freebsd-nq/sys/netinet/ip_output.c

1419 lines
35 KiB
C
Raw Normal View History

/*-
1994-05-24 10:09:53 +00:00
* Copyright (c) 1982, 1986, 1988, 1990, 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_output.c 8.3 (Berkeley) 1/21/94
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_inet.h"
#include "opt_ipsec.h"
#include "opt_mbuf_stress_test.h"
#include "opt_mpath.h"
#include "opt_route.h"
#include "opt_sctp.h"
#include "opt_rss.h"
1994-05-24 10:09:53 +00:00
#include <sys/param.h>
#include <sys/systm.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/rmlock.h>
#include <sys/sdt.h>
1994-05-24 10:09:53 +00:00
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/ucred.h>
1994-05-24 10:09:53 +00:00
#include <net/if.h>
#include <net/if_var.h>
#include <net/if_llatbl.h>
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
#include <net/netisr.h>
#include <net/pfil.h>
1994-05-24 10:09:53 +00:00
#include <net/route.h>
#include <net/flowtable.h>
#ifdef RADIX_MPATH
#include <net/radix_mpath.h>
#endif
#include <net/rss_config.h>
#include <net/vnet.h>
1994-05-24 10:09:53 +00:00
#include <netinet/in.h>
#include <netinet/in_kdtrace.h>
1994-05-24 10:09:53 +00:00
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/in_pcb.h>
#include <netinet/in_rss.h>
1994-05-24 10:09:53 +00:00
#include <netinet/in_var.h>
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>
#ifdef SCTP
#include <netinet/sctp.h>
#include <netinet/sctp_crc32.h>
#endif
1994-05-24 10:09:53 +00:00
#ifdef IPSEC
#include <netinet/ip_ipsec.h>
#include <netipsec/ipsec.h>
#endif /* IPSEC*/
#include <machine/in_cksum.h>
#include <security/mac/mac_framework.h>
#ifdef MBUF_STRESS_TEST
static int mbuf_frag_size = 0;
SYSCTL_INT(_net_inet_ip, OID_AUTO, mbuf_frag_size, CTLFLAG_RW,
&mbuf_frag_size, 0, "Fragment outgoing mbufs to this size");
#endif
static void ip_mloopback(struct ifnet *, const struct mbuf *, int);
1997-02-10 11:45:37 +00:00
extern int in_mcast_loop;
extern struct protosw inetsw[];
static inline int
ip_output_pfil(struct mbuf **mp, struct ifnet *ifp, struct inpcb *inp,
struct sockaddr_in *dst, int *fibnum, int *error)
{
struct m_tag *fwd_tag = NULL;
struct mbuf *m;
struct in_addr odst;
struct ip *ip;
m = *mp;
ip = mtod(m, struct ip *);
/* Run through list of hooks for output packets. */
odst.s_addr = ip->ip_dst.s_addr;
*error = pfil_run_hooks(&V_inet_pfil_hook, mp, ifp, PFIL_OUT, inp);
m = *mp;
if ((*error) != 0 || m == NULL)
return 1; /* Finished */
ip = mtod(m, struct ip *);
/* See if destination IP address was changed by packet filter. */
if (odst.s_addr != ip->ip_dst.s_addr) {
m->m_flags |= M_SKIP_FIREWALL;
/* If destination is now ourself drop to ip_input(). */
if (in_localip(ip->ip_dst)) {
m->m_flags |= M_FASTFWD_OURS;
if (m->m_pkthdr.rcvif == NULL)
m->m_pkthdr.rcvif = V_loif;
if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
m->m_pkthdr.csum_flags |=
CSUM_DATA_VALID | CSUM_PSEUDO_HDR;
m->m_pkthdr.csum_data = 0xffff;
}
m->m_pkthdr.csum_flags |=
CSUM_IP_CHECKED | CSUM_IP_VALID;
#ifdef SCTP
if (m->m_pkthdr.csum_flags & CSUM_SCTP)
m->m_pkthdr.csum_flags |= CSUM_SCTP_VALID;
#endif
*error = netisr_queue(NETISR_IP, m);
return 1; /* Finished */
}
bzero(dst, sizeof(*dst));
dst->sin_family = AF_INET;
dst->sin_len = sizeof(*dst);
dst->sin_addr = ip->ip_dst;
return -1; /* Reloop */
}
/* See if fib was changed by packet filter. */
if ((*fibnum) != M_GETFIB(m)) {
m->m_flags |= M_SKIP_FIREWALL;
*fibnum = M_GETFIB(m);
return -1; /* Reloop for FIB change */
}
/* See if local, if yes, send it to netisr with IP_FASTFWD_OURS. */
if (m->m_flags & M_FASTFWD_OURS) {
if (m->m_pkthdr.rcvif == NULL)
m->m_pkthdr.rcvif = V_loif;
if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
m->m_pkthdr.csum_flags |=
CSUM_DATA_VALID | CSUM_PSEUDO_HDR;
m->m_pkthdr.csum_data = 0xffff;
}
#ifdef SCTP
if (m->m_pkthdr.csum_flags & CSUM_SCTP)
m->m_pkthdr.csum_flags |= CSUM_SCTP_VALID;
#endif
m->m_pkthdr.csum_flags |=
CSUM_IP_CHECKED | CSUM_IP_VALID;
*error = netisr_queue(NETISR_IP, m);
return 1; /* Finished */
}
/* Or forward to some other address? */
if ((m->m_flags & M_IP_NEXTHOP) &&
((fwd_tag = m_tag_find(m, PACKET_TAG_IPFORWARD, NULL)) != NULL)) {
bcopy((fwd_tag+1), dst, sizeof(struct sockaddr_in));
m->m_flags |= M_SKIP_FIREWALL;
m->m_flags &= ~M_IP_NEXTHOP;
m_tag_delete(m, fwd_tag);
return -1; /* Reloop for CHANGE of dst */
}
return 0;
}
1994-05-24 10:09:53 +00:00
/*
* IP output. The packet in mbuf chain m contains a skeletal IP
* header (with len, off, ttl, proto, tos, src, dst).
* The mbuf chain containing the packet will be freed.
* The mbuf opt, if present, will not be freed.
* If route ro is present and has ro_rt initialized, route lookup would be
* skipped and ro->ro_rt would be used. If ro is present but ro->ro_rt is NULL,
* then result of route lookup is stored in ro->ro_rt.
*
* In the IP forwarding case, the packet will arrive with options already
* inserted, so must have a NULL opt pointer.
1994-05-24 10:09:53 +00:00
*/
int
ip_output(struct mbuf *m, struct mbuf *opt, struct route *ro, int flags,
struct ip_moptions *imo, struct inpcb *inp)
1994-05-24 10:09:53 +00:00
{
struct rm_priotracker in_ifa_tracker;
struct ip *ip;
struct ifnet *ifp = NULL; /* keep compiler happy */
struct mbuf *m0;
int hlen = sizeof (struct ip);
int mtu;
int error = 0;
struct sockaddr_in *dst;
const struct sockaddr_in *gw;
struct in_ifaddr *ia;
int isbroadcast;
uint16_t ip_len, ip_off;
struct route iproute;
struct rtentry *rte; /* cache for ro->ro_rt */
uint32_t fibnum;
int have_ia_ref;
#ifdef IPSEC
int no_route_but_check_spd = 0;
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
#endif
M_ASSERTPKTHDR(m);
if (inp != NULL) {
INP_LOCK_ASSERT(inp);
M_SETFIB(m, inp->inp_inc.inc_fibnum);
if ((flags & IP_NODEFAULTFLOWID) == 0) {
m->m_pkthdr.flowid = inp->inp_flowid;
M_HASHTYPE_SET(m, inp->inp_flowtype);
}
}
if (ro == NULL) {
ro = &iproute;
bzero(ro, sizeof (*ro));
} else
ro->ro_flags |= RT_LLE_CACHE;
#ifdef FLOWTABLE
if (ro->ro_rt == NULL)
(void )flowtable_lookup(AF_INET, m, ro);
#endif
1994-05-24 10:09:53 +00:00
if (opt) {
int len = 0;
1994-05-24 10:09:53 +00:00
m = ip_insertoptions(m, opt, &len);
if (len != 0)
hlen = len; /* ip->ip_hl is updated above */
1994-05-24 10:09:53 +00:00
}
ip = mtod(m, struct ip *);
ip_len = ntohs(ip->ip_len);
ip_off = ntohs(ip->ip_off);
1994-05-24 10:09:53 +00:00
if ((flags & (IP_FORWARDING|IP_RAWOUTPUT)) == 0) {
ip->ip_v = IPVERSION;
ip->ip_hl = hlen >> 2;
ip_fillid(ip);
IPSTAT_INC(ips_localout);
1994-05-24 10:09:53 +00:00
} else {
/* Header already set, fetch hlen from there */
hlen = ip->ip_hl << 2;
1994-05-24 10:09:53 +00:00
}
/*
* dst/gw handling:
*
* dst can be rewritten but always points to &ro->ro_dst.
* gw is readonly but can point either to dst OR rt_gateway,
* therefore we need restore gw if we're redoing lookup.
*/
gw = dst = (struct sockaddr_in *)&ro->ro_dst;
fibnum = (inp != NULL) ? inp->inp_inc.inc_fibnum : M_GETFIB(m);
rte = ro->ro_rt;
if (rte == NULL) {
bzero(dst, sizeof(*dst));
1994-05-24 10:09:53 +00:00
dst->sin_family = AF_INET;
dst->sin_len = sizeof(*dst);
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
dst->sin_addr = ip->ip_dst;
1994-05-24 10:09:53 +00:00
}
again:
/*
* Validate route against routing table additions;
* a better/more specific route might have been added.
*/
if (inp)
RT_VALIDATE(ro, &inp->inp_rt_cookie, fibnum);
/*
* If there is a cached route,
* check that it is to the same destination
* and is still up. If not, free it and try again.
* The address family should also be checked in case of sharing the
* cache with IPv6.
* Also check whether routing cache needs invalidation.
*/
rte = ro->ro_rt;
if (rte && ((rte->rt_flags & RTF_UP) == 0 ||
rte->rt_ifp == NULL ||
!RT_LINK_IS_UP(rte->rt_ifp) ||
dst->sin_family != AF_INET ||
dst->sin_addr.s_addr != ip->ip_dst.s_addr)) {
RTFREE(rte);
rte = ro->ro_rt = (struct rtentry *)NULL;
if (ro->ro_lle)
LLE_FREE(ro->ro_lle); /* zeros ro_lle */
ro->ro_lle = (struct llentry *)NULL;
}
ia = NULL;
have_ia_ref = 0;
1994-05-24 10:09:53 +00:00
/*
* If routing to interface only, short circuit routing lookup.
* The use of an all-ones broadcast address implies this; an
* interface is specified by the broadcast address of an interface,
* or the destination address of a ptp interface.
1994-05-24 10:09:53 +00:00
*/
if (flags & IP_SENDONES) {
if ((ia = ifatoia(ifa_ifwithbroadaddr(sintosa(dst),
M_GETFIB(m)))) == NULL &&
(ia = ifatoia(ifa_ifwithdstaddr(sintosa(dst),
M_GETFIB(m)))) == NULL) {
IPSTAT_INC(ips_noroute);
1994-05-24 10:09:53 +00:00
error = ENETUNREACH;
goto bad;
}
have_ia_ref = 1;
ip->ip_dst.s_addr = INADDR_BROADCAST;
dst->sin_addr = ip->ip_dst;
1994-05-24 10:09:53 +00:00
ifp = ia->ia_ifp;
ip->ip_ttl = 1;
isbroadcast = 1;
} else if (flags & IP_ROUTETOIF) {
if ((ia = ifatoia(ifa_ifwithdstaddr(sintosa(dst),
M_GETFIB(m)))) == NULL &&
(ia = ifatoia(ifa_ifwithnet(sintosa(dst), 0,
M_GETFIB(m)))) == NULL) {
IPSTAT_INC(ips_noroute);
error = ENETUNREACH;
goto bad;
}
have_ia_ref = 1;
ifp = ia->ia_ifp;
ip->ip_ttl = 1;
isbroadcast = in_ifaddr_broadcast(dst->sin_addr, ia);
} else if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) &&
imo != NULL && imo->imo_multicast_ifp != NULL) {
/*
* Bypass the normal routing lookup for multicast
* packets if the interface is specified.
*/
ifp = imo->imo_multicast_ifp;
IFP_TO_IA(ifp, ia, &in_ifa_tracker);
if (ia)
have_ia_ref = 1;
isbroadcast = 0; /* fool gcc */
1994-05-24 10:09:53 +00:00
} else {
/*
* We want to do any cloning requested by the link layer,
* as this is probably required in all cases for correct
* operation (as it is for ARP).
