mirror of
https://git.FreeBSD.org/src.git
synced 2024-12-22 11:17:19 +00:00
8b07e49a00
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
249 lines
8.9 KiB
C
249 lines
8.9 KiB
C
/*-
|
|
* Copyright (c) 1982, 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.
|
|
*
|
|
* @(#)ip_var.h 8.2 (Berkeley) 1/9/95
|
|
* $FreeBSD$
|
|
*/
|
|
|
|
#ifndef _NETINET_IP_VAR_H_
|
|
#define _NETINET_IP_VAR_H_
|
|
|
|
#include <sys/queue.h>
|
|
|
|
/*
|
|
* Overlay for ip header used by other protocols (tcp, udp).
|
|
*/
|
|
struct ipovly {
|
|
u_char ih_x1[9]; /* (unused) */
|
|
u_char ih_pr; /* protocol */
|
|
u_short ih_len; /* protocol length */
|
|
struct in_addr ih_src; /* source internet address */
|
|
struct in_addr ih_dst; /* destination internet address */
|
|
};
|
|
|
|
#ifdef _KERNEL
|
|
/*
|
|
* Ip reassembly queue structure. Each fragment
|
|
* being reassembled is attached to one of these structures.
|
|
* They are timed out after ipq_ttl drops to 0, and may also
|
|
* be reclaimed if memory becomes tight.
|
|
*/
|
|
struct ipq {
|
|
TAILQ_ENTRY(ipq) ipq_list; /* to other reass headers */
|
|
u_char ipq_ttl; /* time for reass q to live */
|
|
u_char ipq_p; /* protocol of this fragment */
|
|
u_short ipq_id; /* sequence id for reassembly */
|
|
struct mbuf *ipq_frags; /* to ip headers of fragments */
|
|
struct in_addr ipq_src,ipq_dst;
|
|
u_char ipq_nfrags; /* # frags in this packet */
|
|
struct label *ipq_label; /* MAC label */
|
|
};
|
|
#endif /* _KERNEL */
|
|
|
|
/*
|
|
* Structure stored in mbuf in inpcb.ip_options
|
|
* and passed to ip_output when ip options are in use.
|
|
* The actual length of the options (including ipopt_dst)
|
|
* is in m_len.
|
|
*/
|
|
#define MAX_IPOPTLEN 40
|
|
|
|
struct ipoption {
|
|
struct in_addr ipopt_dst; /* first-hop dst if source routed */
|
|
char ipopt_list[MAX_IPOPTLEN]; /* options proper */
|
|
};
|
|
|
|
/*
|
|
* Multicast source list entry.
|
|
*/
|
|
struct in_msource {
|
|
TAILQ_ENTRY(in_msource) ims_next; /* next source */
|
|
struct sockaddr_storage ims_addr; /* address of this source */
|
|
};
|
|
|
|
/*
|
|
* Multicast filter descriptor; there is one instance per group membership
|
|
* on a socket, allocated as an expandable vector hung off ip_moptions.
|
|
* struct in_multi contains separate IPv4-stack-wide state for IGMPv3.
|
|
*/
|
|
struct in_mfilter {
|
|
uint16_t imf_fmode; /* filter mode for this socket/group */
|
|
uint16_t imf_nsources; /* # of sources for this socket/group */
|
|
TAILQ_HEAD(, in_msource) imf_sources; /* source list */
|
|
};
|
|
|
|
/*
|
|
* Structure attached to inpcb.ip_moptions and
|
|
* passed to ip_output when IP multicast options are in use.
|
|
* This structure is lazy-allocated.
|
|
*/
|
|
struct ip_moptions {
|
|
struct ifnet *imo_multicast_ifp; /* ifp for outgoing multicasts */
|
|
struct in_addr imo_multicast_addr; /* ifindex/addr on MULTICAST_IF */
|
|
u_long imo_multicast_vif; /* vif num outgoing multicasts */
|
|
u_char imo_multicast_ttl; /* TTL for outgoing multicasts */
|
|
u_char imo_multicast_loop; /* 1 => hear sends if a member */
|
|
u_short imo_num_memberships; /* no. memberships this socket */
|
|
u_short imo_max_memberships; /* max memberships this socket */
|
|
struct in_multi **imo_membership; /* group memberships */
|
|
struct in_mfilter *imo_mfilters; /* source filters */
|
|
};
|
|
|
|
struct ipstat {
|
|
u_long ips_total; /* total packets received */
|
|
u_long ips_badsum; /* checksum bad */
|
|
u_long ips_tooshort; /* packet too short */
|
|
u_long ips_toosmall; /* not enough data */
|
|
u_long ips_badhlen; /* ip header length < data size */
|
|
u_long ips_badlen; /* ip length < ip header length */
|
|
u_long ips_fragments; /* fragments received */
|
|
u_long ips_fragdropped; /* frags dropped (dups, out of space) */
|
|
u_long ips_fragtimeout; /* fragments timed out */
|
|
u_long ips_forward; /* packets forwarded */
|
|
u_long ips_fastforward; /* packets fast forwarded */
|
|
u_long ips_cantforward; /* packets rcvd for unreachable dest */
|
|
u_long ips_redirectsent; /* packets forwarded on same net */
|
|
u_long ips_noproto; /* unknown or unsupported protocol */
|
|
u_long ips_delivered; /* datagrams delivered to upper level*/
|
|
