freebsd-dev/sys/netinet/in_proto.c

348 lines
9.3 KiB
C
Raw Normal View History

/*-
* 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.
* 3. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)in_proto.c 8.2 (Berkeley) 2/9/95
*/
1994-05-24 10:09:53 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_mrouting.h"
#include "opt_ipsec.h"
#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_sctp.h"
#include "opt_mpath.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/socket.h>
#include <sys/domain.h>
Conditionally compile out V_ globals while instantiating the appropriate container structures, depending on VIMAGE_GLOBALS compile time option. Make VIMAGE_GLOBALS a new compile-time option, which by default will not be defined, resulting in instatiations of global variables selected for V_irtualization (enclosed in #ifdef VIMAGE_GLOBALS blocks) to be effectively compiled out. Instantiate new global container structures to hold V_irtualized variables: vnet_net_0, vnet_inet_0, vnet_inet6_0, vnet_ipsec_0, vnet_netgraph_0, and vnet_gif_0. Update the VSYM() macro so that depending on VIMAGE_GLOBALS the V_ macros resolve either to the original globals, or to fields inside container structures, i.e. effectively #ifdef VIMAGE_GLOBALS #define V_rt_tables rt_tables #else #define V_rt_tables vnet_net_0._rt_tables #endif Update SYSCTL_V_*() macros to operate either on globals or on fields inside container structs. Extend the internal kldsym() lookups with the ability to resolve selected fields inside the virtualization container structs. This applies only to the fields which are explicitly registered for kldsym() visibility via VNET_MOD_DECLARE() and vnet_mod_register(), currently this is done only in sys/net/if.c. Fix a few broken instances of MODULE_GLOBAL() macro use in SCTP code, and modify the MODULE_GLOBAL() macro to resolve to V_ macros, which in turn result in proper code being generated depending on VIMAGE_GLOBALS. De-virtualize local static variables in sys/contrib/pf/net/pf_subr.c which were prematurely V_irtualized by automated V_ prepending scripts during earlier merging steps. PF virtualization will be done separately, most probably after next PF import. Convert a few variable initializations at instantiation to initialization in init functions, most notably in ipfw. Also convert TUNABLE_INT() initializers for V_ variables to TUNABLE_FETCH_INT() in initializer functions. Discussed at: devsummit Strassburg Reviewed by: bz, julian Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-12-10 23:12:39 +00:00
#include <sys/proc.h>
1995-11-20 12:28:21 +00:00
#include <sys/protosw.h>
#include <sys/queue.h>
#include <sys/sysctl.h>
1994-05-24 10:09:53 +00:00
/*
* While this file provides the domain and protocol switch tables for IPv4, it
* also provides the sysctl node declarations for net.inet.* often shared with
* IPv6 for common features or by upper layer protocols. In case of no IPv4
* support compile out everything but these sysctl nodes.
*/
#ifdef INET
#include <net/if.h>
#include <net/if_var.h>
#include <net/route.h>
#ifdef RADIX_MPATH
#include <net/radix_mpath.h>
#endif
#include <net/vnet.h>
#endif /* INET */
1994-05-24 10:09:53 +00:00
#if defined(INET) || defined(INET6)
#include <netinet/in.h>
#endif
#ifdef INET
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_icmp.h>
#include <netinet/igmp_var.h>
#include <netinet/tcp.h>
#include <netinet/tcp_timer.h>
#include <netinet/tcp_var.h>
#include <netinet/udp.h>
#include <netinet/udp_var.h>
#include <netinet/ip_encap.h>
/*
* TCP/IP protocol family: IP, ICMP, UDP, TCP.