*/
if (rte == NULL) {
#ifdef RADIX_MPATH
Add code to allow the system to handle multiple routing tables. This particular implementation is designed to be fully backwards compatible and to be MFC-able to 7.x (and 6.x) Currently the only protocol that can make use of the multiple tables is IPv4 Similar functionality exists in OpenBSD and Linux. From my notes: ----- One thing where FreeBSD has been falling behind, and which by chance I have some time to work on is "policy based routing", which allows different packet streams to be routed by more than just the destination address. Constraints: ------------ I want to make some form of this available in the 6.x tree (and by extension 7.x) , but FreeBSD in general needs it so I might as well do it in -current and back port the portions I need. One of the ways that this can be done is to have the ability to instantiate multiple kernel routing tables (which I will now refer to as "Forwarding Information Bases" or "FIBs" for political correctness reasons). Which FIB a particular packet uses to make the next hop decision can be decided by a number of mechanisms. The policies these mechanisms implement are the "Policies" referred to in "Policy based routing". One of the constraints I have if I try to back port this work to 6.x is that it must be implemented as a EXTENSION to the existing ABIs in 6.x so that third party applications do not need to be recompiled in timespan of the branch. This first version will not have some of the bells and whistles that will come with later versions. It will, for example, be limited to 16 tables in the first commit. Implementation method, Compatible version. (part 1) ------------------------------- For this reason I have implemented a "sufficient subset" of a multiple routing table solution in Perforce, and back-ported it to 6.x. (also in Perforce though not always caught up with what I have done in -current/P4). The subset allows a number of FIBs to be defined at compile time (8 is sufficient for my purposes in 6.x) and implements the changes needed to allow IPV4 to use them. I have not done the changes for ipv6 simply because I do not need it, and I do not have enough knowledge of ipv6 (e.g. neighbor discovery) needed to do it. Other protocol families are left untouched and should there be users with proprietary protocol families, they should continue to work and be oblivious to the existence of the extra FIBs. To understand how this is done, one must know that the current FIB code starts everything off with a single dimensional array of pointers to FIB head structures (One per protocol family), each of which in turn points to the trie of routes available to that family. The basic change in the ABI compatible version of the change is to extent that array to be a 2 dimensional array, so that instead of protocol family X looking at rt_tables[X] for the table it needs, it looks at rt_tables[Y][X] when for all protocol families except ipv4 Y is always 0. Code that is unaware of the change always just sees the first row of the table, which of course looks just like the one dimensional array that existed before. The entry points rtrequest(), rtalloc(), rtalloc1(), rtalloc_ign() are all maintained, but refer only to the first row of the array, so that existing callers in proprietary protocols can continue to do the "right thing". Some new entry points are added, for the exclusive use of ipv4 code called in_rtrequest(), in_rtalloc(), in_rtalloc1() and in_rtalloc_ign(), which have an extra argument which refers the code to the correct row. In addition, there are some new entry points (currently called rtalloc_fib() and friends) that check the Address family being looked up and call either rtalloc() (and friends) if the protocol is not IPv4 forcing the action to row 0 or to the appropriate row if it IS IPv4 (and that info is available). These are for calling from code that is not specific to any particular protocol. The way these are implemented would change in the non ABI preserving code to be added later. One feature of the first version of the code is that for ipv4, the interface routes show up automatically on all the FIBs, so that no matter what FIB you select you always have the basic direct attached hosts available to you. (rtinit() does this automatically). You CAN delete an interface route from one FIB should you want to but by default it's there. ARP information is also available in each FIB. It's assumed that the same machine would have the same MAC address, regardless of which FIB you are using to get to it. This brings us as to how the correct FIB is selected for an outgoing IPV4 packet. Firstly, all packets have a FIB associated with them. if nothing has been done to change it, it will be FIB 0. The FIB is changed in the following ways. Packets fall into one of a number of classes. 1/ locally generated packets, coming from a socket/PCB. Such packets select a FIB from a number associated with the socket/PCB. This in turn is inherited from the process, but can be changed by a socket option. The process in turn inherits it on fork. I have written a utility call setfib that acts a bit like nice.. setfib -3 ping target.example.com # will use fib 3 for ping. It is an obvious extension to make it a property of a jail but I have not done so. It can be achieved by combining the setfib and jail commands. 2/ packets received on an interface for forwarding. By default these packets would use table 0, (or possibly a number settable in a sysctl(not yet)). but prior to routing the firewall can inspect them (see below). (possibly in the future you may be able to associate a FIB with packets received on an interface.. An ifconfig arg, but not yet.) 3/ packets inspected by a packet classifier, which can arbitrarily associate a fib with it on a packet by packet basis. A fib assigned to a packet by a packet classifier (such as ipfw) would over-ride a fib associated by a more default source. (such as cases 1 or 2). 4/ a tcp listen socket associated with a fib will generate accept sockets that are associated with that same fib. 5/ Packets generated in response to some other packet (e.g. reset or icmp packets). These should use the FIB associated with the packet being reponded to. 6/ Packets generated during encapsulation. gif, tun and other tunnel interfaces will encapsulate using the FIB that was in effect withthe proces that set up the tunnel. thus setfib 1 ifconfig gif0 [tunnel instructions] will set the fib for the tunnel to use to be fib 1. Routing messages would be associated with their process, and thus select one FIB or another. messages from the kernel would be associated with the fib they refer to and would only be received by a routing socket associated with that fib. (not yet implemented) In addition Netstat has been edited to be able to cope with the fact that the array is now 2 dimensional. (It looks in system memory using libkvm (!)). Old versions of netstat see only the first FIB. In addition two sysctls are added to give: a) the number of FIBs compiled in (active) b) the default FIB of the calling process. Early testing experience: ------------------------- Basically our (IronPort's) appliance does this functionality already using ipfw fwd but that method has some drawbacks. For example, It can't fully simulate a routing table because it can't influence the socket's choice of local address when a connect() is done. Testing during the generating of these changes has been remarkably smooth so far. Multiple tables have co-existed with no notable side effects, and packets have been routes accordingly. ipfw has grown 2 new keywords: setfib N ip from anay to any count ip from any to any fib N In pf there seems to be a requirement to be able to give symbolic names to the fibs but I do not have that capacity. I am not sure if it is required. SCTP has interestingly enough built in support for this, called VRFs in Cisco parlance. it will be interesting to see how that handles it when it suddenly actually does something. Where to next: -------------------- After committing the ABI compatible version and MFCing it, I'd like to proceed in a forward direction in -current. this will result in some roto-tilling in the routing code. Firstly: the current code's idea of having a separate tree per protocol family, all of the same format, and pointed to by the 1 dimensional array is a bit silly. Especially when one considers that there is code that makes assumptions about every protocol having the same internal structures there. Some protocols don't WANT that sort of structure. (for example the whole idea of a netmask is foreign to appletalk). This needs to be made opaque to the external code. My suggested first change is to add routing method pointers to the 'domain' structure, along with information pointing the data. instead of having an array of pointers to uniform structures, there would be an array pointing to the 'domain' structures for each protocol address domain (protocol family), and the methods this reached would be called. The methods would have an argument that gives FIB number, but the protocol would be free to ignore it. When the ABI can be changed it raises the possibilty of the addition of a fib entry into the "struct route". Currently, the structure contains the sockaddr of the desination, and the resulting fib entry. To make this work fully, one could add a fib number so that given an address and a fib, one can find the third element, the fib entry. Interaction with the ARP layer/ LL layer would need to be revisited as well. Qing Li has been working on this already. This work was sponsored by Ironport Systems/Cisco Reviewed by: several including rwatson, bz and mlair (parts each) Obtained from: Ironport systems/Cisco
2008-05-09 23:03:00 +00:00
rtalloc_mpath_fib(ro,
ntohl(ip->ip_src.s_addr ^ ip->ip_dst.s_addr),
fibnum);
#else
in_rtalloc_ign(ro, 0, fibnum);
#endif
rte = ro->ro_rt;
}
if (rte == NULL ||
(rte->rt_flags & RTF_UP) == 0 ||
rte->rt_ifp == NULL ||
!RT_LINK_IS_UP(rte->rt_ifp)) {
#ifdef IPSEC
/*
* There is no route for this packet, but it is
* possible that a matching SPD entry exists.
*/
no_route_but_check_spd = 1;
mtu = 0; /* Silence GCC warning. */
goto sendit;
#endif
IPSTAT_INC(ips_noroute);
1994-05-24 10:09:53 +00:00
error = EHOSTUNREACH;
goto bad;
}
ia = ifatoia(rte->rt_ifa);
ifp = rte->rt_ifp;
counter_u64_add(rte->rt_pksent, 1);
rt_update_ro_flags(ro);
if (rte->rt_flags & RTF_GATEWAY)
gw = (struct sockaddr_in *)rte->rt_gateway;
if (rte->rt_flags & RTF_HOST)
isbroadcast = (rte->rt_flags & RTF_BROADCAST);
else
isbroadcast = in_ifaddr_broadcast(gw->sin_addr, ia);
1994-05-24 10:09:53 +00:00
}
/*
* Calculate MTU. If we have a route that is up, use that,
* otherwise use the interface's MTU.
*/
if (rte != NULL && (rte->rt_flags & (RTF_UP|RTF_HOST)))
mtu = rte->rt_mtu;
else
mtu = ifp->if_mtu;
/* Catch a possible divide by zero later. */
KASSERT(mtu > 0, ("%s: mtu %d <= 0, rte=%p (rt_flags=0x%08x) ifp=%p",
__func__, mtu, rte, (rte != NULL) ? rte->rt_flags : 0, ifp));
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 (IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
1994-05-24 10:09:53 +00:00
m->m_flags |= M_MCAST;
/*
* IP destination address is multicast. Make sure "gw"
* still points to the address in "ro". (It may have been
* changed to point to a gateway address, above.)
*/
gw = dst;
1994-05-24 10:09:53 +00:00
/*
* See if the caller provided any multicast options
*/
if (imo != NULL) {
ip->ip_ttl = imo->imo_multicast_ttl;
if (imo->imo_multicast_vif != -1)
ip->ip_src.s_addr =
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
ip_mcast_src ?
ip_mcast_src(imo->imo_multicast_vif) :
INADDR_ANY;
1994-05-24 10:09:53 +00:00
} else
ip->ip_ttl = IP_DEFAULT_MULTICAST_TTL;
/*
* Confirm that the outgoing interface supports multicast.
*/
if ((imo == NULL) || (imo->imo_multicast_vif == -1)) {
if ((ifp->if_flags & IFF_MULTICAST) == 0) {
IPSTAT_INC(ips_noroute);
error = ENETUNREACH;
goto bad;
}
1994-05-24 10:09:53 +00:00
}
/*
* If source address not specified yet, use address
* of outgoing interface.
*/
if (ip->ip_src.s_addr == INADDR_ANY) {
/* Interface may have no addresses. */
if (ia != NULL)
ip->ip_src = IA_SIN(ia)->sin_addr;
1994-05-24 10:09:53 +00:00
}
if ((imo == NULL && in_mcast_loop) ||
(imo && imo->imo_multicast_loop)) {
1994-05-24 10:09:53 +00:00
/*
* Loop back multicast datagram if not expressly
* forbidden to do so, even if we are not a member
* of the group; ip_input() will filter it later,
* thus deferring a hash lookup and mutex acquisition
* at the expense of a cheap copy using m_copym().
1994-05-24 10:09:53 +00:00
*/
ip_mloopback(ifp, m, hlen);
} else {
1994-05-24 10:09:53 +00:00
/*
* If we are acting as a multicast router, perform
* multicast forwarding as if the packet had just
* arrived on the interface to which we are about
* to send. The multicast forwarding function
* recursively calls this function, using the
* IP_FORWARDING flag to prevent infinite recursion.
*
* Multicasts that are looped back by ip_mloopback(),
* above, will be forwarded by the ip_input() routine,
* if necessary.
*/
if (V_ip_mrouter && (flags & IP_FORWARDING) == 0) {
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
/*
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
* If rsvp daemon is not running, do not
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
* set ip_moptions. This ensures that the packet
* is multicast and not just sent down one link
* as prescribed by rsvpd.
*/
if (!V_rsvp_on)
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
imo = NULL;
if (ip_mforward &&
ip_mforward(ip, ifp, m, imo) != 0) {
1994-05-24 10:09:53 +00:00
m_freem(m);
goto done;
}
}
}
1994-05-24 10:09:53 +00:00
/*
* Multicasts with a time-to-live of zero may be looped-
* back, above, but must not be transmitted on a network.
* Also, multicasts addressed to the loopback interface
* are not sent -- the above call to ip_mloopback() will
* loop back a copy. ip_input() will drop the copy if
* this host does not belong to the destination group on
* the loopback interface.
