freebsd-dev/sys/netinet/raw_ip.c

949 lines
23 KiB
C
Raw Normal View History

/*-
1994-05-24 10:09:53 +00:00
* Copyright (c) 1982, 1986, 1988, 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.
*
* @(#)raw_ip.c 8.7 (Berkeley) 5/15/95
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
#include "opt_inet6.h"
#include "opt_ipsec.h"
#include "opt_mac.h"
1994-05-24 10:09:53 +00:00
#include <sys/param.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/lock.h>
1994-05-24 10:09:53 +00:00
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/priv.h>
#include <sys/proc.h>
1994-05-24 10:09:53 +00:00
#include <sys/protosw.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
1994-05-24 10:09:53 +00:00
#include <sys/socketvar.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/systm.h>
#include <vm/uma.h>
1994-05-24 10:09:53 +00:00
#include <net/if.h>
#include <net/route.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
1994-05-24 10:09:53 +00:00
#include <netinet/ip_var.h>
#include <netinet/ip_mroute.h>
#include <netinet/ip_fw.h>
#include <netinet/ip_dummynet.h>
#ifdef FAST_IPSEC
#include <netipsec/ipsec.h>
#endif /*FAST_IPSEC*/
#ifdef IPSEC
#include <netinet6/ipsec.h>
#endif /*IPSEC*/
#include <security/mac/mac_framework.h>
struct inpcbhead ripcb;
struct inpcbinfo ripcbinfo;
1994-05-24 10:09:53 +00:00
/* control hooks for ipfw and dummynet */
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
ip_fw_ctl_t *ip_fw_ctl_ptr = NULL;
ip_dn_ctl_t *ip_dn_ctl_ptr = NULL;
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
/*
* hooks for multicast routing. They all default to NULL,
* so leave them not initialized and rely on BSS being set to 0.
*/
/* The socket used to communicate with the multicast routing daemon. */
struct socket *ip_mrouter;
/* The various mrouter and rsvp functions */
int (*ip_mrouter_set)(struct socket *, struct sockopt *);
int (*ip_mrouter_get)(struct socket *, struct sockopt *);
int (*ip_mrouter_done)(void);
int (*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *,
struct ip_moptions *);
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
int (*mrt_ioctl)(int, caddr_t);
int (*legal_vif_num)(int);
u_long (*ip_mcast_src)(int);
void (*rsvp_input_p)(struct mbuf *m, int off);
int (*ip_rsvp_vif)(struct socket *, struct sockopt *);
void (*ip_rsvp_force_done)(struct socket *);
1994-05-24 10:09:53 +00:00
/*
* Raw interface to IP protocol.
*/
/*
* Initialize raw connection block q.
1994-05-24 10:09:53 +00:00
*/
static void
rip_zone_change(void *tag)
{
uma_zone_set_max(ripcbinfo.ipi_zone, maxsockets);
}
static int
rip_inpcb_init(void *mem, int size, int flags)
{
struct inpcb *inp = mem;
INP_LOCK_INIT(inp, "inp", "rawinp");
return (0);
}
1994-05-24 10:09:53 +00:00
void
rip_init()
1994-05-24 10:09:53 +00:00
{
INP_INFO_LOCK_INIT(&ripcbinfo, "rip");
LIST_INIT(&ripcb);
ripcbinfo.listhead = &ripcb;
/*
* XXX We don't use the hash list for raw IP, but it's easier
* to allocate a one entry hash list than it is to check all
* over the place for hashbase == NULL.
