freebsd-skq/sys/net/if_gif.c

1024 lines
23 KiB
C
Raw Normal View History

/* $FreeBSD$ */
/* $KAME: if_gif.c,v 1.87 2001/10/19 08:50:27 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 "opt_inet.h"
#include "opt_inet6.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
2004-05-30 20:27:19 +00:00
#include <sys/module.h>
#include <sys/socket.h>
#include <sys/sockio.h>
#include <sys/errno.h>
#include <sys/time.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/priv.h>
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
#include <sys/proc.h>
#include <sys/protosw.h>
#include <sys/conf.h>
#include <machine/cpu.h>
#include <net/if.h>
#include <net/if_clone.h>
#include <net/if_types.h>
#include <net/netisr.h>
#include <net/route.h>
#include <net/bpf.h>
#include <net/vnet.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#ifdef INET
#include <netinet/in_var.h>
#include <netinet/in_gif.h>
#include <netinet/ip_var.h>
#endif /* INET */
#ifdef INET6
#ifndef INET
#include <netinet/in.h>
#endif
#include <netinet6/in6_var.h>
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet6/scope6_var.h>
#include <netinet6/in6_gif.h>
#include <netinet6/ip6protosw.h>
#endif /* INET6 */
#include <netinet/ip_encap.h>
#include <net/ethernet.h>
#include <net/if_bridgevar.h>
#include <net/if_gif.h>
#include <security/mac/mac_framework.h>
#define GIFNAME "gif"
/*
* gif_mtx protects the global gif_softc_list.
*/
static struct mtx gif_mtx;
static MALLOC_DEFINE(M_GIF, "gif", "Generic Tunnel Interface");
static VNET_DEFINE(LIST_HEAD(, gif_softc), gif_softc_list);
#define V_gif_softc_list VNET(gif_softc_list)
Conditionally compile out V_ globals while instantiating the appropriate container structures, depending on VIMAGE_GLOBALS compile time option. Make VIMAGE_GLOBALS a new compile-time option, which by default will not be defined, resulting in instatiations of global variables selected for V_irtualization (enclosed in #ifdef VIMAGE_GLOBALS blocks) to be effectively compiled out. Instantiate new global container structures to hold V_irtualized variables: vnet_net_0, vnet_inet_0, vnet_inet6_0, vnet_ipsec_0, vnet_netgraph_0, and vnet_gif_0. Update the VSYM() macro so that depending on VIMAGE_GLOBALS the V_ macros resolve either to the original globals, or to fields inside container structures, i.e. effectively #ifdef VIMAGE_GLOBALS #define V_rt_tables rt_tables #else #define V_rt_tables vnet_net_0._rt_tables #endif Update SYSCTL_V_*() macros to operate either on globals or on fields inside container structs. Extend the internal kldsym() lookups with the ability to resolve selected fields inside the virtualization container structs. This applies only to the fields which are explicitly registered for kldsym() visibility via VNET_MOD_DECLARE() and vnet_mod_register(), currently this is done only in sys/net/if.c. Fix a few broken instances of MODULE_GLOBAL() macro use in SCTP code, and modify the MODULE_GLOBAL() macro to resolve to V_ macros, which in turn result in proper code being generated depending on VIMAGE_GLOBALS. De-virtualize local static variables in sys/contrib/pf/net/pf_subr.c which were prematurely V_irtualized by automated V_ prepending scripts during earlier merging steps. PF virtualization will be done separately, most probably after next PF import. Convert a few variable initializations at instantiation to initialization in init functions, most notably in ipfw. Also convert TUNABLE_INT() initializers for V_ variables to TUNABLE_FETCH_INT() in initializer functions. Discussed at: devsummit Strassburg Reviewed by: bz, julian Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-12-10 23:12:39 +00:00
2001-09-26 23:50:17 +00:00
void (*ng_gif_input_p)(struct ifnet *ifp, struct mbuf **mp, int af);
void (*ng_gif_input_orphan_p)(struct ifnet *ifp, struct mbuf *m, int af);
void (*ng_gif_attach_p)(struct ifnet *ifp);
void (*ng_gif_detach_p)(struct ifnet *ifp);
static void gif_start(struct ifnet *);
static int gif_clone_create(struct if_clone *, int, caddr_t);
static void gif_clone_destroy(struct ifnet *);
