freebsd-skq/sys/netinet/in_var.h

476 lines
16 KiB
C
Raw Normal View History

/*-
1994-05-24 10:09:53 +00:00
* 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
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
1994-08-21 05:27:42 +00:00
#ifndef _NETINET_IN_VAR_H_
#define _NETINET_IN_VAR_H_
#include <sys/queue.h>
#include <sys/fnv_hash.h>
#include <sys/tree.h>
struct igmp_ifinfo;
struct in_multi;
struct lltable;
/*
* IPv4 per-interface state.
*/
struct in_ifinfo {
struct lltable *ii_llt; /* ARP state */
struct igmp_ifinfo *ii_igmp; /* IGMP state */
struct in_multi *ii_allhosts; /* 224.0.0.1 membership */
};
1994-05-24 10:09:53 +00:00
/*
* Interface address, Internet version. One of these structures
* is allocated for each Internet address on an interface.
1994-05-24 10:09:53 +00:00
* 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 */
1994-05-24 10:09:53 +00:00
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))
1994-05-24 10:09:53 +00:00
#define IN_LNAOF(in, ifa) \
((ntohl((in).s_addr) & ~((struct in_ifaddr *)(ifa)->ia_subnetmask))
1995-05-30 08:16:23 +00:00
1994-05-24 10:09:53 +00:00
#ifdef _KERNEL
extern u_char inetctlerrmap[];
1994-05-24 10:09:53 +00:00
2009-04-15 20:49:59 +00:00
#define LLTABLE(ifp) \
((struct in_ifinfo *)(ifp)->if_afdata[AF_INET])->ii_llt
/*
* Hash table for IP addresses.
*/
TAILQ_HEAD(in_ifaddrhead, in_ifaddr);
LIST_HEAD(in_ifaddrhashhead, in_ifaddr);
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
VNET_DECLARE(struct in_ifaddrhashhead *, in_ifaddrhashtbl);
VNET_DECLARE(struct in_ifaddrhead, in_ifaddrhead);
VNET_DECLARE(u_long, in_ifaddrhmask); /* mask for hash table */
#define V_in_ifaddrhashtbl VNET(in_ifaddrhashtbl)
#define V_in_ifaddrhead VNET(in_ifaddrhead)
#define V_in_ifaddrhmask VNET(in_ifaddrhmask)
#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) \
(&V_in_ifaddrhashtbl[INADDR_HASHVAL(x) & V_in_ifaddrhmask])
extern struct rwlock in_ifaddr_lock;
#define IN_IFADDR_LOCK_ASSERT() rw_assert(&in_ifaddr_lock, RA_LOCKED)
#define IN_IFADDR_RLOCK() rw_rlock(&in_ifaddr_lock)
#define IN_IFADDR_RLOCK_ASSERT() rw_assert(&in_ifaddr_lock, RA_RLOCKED)
#define IN_IFADDR_RUNLOCK() rw_runlock(&in_ifaddr_lock)
#define IN_IFADDR_WLOCK() rw_wlock(&in_ifaddr_lock)
#define IN_IFADDR_WLOCK_ASSERT() rw_assert(&in_ifaddr_lock, RA_WLOCKED)
#define IN_IFADDR_WUNLOCK() rw_wunlock(&in_ifaddr_lock)
/*
2006-09-25 11:48:07 +00:00
* 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)
1994-05-24 10:09:53 +00:00
/*
* 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; \
1994-05-24 10:09:53 +00:00
\
INADDR_TO_IFADDR(addr, ia); \
1994-05-24 10:09:53 +00:00
(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(&V_in_ifaddrhead); \
(ia) != NULL && (ia)->ia_ifp != (ifp); \
(ia) = TAILQ_NEXT((ia), ia_link)) \
continue; \
if ((ia) != NULL) \
ifa_ref(&(ia)->ia_ifa); \
1994-05-24 10:09:53 +00:00
}
#endif
/*
* IP datagram reassembly.