1994-05-24 10:09:53 +00:00
*/
if (ip->ip_ttl == 0 || ifp->if_flags & IFF_LOOPBACK) {
1994-05-24 10:09:53 +00:00
m_freem(m);
goto done;
}
goto sendit;
}
1994-05-24 10:09:53 +00:00
/*
Remove (almost all) global variables that were used to hold packet forwarding state ("annotations") during ip processing. The code is considerably cleaner now. The variables removed by this change are: ip_divert_cookie used by divert sockets ip_fw_fwd_addr used for transparent ip redirection last_pkt used by dynamic pipes in dummynet Removal of the first two has been done by carrying the annotations into volatile structs prepended to the mbuf chains, and adding appropriate code to add/remove annotations in the routines which make use of them, i.e. ip_input(), ip_output(), tcp_input(), bdg_forward(), ether_demux(), ether_output_frame(), div_output(). On passing, remove a bug in divert handling of fragmented packet. Now it is the fragment at offset 0 which sets the divert status of the whole packet, whereas formerly it was the last incoming fragment to decide. Removal of last_pkt required a change in the interface of ip_fw_chk() and dummynet_io(). On passing, use the same mechanism for dummynet annotations and for divert/forward annotations. option IPFIREWALL_FORWARD is effectively useless, the code to implement it is very small and is now in by default to avoid the obfuscation of conditionally compiled code. NOTES: * there is at least one global variable left, sro_fwd, in ip_output(). I am not sure if/how this can be removed. * I have deliberately avoided gratuitous style changes in this commit to avoid cluttering the diffs. Minor stule cleanup will likely be necessary * this commit only focused on the IP layer. I am sure there is a number of global variables used in the TCP and maybe UDP stack. * despite the number of files touched, there are absolutely no API's or data structures changed by this commit (except the interfaces of ip_fw_chk() and dummynet_io(), which are internal anyways), so an MFC is quite safe and unintrusive (and desirable, given the improved readability of the code). MFC after: 10 days
2002-06-22 11:51:02 +00:00
* If the source address is not specified yet, use the address
* of the outoing interface.
1994-05-24 10:09:53 +00:00
*/
if (ip->ip_src.s_addr == INADDR_ANY) {
/* Interface may have no addresses. */
if (ia != NULL) {
ip->ip_src = IA_SIN(ia)->sin_addr;
}
}
1994-05-24 10:09:53 +00:00
/*
* Look for broadcast address and
* verify user is allowed to send
1994-05-24 10:09:53 +00:00
* such a packet.
*/
if (isbroadcast) {
1994-05-24 10:09:53 +00:00
if ((ifp->if_flags & IFF_BROADCAST) == 0) {
error = EADDRNOTAVAIL;
goto bad;
}
if ((flags & IP_ALLOWBROADCAST) == 0) {
error = EACCES;
goto bad;
}
/* don't allow broadcast messages to be fragmented */
if (ip_len > mtu) {
1994-05-24 10:09:53 +00:00
error = EMSGSIZE;
goto bad;
}
m->m_flags |= M_BCAST;
} else {
1994-05-24 10:09:53 +00:00
m->m_flags &= ~M_BCAST;
}
1994-05-24 10:09:53 +00:00
sendit:
#ifdef IPSEC
switch(ip_ipsec_output(&m, inp, &error)) {
case 1:
goto bad;
case -1:
goto done;
case 0:
default:
break; /* Continue with packet processing. */
}
/*
* Check if there was a route for this packet; return error if not.
*/
if (no_route_but_check_spd) {
IPSTAT_INC(ips_noroute);
error = EHOSTUNREACH;
goto bad;
}
/* Update variables that are affected by ipsec4_output(). */
ip = mtod(m, struct ip *);
hlen = ip->ip_hl << 2;
#endif /* IPSEC */
/* Jump over all PFIL processing if hooks are not active. */
if (PFIL_HOOKED(&V_inet_pfil_hook)) {
switch (ip_output_pfil(&m, ifp, inp, dst, &fibnum, &error)) {
case 1: /* Finished */
goto done;
case 0: /* Continue normally */
ip = mtod(m, struct ip *);
break;
case -1: /* Need to try again */
/* Reset everything for a new round */
RO_RTFREE(ro);
if (have_ia_ref)
ifa_free(&ia->ia_ifa);
Implement interface link header precomputation API. Add if_requestencap() interface method which is capable of calculating various link headers for given interface. Right now there is support for INET/INET6/ARP llheader calculation (IFENCAP_LL type request). Other types are planned to support more complex calculation (L2 multipath lagg nexthops, tunnel encap nexthops, etc..). Reshape 'struct route' to be able to pass additional data (with is length) to prepend to mbuf. These two changes permits routing code to pass pre-calculated nexthop data (like L2 header for route w/gateway) down to the stack eliminating the need for other lookups. It also brings us closer to more complex scenarios like transparently handling MPLS nexthops and tunnel interfaces. Last, but not least, it removes layering violation introduced by flowtable code (ro_lle) and simplifies handling of existing if_output consumers. ARP/ND changes: Make arp/ndp stack pre-calculate link header upon installing/updating lle record. Interface link address change are handled by re-calculating headers for all lles based on if_lladdr event. After these changes, arpresolve()/nd6_resolve() returns full pre-calculated header for supported interfaces thus simplifying if_output(). Move these lookups to separate ether_resolve_addr() function which ether returs error or fully-prepared link header. Add <arp|nd6_>resolve_addr() compat versions to return link addresses instead of pre-calculated data. BPF changes: Raw bpf writes occupied _two_ cases: AF_UNSPEC and pseudo_AF_HDRCMPLT. Despite the naming, both of there have ther header "complete". The only difference is that interface source mac has to be filled by OS for AF_UNSPEC (controlled via BIOCGHDRCMPLT). This logic has to stay inside BPF and not pollute if_output() routines. Convert BPF to pass prepend data via new 'struct route' mechanism. Note that it does not change non-optimized if_output(): ro_prepend handling is purely optional. Side note: hackish pseudo_AF_HDRCMPLT is supported for ethernet and FDDI. It is not needed for ethernet anymore. The only remaining FDDI user is dev/pdq mostly untouched since 2007. FDDI support was eliminated from OpenBSD in 2013 (sys/net/if_fddisubr.c rev 1.65). Flowtable changes: Flowtable violates layering by saving (and not correctly managing) rtes/lles. Instead of passing lle pointer, pass pointer to pre-calculated header data from that lle. Differential Revision: https://reviews.freebsd.org/D4102
2015-12-31 05:03:27 +00:00
ro->ro_prepend = NULL;
rte = NULL;
gw = dst;
ip = mtod(m, struct ip *);
goto again;
Remove (almost all) global variables that were used to hold packet forwarding state ("annotations") during ip processing. The code is considerably cleaner now. The variables removed by this change are: ip_divert_cookie used by divert sockets ip_fw_fwd_addr used for transparent ip redirection last_pkt used by dynamic pipes in dummynet Removal of the first two has been done by carrying the annotations into volatile structs prepended to the mbuf chains, and adding appropriate code to add/remove annotations in the routines which make use of them, i.e. ip_input(), ip_output(), tcp_input(), bdg_forward(), ether_demux(), ether_output_frame(), div_output(). On passing, remove a bug in divert handling of fragmented packet. Now it is the fragment at offset 0 which sets the divert status of the whole packet, whereas formerly it was the last incoming fragment to decide. Removal of last_pkt required a change in the interface of ip_fw_chk() and dummynet_io(). On passing, use the same mechanism for dummynet annotations and for divert/forward annotations. option IPFIREWALL_FORWARD is effectively useless, the code to implement it is very small and is now in by default to avoid the obfuscation of conditionally compiled code. NOTES: * there is at least one global variable left, sro_fwd, in ip_output(). I am not sure if/how this can be removed. * I have deliberately avoided gratuitous style changes in this commit to avoid cluttering the diffs. Minor stule cleanup will likely be necessary * this commit only focused on the IP layer. I am sure there is a number of global variables used in the TCP and maybe UDP stack. * despite the number of files touched, there are absolutely no API's or data structures changed by this commit (except the interfaces of ip_fw_chk() and dummynet_io(), which are internal anyways), so an MFC is quite safe and unintrusive (and desirable, given the improved readability of the code). MFC after: 10 days
2002-06-22 11:51:02 +00:00
}
}
/* 127/8 must not appear on wire - RFC1122. */
if ((ntohl(ip->ip_dst.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET ||
(ntohl(ip->ip_src.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET) {
if ((ifp->if_flags & IFF_LOOPBACK) == 0) {
IPSTAT_INC(ips_badaddr);
error = EADDRNOTAVAIL;
goto bad;
}
}
m->m_pkthdr.csum_flags |= CSUM_IP;
if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA & ~ifp->if_hwassist) {
in_delayed_cksum(m);
m->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
}
#ifdef SCTP
if (m->m_pkthdr.csum_flags & CSUM_SCTP & ~ifp->if_hwassist) {
sctp_delayed_cksum(m, (uint32_t)(ip->ip_hl << 2));
m->m_pkthdr.csum_flags &= ~CSUM_SCTP;
}
#endif
1994-05-24 10:09:53 +00:00
/*
* If small enough for interface, or the interface will take
* care of the fragmentation for us, we can just send directly.
1994-05-24 10:09:53 +00:00
*/
if (ip_len <= mtu ||
(m->m_pkthdr.csum_flags & ifp->if_hwassist & CSUM_TSO) != 0) {
1994-05-24 10:09:53 +00:00
ip->ip_sum = 0;
if (m->m_pkthdr.csum_flags & CSUM_IP & ~ifp->if_hwassist) {
ip->ip_sum = in_cksum(m, hlen);
m->m_pkthdr.csum_flags &= ~CSUM_IP;
}
/*
* Record statistics for this interface address.
* With CSUM_TSO the byte/packet count will be slightly
* incorrect because we count the IP+TCP headers only
* once instead of for every generated packet.
*/
if (!(flags & IP_FORWARDING) && ia) {
if (m->m_pkthdr.csum_flags & CSUM_TSO)
counter_u64_add(ia->ia_ifa.ifa_opackets,
m->m_pkthdr.len / m->m_pkthdr.tso_segsz);
else
counter_u64_add(ia->ia_ifa.ifa_opackets, 1);
counter_u64_add(ia->ia_ifa.ifa_obytes, m->m_pkthdr.len);
}
#ifdef MBUF_STRESS_TEST
if (mbuf_frag_size && m->m_pkthdr.len > mbuf_frag_size)
m = m_fragment(m, M_NOWAIT, mbuf_frag_size);
#endif
/*
* Reset layer specific mbuf flags
* to avoid confusing lower layers.
*/
m_clrprotoflags(m);
IP_PROBE(send, NULL, NULL, ip, ifp, ip, NULL);
error = (*ifp->if_output)(ifp, m,
(const struct sockaddr *)gw, ro);
1994-05-24 10:09:53 +00:00
goto done;
}
/* Balk when DF bit is set or the interface didn't support TSO. */
if ((ip_off & IP_DF) || (m->m_pkthdr.csum_flags & CSUM_TSO)) {
1994-05-24 10:09:53 +00:00
error = EMSGSIZE;
IPSTAT_INC(ips_cantfrag);
1994-05-24 10:09:53 +00:00
goto bad;
}
/*
* Too large for interface; fragment if possible. If successful,
* on return, m will point to a list of packets to be sent.
*/
error = ip_fragment(ip, &m, mtu, ifp->if_hwassist);
if (error)
1994-05-24 10:09:53 +00:00
goto bad;
for (; m; m = m0) {
m0 = m->m_nextpkt;
m->m_nextpkt = 0;
if (error == 0) {
/* Record statistics for this interface address. */
if (ia != NULL) {
counter_u64_add(ia->ia_ifa.ifa_opackets, 1);
counter_u64_add(ia->ia_ifa.ifa_obytes,
m->m_pkthdr.len);
}
/*
* Reset layer specific mbuf flags
* to avoid confusing upper layers.
*/
m_clrprotoflags(m);
IP_PROBE(send, NULL, NULL, ip, ifp, ip, NULL);
error = (*ifp->if_output)(ifp, m,
(const struct sockaddr *)gw, ro);
} else
m_freem(m);
1994-05-24 10:09:53 +00:00
}
if (error == 0)
IPSTAT_INC(ips_fragmented);
done:
/*
* Release the route if using our private route, or if
* (with flowtable) we don't have our own reference.
*/
if (ro == &iproute || ro->ro_flags & RT_NORTREF)
RO_RTFREE(ro);
else if (rte == NULL)
/*
* If the caller supplied a route but somehow the reference
* to it has been released need to prevent the caller
* calling RTFREE on it again.
