freebsd-dev/sys/netinet/in_gif.c

471 lines
11 KiB
C
Raw Normal View History

/* $KAME: in_gif.c,v 1.54 2001/05/14 14:02:16 itojun Exp $ */
/*-
* Copyright (C) 1995, 1996, 1997, and 1998 WIDE Project.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the project 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 PROJECT 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 PROJECT 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.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_mrouting.h"
#include "opt_inet.h"
#include "opt_inet6.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/socket.h>
#include <sys/sockio.h>
#include <sys/mbuf.h>
#include <sys/errno.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/protosw.h>
#include <sys/malloc.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/route.h>
#include <net/vnet.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/in_gif.h>
#include <netinet/in_var.h>
#include <netinet/ip_encap.h>
#include <netinet/ip_ecn.h>
#ifdef INET6
#include <netinet/ip6.h>
#endif
#ifdef MROUTING
#include <netinet/ip_mroute.h>
#endif /* MROUTING */
#include <net/if_gif.h>
static int gif_validate4(const struct ip *, struct gif_softc *,
struct ifnet *);
extern struct domain inetdomain;
struct protosw in_gif_protosw = {
.pr_type = SOCK_RAW,
.pr_domain = &inetdomain,
.pr_protocol = 0/* IPPROTO_IPV[46] */,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = in_gif_input,
.pr_output = (pr_output_t*)rip_output,
.pr_ctloutput = rip_ctloutput,
.pr_usrreqs = &rip_usrreqs
};
VNET_DEFINE(int, ip_gif_ttl) = GIF_TTL;
#define V_ip_gif_ttl VNET(ip_gif_ttl)
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_INT(_net_inet_ip, IPCTL_GIF_TTL, gifttl, CTLFLAG_RW,
&VNET_NAME(ip_gif_ttl), 0, "");
int
in_gif_output(struct ifnet *ifp, int family, struct mbuf *m)
{
struct gif_softc *sc = ifp->if_softc;
struct sockaddr_in *dst = (struct sockaddr_in *)&sc->gif_ro.ro_dst;
struct sockaddr_in *sin_src = (struct sockaddr_in *)sc->gif_psrc;
struct sockaddr_in *sin_dst = (struct sockaddr_in *)sc->gif_pdst;
struct ip iphdr; /* capsule IP header, host byte ordered */
struct etherip_header eiphdr;
int error, len, proto;
u_int8_t tos;
GIF_LOCK_ASSERT(sc);
if (sin_src == NULL || sin_dst == NULL ||
sin_src->sin_family != AF_INET ||
sin_dst->sin_family != AF_INET) {
m_freem(m);
return EAFNOSUPPORT;
}
switch (family) {
#ifdef INET
case AF_INET:
{
struct ip *ip;
proto = IPPROTO_IPV4;
if (m->m_len < sizeof(*ip)) {
m = m_pullup(m, sizeof(*ip));
if (!m)
return ENOBUFS;
}
ip = mtod(m, struct ip *);
tos = ip->ip_tos;
break;
}
#endif /* INET */
#ifdef INET6
case AF_INET6:
{
struct ip6_hdr *ip6;
proto = IPPROTO_IPV6;
if (m->m_len < sizeof(*ip6)) {
m = m_pullup(m, sizeof(*ip6));
if (!m)
return ENOBUFS;
}
ip6 = mtod(m, struct ip6_hdr *);
tos = (ntohl(ip6->ip6_flow) >> 20) & 0xff;
break;
}
#endif /* INET6 */
case AF_LINK:
proto = IPPROTO_ETHERIP;
/*
* GIF_SEND_REVETHIP (disabled by default) intentionally
* sends an EtherIP packet with revered version field in
* the header. This is a knob for backward compatibility
* with FreeBSD 7.2R or prior.
