:
*
* For >= measurements:
* The first packet marks the start of a measurement interval.
* During an interval we count packets and bytes, and when we
* pass the threshold we deliver an upcall and we are done.
* The first packet after the end of the interval resets the
* count and restarts the measurement.
*
* For <= measurement:
* We start a timer to fire at the end of the interval, and
* then for each incoming packet we count packets and bytes.
* When the timer fires, we compare the value with the threshold,
* schedule an upcall if we are below, and restart the measurement
* (reschedule timer and zero counters).
*/
struct bw_data {
struct timeval b_time;
uint64_t b_packets;
uint64_t b_bytes;
};
struct bw_upcall {
struct in_addr bu_src; /* source address */
struct in_addr bu_dst; /* destination address */
uint32_t bu_flags; /* misc flags (see below) */
#define BW_UPCALL_UNIT_PACKETS (1 << 0) /* threshold (in packets) */
#define BW_UPCALL_UNIT_BYTES (1 << 1) /* threshold (in bytes) */
#define BW_UPCALL_GEQ (1 << 2) /* upcall if bw >= threshold */
#define BW_UPCALL_LEQ (1 << 3) /* upcall if bw <= threshold */
#define BW_UPCALL_DELETE_ALL (1 << 4) /* delete all upcalls for s,d*/
struct bw_data bu_threshold; /* the bw threshold */
struct bw_data bu_measured; /* the measured bw */
};
/* max. number of upcalls to deliver together */
#define BW_UPCALLS_MAX 128
/* min. threshold time interval for bandwidth measurement */
#define BW_UPCALL_THRESHOLD_INTERVAL_MIN_SEC 3
#define BW_UPCALL_THRESHOLD_INTERVAL_MIN_USEC 0
/*
* The kernel's multicast routing statistics.
*/
struct mrtstat {
u_long mrts_mfc_lookups; /* # forw. cache hash table hits */
u_long mrts_mfc_misses; /* # forw. cache hash table misses */
u_long mrts_upcalls; /* # calls to multicast routing daemon */
u_long mrts_no_route; /* no route for packet's origin */
u_long mrts_bad_tunnel; /* malformed tunnel options */
u_long mrts_cant_tunnel; /* no room for tunnel options */
u_long mrts_wrong_if; /* arrived on wrong interface */
u_long mrts_upq_ovflw; /* upcall Q overflow */
u_long mrts_cache_cleanups; /* # entries with no upcalls */
u_long mrts_drop_sel; /* pkts dropped selectively */
u_long mrts_q_overflow; /* pkts dropped - Q overflow */
u_long mrts_pkt2large; /* pkts dropped - size > BKT SIZE */
u_long mrts_upq_sockfull; /* upcalls dropped - socket full */
};
/*
* Argument structure used by mrouted to get src-grp pkt counts
*/
struct sioc_sg_req {
struct in_addr src;
struct in_addr grp;
u_long pktcnt;
u_long bytecnt;
u_long wrong_if;
};
/*
* Argument structure used by mrouted to get vif pkt counts
*/
struct sioc_vif_req {
vifi_t vifi; /* vif number */
u_long icount; /* Input packet count on vif */
u_long ocount; /* Output packet count on vif */
u_long ibytes; /* Input byte count on vif */
u_long obytes; /* Output byte count on vif */
};
/*
* The kernel's virtual-interface structure.