*/
ripcbinfo.hashbase = hashinit(1, M_PCB, &ripcbinfo.hashmask);
Improved connection establishment performance by doing local port lookups via a hashed port list. In the new scheme, in_pcblookup() goes away and is replaced by a new routine, in_pcblookup_local() for doing the local port check. Note that this implementation is space inefficient in that the PCB struct is now too large to fit into 128 bytes. I might deal with this in the future by using the new zone allocator, but I wanted these changes to be extensively tested in their current form first. Also: 1) Fixed off-by-one errors in the port lookup loops in in_pcbbind(). 2) Got rid of some unneeded rehashing. Adding a new routine, in_pcbinshash() to do the initialial hash insertion. 3) Renamed in_pcblookuphash() to in_pcblookup_hash() for easier readability. 4) Added a new routine, in_pcbremlists() to remove the PCB from the various hash lists. 5) Added/deleted comments where appropriate. 6) Removed unnecessary splnet() locking. In general, the PCB functions should be called at splnet()...there are unfortunately a few exceptions, however. 7) Reorganized a few structs for better cache line behavior. 8) Killed my TCP_ACK_HACK kludge. It may come back in a different form in the future, however. These changes have been tested on wcarchive for more than a month. In tests done here, connection establishment overhead is reduced by more than 50 times, thus getting rid of one of the major networking scalability problems. Still to do: make tcp_fastimo/tcp_slowtimo scale well for systems with a large number of connections. tcp_fastimo is easy; tcp_slowtimo is difficult. WARNING: Anything that knows about inpcb and tcpcb structs will have to be recompiled; at the very least, this includes netstat(1).
1998-01-27 09:15:13 +00:00
ripcbinfo.porthashbase = hashinit(1, M_PCB, &ripcbinfo.porthashmask);
ripcbinfo.ipi_zone = uma_zcreate("ripcb", sizeof(struct inpcb),
NULL, NULL, rip_inpcb_init, NULL, UMA_ALIGN_PTR, UMA_ZONE_NOFREE);
uma_zone_set_max(ripcbinfo.ipi_zone, maxsockets);
EVENTHANDLER_REGISTER(maxsockets_change, rip_zone_change,
NULL, EVENTHANDLER_PRI_ANY);
1994-05-24 10:09:53 +00:00
}
1995-12-09 20:43:53 +00:00
static struct sockaddr_in ripsrc = { sizeof(ripsrc), AF_INET };
static int
raw_append(struct inpcb *last, struct ip *ip, struct mbuf *n)
{
int policyfail = 0;
INP_LOCK_ASSERT(last);
#if defined(IPSEC) || defined(FAST_IPSEC)
/* check AH/ESP integrity. */
if (ipsec4_in_reject(n, last)) {
policyfail = 1;
#ifdef IPSEC
ipsecstat.in_polvio++;
#endif /*IPSEC*/
/* do not inject data to pcb */
}
#endif /*IPSEC || FAST_IPSEC*/
#ifdef MAC
if (!policyfail && mac_check_inpcb_deliver(last, n) != 0)
policyfail = 1;
#endif
/* Check the minimum TTL for socket. */
if (last->inp_ip_minttl && last->inp_ip_minttl > ip->ip_ttl)
policyfail = 1;
if (!policyfail) {
struct mbuf *opts = NULL;
struct socket *so;
so = last->inp_socket;
if ((last->inp_flags & INP_CONTROLOPTS) ||
(so->so_options & (SO_TIMESTAMP | SO_BINTIME)))
ip_savecontrol(last, &opts, ip, n);
SOCKBUF_LOCK(&so->so_rcv);
if (sbappendaddr_locked(&so->so_rcv,
(struct sockaddr *)&ripsrc, n, opts) == 0) {
/* should notify about lost packet */
m_freem(n);
if (opts)
m_freem(opts);
SOCKBUF_UNLOCK(&so->so_rcv);
} else
sorwakeup_locked(so);
} else
m_freem(n);
return policyfail;
}
1994-05-24 10:09:53 +00:00
/*
* Setup generic address and protocol structures
* for raw_input routine, then pass them along with
* mbuf chain.