*/
#define IPREASS_NHASH_LOG2 6
#define IPREASS_NHASH (1 << IPREASS_NHASH_LOG2)
#define IPREASS_HMASK (IPREASS_NHASH - 1)
#define IPREASS_HASH(x,y) \
(((((x) & 0xF) | ((((x) >> 8) & 0xF) << 4)) ^ (y)) & IPREASS_HMASK)
Initial get-the-easy-case-working upgrade of the multicast code to something more recent than the ancient 1.2 release contained in 4.4. This code has the following advantages as compared to previous versions (culled from the README file for the SunOS release): - True multicast delivery - Configurable rate-limiting of forwarded multicast traffic on each physical interface or tunnel, using a token-bucket limiter. - Simplistic classification of packets for prioritized dropping. - Administrative scoping of multicast address ranges. - Faster detection of hosts leaving groups. - Support for multicast traceroute (code not yet available). - Support for RSVP, the Resource Reservation Protocol. What still needs to be done: - The multicast forwarder needs testing. - The multicast routing daemon needs to be ported. - Network interface drivers need to have the `#ifdef MULTICAST' goop ripped out of them. - The IGMP code should probably be bogon-tested. Some notes about the porting process: In some cases, the Berkeley people decided to incorporate functionality from later releases of the multicast code, but then had to do things differently. As a result, if you look at Deering's patches, and then look at our code, it is not always obvious whether the patch even applies. Let the reader beware. I ran ip_mroute.c through several passes of `unifdef' to get rid of useless grot, and to permanently enable the RSVP support, which we will include as standard. Ported by: Garrett Wollman Submitted by: Steve Deering and Ajit Thyagarajan (among others)
1994-09-06 22:42:31 +00:00
/*
* Legacy IPv4 IGMP per-link structure.
Initial get-the-easy-case-working upgrade of the multicast code to something more recent than the ancient 1.2 release contained in 4.4. This code has the following advantages as compared to previous versions (culled from the README file for the SunOS release): - True multicast delivery - Configurable rate-limiting of forwarded multicast traffic on each physical interface or tunnel, using a token-bucket limiter. - Simplistic classification of packets for prioritized dropping. - Administrative scoping of multicast address ranges. - Faster detection of hosts leaving groups. - Support for multicast traceroute (code not yet available). - Support for RSVP, the Resource Reservation Protocol. What still needs to be done: - The multicast forwarder needs testing. - The multicast routing daemon needs to be ported. - Network interface drivers need to have the `#ifdef MULTICAST' goop ripped out of them. - The IGMP code should probably be bogon-tested. Some notes about the porting process: In some cases, the Berkeley people decided to incorporate functionality from later releases of the multicast code, but then had to do things differently. As a result, if you look at Deering's patches, and then look at our code, it is not always obvious whether the patch even applies. Let the reader beware. I ran ip_mroute.c through several passes of `unifdef' to get rid of useless grot, and to permanently enable the RSVP support, which we will include as standard. Ported by: Garrett Wollman Submitted by: Steve Deering and Ajit Thyagarajan (among others)
1994-09-06 22:42:31 +00:00
*/
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;
Initial get-the-easy-case-working upgrade of the multicast code to something more recent than the ancient 1.2 release contained in 4.4. This code has the following advantages as compared to previous versions (culled from the README file for the SunOS release): - True multicast delivery - Configurable rate-limiting of forwarded multicast traffic on each physical interface or tunnel, using a token-bucket limiter. - Simplistic classification of packets for prioritized dropping. - Administrative scoping of multicast address ranges. - Faster detection of hosts leaving groups. - Support for multicast traceroute (code not yet available). - Support for RSVP, the Resource Reservation Protocol. What still needs to be done: - The multicast forwarder needs testing. - The multicast routing daemon needs to be ported. - Network interface drivers need to have the `#ifdef MULTICAST' goop ripped out of them. - The IGMP code should probably be bogon-tested. Some notes about the porting process: In some cases, the Berkeley people decided to incorporate functionality from later releases of the multicast code, but then had to do things differently. As a result, if you look at Deering's patches, and then look at our code, it is not always obvious whether the patch even applies. Let the reader beware. I ran ip_mroute.c through several passes of `unifdef' to get rid of useless grot, and to permanently enable the RSVP support, which we will include as standard. Ported by: Garrett Wollman Submitted by: Steve Deering and Ajit Thyagarajan (among others)
1994-09-06 22:42:31 +00:00
};
1994-05-24 10:09:53 +00:00
/*
* Per-interface IGMP router version information.