*/
ro->ro_rt = NULL;
if (have_ia_ref)
ifa_free(&ia->ia_ifa);
return (error);
bad:
m_freem(m);
goto done;
}
/*
* Create a chain of fragments which fit the given mtu. m_frag points to the
* mbuf to be fragmented; on return it points to the chain with the fragments.
* Return 0 if no error. If error, m_frag may contain a partially built
* chain of fragments that should be freed by the caller.
*
* if_hwassist_flags is the hw offload capabilities (see if_data.ifi_hwassist)
*/
int
ip_fragment(struct ip *ip, struct mbuf **m_frag, int mtu,
u_long if_hwassist_flags)
{
int error = 0;
int hlen = ip->ip_hl << 2;
int len = (mtu - hlen) & ~7; /* size of payload in each fragment */
int off;
struct mbuf *m0 = *m_frag; /* the original packet */
int firstlen;
struct mbuf **mnext;
int nfrags;
uint16_t ip_len, ip_off;
ip_len = ntohs(ip->ip_len);
ip_off = ntohs(ip->ip_off);
if (ip_off & IP_DF) { /* Fragmentation not allowed */
IPSTAT_INC(ips_cantfrag);
return EMSGSIZE;
}
/*
* Must be able to put at least 8 bytes per fragment.
*/
if (len < 8)
return EMSGSIZE;
/*
* If the interface will not calculate checksums on
* fragmented packets, then do it here.
*/
if (m0->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
in_delayed_cksum(m0);
m0->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
}
#ifdef SCTP
if (m0->m_pkthdr.csum_flags & CSUM_SCTP) {
sctp_delayed_cksum(m0, hlen);
m0->m_pkthdr.csum_flags &= ~CSUM_SCTP;
}
#endif
At long last, commit the zero copy sockets code. MAKEDEV: Add MAKEDEV glue for the ti(4) device nodes. ti.4: Update the ti(4) man page to include information on the TI_JUMBO_HDRSPLIT and TI_PRIVATE_JUMBOS kernel options, and also include information about the new character device interface and the associated ioctls. man9/Makefile: Add jumbo.9 and zero_copy.9 man pages and associated links. jumbo.9: New man page describing the jumbo buffer allocator interface and operation. zero_copy.9: New man page describing the general characteristics of the zero copy send and receive code, and what an application author should do to take advantage of the zero copy functionality. NOTES: Add entries for ZERO_COPY_SOCKETS, TI_PRIVATE_JUMBOS, TI_JUMBO_HDRSPLIT, MSIZE, and MCLSHIFT. conf/files: Add uipc_jumbo.c and uipc_cow.c. conf/options: Add the 5 options mentioned above. kern_subr.c: Receive side zero copy implementation. This takes "disposable" pages attached to an mbuf, gives them to a user process, and then recycles the user's page. This is only active when ZERO_COPY_SOCKETS is turned on and the kern.ipc.zero_copy.receive sysctl variable is set to 1. uipc_cow.c: Send side zero copy functions. Takes a page written by the user and maps it copy on write and assigns it kernel virtual address space. Removes copy on write mapping once the buffer has been freed by the network stack. uipc_jumbo.c: Jumbo disposable page allocator code. This allocates (optionally) disposable pages for network drivers that want to give the user the option of doing zero copy receive. uipc_socket.c: Add kern.ipc.zero_copy.{send,receive} sysctls that are enabled if ZERO_COPY_SOCKETS is turned on. Add zero copy send support to sosend() -- pages get mapped into the kernel instead of getting copied if they meet size and alignment restrictions. uipc_syscalls.c:Un-staticize some of the sf* functions so that they can be used elsewhere. (uipc_cow.c) if_media.c: In the SIOCGIFMEDIA ioctl in ifmedia_ioctl(), avoid calling malloc() with M_WAITOK. Return an error if the M_NOWAIT malloc fails. The ti(4) driver and the wi(4) driver, at least, call this with a mutex held. This causes witness warnings for 'ifconfig -a' with a wi(4) or ti(4) board in the system. (I've only verified for ti(4)). ip_output.c: Fragment large datagrams so that each segment contains a multiple of PAGE_SIZE amount of data plus headers. This allows the receiver to potentially do page flipping on receives. if_ti.c: Add zero copy receive support to the ti(4) driver. If TI_PRIVATE_JUMBOS is not defined, it now uses the jumbo(9) buffer allocator for jumbo receive buffers. Add a new character device interface for the ti(4) driver for the new debugging interface. This allows (a patched version of) gdb to talk to the Tigon board and debug the firmware. There are also a few additional debugging ioctls available through this interface. Add header splitting support to the ti(4) driver. Tweak some of the default interrupt coalescing parameters to more useful defaults. Add hooks for supporting transmit flow control, but leave it turned off with a comment describing why it is turned off. if_tireg.h: Change the firmware rev to 12.4.11, since we're really at 12.4.11 plus fixes from 12.4.13. Add defines needed for debugging. Remove the ti_stats structure, it is now defined in sys/tiio.h. ti_fw.h: 12.4.11 firmware. ti_fw2.h: 12.4.11 firmware, plus selected fixes from 12.4.13, and my header splitting patches. Revision 12.4.13 doesn't handle 10/100 negotiation properly. (This firmware is the same as what was in the tree previously, with the addition of header splitting support.) sys/jumbo.h: Jumbo buffer allocator interface. sys/mbuf.h: Add a new external mbuf type, EXT_DISPOSABLE, to indicate that the payload buffer can be thrown away / flipped to a userland process. socketvar.h: Add prototype for socow_setup. tiio.h: ioctl interface to the character portion of the ti(4) driver, plus associated structure/type definitions. uio.h: Change prototype for uiomoveco() so that we'll know whether the source page is disposable. ufs_readwrite.c:Update for new prototype of uiomoveco(). vm_fault.c: In vm_fault(), check to see whether we need to do a page based copy on write fault. vm_object.c: Add a new function, vm_object_allocate_wait(). This does the same thing that vm_object allocate does, except that it gives the caller the opportunity to specify whether it should wait on the uma_zalloc() of the object structre. This allows vm objects to be allocated while holding a mutex. (Without generating WITNESS warnings.) vm_object_allocate() is implemented as a call to vm_object_allocate_wait() with the malloc flag set to M_WAITOK. vm_object.h: Add prototype for vm_object_allocate_wait(). vm_page.c: Add page-based copy on write setup, clear and fault routines. vm_page.h: Add page based COW function prototypes and variable in the vm_page structure. Many thanks to Drew Gallatin, who wrote the zero copy send and receive code, and to all the other folks who have tested and reviewed this code over the years.
2002-06-26 03:37:47 +00:00
if (len > PAGE_SIZE) {
/*
* Fragment large datagrams such that each segment
* contains a multiple of PAGE_SIZE amount of data,
* plus headers. This enables a receiver to perform
At long last, commit the zero copy sockets code. MAKEDEV: Add MAKEDEV glue for the ti(4) device nodes. ti.4: Update the ti(4) man page to include information on the TI_JUMBO_HDRSPLIT and TI_PRIVATE_JUMBOS kernel options, and also include information about the new character device interface and the associated ioctls. man9/Makefile: Add jumbo.9 and zero_copy.9 man pages and associated links. jumbo.9: New man page describing the jumbo buffer allocator interface and operation. zero_copy.9: New man page describing the general characteristics of the zero copy send and receive code, and what an application author should do to take advantage of the zero copy functionality. NOTES: Add entries for ZERO_COPY_SOCKETS, TI_PRIVATE_JUMBOS, TI_JUMBO_HDRSPLIT, MSIZE, and MCLSHIFT. conf/files: Add uipc_jumbo.c and uipc_cow.c. conf/options: Add the 5 options mentioned above. kern_subr.c: Receive side zero copy implementation. This takes "disposable" pages attached to an mbuf, gives them to a user process, and then recycles the user's page. This is only active when ZERO_COPY_SOCKETS is turned on and the kern.ipc.zero_copy.receive sysctl variable is set to 1. uipc_cow.c: Send side zero copy functions. Takes a page written by the user and maps it copy on write and assigns it kernel virtual address space. Removes copy on write mapping once the buffer has been freed by the network stack. uipc_jumbo.c: Jumbo disposable page allocator code. This allocates (optionally) disposable pages for network drivers that want to give the user the option of doing zero copy receive. uipc_socket.c: Add kern.ipc.zero_copy.{send,receive} sysctls that are enabled if ZERO_COPY_SOCKETS is turned on. Add zero copy send support to sosend() -- pages get mapped into the kernel instead of getting copied if they meet size and alignment restrictions. uipc_syscalls.c:Un-staticize some of the sf* functions so that they can be used elsewhere. (uipc_cow.c) if_media.c: In the SIOCGIFMEDIA ioctl in ifmedia_ioctl(), avoid calling malloc() with M_WAITOK. Return an error if the M_NOWAIT malloc fails. The ti(4) driver and the wi(4) driver, at least, call this with a mutex held. This causes witness warnings for 'ifconfig -a' with a wi(4) or ti(4) board in the system. (I've only verified for ti(4)). ip_output.c: Fragment large datagrams so that each segment contains a multiple of PAGE_SIZE amount of data plus headers. This allows the receiver to potentially do page flipping on receives. if_ti.c: Add zero copy receive support to the ti(4) driver. If TI_PRIVATE_JUMBOS is not defined, it now uses the jumbo(9) buffer allocator for jumbo receive buffers. Add a new character device interface for the ti(4) driver for the new debugging interface. This allows (a patched version of) gdb to talk to the Tigon board and debug the firmware. There are also a few additional debugging ioctls available through this interface. Add header splitting support to the ti(4) driver. Tweak some of the default interrupt coalescing parameters to more useful defaults. Add hooks for supporting transmit flow control, but leave it turned off with a comment describing why it is turned off. if_tireg.h: Change the firmware rev to 12.4.11, since we're really at 12.4.11 plus fixes from 12.4.13. Add defines needed for debugging. Remove the ti_stats structure, it is now defined in sys/tiio.h. ti_fw.h: 12.4.11 firmware. ti_fw2.h: 12.4.11 firmware, plus selected fixes from 12.4.13, and my header splitting patches. Revision 12.4.13 doesn't handle 10/100 negotiation properly. (This firmware is the same as what was in the tree previously, with the addition of header splitting support.) sys/jumbo.h: Jumbo buffer allocator interface. sys/mbuf.h: Add a new external mbuf type, EXT_DISPOSABLE, to indicate that the payload buffer can be thrown away / flipped to a userland process. socketvar.h: Add prototype for socow_setup. tiio.h: ioctl interface to the character portion of the ti(4) driver, plus associated structure/type definitions. uio.h: Change prototype for uiomoveco() so that we'll know whether the source page is disposable. ufs_readwrite.c:Update for new prototype of uiomoveco(). vm_fault.c: In vm_fault(), check to see whether we need to do a page based copy on write fault. vm_object.c: Add a new function, vm_object_allocate_wait(). This does the same thing that vm_object allocate does, except that it gives the caller the opportunity to specify whether it should wait on the uma_zalloc() of the object structre. This allows vm objects to be allocated while holding a mutex. (Without generating WITNESS warnings.) vm_object_allocate() is implemented as a call to vm_object_allocate_wait() with the malloc flag set to M_WAITOK. vm_object.h: Add prototype for vm_object_allocate_wait(). vm_page.c: Add page-based copy on write setup, clear and fault routines. vm_page.h: Add page based COW function prototypes and variable in the vm_page structure. Many thanks to Drew Gallatin, who wrote the zero copy send and receive code, and to all the other folks who have tested and reviewed this code over the years.
2002-06-26 03:37:47 +00:00
* page-flipping zero-copy optimizations.
*
* XXX When does this help given that sender and receiver
* could have different page sizes, and also mtu could
* be less than the receiver's page size ?