*/
void
rip_input(struct mbuf *m, int off)
1994-05-24 10:09:53 +00:00
{
struct ip *ip = mtod(m, struct ip *);
int proto = ip->ip_p;
struct inpcb *inp, *last;
1994-05-24 10:09:53 +00:00
INP_INFO_RLOCK(&ripcbinfo);
1994-05-24 10:09:53 +00:00
ripsrc.sin_addr = ip->ip_src;
last = NULL;
LIST_FOREACH(inp, &ripcb, inp_list) {
INP_LOCK(inp);
if (inp->inp_ip_p && inp->inp_ip_p != proto) {
docontinue:
INP_UNLOCK(inp);
continue;
}
#ifdef INET6
if ((inp->inp_vflag & INP_IPV4) == 0)
goto docontinue;
#endif
if (inp->inp_laddr.s_addr &&
inp->inp_laddr.s_addr != ip->ip_dst.s_addr)
goto docontinue;
if (inp->inp_faddr.s_addr &&
inp->inp_faddr.s_addr != ip->ip_src.s_addr)
goto docontinue;
if (jailed(inp->inp_socket->so_cred))
if (htonl(prison_getip(inp->inp_socket->so_cred)) !=
ip->ip_dst.s_addr)
goto docontinue;
1994-05-24 10:09:53 +00:00
if (last) {
struct mbuf *n;
n = m_copy(m, 0, (int)M_COPYALL);
if (n != NULL)
(void) raw_append(last, ip, n);
/* XXX count dropped packet */
INP_UNLOCK(last);
1994-05-24 10:09:53 +00:00
}
last = inp;
1994-05-24 10:09:53 +00:00
}
if (last != NULL) {
if (raw_append(last, ip, m) != 0)
ipstat.ips_delivered--;
INP_UNLOCK(last);
1994-05-24 10:09:53 +00:00
} else {
m_freem(m);
ipstat.ips_noproto++;
ipstat.ips_delivered--;
}
INP_INFO_RUNLOCK(&ripcbinfo);
}
1994-05-24 10:09:53 +00:00
/*
* Generate IP header and pass packet to ip_output.
* Tack on options user may have setup with control call.
*/
int
rip_output(struct mbuf *m, struct socket *so, u_long dst)
1994-05-24 10:09:53 +00:00
{
struct ip *ip;
int error;
struct inpcb *inp = sotoinpcb(so);
int flags = ((so->so_options & SO_DONTROUTE) ? IP_ROUTETOIF : 0) |
IP_ALLOWBROADCAST;
1994-05-24 10:09:53 +00:00
/*
* If the user handed us a complete IP packet, use it.
* Otherwise, allocate an mbuf for a header and fill it in.
*/
if ((inp->inp_flags & INP_HDRINCL) == 0) {
if (m->m_pkthdr.len + sizeof(struct ip) > IP_MAXPACKET) {
m_freem(m);
return(EMSGSIZE);
}
M_PREPEND(m, sizeof(struct ip), M_DONTWAIT);
if (m == NULL)
return(ENOBUFS);
INP_LOCK(inp);
1994-05-24 10:09:53 +00:00
ip = mtod(m, struct ip *);
ip->ip_tos = inp->inp_ip_tos;
if (inp->inp_flags & INP_DONTFRAG)
ip->ip_off = IP_DF;
else
ip->ip_off = 0;
ip->ip_p = inp->inp_ip_p;
1994-05-24 10:09:53 +00:00
ip->ip_len = m->m_pkthdr.len;
if (jailed(inp->inp_socket->so_cred))
ip->ip_src.s_addr =
htonl(prison_getip(inp->inp_socket->so_cred));
else
ip->ip_src = inp->inp_laddr;
1994-05-24 10:09:53 +00:00
ip->ip_dst.s_addr = dst;
ip->ip_ttl = inp->inp_ip_ttl;
1994-05-24 10:09:53 +00:00
} else {
if (m->m_pkthdr.len > IP_MAXPACKET) {
m_freem(m);