*/
1994-05-24 10:09:53 +00:00
static struct pr_usrreqs nousrreqs;
#ifdef SCTP
#include <netinet/in_pcb.h>
#include <netinet/sctp_pcb.h>
#include <netinet/sctp.h>
#include <netinet/sctp_var.h>
#endif /* SCTP */
FEATURE(inet, "Internet Protocol version 4");
extern struct domain inetdomain;
/* Spacer for loadable protocols. */
#define IPPROTOSPACER \
{ \
.pr_domain = &inetdomain, \
.pr_protocol = PROTO_SPACER, \
.pr_usrreqs = &nousrreqs \
}
Initial get-the-easy-case-working upgrade of the multicast code to something more recent than the ancient 1.2 release contained in 4.4. This code has the following advantages as compared to previous versions (culled from the README file for the SunOS release): - True multicast delivery - Configurable rate-limiting of forwarded multicast traffic on each physical interface or tunnel, using a token-bucket limiter. - Simplistic classification of packets for prioritized dropping. - Administrative scoping of multicast address ranges. - Faster detection of hosts leaving groups. - Support for multicast traceroute (code not yet available). - Support for RSVP, the Resource Reservation Protocol. What still needs to be done: - The multicast forwarder needs testing. - The multicast routing daemon needs to be ported. - Network interface drivers need to have the `#ifdef MULTICAST' goop ripped out of them. - The IGMP code should probably be bogon-tested. Some notes about the porting process: In some cases, the Berkeley people decided to incorporate functionality from later releases of the multicast code, but then had to do things differently. As a result, if you look at Deering's patches, and then look at our code, it is not always obvious whether the patch even applies. Let the reader beware. I ran ip_mroute.c through several passes of `unifdef' to get rid of useless grot, and to permanently enable the RSVP support, which we will include as standard. Ported by: Garrett Wollman Submitted by: Steve Deering and Ajit Thyagarajan (among others)
1994-09-06 22:42:31 +00:00
struct protosw inetsw[] = {
{
.pr_type = 0,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_IP,
.pr_init = ip_init,
.pr_slowtimo = ip_slowtimo,
.pr_drain = ip_drain,
.pr_usrreqs = &nousrreqs
},
{
.pr_type = SOCK_DGRAM,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_UDP,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = udp_input,
.pr_ctlinput = udp_ctlinput,
.pr_ctloutput = udp_ctloutput,
.pr_init = udp_init,
.pr_usrreqs = &udp_usrreqs
},
{
.pr_type = SOCK_STREAM,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_TCP,
.pr_flags = PR_CONNREQUIRED|PR_IMPLOPCL|PR_WANTRCVD,
.pr_input = tcp_input,
.pr_ctlinput = tcp_ctlinput,
.pr_ctloutput = tcp_ctloutput,
.pr_init = tcp_init,
.pr_slowtimo = tcp_slowtimo,
.pr_drain = tcp_drain,
.pr_usrreqs = &tcp_usrreqs
},
#ifdef SCTP
{
.pr_type = SOCK_SEQPACKET,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_SCTP,
Remove IPsec related PCB code from SCTP. The inpcb structure has inp_sp pointer that is initialized by ipsec_init_pcbpolicy() function. This pointer keeps strorage for IPsec security policies associated with a specific socket. An application can use IP_IPSEC_POLICY and IPV6_IPSEC_POLICY socket options to configure these security policies. Then ip[6]_output() uses inpcb pointer to specify that an outgoing packet is associated with some socket. And IPSEC_OUTPUT() method can use a security policy stored in the inp_sp. For inbound packet the protocol-specific input routine uses IPSEC_CHECK_POLICY() method to check that a packet conforms to inbound security policy configured in the inpcb. SCTP protocol doesn't specify inpcb for ip[6]_output() when it sends packets. Thus IPSEC_OUTPUT() method does not consider such packets as associated with some socket and can not apply security policies from inpcb, even if they are configured. Since IPSEC_CHECK_POLICY() method is called from protocol-specific input routine, it can specify inpcb pointer and associated with socket inbound policy will be checked. But there are two problems: 1. Such check is asymmetric, becasue we can not apply security policy from inpcb for outgoing packet. 2. IPSEC_CHECK_POLICY() expects that caller holds INPCB lock and access to inp_sp is protected. But for SCTP this is not correct, becasue SCTP uses own locks to protect inpcb. To fix these problems remove IPsec related PCB code from SCTP. This imply that IP_IPSEC_POLICY and IPV6_IPSEC_POLICY socket options will be not applicable to SCTP sockets. To be able correctly check inbound security policies for SCTP, mark its protocol header with the PR_LASTHDR flag. Reported by: tuexen Reviewed by: tuexen Differential Revision: https://reviews.freebsd.org/D9538