At long last, commit the zero copy sockets code. MAKEDEV: Add MAKEDEV glue for the ti(4) device nodes. ti.4: Update the ti(4) man page to include information on the TI_JUMBO_HDRSPLIT and TI_PRIVATE_JUMBOS kernel options, and also include information about the new character device interface and the associated ioctls. man9/Makefile: Add jumbo.9 and zero_copy.9 man pages and associated links. jumbo.9: New man page describing the jumbo buffer allocator interface and operation. zero_copy.9: New man page describing the general characteristics of the zero copy send and receive code, and what an application author should do to take advantage of the zero copy functionality. NOTES: Add entries for ZERO_COPY_SOCKETS, TI_PRIVATE_JUMBOS, TI_JUMBO_HDRSPLIT, MSIZE, and MCLSHIFT. conf/files: Add uipc_jumbo.c and uipc_cow.c. conf/options: Add the 5 options mentioned above. kern_subr.c: Receive side zero copy implementation. This takes "disposable" pages attached to an mbuf, gives them to a user process, and then recycles the user's page. This is only active when ZERO_COPY_SOCKETS is turned on and the kern.ipc.zero_copy.receive sysctl variable is set to 1. uipc_cow.c: Send side zero copy functions. Takes a page written by the user and maps it copy on write and assigns it kernel virtual address space. Removes copy on write mapping once the buffer has been freed by the network stack. uipc_jumbo.c: Jumbo disposable page allocator code. This allocates (optionally) disposable pages for network drivers that want to give the user the option of doing zero copy receive. uipc_socket.c: Add kern.ipc.zero_copy.{send,receive} sysctls that are enabled if ZERO_COPY_SOCKETS is turned on. Add zero copy send support to sosend() -- pages get mapped into the kernel instead of getting copied if they meet size and alignment restrictions. uipc_syscalls.c:Un-staticize some of the sf* functions so that they can be used elsewhere. (uipc_cow.c) if_media.c: In the SIOCGIFMEDIA ioctl in ifmedia_ioctl(), avoid calling malloc() with M_WAITOK. Return an error if the M_NOWAIT malloc fails. The ti(4) driver and the wi(4) driver, at least, call this with a mutex held. This causes witness warnings for 'ifconfig -a' with a wi(4) or ti(4) board in the system. (I've only verified for ti(4)). ip_output.c: Fragment large datagrams so that each segment contains a multiple of PAGE_SIZE amount of data plus headers. This allows the receiver to potentially do page flipping on receives. if_ti.c: Add zero copy receive support to the ti(4) driver. If TI_PRIVATE_JUMBOS is not defined, it now uses the jumbo(9) buffer allocator for jumbo receive buffers. Add a new character device interface for the ti(4) driver for the new debugging interface. This allows (a patched version of) gdb to talk to the Tigon board and debug the firmware. There are also a few additional debugging ioctls available through this interface. Add header splitting support to the ti(4) driver. Tweak some of the default interrupt coalescing parameters to more useful defaults. Add hooks for supporting transmit flow control, but leave it turned off with a comment describing why it is turned off. if_tireg.h: Change the firmware rev to 12.4.11, since we're really at 12.4.11 plus fixes from 12.4.13. Add defines needed for debugging. Remove the ti_stats structure, it is now defined in sys/tiio.h. ti_fw.h: 12.4.11 firmware. ti_fw2.h: 12.4.11 firmware, plus selected fixes from 12.4.13, and my header splitting patches. Revision 12.4.13 doesn't handle 10/100 negotiation properly. (This firmware is the same as what was in the tree previously, with the addition of header splitting support.) sys/jumbo.h: Jumbo buffer allocator interface. sys/mbuf.h: Add a new external mbuf type, EXT_DISPOSABLE, to indicate that the payload buffer can be thrown away / flipped to a userland process. socketvar.h: Add prototype for socow_setup. tiio.h: ioctl interface to the character portion of the ti(4) driver, plus associated structure/type definitions. uio.h: Change prototype for uiomoveco() so that we'll know whether the source page is disposable. ufs_readwrite.c:Update for new prototype of uiomoveco(). vm_fault.c: In vm_fault(), check to see whether we need to do a page based copy on write fault. vm_object.c: Add a new function, vm_object_allocate_wait(). This does the same thing that vm_object allocate does, except that it gives the caller the opportunity to specify whether it should wait on the uma_zalloc() of the object structre. This allows vm objects to be allocated while holding a mutex. (Without generating WITNESS warnings.) vm_object_allocate() is implemented as a call to vm_object_allocate_wait() with the malloc flag set to M_WAITOK. vm_object.h: Add prototype for vm_object_allocate_wait(). vm_page.c: Add page-based copy on write setup, clear and fault routines. vm_page.h: Add page based COW function prototypes and variable in the vm_page structure. Many thanks to Drew Gallatin, who wrote the zero copy send and receive code, and to all the other folks who have tested and reviewed this code over the years.
2002-06-26 03:37:47 +00:00
*/
int newlen;
off = MIN(mtu, m0->m_pkthdr.len);
At long last, commit the zero copy sockets code. MAKEDEV: Add MAKEDEV glue for the ti(4) device nodes. ti.4: Update the ti(4) man page to include information on the TI_JUMBO_HDRSPLIT and TI_PRIVATE_JUMBOS kernel options, and also include information about the new character device interface and the associated ioctls. man9/Makefile: Add jumbo.9 and zero_copy.9 man pages and associated links. jumbo.9: New man page describing the jumbo buffer allocator interface and operation. zero_copy.9: New man page describing the general characteristics of the zero copy send and receive code, and what an application author should do to take advantage of the zero copy functionality. NOTES: Add entries for ZERO_COPY_SOCKETS, TI_PRIVATE_JUMBOS, TI_JUMBO_HDRSPLIT, MSIZE, and MCLSHIFT. conf/files: Add uipc_jumbo.c and uipc_cow.c. conf/options: Add the 5 options mentioned above. kern_subr.c: Receive side zero copy implementation. This takes "disposable" pages attached to an mbuf, gives them to a user process, and then recycles the user's page. This is only active when ZERO_COPY_SOCKETS is turned on and the kern.ipc.zero_copy.receive sysctl variable is set to 1. uipc_cow.c: Send side zero copy functions. Takes a page written by the user and maps it copy on write and assigns it kernel virtual address space. Removes copy on write mapping once the buffer has been freed by the network stack. uipc_jumbo.c: Jumbo disposable page allocator code. This allocates (optionally) disposable pages for network drivers that want to give the user the option of doing zero copy receive. uipc_socket.c: Add kern.ipc.zero_copy.{send,receive} sysctls that are enabled if ZERO_COPY_SOCKETS is turned on. Add zero copy send support to sosend() -- pages get mapped into the kernel instead of getting copied if they meet size and alignment restrictions. uipc_syscalls.c:Un-staticize some of the sf* functions so that they can be used elsewhere. (uipc_cow.c) if_media.c: In the SIOCGIFMEDIA ioctl in ifmedia_ioctl(), avoid calling malloc() with M_WAITOK. Return an error if the M_NOWAIT malloc fails. The ti(4) driver and the wi(4) driver, at least, call this with a mutex held. This causes witness warnings for 'ifconfig -a' with a wi(4) or ti(4) board in the system. (I've only verified for ti(4)). ip_output.c: Fragment large datagrams so that each segment contains a multiple of PAGE_SIZE amount of data plus headers. This allows the receiver to potentially do page flipping on receives. if_ti.c: Add zero copy receive support to the ti(4) driver. If TI_PRIVATE_JUMBOS is not defined, it now uses the jumbo(9) buffer allocator for jumbo receive buffers. Add a new character device interface for the ti(4) driver for the new debugging interface. This allows (a patched version of) gdb to talk to the Tigon board and debug the firmware. There are also a few additional debugging ioctls available through this interface. Add header splitting support to the ti(4) driver. Tweak some of the default interrupt coalescing parameters to more useful defaults. Add hooks for supporting transmit flow control, but leave it turned off with a comment describing why it is turned off. if_tireg.h: Change the firmware rev to 12.4.11, since we're really at 12.4.11 plus fixes from 12.4.13. Add defines needed for debugging. Remove the ti_stats structure, it is now defined in sys/tiio.h. ti_fw.h: 12.4.11 firmware. ti_fw2.h: 12.4.11 firmware, plus selected fixes from 12.4.13, and my header splitting patches. Revision 12.4.13 doesn't handle 10/100 negotiation properly. (This firmware is the same as what was in the tree previously, with the addition of header splitting support.) sys/jumbo.h: Jumbo buffer allocator interface. sys/mbuf.h: Add a new external mbuf type, EXT_DISPOSABLE, to indicate that the payload buffer can be thrown away / flipped to a userland process. socketvar.h: Add prototype for socow_setup. tiio.h: ioctl interface to the character portion of the ti(4) driver, plus associated structure/type definitions. uio.h: Change prototype for uiomoveco() so that we'll know whether the source page is disposable. ufs_readwrite.c:Update for new prototype of uiomoveco(). vm_fault.c: In vm_fault(), check to see whether we need to do a page based copy on write fault. vm_object.c: Add a new function, vm_object_allocate_wait(). This does the same thing that vm_object allocate does, except that it gives the caller the opportunity to specify whether it should wait on the uma_zalloc() of the object structre. This allows vm objects to be allocated while holding a mutex. (Without generating WITNESS warnings.) vm_object_allocate() is implemented as a call to vm_object_allocate_wait() with the malloc flag set to M_WAITOK. vm_object.h: Add prototype for vm_object_allocate_wait(). vm_page.c: Add page-based copy on write setup, clear and fault routines. vm_page.h: Add page based COW function prototypes and variable in the vm_page structure. Many thanks to Drew Gallatin, who wrote the zero copy send and receive code, and to all the other folks who have tested and reviewed this code over the years.
2002-06-26 03:37:47 +00:00
/*
* firstlen (off - hlen) must be aligned on an
At long last, commit the zero copy sockets code. MAKEDEV: Add MAKEDEV glue for the ti(4) device nodes. ti.4: Update the ti(4) man page to include information on the TI_JUMBO_HDRSPLIT and TI_PRIVATE_JUMBOS kernel options, and also include information about the new character device interface and the associated ioctls. man9/Makefile: Add jumbo.9 and zero_copy.9 man pages and associated links. jumbo.9: New man page describing the jumbo buffer allocator interface and operation. zero_copy.9: New man page describing the general characteristics of the zero copy send and receive code, and what an application author should do to take advantage of the zero copy functionality. NOTES: Add entries for ZERO_COPY_SOCKETS, TI_PRIVATE_JUMBOS, TI_JUMBO_HDRSPLIT, MSIZE, and MCLSHIFT. conf/files: Add uipc_jumbo.c and uipc_cow.c. conf/options: Add the 5 options mentioned above. kern_subr.c: Receive side zero copy implementation. This takes "disposable" pages attached to an mbuf, gives them to a user process, and then recycles the user's page. This is only active when ZERO_COPY_SOCKETS is turned on and the kern.ipc.zero_copy.receive sysctl variable is set to 1. uipc_cow.c: Send side zero copy functions. Takes a page written by the user and maps it copy on write and assigns it kernel virtual address space. Removes copy on write mapping once the buffer has been freed by the network stack. uipc_jumbo.c: Jumbo disposable page allocator code. This allocates (optionally) disposable pages for network drivers that want to give the user the option of doing zero copy receive. uipc_socket.c: Add kern.ipc.zero_copy.{send,receive} sysctls that are enabled if ZERO_COPY_SOCKETS is turned on. Add zero copy send support to sosend() -- pages get mapped into the kernel instead of getting copied if they meet size and alignment restrictions. uipc_syscalls.c:Un-staticize some of the sf* functions so that they can be used elsewhere. (uipc_cow.c) if_media.c: In the SIOCGIFMEDIA ioctl in ifmedia_ioctl(), avoid calling malloc() with M_WAITOK. Return an error if the M_NOWAIT malloc fails. The ti(4) driver and the wi(4) driver, at least, call this with a mutex held. This causes witness warnings for 'ifconfig -a' with a wi(4) or ti(4) board in the system. (I've only verified for ti(4)). ip_output.c: Fragment large datagrams so that each segment contains a multiple of PAGE_SIZE amount of data plus headers. This allows the receiver to potentially do page flipping on receives. if_ti.c: Add zero copy receive support to the ti(4) driver. If TI_PRIVATE_JUMBOS is not defined, it now uses the jumbo(9) buffer allocator for jumbo receive buffers. Add a new character device interface for the ti(4) driver for the new debugging interface. This allows (a patched version of) gdb to talk to the Tigon board and debug the firmware. There are also a few additional debugging ioctls available through this interface. Add header splitting support to the ti(4) driver. Tweak some of the default interrupt coalescing parameters to more useful defaults. Add hooks for supporting transmit flow control, but leave it turned off with a comment describing why it is turned off. if_tireg.h: Change the firmware rev to 12.4.11, since we're really at 12.4.11 plus fixes from 12.4.13. Add defines needed for debugging. Remove the ti_stats structure, it is now defined in sys/tiio.h. ti_fw.h: 12.4.11 firmware. ti_fw2.h: 12.4.11 firmware, plus selected fixes from 12.4.13, and my header splitting patches. Revision 12.4.13 doesn't handle 10/100 negotiation properly. (This firmware is the same as what was in the tree previously, with the addition of header splitting support.) sys/jumbo.h: Jumbo buffer allocator interface. sys/mbuf.h: Add a new external mbuf type, EXT_DISPOSABLE, to indicate that the payload buffer can be thrown away / flipped to a userland process. socketvar.h: Add prototype for socow_setup. tiio.h: ioctl interface to the character portion of the ti(4) driver, plus associated structure/type definitions. uio.h: Change prototype for uiomoveco() so that we'll know whether the source page is disposable. ufs_readwrite.c:Update for new prototype of uiomoveco(). vm_fault.c: In vm_fault(), check to see whether we need to do a page based copy on write fault. vm_object.c: Add a new function, vm_object_allocate_wait(). This does the same thing that vm_object allocate does, except that it gives the caller the opportunity to specify whether it should wait on the uma_zalloc() of the object structre. This allows vm objects to be allocated while holding a mutex. (Without generating WITNESS warnings.) vm_object_allocate() is implemented as a call to vm_object_allocate_wait() with the malloc flag set to M_WAITOK. vm_object.h: Add prototype for vm_object_allocate_wait(). vm_page.c: Add page-based copy on write setup, clear and fault routines. vm_page.h: Add page based COW function prototypes and variable in the vm_page structure. Many thanks to Drew Gallatin, who wrote the zero copy send and receive code, and to all the other folks who have tested and reviewed this code over the years.