*/
struct vif {
u_char v_flags; /* VIFF_ flags defined above */
u_char v_threshold; /* min ttl required to forward on vif*/
u_int v_rate_limit; /* ignored; kept for compatibility */
struct tbf *v_tbf; /* ignored; kept for compatibility */
struct in_addr v_lcl_addr; /* local interface address */
struct in_addr v_rmt_addr; /* remote address (tunnels only) */
struct ifnet *v_ifp; /* pointer to interface */
u_long v_pkt_in; /* # pkts in on interface */
u_long v_pkt_out; /* # pkts out on interface */
u_long v_bytes_in; /* # bytes in on interface */
u_long v_bytes_out; /* # bytes out on interface */
struct route v_route; /* cached route */
u_int v_rsvp_on; /* RSVP listening on this vif */
struct socket *v_rsvpd; /* RSVP daemon socket */
};
/*
* The kernel's multicast forwarding cache entry structure
* (A field for the type of service (mfc_tos) is to be added
* at a future point)
*/
struct mfc {
struct in_addr mfc_origin; /* IP origin of mcasts */
struct in_addr mfc_mcastgrp; /* multicast group associated*/
vifi_t mfc_parent; /* incoming vif */
u_char mfc_ttls[MAXVIFS]; /* forwarding ttls on vifs */
u_long mfc_pkt_cnt; /* pkt count for src-grp */
u_long mfc_byte_cnt; /* byte count for src-grp */
u_long mfc_wrong_if; /* wrong if for src-grp */
int mfc_expire; /* time to clean entry up */
struct timeval mfc_last_assert; /* last time I sent an assert*/
struct rtdetq *mfc_stall; /* q of packets awaiting mfc */
struct mfc *mfc_next; /* next mfc entry */
uint8_t mfc_flags[MAXVIFS]; /* the MRT_MFC_FLAGS_* flags */
struct in_addr mfc_rp; /* the RP address */
struct bw_meter *mfc_bw_meter; /* list of bandwidth meters */
};
/*
* Struct used to communicate from kernel to multicast router
* note the convenient similarity to an IP packet
*/
struct igmpmsg {
uint32_t unused1;
uint32_t unused2;
u_char im_msgtype; /* what type of message */
#define IGMPMSG_NOCACHE 1 /* no MFC in the kernel */
#define IGMPMSG_WRONGVIF 2 /* packet came from wrong interface */
#define IGMPMSG_WHOLEPKT 3 /* PIM pkt for user level encap. */
#define IGMPMSG_BW_UPCALL 4 /* BW monitoring upcall */
u_char im_mbz; /* must be zero */
u_char im_vif; /* vif rec'd on */
u_char unused3;
struct in_addr im_src, im_dst;
};
/*
* Argument structure used for pkt info. while upcall is made
*/
struct rtdetq {
struct mbuf *m; /* A copy of the packet */
struct ifnet *ifp; /* Interface pkt came in on */
vifi_t xmt_vif; /* Saved copy of imo_multicast_vif */
struct rtdetq *next; /* Next in list of packets */
};
#define MFCTBLSIZ 256
#if (MFCTBLSIZ & (MFCTBLSIZ - 1)) == 0 /* from sys:route.h */
#define MFCHASHMOD(h) ((h) & (MFCTBLSIZ - 1))
#else
#define MFCHASHMOD(h) ((h) % MFCTBLSIZ)
#endif
#define MAX_UPQ 4 /* max. no of pkts in upcall Q */
/*
* Structure for measuring the bandwidth and sending an upcall if the
* measured bandwidth is above or below a threshold.
*/
struct bw_meter {
struct bw_meter *bm_mfc_next; /* next bw meter (same mfc) */
struct bw_meter *bm_time_next; /* next bw meter (same time) */
uint32_t bm_time_hash; /* the time hash value */
struct mfc *bm_mfc; /* the corresponding mfc */
uint32_t bm_flags; /* misc flags (see below) */
#define BW_METER_UNIT_PACKETS (1 << 0) /* threshold (in packets) */
#define BW_METER_UNIT_BYTES (1 << 1) /* threshold (in bytes) */
#define BW_METER_GEQ (1 << 2) /* upcall if bw >= threshold */
#define BW_METER_LEQ (1 << 3) /* upcall if bw <= threshold */
#define BW_METER_USER_FLAGS (BW_METER_UNIT_PACKETS | \
BW_METER_UNIT_BYTES | \
BW_METER_GEQ | \
BW_METER_LEQ)
#define BW_METER_UPCALL_DELIVERED (1 << 24) /* upcall was delivered */
struct bw_data bm_threshold; /* the upcall threshold */
struct bw_data bm_measured; /* the measured bw */
struct timeval bm_start_time; /* abs. time */
};
#ifdef _KERNEL
struct sockopt;
extern int (*ip_mrouter_set)(struct socket *, struct sockopt *);
extern int (*ip_mrouter_get)(struct socket *, struct sockopt *);
extern int (*ip_mrouter_done)(void);
extern int (*mrt_ioctl)(int, caddr_t, int);
#endif /* _KERNEL */
#endif /* _NETINET_IP_MROUTE_H_ */
Reference in New Issue View Git Blame Copy Permalink