freebsd-nq/sys/netinet/ip_var.h

322 lines
12 KiB
C
Raw Normal View History

/*-
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.
*
* @(#)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_
#define _NETINET_IP_VAR_H_
1994-08-21 05:27:42 +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 {
u_char ih_x1[9]; /* (unused) */
1994-05-24 10:09:53 +00:00
u_char ih_pr; /* protocol */
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 */
};
#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 */
struct mbuf *ipq_frags; /* to ip headers of fragments */
1994-05-24 10:09:53 +00:00
struct in_addr ipq_src,ipq_dst;
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
};
#endif /* _KERNEL */
1994-05-24 10:09:53 +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 */
struct in_addr imo_multicast_addr; /* ifindex/addr on MULTICAST_IF */
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 */
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 */
STAILQ_ENTRY(ip_moptions) imo_link;
1994-05-24 10:09:53 +00:00
};
struct ipstat {
uint64_t ips_total; /* total packets received */
uint64_t ips_badsum; /* checksum bad */
uint64_t ips_tooshort; /* packet too short */
uint64_t ips_toosmall; /* not enough data */
uint64_t ips_badhlen; /* ip header length < data size */
uint64_t ips_badlen; /* ip length < ip header length */
uint64_t ips_fragments; /* fragments received */
uint64_t ips_fragdropped; /* frags dropped (dups, out of space) */
uint64_t ips_fragtimeout; /* fragments timed out */
uint64_t ips_forward; /* packets forwarded */
uint64_t ips_fastforward; /* packets fast forwarded */
uint64_t ips_cantforward; /* packets rcvd for unreachable dest */
uint64_t ips_redirectsent; /* packets forwarded on same net */
uint64_t ips_noproto; /* unknown or unsupported protocol */
uint64_t ips_delivered; /* datagrams delivered to upper level*/
uint64_t ips_localout; /* total ip packets generated here */
uint64_t ips_odropped; /* lost packets due to nobufs, etc. */
uint64_t ips_reassembled; /* total packets reassembled ok */
uint64_t ips_fragmented; /* datagrams successfully fragmented */
uint64_t ips_ofragments; /* output fragments created */
uint64_t ips_cantfrag; /* don't fragment flag was set, etc. */
uint64_t ips_badoptions; /* error in option processing */
uint64_t ips_noroute; /* packets discarded due to no route */
uint64_t ips_badvers; /* ip version != 4 */
uint64_t ips_rawout; /* total raw ip packets generated */
uint64_t ips_toolong; /* ip length > max ip packet size */
uint64_t ips_notmember; /* multicasts for unregistered grps */
uint64_t ips_nogif; /* no match gif found */
uint64_t ips_badaddr; /* invalid address on header */
1994-05-24 10:09:53 +00:00
};
#ifdef _KERNEL
#include <sys/counter.h>
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>
VNET_PCPUSTAT_DECLARE(struct ipstat, ipstat);
/*
* In-kernel consumers can use these accessor macros directly to update
* stats.
*/
#define IPSTAT_ADD(name, val) \
VNET_PCPUSTAT_ADD(struct ipstat, ipstat, name, (val))
#define IPSTAT_SUB(name, val) IPSTAT_ADD(name, -(val))
#define IPSTAT_INC(name) IPSTAT_ADD(name, 1)
#define IPSTAT_DEC(name) IPSTAT_SUB(name, 1)
/*
* 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(uint64_t))
void kmod_ipstat_dec(int statnum);
#define KMOD_IPSTAT_DEC(name) \
kmod_ipstat_dec(offsetof(struct ipstat, name) / sizeof(uint64_t))
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
/*
* IPv4 protocol layer specific mbuf flags.