*/
struct igmp_ifinfo {
LIST_ENTRY(igmp_ifinfo) igi_link;
struct ifnet *igi_ifp; /* interface this instance belongs to */
uint32_t igi_version; /* IGMPv3 Host Compatibility Mode */
uint32_t igi_v1_timer; /* IGMPv1 Querier Present timer (s) */
uint32_t igi_v2_timer; /* IGMPv2 Querier Present timer (s) */
uint32_t igi_v3_timer; /* IGMPv3 General Query (interface) timer (s)*/
uint32_t igi_flags; /* IGMP per-interface flags */
uint32_t igi_rv; /* IGMPv3 Robustness Variable */
uint32_t igi_qi; /* IGMPv3 Query Interval (s) */
uint32_t igi_qri; /* IGMPv3 Query Response Interval (s) */
uint32_t igi_uri; /* IGMPv3 Unsolicited Report Interval (s) */
SLIST_HEAD(,in_multi) igi_relinmhead; /* released groups */
struct ifqueue igi_gq; /* queue of general query responses */
};
#define IGIF_SILENT 0x00000001 /* Do not use IGMP on this ifp */
#define IGIF_LOOPBACK 0x00000002 /* Send IGMP reports to loopback */
/*
* IPv4 multicast IGMP-layer source entry.
*/
struct ip_msource {
RB_ENTRY(ip_msource) ims_link; /* RB tree links */
in_addr_t ims_haddr; /* host byte order */
struct ims_st {
uint16_t ex; /* # of exclusive members */
uint16_t in; /* # of inclusive members */
} ims_st[2]; /* state at t0, t1 */
uint8_t ims_stp; /* pending query */
};
/*
* IPv4 multicast PCB-layer source entry.
*/
struct in_msource {
RB_ENTRY(ip_msource) ims_link; /* RB tree links */
in_addr_t ims_haddr; /* host byte order */
uint8_t imsl_st[2]; /* state before/at commit */
};
RB_HEAD(ip_msource_tree, ip_msource); /* define struct ip_msource_tree */
static __inline int
ip_msource_cmp(const struct ip_msource *a, const struct ip_msource *b)
{
if (a->ims_haddr < b->ims_haddr)
return (-1);
if (a->ims_haddr == b->ims_haddr)
return (0);
return (1);
}
RB_PROTOTYPE(ip_msource_tree, ip_msource, ims_link, ip_msource_cmp);
/*
* IPv4 multicast PCB-layer group filter descriptor.
*/
struct in_mfilter {
struct ip_msource_tree imf_sources; /* source list for (S,G) */
u_long imf_nsrc; /* # of source entries */
uint8_t imf_st[2]; /* state before/at commit */
};
/*
* IPv4 group descriptor.
*
* For every entry on an ifnet's if_multiaddrs list which represents
* an IP multicast group, there is one of these structures.
*
* If any source filters are present, then a node will exist in the RB-tree
* to permit fast lookup by source whenever an operation takes place.
* This permits pre-order traversal when we issue reports.
* Source filter trees are kept separately from the socket layer to
* greatly simplify locking.
*
* When IGMPv3 is active, inm_timer is the response to group query timer.
* The state-change timer inm_sctimer is separate; whenever state changes
* for the group the state change record is generated and transmitted,
* and kept if retransmissions are necessary.
*
* FUTURE: inm_link is now only used when groups are being purged
* on a detaching ifnet. It could be demoted to a SLIST_ENTRY, but
* because it is at the very start of the struct, we can't do this
* w/o breaking the ABI for ifmcstat.
1994-05-24 10:09:53 +00:00
*/
struct in_multi {
LIST_ENTRY(in_multi) inm_link; /* to-be-released by in_ifdetach */
struct in_addr inm_addr; /* IP multicast address, convenience */
1994-05-24 10:09:53 +00:00
struct ifnet *inm_ifp; /* back pointer to ifnet */
struct ifmultiaddr *inm_ifma; /* back pointer to ifmultiaddr */
u_int inm_timer; /* IGMPv1/v2 group / v3 query timer */
u_int inm_state; /* state of the membership */
void *inm_rti; /* unused, legacy field */
u_int inm_refcount; /* reference count */
/* New fields for IGMPv3 follow. */
struct igmp_ifinfo *inm_igi; /* IGMP info */
SLIST_ENTRY(in_multi) inm_nrele; /* to-be-released by IGMP */
struct ip_msource_tree inm_srcs; /* tree of sources */
u_long inm_nsrc; /* # of tree entries */
struct ifqueue inm_scq; /* queue of pending
* state-change packets */
struct timeval inm_lastgsrtv; /* Time of last G-S-R query */
uint16_t inm_sctimer; /* state-change timer */
uint16_t inm_scrv; /* state-change rexmit count */
/*
* SSM state counters which track state at T0 (the time the last
* state-change report's RV timer went to zero) and T1
* (time of pending report, i.e. now).