2002-06-26 03:37:47 +00:00
* 8-byte boundary
*/
if (off < hlen)
goto smart_frag_failure;
off = ((off - hlen) & ~7) + hlen;
newlen = (~PAGE_MASK) & mtu;
if ((newlen + sizeof (struct ip)) > mtu) {
At long last, commit the zero copy sockets code. MAKEDEV: Add MAKEDEV glue for the ti(4) device nodes. ti.4: Update the ti(4) man page to include information on the TI_JUMBO_HDRSPLIT and TI_PRIVATE_JUMBOS kernel options, and also include information about the new character device interface and the associated ioctls. man9/Makefile: Add jumbo.9 and zero_copy.9 man pages and associated links. jumbo.9: New man page describing the jumbo buffer allocator interface and operation. zero_copy.9: New man page describing the general characteristics of the zero copy send and receive code, and what an application author should do to take advantage of the zero copy functionality. NOTES: Add entries for ZERO_COPY_SOCKETS, TI_PRIVATE_JUMBOS, TI_JUMBO_HDRSPLIT, MSIZE, and MCLSHIFT. conf/files: Add uipc_jumbo.c and uipc_cow.c. conf/options: Add the 5 options mentioned above. kern_subr.c: Receive side zero copy implementation. This takes "disposable" pages attached to an mbuf, gives them to a user process, and then recycles the user's page. This is only active when ZERO_COPY_SOCKETS is turned on and the kern.ipc.zero_copy.receive sysctl variable is set to 1. uipc_cow.c: Send side zero copy functions. Takes a page written by the user and maps it copy on write and assigns it kernel virtual address space. Removes copy on write mapping once the buffer has been freed by the network stack. uipc_jumbo.c: Jumbo disposable page allocator code. This allocates (optionally) disposable pages for network drivers that want to give the user the option of doing zero copy receive. uipc_socket.c: Add kern.ipc.zero_copy.{send,receive} sysctls that are enabled if ZERO_COPY_SOCKETS is turned on. Add zero copy send support to sosend() -- pages get mapped into the kernel instead of getting copied if they meet size and alignment restrictions. uipc_syscalls.c:Un-staticize some of the sf* functions so that they can be used elsewhere. (uipc_cow.c) if_media.c: In the SIOCGIFMEDIA ioctl in ifmedia_ioctl(), avoid calling malloc() with M_WAITOK. Return an error if the M_NOWAIT malloc fails. The ti(4) driver and the wi(4) driver, at least, call this with a mutex held. This causes witness warnings for 'ifconfig -a' with a wi(4) or ti(4) board in the system. (I've only verified for ti(4)). ip_output.c: Fragment large datagrams so that each segment contains a multiple of PAGE_SIZE amount of data plus headers. This allows the receiver to potentially do page flipping on receives. if_ti.c: Add zero copy receive support to the ti(4) driver. If TI_PRIVATE_JUMBOS is not defined, it now uses the jumbo(9) buffer allocator for jumbo receive buffers. Add a new character device interface for the ti(4) driver for the new debugging interface. This allows (a patched version of) gdb to talk to the Tigon board and debug the firmware. There are also a few additional debugging ioctls available through this interface. Add header splitting support to the ti(4) driver. Tweak some of the default interrupt coalescing parameters to more useful defaults. Add hooks for supporting transmit flow control, but leave it turned off with a comment describing why it is turned off. if_tireg.h: Change the firmware rev to 12.4.11, since we're really at 12.4.11 plus fixes from 12.4.13. Add defines needed for debugging. Remove the ti_stats structure, it is now defined in sys/tiio.h. ti_fw.h: 12.4.11 firmware. ti_fw2.h: 12.4.11 firmware, plus selected fixes from 12.4.13, and my header splitting patches. Revision 12.4.13 doesn't handle 10/100 negotiation properly. (This firmware is the same as what was in the tree previously, with the addition of header splitting support.) sys/jumbo.h: Jumbo buffer allocator interface. sys/mbuf.h: Add a new external mbuf type, EXT_DISPOSABLE, to indicate that the payload buffer can be thrown away / flipped to a userland process. socketvar.h: Add prototype for socow_setup. tiio.h: ioctl interface to the character portion of the ti(4) driver, plus associated structure/type definitions. uio.h: Change prototype for uiomoveco() so that we'll know whether the source page is disposable. ufs_readwrite.c:Update for new prototype of uiomoveco(). vm_fault.c: In vm_fault(), check to see whether we need to do a page based copy on write fault. vm_object.c: Add a new function, vm_object_allocate_wait(). This does the same thing that vm_object allocate does, except that it gives the caller the opportunity to specify whether it should wait on the uma_zalloc() of the object structre. This allows vm objects to be allocated while holding a mutex. (Without generating WITNESS warnings.) vm_object_allocate() is implemented as a call to vm_object_allocate_wait() with the malloc flag set to M_WAITOK. vm_object.h: Add prototype for vm_object_allocate_wait(). vm_page.c: Add page-based copy on write setup, clear and fault routines. vm_page.h: Add page based COW function prototypes and variable in the vm_page structure. Many thanks to Drew Gallatin, who wrote the zero copy send and receive code, and to all the other folks who have tested and reviewed this code over the years.
2002-06-26 03:37:47 +00:00
/* we failed, go back the default */
smart_frag_failure:
newlen = len;
off = hlen + len;
}
len = newlen;
} else {
off = hlen + len;
}
firstlen = off - hlen;
mnext = &m0->m_nextpkt; /* pointer to next packet */
1994-05-24 10:09:53 +00:00
/*
* Loop through length of segment after first fragment,
* make new header and copy data of each part and link onto chain.
* Here, m0 is the original packet, m is the fragment being created.
* The fragments are linked off the m_nextpkt of the original
* packet, which after processing serves as the first fragment.
1994-05-24 10:09:53 +00:00
*/
for (nfrags = 1; off < ip_len; off += len, nfrags++) {
struct ip *mhip; /* ip header on the fragment */
struct mbuf *m;
int mhlen = sizeof (struct ip);
m = m_gethdr(M_NOWAIT, MT_DATA);
if (m == NULL) {
1994-05-24 10:09:53 +00:00
error = ENOBUFS;
IPSTAT_INC(ips_odropped);
goto done;
1994-05-24 10:09:53 +00:00
}
/*
* Make sure the complete packet header gets copied
* from the originating mbuf to the newly created
* mbuf. This also ensures that existing firewall
* classification(s), VLAN tags and so on get copied
* to the resulting fragmented packet(s):
*/
if (m_dup_pkthdr(m, m0, M_NOWAIT) == 0) {
m_free(m);
error = ENOBUFS;
IPSTAT_INC(ips_odropped);
goto done;
}
/*
* In the first mbuf, leave room for the link header, then
* copy the original IP header including options. The payload
* goes into an additional mbuf chain returned by m_copym().
*/
1994-05-24 10:09:53 +00:00
m->m_data += max_linkhdr;
mhip = mtod(m, struct ip *);
*mhip = *ip;
if (hlen > sizeof (struct ip)) {
mhlen = ip_optcopy(ip, mhip) + sizeof (struct ip);
mhip->ip_v = IPVERSION;
mhip->ip_hl = mhlen >> 2;
1994-05-24 10:09:53 +00:00
}
m->m_len = mhlen;
/* XXX do we need to add ip_off below ? */
mhip->ip_off = ((off - hlen) >> 3) + ip_off;
if (off + len >= ip_len)
len = ip_len - off;
else
1994-05-24 10:09:53 +00:00
mhip->ip_off |= IP_MF;
mhip->ip_len = htons((u_short)(len + mhlen));
m->m_next = m_copym(m0, off, len, M_NOWAIT);
if (m->m_next == NULL) { /* copy failed */
m_free(m);
1994-05-24 10:09:53 +00:00
error = ENOBUFS; /* ??? */
IPSTAT_INC(ips_odropped);
goto done;
1994-05-24 10:09:53 +00:00
}
m->m_pkthdr.len = mhlen + len;
#ifdef MAC
mac_netinet_fragment(m0, m);
#endif
mhip->ip_off = htons(mhip->ip_off);
1994-05-24 10:09:53 +00:00
mhip->ip_sum = 0;
if (m->m_pkthdr.csum_flags & CSUM_IP & ~if_hwassist_flags) {
mhip->ip_sum = in_cksum(m, mhlen);
m->m_pkthdr.csum_flags &= ~CSUM_IP;
}
1994-05-24 10:09:53 +00:00
*mnext = m;
mnext = &m->m_nextpkt;
}
IPSTAT_ADD(ips_ofragments, nfrags);
1994-05-24 10:09:53 +00:00
/*
* Update first fragment by trimming what's been copied out
* and updating header.
1994-05-24 10:09:53 +00:00
*/
m_adj(m0, hlen + firstlen - ip_len);
m0->m_pkthdr.len = hlen + firstlen;
ip->ip_len = htons((u_short)m0->m_pkthdr.len);
ip->ip_off = htons(ip_off | IP_MF);
1994-05-24 10:09:53 +00:00
ip->ip_sum = 0;
if (m0->m_pkthdr.csum_flags & CSUM_IP & ~if_hwassist_flags) {
ip->ip_sum = in_cksum(m0, hlen);
m0->m_pkthdr.csum_flags &= ~CSUM_IP;
}
done:
*m_frag = m0;
return error;
1994-05-24 10:09:53 +00:00
}
void
in_delayed_cksum(struct mbuf *m)
{
struct ip *ip;
uint16_t csum, offset, ip_len;
ip = mtod(m, struct ip *);
offset = ip->ip_hl << 2 ;
ip_len = ntohs(ip->ip_len);
csum = in_cksum_skip(m, ip_len, offset);
if (m->m_pkthdr.csum_flags & CSUM_UDP && csum == 0)
csum = 0xffff;
offset += m->m_pkthdr.csum_data; /* checksum offset */
/* find the mbuf in the chain where the checksum starts*/
while ((m != NULL) && (offset >= m->m_len)) {
offset -= m->m_len;
m = m->m_next;
}
KASSERT(m != NULL, ("in_delayed_cksum: checksum outside mbuf chain."));
KASSERT(offset + sizeof(u_short) <= m->m_len, ("in_delayed_cksum: checksum split between mbufs."));
*(u_short *)(m->m_data + offset) = csum;
}
1994-05-24 10:09:53 +00:00
/*
* IP socket option processing.