return(EMSGSIZE);
}
INP_LOCK(inp);
1994-05-24 10:09:53 +00:00
ip = mtod(m, struct ip *);
if (jailed(inp->inp_socket->so_cred)) {
if (ip->ip_src.s_addr !=
htonl(prison_getip(inp->inp_socket->so_cred))) {
INP_UNLOCK(inp);
m_freem(m);
return (EPERM);
}
}
/* don't allow both user specified and setsockopt options,
and don't allow packet length sizes that will crash */
if (((ip->ip_hl != (sizeof (*ip) >> 2))
&& inp->inp_options)
|| (ip->ip_len > m->m_pkthdr.len)
|| (ip->ip_len < (ip->ip_hl << 2))) {
INP_UNLOCK(inp);
m_freem(m);
return EINVAL;
}
1994-05-24 10:09:53 +00:00
if (ip->ip_id == 0)
ip->ip_id = ip_newid();
1994-05-24 10:09:53 +00:00
/* XXX prevent ip_output from overwriting header fields */
flags |= IP_RAWOUTPUT;
ipstat.ips_rawout++;
}
if (inp->inp_flags & INP_ONESBCAST)
flags |= IP_SENDONES;
#ifdef MAC
mac_create_mbuf_from_inpcb(inp, m);
#endif
error = ip_output(m, inp->inp_options, NULL, flags,
inp->inp_moptions, inp);
INP_UNLOCK(inp);
return error;
1994-05-24 10:09:53 +00:00
}
/*
* Raw IP socket option processing.
*
* IMPORTANT NOTE regarding access control: Traditionally, raw sockets could
* only be created by a privileged process, and as such, socket option
* operations to manage system properties on any raw socket were allowed to
* take place without explicit additional access control checks. However,
* raw sockets can now also be created in jail(), and therefore explicit
* checks are now required. Likewise, raw sockets can be used by a process
* after it gives up privilege, so some caution is required. For options
* passed down to the IP layer via ip_ctloutput(), checks are assumed to be
* performed in ip_ctloutput() and therefore no check occurs here.
* Unilaterally checking suser() here breaks normal IP socket option
* operations on raw sockets.
*
* When adding new socket options here, make sure to add access control
* checks here as necessary.
1994-05-24 10:09:53 +00:00
*/
int
rip_ctloutput(struct socket *so, struct sockopt *sopt)
1994-05-24 10:09:53 +00:00
{
struct inpcb *inp = sotoinpcb(so);
int error, optval;
1994-05-24 10:09:53 +00:00
if (sopt->sopt_level != IPPROTO_IP)
1994-05-24 10:09:53 +00:00
return (EINVAL);
error = 0;
switch (sopt->sopt_dir) {
case SOPT_GET:
switch (sopt->sopt_name) {
case IP_HDRINCL:
optval = inp->inp_flags & INP_HDRINCL;
error = sooptcopyout(sopt, &optval, sizeof optval);
break;
case IP_FW_ADD: /* ADD actually returns the body... */
case IP_FW_GET:
case IP_FW_TABLE_GETSIZE:
case IP_FW_TABLE_LIST:
case IP_FW_NAT_GET_CONFIG:
case IP_FW_NAT_GET_LOG:
/*
* XXXRW: Isn't this checked one layer down? Yes, it
* is.
