2005-01-07 01:45:51 +00:00
|
|
|
/*-
|
1994-05-24 10:09:53 +00:00
|
|
|
* 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.
|
|
|
|
|
*
|
1995-09-21 18:04:43 +00:00
|
|
|
* @(#)ip_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_IP_VAR_H_
|
1996-10-15 16:54:47 +00:00
|
|
|
#define _NETINET_IP_VAR_H_
|
1994-08-21 05:27:42 +00:00
|
|
|
|
2001-06-11 12:39:29 +00:00
|
|
|
#include <sys/queue.h>
|
|
|
|
|
|
1994-05-24 10:09:53 +00:00
|
|
|
/*
|
|
|
|
|
* Overlay for ip header used by other protocols (tcp, udp).
|
|
|
|
|
*/
|
|
|
|
|
struct ipovly {
|
1998-08-24 07:47:39 +00:00
|
|
|
u_char ih_x1[9]; /* (unused) */
|
1994-05-24 10:09:53 +00:00
|
|
|
u_char ih_pr; /* protocol */
|
1996-10-25 17:57:53 +00:00
|
|
|
u_short ih_len; /* protocol length */
|
1994-05-24 10:09:53 +00:00
|
|
|
struct in_addr ih_src; /* source internet address */
|
|
|
|
|
struct in_addr ih_dst; /* destination internet address */
|
|
|
|
|
};
|
|
|
|
|
|
2002-07-20 22:46:20 +00:00
|
|
|
#ifdef _KERNEL
|
1994-05-24 10:09:53 +00:00
|
|
|
/*
|
|
|
|
|
* 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 {
|
2001-03-16 20:00:53 +00:00
|
|
|
TAILQ_ENTRY(ipq) ipq_list; /* to other reass headers */
|
1994-05-24 10:09:53 +00:00
|
|
|
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 */
|
1998-08-24 07:47:39 +00:00
|
|
|
struct mbuf *ipq_frags; /* to ip headers of fragments */
|
1994-05-24 10:09:53 +00:00
|
|
|
struct in_addr ipq_src,ipq_dst;
|
2003-02-22 06:41:47 +00:00
|
|
|
u_char ipq_nfrags; /* # frags in this packet */
|
2007-04-04 15:30:31 +00:00
|
|
|
struct label *ipq_label; /* MAC label */
|
1994-05-24 10:09:53 +00:00
|
|
|
};
|
2002-07-20 22:46:20 +00:00
|
|
|
#endif /* _KERNEL */
|
1994-05-24 10:09:53 +00:00
|
|
|
|
2005-11-19 14:01:32 +00:00
|
|
|
/*
|
|
|
|
|
* 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 */
|
|
|
|
|
};
|
|
|
|
|
|
1994-05-24 10:09:53 +00:00
|
|
|
/*
|
|
|
|
|
* Structure attached to inpcb.ip_moptions and
|
|
|
|
|
* passed to ip_output when IP multicast options are in use.
|
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
|
|
|
* This structure is lazy-allocated.
|
1994-05-24 10:09:53 +00:00
|
|
|
*/
|
|
|
|
|
struct ip_moptions {
|
|
|
|
|
struct ifnet *imo_multicast_ifp; /* ifp for outgoing multicasts */
|
2001-06-11 12:39:29 +00:00
|
|
|
struct in_addr imo_multicast_addr; /* ifindex/addr on MULTICAST_IF */
|
2006-05-14 14:22:49 +00:00
|
|
|
u_long imo_multicast_vif; /* vif num outgoing multicasts */
|
1994-05-24 10:09:53 +00:00
|
|
|
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 */
|
2006-05-14 14:22:49 +00:00
|
|
|
u_short imo_max_memberships; /* max memberships this socket */
|
|
|
|
|
struct in_multi **imo_membership; /* group memberships */
|
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 in_mfilter *imo_mfilters; /* source filters */
|
1994-05-24 10:09:53 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
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 */
|
1998-05-19 14:04:36 +00:00
|
|
|
u_long ips_fastforward; /* packets fast forwarded */
|
1994-05-24 10:09:53 +00:00
|
|
|
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 */
|
1996-01-30 23:02:38 +00:00
|
|
|
u_long ips_fragmented; /* datagrams successfully fragmented */
|
1994-05-24 10:09:53 +00:00
|
|
|
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 */
|
1996-10-25 17:57:53 +00:00
|
|
|
u_long ips_toolong; /* ip length > max ip packet size */
|
1997-01-21 21:08:09 +00:00
|
|
|
u_long ips_notmember; /* multicasts for unregistered grps */
|
1999-11-05 14:41:39 +00:00
|
|
|
u_long ips_nogif; /* no match gif found */
|
2001-06-11 12:39:29 +00:00
|
|
|
u_long ips_badaddr; /* invalid address on header */
|
1994-05-24 10:09:53 +00:00
|
|
|
};
|
|
|
|
|
|
1999-12-29 04:46:21 +00:00
|
|
|
#ifdef _KERNEL
|
1998-07-13 12:20:07 +00:00
|
|
|
|
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
|
|
|
#include <net/vnet.h>
|
|
|
|
|
|
2009-08-02 19:43:32 +00:00
|
|
|
/*
|
|
|
|
|
* In-kernel consumers can use these accessor macros directly to update
|
|
|
|
|
* stats.