*/
if ((sc->gif_options & GIF_SEND_REVETHIP)) {
eiphdr.eip_ver = 0;
eiphdr.eip_resvl = ETHERIP_VERSION;
eiphdr.eip_resvh = 0;
} else {
eiphdr.eip_ver = ETHERIP_VERSION;
eiphdr.eip_resvl = 0;
eiphdr.eip_resvh = 0;
}
/* prepend Ethernet-in-IP header */
M_PREPEND(m, sizeof(struct etherip_header), M_NOWAIT);
if (m && m->m_len < sizeof(struct etherip_header))
m = m_pullup(m, sizeof(struct etherip_header));
if (m == NULL)
return ENOBUFS;
bcopy(&eiphdr, mtod(m, struct etherip_header *),
sizeof(struct etherip_header));
tos = 0;
break;
default:
#ifdef DEBUG
printf("in_gif_output: warning: unknown family %d passed\n",
family);
#endif
m_freem(m);
return EAFNOSUPPORT;
}
bzero(&iphdr, sizeof(iphdr));
iphdr.ip_src = sin_src->sin_addr;
/* bidirectional configured tunnel mode */
if (sin_dst->sin_addr.s_addr != INADDR_ANY)
iphdr.ip_dst = sin_dst->sin_addr;
else {
m_freem(m);
return ENETUNREACH;
}
iphdr.ip_p = proto;
/* version will be set in ip_output() */
iphdr.ip_ttl = V_ip_gif_ttl;
iphdr.ip_len = htons(m->m_pkthdr.len + sizeof(struct ip));
ip_ecn_ingress((ifp->if_flags & IFF_LINK1) ? ECN_ALLOWED : ECN_NOCARE,
&iphdr.ip_tos, &tos);
/* prepend new IP header */
len = sizeof(struct ip);
#ifndef __NO_STRICT_ALIGNMENT
if (family == AF_LINK)
len += ETHERIP_ALIGN;
#endif
M_PREPEND(m, len, M_NOWAIT);
if (m != NULL && m->m_len < len)
m = m_pullup(m, len);
if (m == NULL) {
printf("ENOBUFS in in_gif_output %d\n", __LINE__);
return ENOBUFS;
}
#ifndef __NO_STRICT_ALIGNMENT
if (family == AF_LINK) {
len = mtod(m, vm_offset_t) & 3;
KASSERT(len == 0 || len == ETHERIP_ALIGN,
("in_gif_output: unexpected misalignment"));
m->m_data += len;
m->m_len -= ETHERIP_ALIGN;
}
#endif
bcopy(&iphdr, mtod(m, struct ip *), sizeof(struct ip));
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
M_SETFIB(m, sc->gif_fibnum);
if (dst->sin_family != sin_dst->sin_family ||
dst->sin_addr.s_addr != sin_dst->sin_addr.s_addr) {
/* cache route doesn't match */
bzero(dst, sizeof(*dst));
dst->sin_family = sin_dst->sin_family;
dst->sin_len = sizeof(struct sockaddr_in);
dst->sin_addr = sin_dst->sin_addr;
if (sc->gif_ro.ro_rt) {
RTFREE(sc->gif_ro.ro_rt);
sc->gif_ro.ro_rt = NULL;
}
#if 0
GIF2IFP(sc)->if_mtu = GIF_MTU;
#endif
}
if (sc->gif_ro.ro_rt == NULL) {
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
in_rtalloc_ign(&sc->gif_ro, 0, sc->gif_fibnum);
if (sc->gif_ro.ro_rt == NULL) {
m_freem(m);
return ENETUNREACH;
}
/* if it constitutes infinite encapsulation, punt. */
if (sc->gif_ro.ro_rt->rt_ifp == ifp) {
m_freem(m);
return ENETUNREACH; /* XXX */
}
#if 0
ifp->if_mtu = sc->gif_ro.ro_rt->rt_ifp->if_mtu
- sizeof(struct ip);
#endif
}
m->m_flags &= ~(M_BCAST|M_MCAST);
error = ip_output(m, NULL, &sc->gif_ro, 0, NULL, NULL);
if (!(GIF2IFP(sc)->if_flags & IFF_LINK0) &&
sc->gif_ro.ro_rt != NULL) {
RTFREE(sc->gif_ro.ro_rt);
sc->gif_ro.ro_rt = NULL;
}
return (error);
}
void
in_gif_input(struct mbuf *m, int off)
{
struct ifnet *gifp = NULL;
struct gif_softc *sc;
struct ip *ip;
int af;
u_int8_t otos;
int proto;
ip = mtod(m, struct ip *);
proto = ip->ip_p;
sc = (struct gif_softc *)encap_getarg(m);
if (sc == NULL) {
m_freem(m);
KMOD_IPSTAT_INC(ips_nogif);
return;
}
gifp = GIF2IFP(sc);
if (gifp == NULL || (gifp->if_flags & IFF_UP) == 0) {
m_freem(m);
KMOD_IPSTAT_INC(ips_nogif);
return;
}
otos = ip->ip_tos;
m_adj(m, off);
switch (proto) {
#ifdef INET
case IPPROTO_IPV4:
{
struct ip *ip;
af = AF_INET;
if (m->m_len < sizeof(*ip)) {
m = m_pullup(m, sizeof(*ip));
if (!m)
return;
}
ip = mtod(m, struct ip *);
if (ip_ecn_egress((gifp->if_flags & IFF_LINK1) ?