*/
int
ip_ctloutput(struct socket *so, struct sockopt *sopt)
1994-05-24 10:09:53 +00:00
{
struct inpcb *inp = sotoinpcb(so);
int error, optval;
#ifdef RSS
uint32_t rss_bucket;
int retval;
#endif
1994-05-24 10:09:53 +00:00
error = optval = 0;
if (sopt->sopt_level != IPPROTO_IP) {
error = EINVAL;
if (sopt->sopt_level == SOL_SOCKET &&
sopt->sopt_dir == SOPT_SET) {
switch (sopt->sopt_name) {
case SO_REUSEADDR:
INP_WLOCK(inp);
if ((so->so_options & SO_REUSEADDR) != 0)
inp->inp_flags2 |= INP_REUSEADDR;
else
inp->inp_flags2 &= ~INP_REUSEADDR;
INP_WUNLOCK(inp);
error = 0;
break;
case SO_REUSEPORT:
INP_WLOCK(inp);
if ((so->so_options & SO_REUSEPORT) != 0)
inp->inp_flags2 |= INP_REUSEPORT;
else
inp->inp_flags2 &= ~INP_REUSEPORT;
INP_WUNLOCK(inp);
error = 0;
break;
case SO_SETFIB:
INP_WLOCK(inp);
inp->inp_inc.inc_fibnum = so->so_fibnum;
INP_WUNLOCK(inp);
error = 0;
break;
default:
break;
}
}
return (error);
}
1994-05-24 10:09:53 +00:00
switch (sopt->sopt_dir) {
case SOPT_SET:
switch (sopt->sopt_name) {
1994-05-24 10:09:53 +00:00
case IP_OPTIONS:
#ifdef notyet
case IP_RETOPTS:
#endif
{
struct mbuf *m;
if (sopt->sopt_valsize > MLEN) {
error = EMSGSIZE;
break;
}
m = m_get(sopt->sopt_td ? M_WAITOK : M_NOWAIT, MT_DATA);
if (m == NULL) {
error = ENOBUFS;
break;
}
m->m_len = sopt->sopt_valsize;
error = sooptcopyin(sopt, mtod(m, char *), m->m_len,
m->m_len);
if (error) {
m_free(m);
break;
}
INP_WLOCK(inp);
error = ip_pcbopts(inp, sopt->sopt_name, m);
INP_WUNLOCK(inp);
return (error);
}
1994-05-24 10:09:53 +00:00
case IP_BINDANY:
if (sopt->sopt_td != NULL) {
error = priv_check(sopt->sopt_td,
PRIV_NETINET_BINDANY);
if (error)
break;
}
/* FALLTHROUGH */
2014-07-10 03:10:56 +00:00
case IP_BINDMULTI:
#ifdef RSS
case IP_RSS_LISTEN_BUCKET:
#endif
1994-05-24 10:09:53 +00:00
case IP_TOS:
case IP_TTL:
case IP_MINTTL:
1994-05-24 10:09:53 +00:00
case IP_RECVOPTS:
case IP_RECVRETOPTS:
case IP_RECVDSTADDR:
case IP_RECVTTL:
case IP_RECVIF:
case IP_ONESBCAST:
case IP_DONTFRAG:
case IP_RECVTOS:
case IP_RECVFLOWID:
#ifdef RSS
case IP_RECVRSSBUCKETID:
#endif
error = sooptcopyin(sopt, &optval, sizeof optval,
sizeof optval);
if (error)
break;
1994-05-24 10:09:53 +00:00
switch (sopt->sopt_name) {
case IP_TOS:
inp->inp_ip_tos = optval;
break;
1994-05-24 10:09:53 +00:00
case IP_TTL:
inp->inp_ip_ttl = optval;
break;
case IP_MINTTL:
if (optval >= 0 && optval <= MAXTTL)
inp->inp_ip_minttl = optval;
else
error = EINVAL;
break;
#define OPTSET(bit) do { \
INP_WLOCK(inp); \
if (optval) \
inp->inp_flags |= bit; \
else \
inp->inp_flags &= ~bit; \
INP_WUNLOCK(inp); \
} while (0)
1994-05-24 10:09:53 +00:00
2014-07-10 03:10:56 +00:00
#define OPTSET2(bit, val) do { \
INP_WLOCK(inp); \
if (val) \
inp->inp_flags2 |= bit; \
else \
inp->inp_flags2 &= ~bit; \
INP_WUNLOCK(inp); \
} while (0)
case IP_RECVOPTS:
OPTSET(INP_RECVOPTS);
break;
1994-05-24 10:09:53 +00:00
case IP_RECVRETOPTS:
OPTSET(INP_RECVRETOPTS);
break;
1994-05-24 10:09:53 +00:00
case IP_RECVDSTADDR:
OPTSET(INP_RECVDSTADDR);
break;
case IP_RECVTTL:
OPTSET(INP_RECVTTL);
break;
case IP_RECVIF:
OPTSET(INP_RECVIF);
break;
case IP_ONESBCAST:
OPTSET(INP_ONESBCAST);
break;
case IP_DONTFRAG:
OPTSET(INP_DONTFRAG);
break;
case IP_BINDANY:
OPTSET(INP_BINDANY);
break;
case IP_RECVTOS:
OPTSET(INP_RECVTOS);
break;
2014-07-10 03:10:56 +00:00
case IP_BINDMULTI:
OPTSET2(INP_BINDMULTI, optval);
break;
case IP_RECVFLOWID:
OPTSET2(INP_RECVFLOWID, optval);
break;
2014-07-10 03:10:56 +00:00
#ifdef RSS
case IP_RSS_LISTEN_BUCKET:
if ((optval >= 0) &&
(optval < rss_getnumbuckets())) {
inp->inp_rss_listen_bucket = optval;
OPTSET2(INP_RSS_BUCKET_SET, 1);
} else {
error = EINVAL;
}
break;
case IP_RECVRSSBUCKETID:
OPTSET2(INP_RECVRSSBUCKETID, optval);
break;
2014-07-10 03:10:56 +00:00
#endif
1994-05-24 10:09:53 +00:00
}
break;
#undef OPTSET
2014-07-10 03:10:56 +00:00
#undef OPTSET2
1994-05-24 10:09:53 +00:00
Import rewrite of IPv4 socket multicast layer to support source-specific and protocol-independent host mode multicast. The code is written to accomodate IPv6, IGMPv3 and MLDv2 with only a little additional work. This change only pertains to FreeBSD's use as a multicast end-station and does not concern multicast routing; for an IGMPv3/MLDv2 router implementation, consider the XORP project. The work is based on Wilbert de Graaf's IGMPv3 code drop for FreeBSD 4.6, which is available at: http://www.kloosterhof.com/wilbert/igmpv3.html Summary * IPv4 multicast socket processing is now moved out of ip_output.c into a new module, in_mcast.c. * The in_mcast.c module implements the IPv4 legacy any-source API in terms of the protocol-independent source-specific API. * Source filters are lazy allocated as the common case does not use them. They are part of per inpcb state and are covered by the inpcb lock. * struct ip_mreqn is now supported to allow applications to specify multicast joins by interface index in the legacy IPv4 any-source API. * In UDP, an incoming multicast datagram only requires that the source port matches the 4-tuple if the socket was already bound by source port. An unbound socket SHOULD be able to receive multicasts sent from an ephemeral source port. * The UDP socket multicast filter mode defaults to exclusive, that is, sources present in the per-socket list will be blocked from delivery. * The RFC 3678 userland functions have been added to libc: setsourcefilter, getsourcefilter, setipv4sourcefilter, getipv4sourcefilter. * Definitions for IGMPv3 are merged but not yet used. * struct sockaddr_storage is now referenced from <netinet/in.h>. It is therefore defined there if not already declared in the same way as for the C99 types. * The RFC 1724 hack (specify 0.0.0.0/8 addresses to IP_MULTICAST_IF which are then interpreted as interface indexes) is now deprecated. * A patch for the Rhyolite.com routed in the FreeBSD base system is available in the -net archives. This only affects individuals running RIPv1 or RIPv2 via point-to-point and/or unnumbered interfaces. * Make IPv6 detach path similar to IPv4's in code flow; functionally same. * Bump __FreeBSD_version to 700048; see UPDATING. This work was financially supported by another FreeBSD committer. Obtained from: p4://bms_netdev Submitted by: Wilbert de Graaf (original work) Reviewed by: rwatson (locking), silence from fenner, net@ (but with encouragement)
2007-06-12 16:24:56 +00:00
/*
* Multicast socket options are processed by the in_mcast
* module.
*/
1994-05-24 10:09:53 +00:00
case IP_MULTICAST_IF:
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_MULTICAST_VIF:
1994-05-24 10:09:53 +00:00
case IP_MULTICAST_TTL:
case IP_MULTICAST_LOOP:
case IP_ADD_MEMBERSHIP:
case IP_DROP_MEMBERSHIP:
Import rewrite of IPv4 socket multicast layer to support source-specific and protocol-independent host mode multicast. The code is written to accomodate IPv6, IGMPv3 and MLDv2 with only a little additional work. This change only pertains to FreeBSD's use as a multicast end-station and does not concern multicast routing; for an IGMPv3/MLDv2 router implementation, consider the XORP project. The work is based on Wilbert de Graaf's IGMPv3 code drop for FreeBSD 4.6, which is available at: http://www.kloosterhof.com/wilbert/igmpv3.html Summary * IPv4 multicast socket processing is now moved out of ip_output.c into a new module, in_mcast.c. * The in_mcast.c module implements the IPv4 legacy any-source API in terms of the protocol-independent source-specific API. * Source filters are lazy allocated as the common case does not use them. They are part of per inpcb state and are covered by the inpcb lock. * struct ip_mreqn is now supported to allow applications to specify multicast joins by interface index in the legacy IPv4 any-source API. * In UDP, an incoming multicast datagram only requires that the source port matches the 4-tuple if the socket was already bound by source port. An unbound socket SHOULD be able to receive multicasts sent from an ephemeral source port. * The UDP socket multicast filter mode defaults to exclusive, that is, sources present in the per-socket list will be blocked from delivery. * The RFC 3678 userland functions have been added to libc: setsourcefilter, getsourcefilter, setipv4sourcefilter, getipv4sourcefilter. * Definitions for IGMPv3 are merged but not yet used. * struct sockaddr_storage is now referenced from <netinet/in.h>. It is therefore defined there if not already declared in the same way as for the C99 types. * The RFC 1724 hack (specify 0.0.0.0/8 addresses to IP_MULTICAST_IF which are then interpreted as interface indexes) is now deprecated. * A patch for the Rhyolite.com routed in the FreeBSD base system is available in the -net archives. This only affects individuals running RIPv1 or RIPv2 via point-to-point and/or unnumbered interfaces. * Make IPv6 detach path similar to IPv4's in code flow; functionally same. * Bump __FreeBSD_version to 700048; see UPDATING. This work was financially supported by another FreeBSD committer. Obtained from: p4://bms_netdev Submitted by: Wilbert de Graaf (original work) Reviewed by: rwatson (locking), silence from fenner, net@ (but with encouragement)
2007-06-12 16:24:56 +00:00
case IP_ADD_SOURCE_MEMBERSHIP:
case IP_DROP_SOURCE_MEMBERSHIP:
case IP_BLOCK_SOURCE:
case IP_UNBLOCK_SOURCE:
case IP_MSFILTER:
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
error = inp_setmoptions(inp, sopt);
1994-05-24 10:09:53 +00:00
break;
case IP_PORTRANGE:
error = sooptcopyin(sopt, &optval, sizeof optval,
sizeof optval);
if (error)
break;
INP_WLOCK(inp);
switch (optval) {
case IP_PORTRANGE_DEFAULT:
inp->inp_flags &= ~(INP_LOWPORT);
inp->inp_flags &= ~(INP_HIGHPORT);
break;
case IP_PORTRANGE_HIGH:
inp->inp_flags &= ~(INP_LOWPORT);
inp->inp_flags |= INP_HIGHPORT;
break;
case IP_PORTRANGE_LOW:
inp->inp_flags &= ~(INP_HIGHPORT);
inp->inp_flags |= INP_LOWPORT;
break;
default:
error = EINVAL;
break;
}
INP_WUNLOCK(inp);
break;
#ifdef IPSEC
case IP_IPSEC_POLICY:
{
caddr_t req;
struct mbuf *m;
if ((error = soopt_getm(sopt, &m)) != 0) /* XXX */
break;
if ((error = soopt_mcopyin(sopt, m)) != 0) /* XXX */
break;
req = mtod(m, caddr_t);
Try to remove/assimilate as much of formerly IPv4/6 specific (duplicate) code in sys/netipsec/ipsec.c and fold it into common, INET/6 independent functions. The file local functions ipsec4_setspidx_inpcb() and ipsec6_setspidx_inpcb() were 1:1 identical after the change in r186528. Rename to ipsec_setspidx_inpcb() and remove the duplicate. Public functions ipsec[46]_get_policy() were 1:1 identical. Remove one copy and merge in the factored out code from ipsec_get_policy() into the other. The public function left is now called ipsec_get_policy() and callers were adapted. Public functions ipsec[46]_set_policy() were 1:1 identical. Rename file local ipsec_set_policy() function to ipsec_set_policy_internal(). Remove one copy of the public functions, rename the other to ipsec_set_policy() and adapt callers. Public functions ipsec[46]_hdrsiz() were logically identical (ignoring one questionable assert in the v6 version). Rename the file local ipsec_hdrsiz() to ipsec_hdrsiz_internal(), the public function to ipsec_hdrsiz(), remove the duplicate copy and adapt the callers. The v6 version had been unused anyway. Cleanup comments. Public functions ipsec[46]_in_reject() were logically identical apart from statistics. Move the common code into a file local ipsec46_in_reject() leaving vimage+statistics in small AF specific wrapper functions. Note: unfortunately we already have a public ipsec_in_reject(). Reviewed by: sam Discussed with: rwatson (renaming to *_internal) MFC after: 26 days X-MFC: keep wrapper functions for public symbols?