*/
error = priv_check(curthread, PRIV_NETINET_IPFW);
if (error != 0)
return (error);
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
if (ip_fw_ctl_ptr != NULL)
error = ip_fw_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break;
case IP_DUMMYNET_GET:
error = priv_check(curthread, PRIV_NETINET_DUMMYNET);
if (error != 0)
return (error);
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
if (ip_dn_ctl_ptr != NULL)
error = ip_dn_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break ;
case MRT_INIT:
case MRT_DONE:
case MRT_ADD_VIF:
case MRT_DEL_VIF:
case MRT_ADD_MFC:
case MRT_DEL_MFC:
case MRT_VERSION:
case MRT_ASSERT:
case MRT_API_SUPPORT:
case MRT_API_CONFIG:
case MRT_ADD_BW_UPCALL:
case MRT_DEL_BW_UPCALL:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
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
error = ip_mrouter_get ? ip_mrouter_get(so, sopt) :
EOPNOTSUPP;
break;
1994-05-24 10:09:53 +00:00
default:
error = ip_ctloutput(so, sopt);
break;
}
break;
case SOPT_SET:
switch (sopt->sopt_name) {
case IP_HDRINCL:
error = sooptcopyin(sopt, &optval, sizeof optval,
sizeof optval);
if (error)
break;
if (optval)
inp->inp_flags |= INP_HDRINCL;
else
inp->inp_flags &= ~INP_HDRINCL;
break;
1994-05-24 10:09:53 +00:00
case IP_FW_ADD:
case IP_FW_DEL:
case IP_FW_FLUSH:
case IP_FW_ZERO:
case IP_FW_RESETLOG:
case IP_FW_TABLE_ADD:
case IP_FW_TABLE_DEL:
case IP_FW_TABLE_FLUSH:
case IP_FW_NAT_CFG:
case IP_FW_NAT_DEL:
/*
* XXXRW: Isn't this checked one layer down?
*/
error = priv_check(curthread, PRIV_NETINET_IPFW);
if (error != 0)
return (error);
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
if (ip_fw_ctl_ptr != NULL)
error = ip_fw_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break;
case IP_DUMMYNET_CONFIGURE:
case IP_DUMMYNET_DEL:
case IP_DUMMYNET_FLUSH:
error = priv_check(curthread, PRIV_NETINET_DUMMYNET);
if (error != 0)
return (error);
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
if (ip_dn_ctl_ptr != NULL)
error = ip_dn_ctl_ptr(sopt);
else
error = ENOPROTOOPT ;
break ;
case IP_RSVP_ON:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_init(so);
break;
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
case IP_RSVP_OFF:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_done();
break;
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
case IP_RSVP_VIF_ON:
case IP_RSVP_VIF_OFF:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
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
error = ip_rsvp_vif ?
ip_rsvp_vif(so, sopt) : EINVAL;
break;
case MRT_INIT:
case MRT_DONE:
case MRT_ADD_VIF:
case MRT_DEL_VIF:
case MRT_ADD_MFC:
case MRT_DEL_MFC:
case MRT_VERSION:
case MRT_ASSERT:
case MRT_API_SUPPORT:
case MRT_API_CONFIG:
case MRT_ADD_BW_UPCALL:
case MRT_DEL_BW_UPCALL:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
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
error = ip_mrouter_set ? ip_mrouter_set(so, sopt) :
EOPNOTSUPP;
break;
default:
error = ip_ctloutput(so, sopt);
break;
}
break;
1994-05-24 10:09:53 +00:00
}
return (error);
1994-05-24 10:09:53 +00:00
}
/*
* This function exists solely to receive the PRC_IFDOWN messages which
* are sent by if_down(). It looks for an ifaddr whose ifa_addr is sa,
* and calls in_ifadown() to remove all routes corresponding to that address.
* It also receives the PRC_IFUP messages from if_up() and reinstalls the
* interface routes.
*/
void
rip_ctlinput(int cmd, struct sockaddr *sa, void *vip)
{
struct in_ifaddr *ia;
struct ifnet *ifp;
int err;
int flags;
switch (cmd) {
case PRC_IFDOWN:
2001-03-16 20:00:53 +00:00
TAILQ_FOREACH(ia, &in_ifaddrhead, ia_link) {
if (ia->ia_ifa.ifa_addr == sa
&& (ia->ia_flags & IFA_ROUTE)) {
/*
* in_ifscrub kills the interface route.
*/
in_ifscrub(ia->ia_ifp, ia);
/*
* in_ifadown gets rid of all the rest of
* the routes. This is not quite the right
* thing to do, but at least if we are running
* a routing process they will come back.