* Used for computing IGMPv3 state-change reports. Several refcounts
* are maintained here to optimize for common use-cases.
*/
struct inm_st {
uint16_t iss_fmode; /* IGMP filter mode */
uint16_t iss_asm; /* # of ASM listeners */
uint16_t iss_ex; /* # of exclusive members */
uint16_t iss_in; /* # of inclusive members */
uint16_t iss_rec; /* # of recorded sources */
} inm_st[2]; /* state at t0, t1 */
Import rewrite of IPv4 socket multicast layer to support source-specific and protocol-independent host mode multicast. The code is written to accomodate IPv6, IGMPv3 and MLDv2 with only a little additional work. This change only pertains to FreeBSD's use as a multicast end-station and does not concern multicast routing; for an IGMPv3/MLDv2 router implementation, consider the XORP project. The work is based on Wilbert de Graaf's IGMPv3 code drop for FreeBSD 4.6, which is available at: http://www.kloosterhof.com/wilbert/igmpv3.html Summary * IPv4 multicast socket processing is now moved out of ip_output.c into a new module, in_mcast.c. * The in_mcast.c module implements the IPv4 legacy any-source API in terms of the protocol-independent source-specific API. * Source filters are lazy allocated as the common case does not use them. They are part of per inpcb state and are covered by the inpcb lock. * struct ip_mreqn is now supported to allow applications to specify multicast joins by interface index in the legacy IPv4 any-source API. * In UDP, an incoming multicast datagram only requires that the source port matches the 4-tuple if the socket was already bound by source port. An unbound socket SHOULD be able to receive multicasts sent from an ephemeral source port. * The UDP socket multicast filter mode defaults to exclusive, that is, sources present in the per-socket list will be blocked from delivery. * The RFC 3678 userland functions have been added to libc: setsourcefilter, getsourcefilter, setipv4sourcefilter, getipv4sourcefilter. * Definitions for IGMPv3 are merged but not yet used. * struct sockaddr_storage is now referenced from <netinet/in.h>. It is therefore defined there if not already declared in the same way as for the C99 types. * The RFC 1724 hack (specify 0.0.0.0/8 addresses to IP_MULTICAST_IF which are then interpreted as interface indexes) is now deprecated. * A patch for the Rhyolite.com routed in the FreeBSD base system is available in the -net archives. This only affects individuals running RIPv1 or RIPv2 via point-to-point and/or unnumbered interfaces. * Make IPv6 detach path similar to IPv4's in code flow; functionally same. * Bump __FreeBSD_version to 700048; see UPDATING. This work was financially supported by another FreeBSD committer. Obtained from: p4://bms_netdev Submitted by: Wilbert de Graaf (original work) Reviewed by: rwatson (locking), silence from fenner, net@ (but with encouragement)
2007-06-12 16:24:56 +00:00
};
/*
* Helper function to derive the filter mode on a source entry
* from its internal counters. Predicates are:
* A source is only excluded if all listeners exclude it.
* A source is only included if no listeners exclude it,
* and at least one listener includes it.
* May be used by ifmcstat(8).