2009-02-08 09:27:07 +00:00
error = ipsec_set_policy(inp, sopt->sopt_name, req,
m->m_len, (sopt->sopt_td != NULL) ?
sopt->sopt_td->td_ucred : NULL);
m_freem(m);
break;
}
#endif /* IPSEC */
1994-05-24 10:09:53 +00:00
default:
error = ENOPROTOOPT;
break;
}
break;
case SOPT_GET:
switch (sopt->sopt_name) {
1994-05-24 10:09:53 +00:00
case IP_OPTIONS:
case IP_RETOPTS:
if (inp->inp_options)
error = sooptcopyout(sopt,
mtod(inp->inp_options,
char *),
inp->inp_options->m_len);
else
sopt->sopt_valsize = 0;
1994-05-24 10:09:53 +00:00
break;
case IP_TOS:
case IP_TTL:
case IP_MINTTL:
1994-05-24 10:09:53 +00:00
case IP_RECVOPTS:
case IP_RECVRETOPTS:
case IP_RECVDSTADDR:
case IP_RECVTTL:
case IP_RECVIF:
case IP_PORTRANGE:
case IP_ONESBCAST:
case IP_DONTFRAG:
case IP_BINDANY:
case IP_RECVTOS:
2014-07-10 03:10:56 +00:00
case IP_BINDMULTI:
case IP_FLOWID:
case IP_FLOWTYPE:
case IP_RECVFLOWID:
2014-07-10 03:10:56 +00:00
#ifdef RSS
case IP_RSSBUCKETID:
case IP_RECVRSSBUCKETID:
2014-07-10 03:10:56 +00:00
#endif
switch (sopt->sopt_name) {
1994-05-24 10:09:53 +00:00
case IP_TOS:
optval = inp->inp_ip_tos;
1994-05-24 10:09:53 +00:00
break;
case IP_TTL:
optval = inp->inp_ip_ttl;
1994-05-24 10:09:53 +00:00
break;
case IP_MINTTL:
optval = inp->inp_ip_minttl;
break;
1994-05-24 10:09:53 +00:00
#define OPTBIT(bit) (inp->inp_flags & bit ? 1 : 0)
2014-07-10 03:10:56 +00:00
#define OPTBIT2(bit) (inp->inp_flags2 & bit ? 1 : 0)
1994-05-24 10:09:53 +00:00
case IP_RECVOPTS:
optval = OPTBIT(INP_RECVOPTS);
break;
case IP_RECVRETOPTS:
optval = OPTBIT(INP_RECVRETOPTS);
break;
case IP_RECVDSTADDR:
optval = OPTBIT(INP_RECVDSTADDR);
break;
case IP_RECVTTL:
optval = OPTBIT(INP_RECVTTL);
break;
case IP_RECVIF:
optval = OPTBIT(INP_RECVIF);
break;
case IP_PORTRANGE:
if (inp->inp_flags & INP_HIGHPORT)
optval = IP_PORTRANGE_HIGH;
else if (inp->inp_flags & INP_LOWPORT)
optval = IP_PORTRANGE_LOW;
else
optval = 0;
break;
case IP_ONESBCAST:
optval = OPTBIT(INP_ONESBCAST);
break;
case IP_DONTFRAG:
optval = OPTBIT(INP_DONTFRAG);
break;
case IP_BINDANY:
optval = OPTBIT(INP_BINDANY);
break;
case IP_RECVTOS:
optval = OPTBIT(INP_RECVTOS);
break;
case IP_FLOWID:
optval = inp->inp_flowid;
break;
case IP_FLOWTYPE:
optval = inp->inp_flowtype;
break;
case IP_RECVFLOWID:
optval = OPTBIT2(INP_RECVFLOWID);
break;
#ifdef RSS
case IP_RSSBUCKETID:
retval = rss_hash2bucket(inp->inp_flowid,
inp->inp_flowtype,
&rss_bucket);
if (retval == 0)
optval = rss_bucket;
else
error = EINVAL;
break;
case IP_RECVRSSBUCKETID:
optval = OPTBIT2(INP_RECVRSSBUCKETID);
break;
#endif
2014-07-10 03:10:56 +00:00
case IP_BINDMULTI:
optval = OPTBIT2(INP_BINDMULTI);
break;
1994-05-24 10:09:53 +00:00
}
error = sooptcopyout(sopt, &optval, sizeof optval);
1994-05-24 10:09:53 +00:00
break;
Import rewrite of IPv4 socket multicast layer to support source-specific and protocol-independent host mode multicast. The code is written to accomodate IPv6, IGMPv3 and MLDv2 with only a little additional work. This change only pertains to FreeBSD's use as a multicast end-station and does not concern multicast routing; for an IGMPv3/MLDv2 router implementation, consider the XORP project. The work is based on Wilbert de Graaf's IGMPv3 code drop for FreeBSD 4.6, which is available at: http://www.kloosterhof.com/wilbert/igmpv3.html Summary * IPv4 multicast socket processing is now moved out of ip_output.c into a new module, in_mcast.c. * The in_mcast.c module implements the IPv4 legacy any-source API in terms of the protocol-independent source-specific API. * Source filters are lazy allocated as the common case does not use them. They are part of per inpcb state and are covered by the inpcb lock. * struct ip_mreqn is now supported to allow applications to specify multicast joins by interface index in the legacy IPv4 any-source API. * In UDP, an incoming multicast datagram only requires that the source port matches the 4-tuple if the socket was already bound by source port. An unbound socket SHOULD be able to receive multicasts sent from an ephemeral source port. * The UDP socket multicast filter mode defaults to exclusive, that is, sources present in the per-socket list will be blocked from delivery. * The RFC 3678 userland functions have been added to libc: setsourcefilter, getsourcefilter, setipv4sourcefilter, getipv4sourcefilter. * Definitions for IGMPv3 are merged but not yet used. * struct sockaddr_storage is now referenced from <netinet/in.h>. It is therefore defined there if not already declared in the same way as for the C99 types. * The RFC 1724 hack (specify 0.0.0.0/8 addresses to IP_MULTICAST_IF which are then interpreted as interface indexes) is now deprecated. * A patch for the Rhyolite.com routed in the FreeBSD base system is available in the -net archives. This only affects individuals running RIPv1 or RIPv2 via point-to-point and/or unnumbered interfaces. * Make IPv6 detach path similar to IPv4's in code flow; functionally same. * Bump __FreeBSD_version to 700048; see UPDATING. This work was financially supported by another FreeBSD committer. Obtained from: p4://bms_netdev Submitted by: Wilbert de Graaf (original work) Reviewed by: rwatson (locking), silence from fenner, net@ (but with encouragement)
2007-06-12 16:24:56 +00:00
/*
* Multicast socket options are processed by the in_mcast
* module.
*/
1994-05-24 10:09:53 +00:00
case IP_MULTICAST_IF:
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_MULTICAST_VIF:
1994-05-24 10:09:53 +00:00
case IP_MULTICAST_TTL:
case IP_MULTICAST_LOOP:
Import rewrite of IPv4 socket multicast layer to support source-specific and protocol-independent host mode multicast. The code is written to accomodate IPv6, IGMPv3 and MLDv2 with only a little additional work. This change only pertains to FreeBSD's use as a multicast end-station and does not concern multicast routing; for an IGMPv3/MLDv2 router implementation, consider the XORP project. The work is based on Wilbert de Graaf's IGMPv3 code drop for FreeBSD 4.6, which is available at: http://www.kloosterhof.com/wilbert/igmpv3.html Summary * IPv4 multicast socket processing is now moved out of ip_output.c into a new module, in_mcast.c. * The in_mcast.c module implements the IPv4 legacy any-source API in terms of the protocol-independent source-specific API. * Source filters are lazy allocated as the common case does not use them. They are part of per inpcb state and are covered by the inpcb lock. * struct ip_mreqn is now supported to allow applications to specify multicast joins by interface index in the legacy IPv4 any-source API. * In UDP, an incoming multicast datagram only requires that the source port matches the 4-tuple if the socket was already bound by source port. An unbound socket SHOULD be able to receive multicasts sent from an ephemeral source port. * The UDP socket multicast filter mode defaults to exclusive, that is, sources present in the per-socket list will be blocked from delivery. * The RFC 3678 userland functions have been added to libc: setsourcefilter, getsourcefilter, setipv4sourcefilter, getipv4sourcefilter. * Definitions for IGMPv3 are merged but not yet used. * struct sockaddr_storage is now referenced from <netinet/in.h>. It is therefore defined there if not already declared in the same way as for the C99 types. * The RFC 1724 hack (specify 0.0.0.0/8 addresses to IP_MULTICAST_IF which are then interpreted as interface indexes) is now deprecated. * A patch for the Rhyolite.com routed in the FreeBSD base system is available in the -net archives. This only affects individuals running RIPv1 or RIPv2 via point-to-point and/or unnumbered interfaces. * Make IPv6 detach path similar to IPv4's in code flow; functionally same. * Bump __FreeBSD_version to 700048; see UPDATING. This work was financially supported by another FreeBSD committer. Obtained from: p4://bms_netdev Submitted by: Wilbert de Graaf (original work) Reviewed by: rwatson (locking), silence from fenner, net@ (but with encouragement)
2007-06-12 16:24:56 +00:00
case IP_MSFILTER:
error = inp_getmoptions(inp, sopt);
break;
#ifdef IPSEC
case IP_IPSEC_POLICY:
{
struct mbuf *m = NULL;
caddr_t req = NULL;
size_t len = 0;
if (m != NULL) {
req = mtod(m, caddr_t);
len = m->m_len;
}
Try to remove/assimilate as much of formerly IPv4/6 specific (duplicate) code in sys/netipsec/ipsec.c and fold it into common, INET/6 independent functions. The file local functions ipsec4_setspidx_inpcb() and ipsec6_setspidx_inpcb() were 1:1 identical after the change in r186528. Rename to ipsec_setspidx_inpcb() and remove the duplicate. Public functions ipsec[46]_get_policy() were 1:1 identical. Remove one copy and merge in the factored out code from ipsec_get_policy() into the other. The public function left is now called ipsec_get_policy() and callers were adapted. Public functions ipsec[46]_set_policy() were 1:1 identical. Rename file local ipsec_set_policy() function to ipsec_set_policy_internal(). Remove one copy of the public functions, rename the other to ipsec_set_policy() and adapt callers. Public functions ipsec[46]_hdrsiz() were logically identical (ignoring one questionable assert in the v6 version). Rename the file local ipsec_hdrsiz() to ipsec_hdrsiz_internal(), the public function to ipsec_hdrsiz(), remove the duplicate copy and adapt the callers. The v6 version had been unused anyway. Cleanup comments. Public functions ipsec[46]_in_reject() were logically identical apart from statistics. Move the common code into a file local ipsec46_in_reject() leaving vimage+statistics in small AF specific wrapper functions. Note: unfortunately we already have a public ipsec_in_reject(). Reviewed by: sam Discussed with: rwatson (renaming to *_internal) MFC after: 26 days X-MFC: keep wrapper functions for public symbols?
2009-02-08 09:27:07 +00:00
error = ipsec_get_policy(sotoinpcb(so), req, len, &m);
if (error == 0)
error = soopt_mcopyout(sopt, m); /* XXX */
if (error == 0)
m_freem(m);
break;
}
#endif /* IPSEC */
1994-05-24 10:09:53 +00:00
default:
error = ENOPROTOOPT;
break;
}
break;
}
return (error);
}
/*
* Routine called from ip_output() to loop back a copy of an IP multicast
* packet to the input queue of a specified interface. Note that this
* calls the output routine of the loopback "driver", but with an interface
* pointer that might NOT be a loopback interface -- evil, but easier than
* replicating that code here.
1994-05-24 10:09:53 +00:00
*/
static void
ip_mloopback(struct ifnet *ifp, const struct mbuf *m, int hlen)
1994-05-24 10:09:53 +00:00
{
struct ip *ip;
1994-05-24 10:09:53 +00:00
struct mbuf *copym;
/*
* Make a deep copy of the packet because we're going to
* modify the pack in order to generate checksums.
*/
copym = m_dup(m, M_NOWAIT);
if (copym != NULL && (!M_WRITABLE(copym) || copym->m_len < hlen))
copym = m_pullup(copym, hlen);
1994-05-24 10:09:53 +00:00
if (copym != NULL) {
/* If needed, compute the checksum and mark it as valid. */
if (copym->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
in_delayed_cksum(copym);
copym->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
copym->m_pkthdr.csum_flags |=
CSUM_DATA_VALID | CSUM_PSEUDO_HDR;
copym->m_pkthdr.csum_data = 0xffff;
}
1994-05-24 10:09:53 +00:00
/*
* We don't bother to fragment if the IP length is greater
* than the interface's MTU. Can this possibly matter?
*/
ip = mtod(copym, struct ip *);
1994-05-24 10:09:53 +00:00
ip->ip_sum = 0;
ip->ip_sum = in_cksum(copym, hlen);
if_simloop(ifp, copym, AF_INET, 0);
1994-05-24 10:09:53 +00:00
}
}