freebsd-nq/sys/netinet/ip_var.h

217 lines
8.0 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 */
Modify the MAC Framework so that instead of embedding a (struct label) in various kernel objects to represent security data, we embed a (struct label *) pointer, which now references labels allocated using a UMA zone (mac_label.c). This allows the size and shape of struct label to be varied without changing the size and shape of these kernel objects, which become part of the frozen ABI with 5-STABLE. This opens the door for boot-time selection of the number of label slots, and hence changes to the bound on the number of simultaneous labeled policies at boot-time instead of compile-time. This also makes it easier to embed label references in new objects as required for locking/caching with fine-grained network stack locking, such as inpcb structures. This change also moves us further in the direction of hiding the structure of kernel objects from MAC policy modules, not to mention dramatically reducing the number of '&' symbols appearing in both the MAC Framework and MAC policy modules, and improving readability. While this results in minimal performance change with MAC enabled, it will observably shrink the size of a number of critical kernel data structures for the !MAC case, and should have a small (but measurable) performance benefit (i.e., struct vnode, struct socket) do to memory conservation and reduced cost of zeroing memory. NOTE: Users of MAC must recompile their kernel and all MAC modules as a result of this change. Because this is an API change, third party MAC modules will also need to be updated to make less use of the '&' symbol. Suggestions from: bmilekic Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2003-11-12 03:14:31 +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 */
};
/*
* Structure attached to inpcb.ip_moptions and
* passed to ip_output when IP multicast options are in use.
*/
struct ip_moptions {
struct ifnet *imo_multicast_ifp; /* ifp for outgoing multicasts */
struct in_addr imo_multicast_addr; /* ifindex/addr on MULTICAST_IF */
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 */
struct in_multi *imo_membership[IP_MAX_MEMBERSHIPS];
u_long imo_multicast_vif; /* vif num outgoing multicasts */
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 */
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 */
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 */
u_long ips_toolong; /* ip length > max ip packet size */
u_long ips_notmember; /* multicasts for unregistered grps */
u_long ips_nogif; /* no match gif found */
u_long ips_badaddr; /* invalid address on header */
1994-05-24 10:09:53 +00:00
};
#ifdef _KERNEL
1994-05-24 10:09:53 +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 */
1994-05-24 10:09:53 +00:00
#define IP_ROUTETOIF SO_DONTROUTE /* bypass routing tables */
#define IP_ALLOWBROADCAST SO_BROADCAST /* can send broadcast packets */
/* mbuf flag used by ip_fastfwd */
#define M_FASTFWD_OURS M_PROTO1 /* changed dst to local */
struct ip;
struct inpcb;
struct route;
struct sockopt;
extern struct ipstat ipstat;
extern u_short ip_id; /* ip packet ctr, for ids */
extern int ip_defttl; /* default IP ttl */
extern int ipforwarding; /* ip forwarding */
extern int ip_doopts; /* process or ignore IP options */
#ifdef IPSTEALTH
extern int ipstealth; /* stealth forwarding */
#endif
extern u_char ip_protox[];
Initial get-the-easy-case-working upgrade of the multicast code to something more recent than the ancient 1.2 release contained in 4.4. This code has the following advantages as compared to previous versions (culled from the README file for the SunOS release): - True multicast delivery - Configurable rate-limiting of forwarded multicast traffic on each physical interface or tunnel, using a token-bucket limiter. - Simplistic classification of packets for prioritized dropping. - Administrative scoping of multicast address ranges. - Faster detection of hosts leaving groups. - Support for multicast traceroute (code not yet available). - Support for RSVP, the Resource Reservation Protocol. What still needs to be done: - The multicast forwarder needs testing. - The multicast routing daemon needs to be ported. - Network interface drivers need to have the `#ifdef MULTICAST' goop ripped out of them. - The IGMP code should probably be bogon-tested. Some notes about the porting process: In some cases, the Berkeley people decided to incorporate functionality from later releases of the multicast code, but then had to do things differently. As a result, if you look at Deering's patches, and then look at our code, it is not always obvious whether the patch even applies. Let the reader beware. I ran ip_mroute.c through several passes of `unifdef' to get rid of useless grot, and to permanently enable the RSVP support, which we will include as standard. Ported by: Garrett Wollman Submitted by: Steve Deering and Ajit Thyagarajan (among others)
1994-09-06 22:42:31 +00:00
extern struct socket *ip_rsvpd; /* reservation protocol daemon */
extern struct socket *ip_mrouter; /* multicast routing daemon */
2002-03-19 21:25:46 +00:00
extern int (*legal_vif_num)(int);
extern u_long (*ip_mcast_src)(int);
extern int rsvp_on;
extern struct pr_usrreqs rip_usrreqs;
1994-05-24 10:09:53 +00:00
2002-03-19 21:25:46 +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,
u_long if_hwassist_flags, int sw_csum);
2002-03-19 21:25:46 +00:00
void ip_freemoptions(struct ip_moptions *);
void ip_init(void);
extern int (*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *,
struct ip_moptions *);
int ip_output(struct mbuf *,
struct mbuf *, struct route *, int, struct ip_moptions *,
struct inpcb *);
int ipproto_register(u_char);
int ipproto_unregister(u_char);
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 *
ip_reass(struct mbuf *);
struct in_ifaddr *
ip_rtaddr(struct in_addr);
2002-03-19 21:25:46 +00:00
void ip_savecontrol(struct inpcb *, struct mbuf **, struct ip *,
struct mbuf *);
void ip_slowtimo(void);
1994-05-24 10:09:53 +00:00
struct mbuf *
ip_srcroute(struct mbuf *);
2002-03-19 21:25:46 +00:00
void ip_stripoptions(struct mbuf *, struct mbuf *);
u_int16_t ip_randomid(void);
int rip_ctloutput(struct socket *, struct sockopt *);
void rip_ctlinput(int, struct sockaddr *, void *);
void rip_init(void);
void rip_input(struct mbuf *, int);
int rip_output(struct mbuf *, struct socket *, u_long);
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);
extern struct pfil_head inet_pfil_hook; /* packet filter hooks */
void in_delayed_cksum(struct mbuf *m);
static __inline uint16_t ip_newid(void);
extern int ip_do_randomid;
static __inline uint16_t
ip_newid(void)
{
if (ip_do_randomid)
return ip_randomid();
return htons(ip_id++);
}
#endif /* _KERNEL */
1994-08-21 05:27:42 +00:00
#endif /* !_NETINET_IP_VAR_H_ */