Import rewrite of IPv4 socket multicast layer to support source-specific and protocol-independent host mode multicast. The code is written to accomodate IPv6, IGMPv3 and MLDv2 with only a little additional work. This change only pertains to FreeBSD's use as a multicast end-station and does not concern multicast routing; for an IGMPv3/MLDv2 router implementation, consider the XORP project. The work is based on Wilbert de Graaf's IGMPv3 code drop for FreeBSD 4.6, which is available at: http://www.kloosterhof.com/wilbert/igmpv3.html Summary * IPv4 multicast socket processing is now moved out of ip_output.c into a new module, in_mcast.c. * The in_mcast.c module implements the IPv4 legacy any-source API in terms of the protocol-independent source-specific API. * Source filters are lazy allocated as the common case does not use them. They are part of per inpcb state and are covered by the inpcb lock. * struct ip_mreqn is now supported to allow applications to specify multicast joins by interface index in the legacy IPv4 any-source API. * In UDP, an incoming multicast datagram only requires that the source port matches the 4-tuple if the socket was already bound by source port. An unbound socket SHOULD be able to receive multicasts sent from an ephemeral source port. * The UDP socket multicast filter mode defaults to exclusive, that is, sources present in the per-socket list will be blocked from delivery. * The RFC 3678 userland functions have been added to libc: setsourcefilter, getsourcefilter, setipv4sourcefilter, getipv4sourcefilter. * Definitions for IGMPv3 are merged but not yet used. * struct sockaddr_storage is now referenced from <netinet/in.h>. It is therefore defined there if not already declared in the same way as for the C99 types. * The RFC 1724 hack (specify 0.0.0.0/8 addresses to IP_MULTICAST_IF which are then interpreted as interface indexes) is now deprecated. * A patch for the Rhyolite.com routed in the FreeBSD base system is available in the -net archives. This only affects individuals running RIPv1 or RIPv2 via point-to-point and/or unnumbered interfaces. * Make IPv6 detach path similar to IPv4's in code flow; functionally same. * Bump __FreeBSD_version to 700048; see UPDATING. This work was financially supported by another FreeBSD committer. Obtained from: p4://bms_netdev Submitted by: Wilbert de Graaf (original work) Reviewed by: rwatson (locking), silence from fenner, net@ (but with encouragement)
2007-06-12 16:24:56 +00:00
*/
static __inline uint8_t
ims_get_mode(const struct in_multi *inm, const struct ip_msource *ims,
uint8_t t)
{
t = !!t;
if (inm->inm_st[t].iss_ex > 0 &&
inm->inm_st[t].iss_ex == ims->ims_st[t].ex)
return (MCAST_EXCLUDE);
else if (ims->ims_st[t].in > 0 && ims->ims_st[t].ex == 0)
return (MCAST_INCLUDE);
return (MCAST_UNDEFINED);
}
1994-05-24 10:09:53 +00:00
#ifdef _KERNEL
#ifdef SYSCTL_DECL
SYSCTL_DECL(_net_inet);
SYSCTL_DECL(_net_inet_ip);
SYSCTL_DECL(_net_inet_raw);
#endif
/*
* 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)
#define IN_MULTI_UNLOCK_ASSERT() mtx_assert(&in_multi_mtx, MA_NOTOWNED)
1994-05-24 10:09:53 +00:00
/*
* Function for looking up an in_multi record for an IPv4 multicast address
* on a given interface. ifp must be valid. If no record found, return NULL.
* The IN_MULTI_LOCK and IF_ADDR_LOCK on ifp must be held.
1994-05-24 10:09:53 +00:00
*/
static __inline struct in_multi *
inm_lookup_locked(struct ifnet *ifp, const struct in_addr ina)
{
struct ifmultiaddr *ifma;
struct in_multi *inm;
IN_MULTI_LOCK_ASSERT();
IF_ADDR_LOCK_ASSERT(ifp);
inm = NULL;
TAILQ_FOREACH(ifma, &((ifp)->if_multiaddrs), ifma_link) {
if (ifma->ifma_addr->sa_family == AF_INET) {
inm = (struct in_multi *)ifma->ifma_protospec;
if (inm->inm_addr.s_addr == ina.s_addr)
break;
inm = NULL;
}
}
return (inm);
}
1994-05-24 10:09:53 +00:00
/*
* Wrapper for inm_lookup_locked().
* The IF_ADDR_LOCK will be taken on ifp and released on return.
1994-05-24 10:09:53 +00:00
*/
static __inline struct in_multi *
inm_lookup(struct ifnet *ifp, const struct in_addr ina)
{
struct in_multi *inm;
IN_MULTI_LOCK_ASSERT();
IF_ADDR_LOCK(ifp);
inm = inm_lookup_locked(ifp, ina);
IF_ADDR_UNLOCK(ifp);
return (inm);
}
/* Acquire an in_multi record. */
static __inline void
inm_acquire_locked(struct in_multi *inm)
{
IN_MULTI_LOCK_ASSERT();
++inm->inm_refcount;
}
1994-05-24 10:09:53 +00:00
/*
* Return values for imo_multi_filter().