2017-02-13 11:37:52 +00:00
.pr_flags = PR_WANTRCVD|PR_LASTHDR,
.pr_input = sctp_input,
.pr_ctlinput = sctp_ctlinput,
.pr_ctloutput = sctp_ctloutput,
.pr_init = sctp_init,
.pr_drain = sctp_drain,
.pr_usrreqs = &sctp_usrreqs
},
{
.pr_type = SOCK_STREAM,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_SCTP,
Remove IPsec related PCB code from SCTP. The inpcb structure has inp_sp pointer that is initialized by ipsec_init_pcbpolicy() function. This pointer keeps strorage for IPsec security policies associated with a specific socket. An application can use IP_IPSEC_POLICY and IPV6_IPSEC_POLICY socket options to configure these security policies. Then ip[6]_output() uses inpcb pointer to specify that an outgoing packet is associated with some socket. And IPSEC_OUTPUT() method can use a security policy stored in the inp_sp. For inbound packet the protocol-specific input routine uses IPSEC_CHECK_POLICY() method to check that a packet conforms to inbound security policy configured in the inpcb. SCTP protocol doesn't specify inpcb for ip[6]_output() when it sends packets. Thus IPSEC_OUTPUT() method does not consider such packets as associated with some socket and can not apply security policies from inpcb, even if they are configured. Since IPSEC_CHECK_POLICY() method is called from protocol-specific input routine, it can specify inpcb pointer and associated with socket inbound policy will be checked. But there are two problems: 1. Such check is asymmetric, becasue we can not apply security policy from inpcb for outgoing packet. 2. IPSEC_CHECK_POLICY() expects that caller holds INPCB lock and access to inp_sp is protected. But for SCTP this is not correct, becasue SCTP uses own locks to protect inpcb. To fix these problems remove IPsec related PCB code from SCTP. This imply that IP_IPSEC_POLICY and IPV6_IPSEC_POLICY socket options will be not applicable to SCTP sockets. To be able correctly check inbound security policies for SCTP, mark its protocol header with the PR_LASTHDR flag. Reported by: tuexen Reviewed by: tuexen Differential Revision: https://reviews.freebsd.org/D9538
2017-02-13 11:37:52 +00:00
.pr_flags = PR_CONNREQUIRED|PR_WANTRCVD|PR_LASTHDR,
.pr_input = sctp_input,
.pr_ctlinput = sctp_ctlinput,
.pr_ctloutput = sctp_ctloutput,
.pr_drain = sctp_drain,
.pr_usrreqs = &sctp_usrreqs
},
#endif /* SCTP */
{
.pr_type = SOCK_DGRAM,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_UDPLITE,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = udp_input,
.pr_ctlinput = udplite_ctlinput,
.pr_ctloutput = udp_ctloutput,
.pr_init = udplite_init,
.pr_usrreqs = &udp_usrreqs
},
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_RAW,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = rip_input,
.pr_ctlinput = rip_ctlinput,
.pr_ctloutput = rip_ctloutput,
.pr_usrreqs = &rip_usrreqs
},
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_ICMP,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = icmp_input,
.pr_ctloutput = rip_ctloutput,
.pr_usrreqs = &rip_usrreqs
},
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_IGMP,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = igmp_input,
.pr_ctloutput = rip_ctloutput,
.pr_fasttimo = igmp_fasttimo,
.pr_slowtimo = igmp_slowtimo,
.pr_usrreqs = &rip_usrreqs
},
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_RSVP,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = rsvp_input,
.pr_ctloutput = rip_ctloutput,
.pr_usrreqs = &rip_usrreqs
},
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_IPV4,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = encap4_input,
.pr_ctloutput = rip_ctloutput,
.pr_init = encap_init,
.pr_usrreqs = &rip_usrreqs
},
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_MOBILE,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = encap4_input,
.pr_ctloutput = rip_ctloutput,
.pr_init = encap_init,
.pr_usrreqs = &rip_usrreqs
},
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_ETHERIP,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = encap4_input,
.pr_ctloutput = rip_ctloutput,
.pr_init = encap_init,
.pr_usrreqs = &rip_usrreqs
},
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_GRE,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = encap4_input,
.pr_ctloutput = rip_ctloutput,
.pr_init = encap_init,
.pr_usrreqs = &rip_usrreqs
},
# ifdef INET6
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_IPV6,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = encap4_input,
.pr_ctloutput = rip_ctloutput,
.pr_init = encap_init,
.pr_usrreqs = &rip_usrreqs
},
#endif
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = IPPROTO_PIM,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = encap4_input,
.pr_ctloutput = rip_ctloutput,