2007-04-04 15:30:31 +00:00
*/
#define M_FASTFWD_OURS M_PROTO1 /* changed dst to local */
#define M_IP_NEXTHOP M_PROTO2 /* explicit ip nexthop */
#define M_SKIP_FIREWALL M_PROTO3 /* skip firewall processing,
keep in sync with IP6 */
#define M_IP_FRAG M_PROTO4 /* fragment reassembly */
#ifdef __NO_STRICT_ALIGNMENT
#define IP_HDR_ALIGNED_P(ip) 1
#else
#define IP_HDR_ALIGNED_P(ip) ((((intptr_t) (ip)) & 3) == 0)
#endif
struct ip;
struct inpcb;
struct route;
struct sockopt;
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(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
extern u_char ip_protox[];
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 socket *, ip_rsvpd); /* reservation protocol daemon*/
VNET_DECLARE(struct socket *, ip_mrouter); /* multicast routing daemon */
extern int (*legal_vif_num)(int);
extern u_long (*ip_mcast_src)(int);
VNET_DECLARE(int, rsvp_on);
VNET_DECLARE(int, drop_redirect);
extern struct pr_usrreqs rip_usrreqs;
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 V_ip_id VNET(ip_id)
#define V_ip_defttl VNET(ip_defttl)
#define V_ipforwarding VNET(ipforwarding)
#ifdef IPSTEALTH
#define V_ipstealth VNET(ipstealth)
#endif
#define V_ip_rsvpd VNET(ip_rsvpd)
#define V_ip_mrouter VNET(ip_mrouter)
#define V_rsvp_on VNET(rsvp_on)
#define V_drop_redirect VNET(drop_redirect)
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);
int ip_fragment(struct ip *ip, struct mbuf **m_frag, int mtu,
u_long if_hwassist_flags);
2007-04-04 15:30:31 +00:00
void ip_forward(struct mbuf *m, int srcrt);
void ip_init(void);
#ifdef VIMAGE
void ip_destroy(void);
#endif
2007-04-04 15:30:31 +00:00
extern int
(*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *,
struct ip_moptions *);
int ip_output(struct mbuf *,
struct mbuf *, struct route *, int, struct ip_moptions *,
struct inpcb *);
int ipproto_register(short);
int ipproto_unregister(short);
Convert ipfw to use PFIL_HOOKS. This is change is transparent to userland and preserves the ipfw ABI. The ipfw core packet inspection and filtering functions have not been changed, only how ipfw is invoked is different. However there are many changes how ipfw is and its add-on's are handled: In general ipfw is now called through the PFIL_HOOKS and most associated magic, that was in ip_input() or ip_output() previously, is now done in ipfw_check_[in|out]() in the ipfw PFIL handler. IPDIVERT is entirely handled within the ipfw PFIL handlers. A packet to be diverted is checked if it is fragmented, if yes, ip_reass() gets in for reassembly. If not, or all fragments arrived and the packet is complete, divert_packet is called directly. For 'tee' no reassembly attempt is made and a copy of the packet is sent to the divert socket unmodified. The original packet continues its way through ip_input/output(). ipfw 'forward' is done via m_tag's. The ipfw PFIL handlers tag the packet with the new destination sockaddr_in. A check if the new destination is a local IP address is made and the m_flags are set appropriately. ip_input() and ip_output() have some more work to do here. For ip_input() the m_flags are checked and a packet for us is directly sent to the 'ours' section for further processing. Destination changes on the input path are only tagged and the 'srcrt' flag to ip_forward() is set to disable destination checks and ICMP replies at this stage. The tag is going to be handled on output. ip_output() again checks for m_flags and the 'ours' tag. If found, the packet will be dropped back to the IP netisr where it is going to be picked up by ip_input() again and the directly sent to the 'ours' section. When only the destination changes, the route's 'dst' is overwritten with the new destination from the forward m_tag. Then it jumps back at the route lookup again and skips the firewall check because it has been marked with M_SKIP_FIREWALL. ipfw 'forward' has to be compiled into the kernel with 'option IPFIREWALL_FORWARD' to enable it. DUMMYNET is entirely handled within the ipfw PFIL handlers. A packet for a dummynet pipe or queue is directly sent to dummynet_io(). Dummynet will then inject it back into ip_input/ip_output() after it has served its time. Dummynet packets are tagged and will continue from the next rule when they hit the ipfw PFIL handlers again after re-injection. BRIDGING and IPFW_ETHER are not changed yet and use ipfw_chk() directly as they did before. Later this will be changed to dedicated ETHER PFIL_HOOKS. More detailed changes to the code: conf/files Add netinet/ip_fw_pfil.c. conf/options Add IPFIREWALL_FORWARD option. modules/ipfw/Makefile Add ip_fw_pfil.c. net/bridge.c Disable PFIL_HOOKS if ipfw for bridging is active. Bridging ipfw is still directly invoked to handle layer2 headers and packets would get a double ipfw when run through PFIL_HOOKS as well. netinet/ip_divert.c Removed divert_clone() function. It is no longer used. netinet/ip_dummynet.