1994-05-24 10:09:53 +00:00
*/
#define MCAST_PASS 0 /* Pass */
#define MCAST_NOTGMEMBER 1 /* This host not a member of group */
#define MCAST_NOTSMEMBER 2 /* This host excluded source */
#define MCAST_MUTED 3 /* [deprecated] */
1994-05-24 10:09:53 +00:00
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
struct rtentry;
struct route;
Import rewrite of IPv4 socket multicast layer to support source-specific and protocol-independent host mode multicast. The code is written to accomodate IPv6, IGMPv3 and MLDv2 with only a little additional work. This change only pertains to FreeBSD's use as a multicast end-station and does not concern multicast routing; for an IGMPv3/MLDv2 router implementation, consider the XORP project. The work is based on Wilbert de Graaf's IGMPv3 code drop for FreeBSD 4.6, which is available at: http://www.kloosterhof.com/wilbert/igmpv3.html Summary * IPv4 multicast socket processing is now moved out of ip_output.c into a new module, in_mcast.c. * The in_mcast.c module implements the IPv4 legacy any-source API in terms of the protocol-independent source-specific API. * Source filters are lazy allocated as the common case does not use them. They are part of per inpcb state and are covered by the inpcb lock. * struct ip_mreqn is now supported to allow applications to specify multicast joins by interface index in the legacy IPv4 any-source API. * In UDP, an incoming multicast datagram only requires that the source port matches the 4-tuple if the socket was already bound by source port. An unbound socket SHOULD be able to receive multicasts sent from an ephemeral source port. * The UDP socket multicast filter mode defaults to exclusive, that is, sources present in the per-socket list will be blocked from delivery. * The RFC 3678 userland functions have been added to libc: setsourcefilter, getsourcefilter, setipv4sourcefilter, getipv4sourcefilter. * Definitions for IGMPv3 are merged but not yet used. * struct sockaddr_storage is now referenced from <netinet/in.h>. It is therefore defined there if not already declared in the same way as for the C99 types. * The RFC 1724 hack (specify 0.0.0.0/8 addresses to IP_MULTICAST_IF which are then interpreted as interface indexes) is now deprecated. * A patch for the Rhyolite.com routed in the FreeBSD base system is available in the -net archives. This only affects individuals running RIPv1 or RIPv2 via point-to-point and/or unnumbered interfaces. * Make IPv6 detach path similar to IPv4's in code flow; functionally same. * Bump __FreeBSD_version to 700048; see UPDATING. This work was financially supported by another FreeBSD committer. Obtained from: p4://bms_netdev Submitted by: Wilbert de Graaf (original work) Reviewed by: rwatson (locking), silence from fenner, net@ (but with encouragement)
2007-06-12 16:24:56 +00:00
struct ip_moptions;
int imo_multi_filter(const struct ip_moptions *, const struct ifnet *,
const struct sockaddr *, const struct sockaddr *);
void inm_commit(struct in_multi *);
void inm_clear_recorded(struct in_multi *);
void inm_print(const struct in_multi *);
int inm_record_source(struct in_multi *inm, const in_addr_t);
void inm_release(struct in_multi *);
void inm_release_locked(struct in_multi *);
struct in_multi *
in_addmulti(struct in_addr *, struct ifnet *);
2002-03-19 21:25:46 +00:00
void in_delmulti(struct in_multi *);
int in_joingroup(struct ifnet *, const struct in_addr *,
/*const*/ struct in_mfilter *, struct in_multi **);
int in_joingroup_locked(struct ifnet *, const struct in_addr *,
/*const*/ struct in_mfilter *, struct in_multi **);
int in_leavegroup(struct in_multi *, /*const*/ struct in_mfilter *);
int in_leavegroup_locked(struct in_multi *,
/*const*/ struct in_mfilter *);
2002-03-19 21:25:46 +00:00
int in_control(struct socket *, u_long, caddr_t, struct ifnet *,
struct thread *);
2002-03-19 21:25:46 +00:00
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 *);
void *in_domifattach(struct ifnet *);
void in_domifdetach(struct ifnet *, void *);
1994-08-21 05:27:42 +00:00
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
/* 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);
#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_ */