|
|
|
|
|
*/
|
2009-04-11 23:35:20 +00:00
|
|
|
#define IPSTAT_ADD(name, val) V_ipstat.name += (val)
|
|
|
|
|
#define IPSTAT_SUB(name, val) V_ipstat.name -= (val)
|
|
|
|
|
#define IPSTAT_INC(name) IPSTAT_ADD(name, 1)
|
|
|
|
|
#define IPSTAT_DEC(name) IPSTAT_SUB(name, 1)
|
|
|
|
|
|
2009-08-02 19:43:32 +00:00
|
|
|
/*
|
|
|
|
|
* Kernel module consumers must use this accessor macro.
|
|
|
|
|
*/
|
|
|
|
|
void kmod_ipstat_inc(int statnum);
|
|
|
|
|
#define KMOD_IPSTAT_INC(name) \
|
|
|
|
|
kmod_ipstat_inc(offsetof(struct ipstat, name) / sizeof(u_long))
|
|
|
|
|
void kmod_ipstat_dec(int statnum);
|
|
|
|
|
#define KMOD_IPSTAT_DEC(name) \
|
|
|
|
|
kmod_ipstat_dec(offsetof(struct ipstat, name) / sizeof(u_long))
|
|
|
|
|
|
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
|
|
|
/* 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 */
|
2007-04-04 15:30:31 +00:00
|
|
|
#define IP_ROUTETOIF SO_DONTROUTE /* 0x10 bypass routing tables */
|
|
|
|
|
#define IP_ALLOWBROADCAST SO_BROADCAST /* 0x20 can send broadcast packets */
|
1994-05-24 10:09:53 +00:00
|
|
|
|
2007-04-04 15:30:31 +00:00
|
|
|
/*
|
|
|
|
|
* mbuf flag used by ip_fastfwd
|
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
#define M_FASTFWD_OURS M_PROTO1 /* changed dst to local */
|
|
|
|
|
|
2005-07-02 23:13:31 +00:00
|
|
|
#ifdef __NO_STRICT_ALIGNMENT
|
|
|
|
|
#define IP_HDR_ALIGNED_P(ip) 1
|
|
|
|
|
#else
|
|
|
|
|
#define IP_HDR_ALIGNED_P(ip) ((((intptr_t) (ip)) & 3) == 0)
|
|
|
|
|
#endif
|
|
|
|
|
|
1998-08-23 03:07:17 +00:00
|
|
|
struct ip;
|
1996-11-12 10:02:09 +00:00
|
|
|
struct inpcb;
|
1996-10-15 16:54:47 +00:00
|
|
|
struct route;
|
1998-08-23 03:07:17 +00:00
|
|
|
struct sockopt;
|
1996-10-15 16:54:47 +00:00
|
|
|
|
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 ipstat, ipstat);
|
|
|
|
|
VNET_DECLARE(u_short, ip_id); /* ip packet ctr, for ids */
|
|
|
|
|
VNET_DECLARE(int, ip_defttl); /* default IP ttl */
|
|
|
|
|
VNET_DECLARE(int, ipforwarding); /* ip forwarding */
|
|
|
|
|
#ifdef IPSTEALTH
|
|
|
|
|
VNET_DECLARE(int, ipstealth); /* stealth forwarding */
|
|
|
|
|
#endif
|
|
|
|
|
VNET_DECLARE(int, rsvp_on);
|
|
|
|
|
VNET_DECLARE(struct socket *, ip_rsvpd); /* reservation protocol daemon*/
|
|
|
|
|
VNET_DECLARE(struct socket *, ip_mrouter); /* multicast routing daemon */
|
|
|
|
|
|
2009-07-16 21:13:04 +00:00
|
|
|
#define V_ipstat VNET(ipstat)
|
|
|
|
|
#define V_ip_id VNET(ip_id)
|
|
|
|
|
#define V_ip_defttl VNET(ip_defttl)
|
|
|
|
|
#define V_ipforwarding VNET(ipforwarding)
|
2003-11-15 01:45:56 +00:00
|
|
|
#ifdef IPSTEALTH
|
2009-07-16 21:13:04 +00:00