u_long ips_localout; /* total ip packets generated here */
|
|
u_long ips_odropped; /* lost packets due to nobufs, etc. */
|
|
u_long ips_reassembled; /* total packets reassembled ok */
|
|
u_long ips_fragmented; /* datagrams successfully fragmented */
|
|
u_long ips_ofragments; /* output fragments created */
|
|
u_long ips_cantfrag; /* don't fragment flag was set, etc. */
|
|
u_long ips_badoptions; /* error in option processing */
|
|
u_long ips_noroute; /* packets discarded due to no route */
|
|
u_long ips_badvers; /* ip version != 4 */
|
|
u_long ips_rawout; /* total raw ip packets generated */
|
|
u_long ips_toolong; /* ip length > max ip packet size */
|
|
u_long ips_notmember; /* multicasts for unregistered grps */
|
|
u_long ips_nogif; /* no match gif found */
|
|
u_long ips_badaddr; /* invalid address on header */
|
|
};
|
|
|
|
#ifdef _KERNEL
|
|
|
|
/* flags passed to ip_output as last parameter */
|
|
#define IP_FORWARDING 0x1 /* most of ip header exists */
|
|
#define IP_RAWOUTPUT 0x2 /* raw ip header exists */
|
|
#define IP_SENDONES 0x4 /* send all-ones broadcast */
|
|
#define IP_SENDTOIF 0x8 /* send on specific ifnet */
|
|
#define IP_ROUTETOIF SO_DONTROUTE /* 0x10 bypass routing tables */
|
|
#define IP_ALLOWBROADCAST SO_BROADCAST /* 0x20 can send broadcast packets */
|
|
|
|
/*
|
|
* mbuf flag used by ip_fastfwd
|
|
*/
|
|
#define M_FASTFWD_OURS M_PROTO1 /* changed dst to local */
|
|
|
|
#ifdef __NO_STRICT_ALIGNMENT
|
|
#define IP_HDR_ALIGNED_P(ip) 1
|
|
#else
|
|
#define IP_HDR_ALIGNED_P(ip) ((((intptr_t) (ip)) & 3) == 0)
|
|
#endif
|
|
|
|
struct ip;
|
|
struct inpcb;
|
|
struct route;
|
|
struct sockopt;
|
|
|
|
extern struct ipstat ipstat;
|
|
extern u_short ip_id; /* ip packet ctr, for ids */
|
|
extern int ip_defttl; /* default IP ttl */
|
|
extern int ipforwarding; /* ip forwarding */
|
|
#ifdef IPSTEALTH
|
|
extern int ipstealth; /* stealth forwarding */
|
|
#endif
|
|
extern u_char ip_protox[];
|
|
extern struct socket *ip_rsvpd; /* reservation protocol daemon */
|
|
extern struct socket *ip_mrouter; /* multicast routing daemon */
|
|
extern int (*legal_vif_num)(int);
|
|
extern u_long (*ip_mcast_src)(int);
|
|
extern int rsvp_on;
|
|
extern struct pr_usrreqs rip_usrreqs;
|
|
|
|
void inp_freemoptions(struct ip_moptions *);
|
|
int inp_getmoptions(struct inpcb *, struct sockopt *);
|
|
int inp_setmoptions(struct inpcb *, struct sockopt *);
|
|
|
|
int ip_ctloutput(struct socket *, struct sockopt *sopt);
|
|
void ip_drain(void);
|
|
void ip_fini(void *xtp);
|
|
int ip_fragment(struct ip *ip, struct mbuf **m_frag, int mtu,
|
|
u_long if_hwassist_flags, int sw_csum);
|
|
void ip_forward(struct mbuf *m, int srcrt);
|
|
void ip_init(void);
|
|
extern int
|
|
(*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *,
|
|
struct ip_moptions *);
|
|
int ip_output(struct mbuf *,
|
|
struct mbuf *, struct route *, int, struct ip_moptions *,
|
|
struct inpcb *);
|
|
int ipproto_register(u_char);
|
|
int ipproto_unregister(u_char);
|
|
struct mbuf *
|
|
ip_reass(struct mbuf *);
|
|
struct in_ifaddr *
|
|
ip_rtaddr(struct in_addr, u_int fibnum);
|
|
void ip_savecontrol(struct inpcb *, struct mbuf **, struct ip *,
|
|
struct mbuf *);
|
|
void ip_slowtimo(void);
|
|
u_int16_t ip_randomid(void);
|
|
int rip_ctloutput(struct socket *, struct sockopt *);
|
|
void rip_ctlinput(int, struct sockaddr *, void *);
|
|
void rip_init(void);
|
|
void rip_input(struct mbuf *, int);
|
|
int rip_output(struct mbuf *, struct socket *, u_long);
|
|
void ipip_input(struct mbuf *, int);
|
|
void rsvp_input(struct mbuf *, int);
|
|
int ip_rsvp_init(struct socket *);
|
|
int ip_rsvp_done(void);
|
|
extern int (*ip_rsvp_vif)(struct socket *, struct sockopt *);
|
|
extern void (*ip_rsvp_force_done)(struct socket *);
|
|
extern void (*rsvp_input_p)(struct mbuf *m, int off);
|
|
|
|
extern struct pfil_head inet_pfil_hook; /* packet filter hooks */
|
|
|
|
void in_delayed_cksum(struct mbuf *m);
|
|
|
|
static __inline uint16_t ip_newid(void);
|
|
extern int ip_do_randomid;
|
|
|
|
static __inline uint16_t
|
|
ip_newid(void)
|
|
{
|
|
if (ip_do_randomid)
|
|
return ip_randomid();
|
|
|
|
return htons(ip_id++);
|
|
}
|
|
|
|
#endif /* _KERNEL */
|
|
|
|
#endif /* !_NETINET_IP_VAR_H_ */
|