ECN_ALLOWED : ECN_NOCARE,
&otos, &ip->ip_tos) == 0) {
m_freem(m);
return;
}
break;
}
#endif
#ifdef INET6
case IPPROTO_IPV6:
{
struct ip6_hdr *ip6;
u_int8_t itos, oitos;
af = AF_INET6;
if (m->m_len < sizeof(*ip6)) {
m = m_pullup(m, sizeof(*ip6));
if (!m)
return;
}
ip6 = mtod(m, struct ip6_hdr *);
itos = oitos = (ntohl(ip6->ip6_flow) >> 20) & 0xff;
if (ip_ecn_egress((gifp->if_flags & IFF_LINK1) ?
ECN_ALLOWED : ECN_NOCARE,
&otos, &itos) == 0) {
m_freem(m);
return;
}
if (itos != oitos) {
ip6->ip6_flow &= ~htonl(0xff << 20);
ip6->ip6_flow |= htonl((u_int32_t)itos << 20);
}
break;
}
#endif /* INET6 */
case IPPROTO_ETHERIP:
af = AF_LINK;
break;
default:
KMOD_IPSTAT_INC(ips_nogif);
m_freem(m);
return;
}
gif_input(m, af, gifp);
return;
}
/*
* validate outer address.
*/
static int
gif_validate4(const struct ip *ip, struct gif_softc *sc, struct ifnet *ifp)
{
struct sockaddr_in *src, *dst;
struct in_ifaddr *ia4;
src = (struct sockaddr_in *)sc->gif_psrc;
dst = (struct sockaddr_in *)sc->gif_pdst;
/* check for address match */
if (src->sin_addr.s_addr != ip->ip_dst.s_addr ||
dst->sin_addr.s_addr != ip->ip_src.s_addr)
return 0;
/* martian filters on outer source - NOT done in ip_input! */
if (IN_MULTICAST(ntohl(ip->ip_src.s_addr)))
return 0;
switch ((ntohl(ip->ip_src.s_addr) & 0xff000000) >> 24) {
case 0: case 127: case 255:
return 0;
}
/* reject packets with broadcast on source */
/* XXXRW: should use hash lists? */
IN_IFADDR_RLOCK();
TAILQ_FOREACH(ia4, &V_in_ifaddrhead, ia_link) {
if ((ia4->ia_ifa.ifa_ifp->if_flags & IFF_BROADCAST) == 0)
continue;
if (ip->ip_src.s_addr == ia4->ia_broadaddr.sin_addr.s_addr) {
IN_IFADDR_RUNLOCK();
return 0;
}
}
IN_IFADDR_RUNLOCK();
/* ingress filters on outer source */
if ((GIF2IFP(sc)->if_flags & IFF_LINK2) == 0 && ifp) {
struct sockaddr_in sin;
struct rtentry *rt;
bzero(&sin, sizeof(sin));
sin.sin_family = AF_INET;
sin.sin_len = sizeof(struct sockaddr_in);
sin.sin_addr = ip->ip_src;
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
/* XXX MRT check for the interface we would use on output */
rt = in_rtalloc1((struct sockaddr *)&sin, 0,
0UL, sc->gif_fibnum);
if (!rt || rt->rt_ifp != ifp) {
#if 0
log(LOG_WARNING, "%s: packet from 0x%x dropped "
"due to ingress filter\n", if_name(GIF2IFP(sc)),
(u_int32_t)ntohl(sin.sin_addr.s_addr));
#endif
if (rt)
RTFREE_LOCKED(rt);
return 0;
}
RTFREE_LOCKED(rt);
}
return 32 * 2;
}
/*
* we know that we are in IFF_UP, outer address available, and outer family
* matched the physical addr family. see gif_encapcheck().
*/
int
gif_encapcheck4(const struct mbuf *m, int off, int proto, void *arg)
{
struct ip ip;
struct gif_softc *sc;
struct ifnet *ifp;
/* sanity check done in caller */
sc = (struct gif_softc *)arg;
/* LINTED const cast */
m_copydata(m, 0, sizeof(ip), (caddr_t)&ip);
ifp = ((m->m_flags & M_PKTHDR) != 0) ? m->m_pkthdr.rcvif : NULL;
return gif_validate4(&ip, sc, ifp);
}
int
in_gif_attach(struct gif_softc *sc)
{
sc->encap_cookie4 = encap_attach_func(AF_INET, -1, gif_encapcheck,
&in_gif_protosw, sc);
if (sc->encap_cookie4 == NULL)
return EEXIST;
return 0;
}
int
in_gif_detach(struct gif_softc *sc)
{
int error;
error = encap_detach(sc->encap_cookie4);
if (error == 0)
sc->encap_cookie4 = NULL;
return error;
}