*/
in_ifadown(&ia->ia_ifa, 0);
break;
}
}
break;
case PRC_IFUP:
2001-03-16 20:00:53 +00:00
TAILQ_FOREACH(ia, &in_ifaddrhead, ia_link) {
if (ia->ia_ifa.ifa_addr == sa)
break;
}
if (ia == 0 || (ia->ia_flags & IFA_ROUTE))
return;
flags = RTF_UP;
ifp = ia->ia_ifa.ifa_ifp;
if ((ifp->if_flags & IFF_LOOPBACK)
|| (ifp->if_flags & IFF_POINTOPOINT))
flags |= RTF_HOST;
err = rtinit(&ia->ia_ifa, RTM_ADD, flags);
if (err == 0)
ia->ia_flags |= IFA_ROUTE;
break;
}
}
u_long rip_sendspace = 9216;
u_long rip_recvspace = 9216;
SYSCTL_ULONG(_net_inet_raw, OID_AUTO, maxdgram, CTLFLAG_RW,
&rip_sendspace, 0, "Maximum outgoing raw IP datagram size");
SYSCTL_ULONG(_net_inet_raw, OID_AUTO, recvspace, CTLFLAG_RW,
&rip_recvspace, 0, "Maximum space for incoming raw IP datagrams");
static int
rip_attach(struct socket *so, int proto, struct thread *td)
{
struct inpcb *inp;
int error;
inp = sotoinpcb(so);
KASSERT(inp == NULL, ("rip_attach: inp != NULL"));
/*
* XXXRW: Centralize privilege decision in kern_jail.c.
*/
if (jailed(td->td_ucred) && !jail_allow_raw_sockets)
return (EPERM);
error = priv_check_cred(td->td_ucred, PRIV_NETINET_RAW,
SUSER_ALLOWJAIL);
if (error)
return error;
if (proto >= IPPROTO_MAX || proto < 0)
return EPROTONOSUPPORT;
error = soreserve(so, rip_sendspace, rip_recvspace);
if (error)
return error;
INP_INFO_WLOCK(&ripcbinfo);
error = in_pcballoc(so, &ripcbinfo);
if (error) {
INP_INFO_WUNLOCK(&ripcbinfo);
return error;
}
inp = (struct inpcb *)so->so_pcb;
INP_INFO_WUNLOCK(&ripcbinfo);
inp->inp_vflag |= INP_IPV4;
inp->inp_ip_p = proto;
inp->inp_ip_ttl = ip_defttl;
INP_UNLOCK(inp);
return 0;
}
1994-05-24 10:09:53 +00:00
static void
rip_detach(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_detach: inp == NULL"));
KASSERT(inp->inp_faddr.s_addr == INADDR_ANY,
("rip_detach: not closed"));
INP_INFO_WLOCK(&ripcbinfo);
INP_LOCK(inp);
if (so == ip_mrouter && ip_mrouter_done)
ip_mrouter_done();
if (ip_rsvp_force_done)
ip_rsvp_force_done(so);
if (so == ip_rsvpd)
ip_rsvp_done();
in_pcbdetach(inp);
in_pcbfree(inp);
INP_INFO_WUNLOCK(&ripcbinfo);
}
static void
rip_dodisconnect(struct socket *so, struct inpcb *inp)
{
INP_LOCK_ASSERT(inp);
inp->inp_faddr.s_addr = INADDR_ANY;
SOCK_LOCK(so);
so->so_state &= ~SS_ISCONNECTED;
SOCK_UNLOCK(so);
}
static void
rip_abort(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_abort: inp == NULL"));
INP_INFO_WLOCK(&ripcbinfo);
INP_LOCK(inp);
rip_dodisconnect(so, inp);
INP_UNLOCK(inp);
INP_INFO_WUNLOCK(&ripcbinfo);
}
1994-05-24 10:09:53 +00:00
static void
rip_close(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_close: inp == NULL"));
INP_INFO_WLOCK(&ripcbinfo);
INP_LOCK(inp);
rip_dodisconnect(so, inp);
INP_UNLOCK(inp);
INP_INFO_WUNLOCK(&ripcbinfo);
}
1994-05-24 10:09:53 +00:00
static int
rip_disconnect(struct socket *so)
{
struct inpcb *inp;
if ((so->so_state & SS_ISCONNECTED) == 0)
return ENOTCONN;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_disconnect: inp == NULL"));