[ch] Neither the route 'ro' nor the destination 'dst' need to be stored while in dummynet transit. Structure members and associated macros are removed. netinet/ip_fastfwd.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_fw.h Removed 'ro' and 'dst' from struct ip_fw_args. netinet/ip_fw2.c (Re)moved some global variables and the module handling. netinet/ip_fw_pfil.c New file containing the ipfw PFIL handlers and module initialization. netinet/ip_input.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. ip_forward() does not longer require the 'next_hop' struct sockaddr_in argument. Disable early checks if 'srcrt' is set. netinet/ip_output.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_var.h Add ip_reass() as general function. (Used from ipfw PFIL handlers for IPDIVERT.) netinet/raw_ip.c Directly check if ipfw and dummynet control pointers are active. netinet/tcp_input.c Rework the 'ipfw forward' to local code to work with the new way of forward tags. netinet/tcp_sack.c Remove include 'opt_ipfw.h' which is not needed here. sys/mbuf.h Remove m_claim_next() macro which was exclusively for ipfw 'forward' and is no longer needed. Approved by: re (scottl)
2004-08-17 22:05:54 +00:00
struct mbuf *
2007-04-04 15:30:31 +00:00
ip_reass(struct mbuf *);
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);
u_int16_t ip_randomid(void);
int rip_ctloutput(struct socket *, struct sockopt *);
void rip_ctlinput(int, struct sockaddr *, void *);
void rip_init(void);
#ifdef VIMAGE
void rip_destroy(void);
#endif
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);
VNET_DECLARE(struct pfil_head, inet_pfil_hook); /* packet filter hooks */
#define V_inet_pfil_hook VNET(inet_pfil_hook)
void in_delayed_cksum(struct mbuf *m);
/* Hooks for ipfw, dummynet, divert etc. Most are declared in raw_ip.c */
/*
* Reference to an ipfw or packet filter rule that can be carried
* outside critical sections.
* A rule is identified by rulenum:rule_id which is ordered.
* In version chain_id the rule can be found in slot 'slot', so
* we don't need a lookup if chain_id == chain->id.
*
* On exit from the firewall this structure refers to the rule after
* the matching one (slot points to the new rule; rulenum:rule_id-1
* is the matching rule), and additional info (e.g. info often contains
* the insn argument or tablearg in the low 16 bits, in host format).
* On entry, the structure is valid if slot>0, and refers to the starting
* rules. 'info' contains the reason for reinject, e.g. divert port,
* divert direction, and so on.
*/
struct ipfw_rule_ref {
uint32_t slot; /* slot for matching rule */
uint32_t rulenum; /* matching rule number */
uint32_t rule_id; /* matching rule id */
uint32_t chain_id; /* ruleset id */
uint32_t info; /* see below */
};
enum {
IPFW_INFO_MASK = 0x0000ffff,
IPFW_INFO_OUT = 0x00000000, /* outgoing, just for convenience */
IPFW_INFO_IN = 0x80000000, /* incoming, overloads dir */
IPFW_ONEPASS = 0x40000000, /* One-pass, do not reinject */
IPFW_IS_MASK = 0x30000000, /* which source ? */
IPFW_IS_DIVERT = 0x20000000,
IPFW_IS_DUMMYNET =0x10000000,
IPFW_IS_PIPE = 0x08000000, /* pip1=1, queue = 0 */
};
#define MTAG_IPFW 1148380143 /* IPFW-tagged cookie */
#define MTAG_IPFW_RULE 1262273568 /* rule reference */
#define MTAG_IPFW_CALL 1308397630 /* call stack */
struct ip_fw_args;
typedef int (*ip_fw_chk_ptr_t)(struct ip_fw_args *args);
typedef int (*ip_fw_ctl_ptr_t)(struct sockopt *);
VNET_DECLARE(ip_fw_ctl_ptr_t, ip_fw_ctl_ptr);
#define V_ip_fw_ctl_ptr VNET(ip_fw_ctl_ptr)
/* Divert hooks. */
extern void (*ip_divert_ptr)(struct mbuf *m, int incoming);
/* ng_ipfw hooks -- XXX make it the same as divert and dummynet */
extern int (*ng_ipfw_input_p)(struct mbuf **, int,
struct ip_fw_args *, int);
extern int (*ip_dn_ctl_ptr)(struct sockopt *);
extern int (*ip_dn_io_ptr)(struct mbuf **, int, struct ip_fw_args *);
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);
#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++))
#endif /* _KERNEL */
1994-08-21 05:27:42 +00:00
#endif /* !_NETINET_IP_VAR_H_ */