|
|
|
#define V_ipstealth VNET(ipstealth)
|
2003-11-15 01:45:56 +00:00
|
|
|
#endif
|
2009-07-16 21:13:04 +00:00
|
|
|
#define V_rsvp_on VNET(rsvp_on)
|
|
|
|
|
#define V_ip_rsvpd VNET(ip_rsvpd)
|
|
|
|
|
#define V_ip_mrouter VNET(ip_mrouter)
|
2009-06-05 13:44:30 +00:00
|
|
|
|
2008-12-11 16:26:38 +00:00
|
|
|
extern u_char ip_protox[];
|
2002-03-19 21:25:46 +00:00
|
|
|
extern int (*legal_vif_num)(int);
|
|
|
|
|
extern u_long (*ip_mcast_src)(int);
|
1997-02-18 20:46:36 +00:00
|
|
|
extern struct pr_usrreqs rip_usrreqs;
|
1994-05-24 10:09:53 +00:00
|
|
|
|
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
|
|
|
void inp_freemoptions(struct ip_moptions *);
|
|
|
|
|
int inp_getmoptions(struct inpcb *, struct sockopt *);
|
|
|
|
|
int inp_setmoptions(struct inpcb *, struct sockopt *);
|
|
|
|
|
|
2007-04-04 15:30:31 +00:00
|
|
|
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,
|
2003-08-07 18:16:59 +00:00
|
|
|
u_long if_hwassist_flags, int sw_csum);
|
2007-04-04 15:30:31 +00:00
|
|
|
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 *,
|
2002-10-16 01:54:46 +00:00
|
|
|
struct mbuf *, struct route *, int, struct ip_moptions *,
|
|
|
|
|
struct inpcb *);
|
2007-04-04 15:30:31 +00:00
|
|
|
int ipproto_register(u_char);
|
|
|
|
|
int ipproto_unregister(u_char);
|
2004-08-17 22:05:54 +00:00
|
|
|
struct mbuf *
|
2007-04-04 15:30:31 +00:00
|
|
|
ip_reass(struct mbuf *);
|
2001-11-30 10:40:28 +00:00
|
|
|
struct in_ifaddr *
|
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
|
|
|
ip_rtaddr(struct in_addr, u_int fibnum);
|
2007-04-04 15:30:31 +00:00
|
|
|
void ip_savecontrol(struct inpcb *, struct mbuf **, struct ip *,
|
|
|
|
|
struct mbuf *);
|
|
|
|
|
void ip_slowtimo(void);
|
2004-08-14 15:32:40 +00:00
|
|
|
u_int16_t ip_randomid(void);
|
2002-06-23 09:03:42 +00:00
|
|
|
int rip_ctloutput(struct socket *, struct sockopt *);
|
|
|
|
|
void rip_ctlinput(int, struct sockaddr *, void *);
|
|
|
|
|
void rip_init(void);
|
Introduce an infrastructure for dismantling vnet instances.
Vnet modules and protocol domains may now register destructor
functions to clean up and release per-module state. The destructor
mechanisms can be triggered by invoking "vimage -d", or a future
equivalent command which will be provided via the new jail framework.
While this patch introduces numerous placeholder destructor functions,
many of those are currently incomplete, thus leaking memory or (even
worse) failing to stop all running timers. Many of such issues are
already known and will be incrementaly fixed over the next weeks in
smaller incremental commits.