INP_INFO_WLOCK(&ripcbinfo);
INP_LOCK(inp);
rip_dodisconnect(so, inp);
INP_UNLOCK(inp);
INP_INFO_WUNLOCK(&ripcbinfo);
return (0);
}
1994-05-24 10:09:53 +00:00
static int
rip_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
{
struct sockaddr_in *addr = (struct sockaddr_in *)nam;
struct inpcb *inp;
if (nam->sa_len != sizeof(*addr))
return EINVAL;
if (jailed(td->td_ucred)) {
if (addr->sin_addr.s_addr == INADDR_ANY)
addr->sin_addr.s_addr =
htonl(prison_getip(td->td_ucred));
if (htonl(prison_getip(td->td_ucred)) != addr->sin_addr.s_addr)
return (EADDRNOTAVAIL);
}
if (TAILQ_EMPTY(&ifnet) ||
(addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK) ||
(addr->sin_addr.s_addr &&
ifa_ifwithaddr((struct sockaddr *)addr) == 0))
return EADDRNOTAVAIL;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_bind: inp == NULL"));
INP_INFO_WLOCK(&ripcbinfo);
INP_LOCK(inp);
inp->inp_laddr = addr->sin_addr;
INP_UNLOCK(inp);
INP_INFO_WUNLOCK(&ripcbinfo);
return 0;
}
1994-05-24 10:09:53 +00:00
static int
rip_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
{
struct sockaddr_in *addr = (struct sockaddr_in *)nam;
struct inpcb *inp;
if (nam->sa_len != sizeof(*addr))
return EINVAL;
if (TAILQ_EMPTY(&ifnet))
return EADDRNOTAVAIL;
if (addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK)
return EAFNOSUPPORT;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_connect: inp == NULL"));
INP_INFO_WLOCK(&ripcbinfo);
INP_LOCK(inp);
inp->inp_faddr = addr->sin_addr;
soisconnected(so);
INP_UNLOCK(inp);
INP_INFO_WUNLOCK(&ripcbinfo);
return 0;
}
1994-05-24 10:09:53 +00:00
static int
rip_shutdown(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_shutdown: inp == NULL"));
INP_LOCK(inp);
socantsendmore(so);
INP_UNLOCK(inp);
return 0;
}
1994-05-24 10:09:53 +00:00
static int
rip_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *nam,
struct mbuf *control, struct thread *td)
{
struct inpcb *inp;
u_long dst;
1994-05-24 10:09:53 +00:00
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_send: inp == NULL"));
/*
* Note: 'dst' reads below are unlocked.
*/
if (so->so_state & SS_ISCONNECTED) {
if (nam) {
m_freem(m);
return EISCONN;
1994-05-24 10:09:53 +00:00
}
dst = inp->inp_faddr.s_addr; /* Unlocked read. */
} else {
if (nam == NULL) {
m_freem(m);
return ENOTCONN;
}
dst = ((struct sockaddr_in *)nam)->sin_addr.s_addr;
1994-05-24 10:09:53 +00:00
}
return rip_output(m, so, dst);
1994-05-24 10:09:53 +00:00
}
static int
rip_pcblist(SYSCTL_HANDLER_ARGS)
{
int error, i, n;
struct inpcb *inp, **inp_list;
inp_gen_t gencnt;
struct xinpgen xig;
/*
* The process of preparing the TCB list is too time-consuming and
* resource-intensive to repeat twice on every request.
*/
if (req->oldptr == 0) {
n = ripcbinfo.ipi_count;
req->oldidx = 2 * (sizeof xig)
+ (n + n/8) * sizeof(struct xinpcb);
return 0;
}
if (req->newptr != 0)
return EPERM;
/*
* OK, now we're committed to doing something.