.pr_usrreqs = &rip_usrreqs
},
/* Spacer n-times for loadable protocols. */
IPPROTOSPACER,
IPPROTOSPACER,
IPPROTOSPACER,
IPPROTOSPACER,
IPPROTOSPACER,
IPPROTOSPACER,
IPPROTOSPACER,
IPPROTOSPACER,
/* raw wildcard */
{
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = rip_input,
.pr_ctloutput = rip_ctloutput,
.pr_init = rip_init,
.pr_usrreqs = &rip_usrreqs
1994-05-24 10:09:53 +00:00
},
};
2002-03-19 21:25:46 +00:00
extern int in_inithead(void **, int);
extern int in_detachhead(void **, int);
struct domain inetdomain = {
.dom_family = AF_INET,
.dom_name = "internet",
.dom_protosw = inetsw,
.dom_protoswNPROTOSW = &inetsw[nitems(inetsw)],
#ifdef RADIX_MPATH
.dom_rtattach = rn4_mpath_inithead,
#else
.dom_rtattach = in_inithead,
#endif
#ifdef VIMAGE
.dom_rtdetach = in_detachhead,
#endif
.dom_ifattach = in_domifattach,
.dom_ifdetach = in_domifdetach
};
1994-05-24 10:09:53 +00:00
VNET_DOMAIN_SET(inet);
#endif /* INET */
SYSCTL_NODE(_net, PF_INET, inet, CTLFLAG_RW, 0,
"Internet Family");
SYSCTL_NODE(_net_inet, IPPROTO_IP, ip, CTLFLAG_RW, 0, "IP");
SYSCTL_NODE(_net_inet, IPPROTO_ICMP, icmp, CTLFLAG_RW, 0, "ICMP");
SYSCTL_NODE(_net_inet, IPPROTO_UDP, udp, CTLFLAG_RW, 0, "UDP");
SYSCTL_NODE(_net_inet, IPPROTO_TCP, tcp, CTLFLAG_RW, 0, "TCP");
#ifdef SCTP
SYSCTL_NODE(_net_inet, IPPROTO_SCTP, sctp, CTLFLAG_RW, 0, "SCTP");
#endif
SYSCTL_NODE(_net_inet, IPPROTO_IGMP, igmp, CTLFLAG_RW, 0, "IGMP");
Merge projects/ipsec into head/. Small summary ------------- o Almost all IPsec releated code was moved into sys/netipsec. o New kernel modules added: ipsec.ko and tcpmd5.ko. New kernel option IPSEC_SUPPORT added. It enables support for loading and unloading of ipsec.ko and tcpmd5.ko kernel modules. o IPSEC_NAT_T option was removed. Now NAT-T support is enabled by default. The UDP_ENCAP_ESPINUDP_NON_IKE encapsulation type support was removed. Added TCP/UDP checksum handling for inbound packets that were decapsulated by transport mode SAs. setkey(8) modified to show run-time NAT-T configuration of SA. o New network pseudo interface if_ipsec(4) added. For now it is build as part of ipsec.ko module (or with IPSEC kernel). It implements IPsec virtual tunnels to create route-based VPNs. o The network stack now invokes IPsec functions using special methods. The only one header file <netipsec/ipsec_support.h> should be included to declare all the needed things to work with IPsec. o All IPsec protocols handlers (ESP/AH/IPCOMP protosw) were removed. Now these protocols are handled directly via IPsec methods. o TCP_SIGNATURE support was reworked to be more close to RFC. o PF_KEY SADB was reworked: - now all security associations stored in the single SPI namespace, and all SAs MUST have unique SPI. - several hash tables added to speed up lookups in SADB. - SADB now uses rmlock to protect access, and concurrent threads can do SA lookups in the same time. - many PF_KEY message handlers were reworked to reflect changes in SADB. - SADB_UPDATE message was extended to support new PF_KEY headers: SADB_X_EXT_NEW_ADDRESS_SRC and SADB_X_EXT_NEW_ADDRESS_DST. They can be used by IKE daemon to change SA addresses. o ipsecrequest and secpolicy structures were cardinally changed to avoid locking protection for ipsecrequest. Now we support only limited number (4) of bundled SAs, but they are supported for both INET and INET6. o INPCB security policy cache was introduced. Each PCB now caches used security policies to avoid SP lookup for each packet. o For inbound security policies added the mode, when the kernel does check for full history of applied IPsec transforms. o References counting rules for security policies and security associations were changed. The proper SA locking added into xform code. o xform code was also changed. Now it is possible to unregister xforms. tdb_xxx structures were changed and renamed to reflect changes in SADB/SPDB, and changed rules for locking and refcounting. Reviewed by: gnn, wblock Obtained from: Yandex LLC Relnotes: yes Sponsored by: Yandex LLC Differential Revision: https://reviews.freebsd.org/D9352
2017-02-06 08:49:57 +00:00
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
/* XXX no protocol # to use, pick something "reserved" */
SYSCTL_NODE(_net_inet, 253, ipsec, CTLFLAG_RW, 0, "IPSEC");
SYSCTL_NODE(_net_inet, IPPROTO_AH, ah, CTLFLAG_RW, 0, "AH");
SYSCTL_NODE(_net_inet, IPPROTO_ESP, esp, CTLFLAG_RW, 0, "ESP");
SYSCTL_NODE(_net_inet, IPPROTO_IPCOMP, ipcomp, CTLFLAG_RW, 0, "IPCOMP");
SYSCTL_NODE(_net_inet, IPPROTO_IPIP, ipip, CTLFLAG_RW, 0, "IPIP");
#endif /* IPSEC */
SYSCTL_NODE(_net_inet, IPPROTO_RAW, raw, CTLFLAG_RW, 0, "RAW");
SYSCTL_NODE(_net_inet, OID_AUTO, accf, CTLFLAG_RW, 0,
"Accept filters");