Apart from introducing new fields in structs ifnet, domain, protosw
and vnet_net, which requires the kernel and modules to be rebuilt, this
change should have no impact on nooptions VIMAGE builds, since vnet
destructors can only be called in VIMAGE kernels. Moreover,
destructor functions should be in general compiled in only in
options VIMAGE builds, except for kernel modules which can be safely
kldunloaded at run time.
Bump __FreeBSD_version to 800097.
Reviewed by: bz, julian
Approved by: rwatson, kib (re), julian (mentor)
2009-06-08 17:15:40 +00:00
|
|
|
#ifdef VIMAGE
|
|
|
|
|
void rip_destroy(void);
|
|
|
|
|
#endif
|
2002-06-23 09:03:42 +00:00
|
|
|
void rip_input(struct mbuf *, int);
|
|
|
|
|
int rip_output(struct mbuf *, struct socket *, u_long);
|
2002-03-19 21:25:46 +00:00
|
|
|
void ipip_input(struct mbuf *, int);
|
|
|
|
|
void rsvp_input(struct mbuf *, int);
|
|
|
|
|
int ip_rsvp_init(struct socket *);
|
|
|
|
|
int ip_rsvp_done(void);
|
Massive cleanup of the ip_mroute code.
No functional changes, but:
+ the mrouting module now should behave the same as the compiled-in
version (it did not before, some of the rsvp code was not loaded
properly);
+ netinet/ip_mroute.c is now truly optional;
+ removed some redundant/unused code;
+ changed many instances of '0' to NULL and INADDR_ANY as appropriate;
+ removed several static variables to make the code more SMP-friendly;
+ fixed some minor bugs in the mrouting code (mostly, incorrect return
values from functions).
This commit is also a prerequisite to the addition of support for PIM,
which i would like to put in before DP2 (it does not change any of
the existing APIs, anyways).
Note, in the process we found out that some device drivers fail to
properly handle changes in IFF_ALLMULTI, leading to interesting
behaviour when a multicast router is started. This bug is not
corrected by this commit, and will be fixed with a separate commit.
Detailed changes:
--------------------
netinet/ip_mroute.c all the above.
conf/files make ip_mroute.c optional
net/route.c fix mrt_ioctl hook
netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here
together with other rsvp code, and a couple
of indentation fixes.
netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks
netinet/ip_var.h rsvp function hooks
netinet/raw_ip.c hooks for mrouting and rsvp functions, plus
interface cleanup.
netinet/ip_mroute.h remove an unused and optional field from a struct
Most of the code is from Pavlin Radoslavov and the XORP project
Reviewed by: sam
MFC after: 1 week
2002-11-15 22:53:53 +00:00
|
|
|
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);
|
|
|
|
|
|
2004-08-27 15:16:24 +00:00
|
|
|
extern struct pfil_head inet_pfil_hook; /* packet filter hooks */
|
2003-09-23 17:54:04 +00:00
|
|
|
|
2000-05-21 21:26:06 +00:00
|
|
|
void in_delayed_cksum(struct mbuf *m);
|
|
|
|
|
|
2009-06-05 13:44:30 +00:00
|
|
|
/* ipfw and dummynet hooks. Most are declared in raw_ip.c */
|
|
|
|
|
struct ip_fw_args;
|
|
|
|
|
extern int (*ip_fw_chk_ptr)(struct ip_fw_args *args);
|
|
|
|
|
extern int (*ip_fw_ctl_ptr)(struct sockopt *);
|
|
|
|
|
extern int (*ip_dn_ctl_ptr)(struct sockopt *);
|
|
|
|
|
extern int (*ip_dn_io_ptr)(struct mbuf **m, int dir, struct ip_fw_args *fwa);
|
|
|
|
|
extern void (*ip_dn_ruledel_ptr)(void *); /* in ip_fw2.c */
|
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(int, ip_do_randomid);
|
2009-07-16 21:13:04 +00:00
|
|
|
#define V_ip_do_randomid VNET(ip_do_randomid)
|
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
|
|
|
#define ip_newid() ((V_ip_do_randomid != 0) ? ip_randomid() : \
|
|
|
|
|
htons(V_ip_id++))
|
|
|
|
|
|
1999-12-29 04:46:21 +00:00
|
|
|
#endif /* _KERNEL */
|
1994-08-21 05:27:42 +00:00
|
|
|
|
1998-07-13 12:20:07 +00:00
|
|
|
#endif /* !_NETINET_IP_VAR_H_ */
|