*/
INP_INFO_RLOCK(&ripcbinfo);
gencnt = ripcbinfo.ipi_gencnt;
n = ripcbinfo.ipi_count;
INP_INFO_RUNLOCK(&ripcbinfo);
xig.xig_len = sizeof xig;
xig.xig_count = n;
xig.xig_gen = gencnt;
xig.xig_sogen = so_gencnt;
error = SYSCTL_OUT(req, &xig, sizeof xig);
if (error)
return error;
inp_list = malloc(n * sizeof *inp_list, M_TEMP, M_WAITOK);
if (inp_list == 0)
return ENOMEM;
INP_INFO_RLOCK(&ripcbinfo);
for (inp = LIST_FIRST(ripcbinfo.listhead), i = 0; inp && i < n;
inp = LIST_NEXT(inp, inp_list)) {
INP_LOCK(inp);
if (inp->inp_gencnt <= gencnt &&
cr_canseesocket(req->td->td_ucred, inp->inp_socket) == 0) {
/* XXX held references? */
inp_list[i++] = inp;
}
INP_UNLOCK(inp);
}
INP_INFO_RUNLOCK(&ripcbinfo);
n = i;
error = 0;
for (i = 0; i < n; i++) {
inp = inp_list[i];
INP_LOCK(inp);
if (inp->inp_gencnt <= gencnt) {
struct xinpcb xi;
bzero(&xi, sizeof(xi));
xi.xi_len = sizeof xi;
/* XXX should avoid extra copy */
bcopy(inp, &xi.xi_inp, sizeof *inp);
if (inp->inp_socket)
sotoxsocket(inp->inp_socket, &xi.xi_socket);
INP_UNLOCK(inp);
error = SYSCTL_OUT(req, &xi, sizeof xi);
} else
INP_UNLOCK(inp);
}
if (!error) {
/*
* Give the user an updated idea of our state.
* If the generation differs from what we told
* her before, she knows that something happened
* while we were processing this request, and it
* might be necessary to retry.
*/
INP_INFO_RLOCK(&ripcbinfo);
xig.xig_gen = ripcbinfo.ipi_gencnt;
xig.xig_sogen = so_gencnt;
xig.xig_count = ripcbinfo.ipi_count;
INP_INFO_RUNLOCK(&ripcbinfo);
error = SYSCTL_OUT(req, &xig, sizeof xig);
}
free(inp_list, M_TEMP);
return error;
}
/*
* This is the wrapper function for in_setsockaddr. We just pass down
* the pcbinfo for in_setpeeraddr to lock.
*/
static int
rip_sockaddr(struct socket *so, struct sockaddr **nam)
{
return (in_setsockaddr(so, nam, &ripcbinfo));
}
/*
* This is the wrapper function for in_setpeeraddr. We just pass down
* the pcbinfo for in_setpeeraddr to lock.
*/
static int
rip_peeraddr(struct socket *so, struct sockaddr **nam)
{
return (in_setpeeraddr(so, nam, &ripcbinfo));
}
SYSCTL_PROC(_net_inet_raw, OID_AUTO/*XXX*/, pcblist, CTLFLAG_RD, 0, 0,
rip_pcblist, "S,xinpcb", "List of active raw IP sockets");
struct pr_usrreqs rip_usrreqs = {
.pru_abort = rip_abort,
.pru_attach = rip_attach,
.pru_bind = rip_bind,
.pru_connect = rip_connect,
.pru_control = in_control,
.pru_detach = rip_detach,
.pru_disconnect = rip_disconnect,
.pru_peeraddr = rip_peeraddr,
.pru_send = rip_send,
.pru_shutdown = rip_shutdown,
.pru_sockaddr = rip_sockaddr,
.pru_sosetlabel = in_pcbsosetlabel,
.pru_close = rip_close,
};