Introduce vnet module registration / initialization framework with dependency tracking and ordering enforcement. With this change, per-vnet initialization functions introduced with r190787 are no longer directly called from traditional initialization functions (which cc in most cases inlined to pre-r190787 code), but are instead registered via the vnet framework first, and are invoked only after all prerequisite modules have been initialized. In the long run, this framework should allow us to both initialize and dismantle multiple vnet instances in a correct order. The problem this change aims to solve is how to replay the initialization sequence of various network stack components, which have been traditionally triggered via different mechanisms (SYSINIT, protosw). Note that this initialization sequence was and still can be subtly different depending on whether certain pieces of code have been statically compiled into the kernel, loaded as modules by boot loader, or kldloaded at run time. The approach is simple - we record the initialization sequence established by the traditional mechanisms whenever vnet_mod_register() is called for a particular vnet module. The vnet_mod_register_multi() variant allows a single initializer function to be registered multiple times but with different arguments - currently this is only used in kern/uipc_domain.c by net_add_domain() with different struct domain * as arguments, which allows for protosw-registered initialization routines to be invoked in a correct order by the new vnet initialization framework. For the purpose of identifying vnet modules, each vnet module has to have a unique ID, which is statically assigned in sys/vimage.h. Dynamic assignment of vnet module IDs is not supported yet. A vnet module may specify a single prerequisite module at registration time by filling in the vmi_dependson field of its vnet_modinfo struct with the ID of the module it depends on. Unless specified otherwise, all vnet modules depend on VNET_MOD_NET (container for ifnet list head, rt_tables etc.), which thus has to and will always be initialized first. The framework will panic if it detects any unresolved dependencies before completing system initialization. Detection of unresolved dependencies for vnet modules registered after boot (kldloaded modules) is not provided. Note that the fact that each module can specify only a single prerequisite may become problematic in the long run. In particular, INET6 depends on INET being already instantiated, due to TCP / UDP structures residing in INET container. IPSEC also depends on INET, which will in turn additionally complicate making INET6-only kernel configs a reality. The entire registration framework can be compiled out by turning on the VIMAGE_GLOBALS kernel config option. Reviewed by: bz Approved by: julian (mentor)
2009-04-11 05:58:58 +00:00
IFC_SIMPLE_DECLARE(gif, 0);
2002-03-19 21:54:18 +00:00
static int gifmodevent(module_t, int, void *);
SYSCTL_DECL(_net_link);
SYSCTL_NODE(_net_link, IFT_GIF, gif, CTLFLAG_RW, 0,
"Generic Tunnel Interface");
#ifndef MAX_GIF_NEST
/*
* This macro controls the default upper limitation on nesting of gif tunnels.
* Since, setting a large value to this macro with a careless configuration
* may introduce system crash, we don't allow any nestings by default.
* If you need to configure nested gif tunnels, you can define this macro
* in your kernel configuration file. However, if you do so, please be
* careful to configure the tunnels so that it won't make a loop.
*/
#define MAX_GIF_NEST 1
#endif
static VNET_DEFINE(int, max_gif_nesting) = MAX_GIF_NEST;
#define V_max_gif_nesting VNET(max_gif_nesting)
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_link_gif, OID_AUTO, max_nesting, CTLFLAG_RW,
&VNET_NAME(max_gif_nesting), 0, "Max nested tunnels");
/*
* By default, we disallow creation of multiple tunnels between the same
* pair of addresses. Some applications require this functionality so
* we allow control over this check here.
*/
#ifdef XBONEHACK
static VNET_DEFINE(int, parallel_tunnels) = 1;
#else
static VNET_DEFINE(int, parallel_tunnels) = 0;
#endif
#define V_parallel_tunnels VNET(parallel_tunnels)
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_link_gif, OID_AUTO, parallel_tunnels, CTLFLAG_RW,
&VNET_NAME(parallel_tunnels), 0, "Allow parallel tunnels?");
/* copy from src/sys/net/if_ethersubr.c */
static const u_char etherbroadcastaddr[ETHER_ADDR_LEN] =
{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
#ifndef ETHER_IS_BROADCAST
#define ETHER_IS_BROADCAST(addr) \
(bcmp(etherbroadcastaddr, (addr), ETHER_ADDR_LEN) == 0)
#endif
static int
gif_clone_create(ifc, unit, params)
struct if_clone *ifc;
int unit;
caddr_t params;
{
struct gif_softc *sc;
2004-07-06 03:26:26 +00:00
sc = malloc(sizeof(struct gif_softc), M_GIF, M_WAITOK | M_ZERO);
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
sc->gif_fibnum = curthread->td_proc->p_fibnum;
GIF2IFP(sc) = if_alloc(IFT_GIF);
if (GIF2IFP(sc) == NULL) {
free(sc, M_GIF);
return (ENOSPC);
}
GIF_LOCK_INIT(sc);
GIF2IFP(sc)->if_softc = sc;
if_initname(GIF2IFP(sc), ifc->ifc_name, unit);
sc->encap_cookie4 = sc->encap_cookie6 = NULL;
sc->gif_options = GIF_ACCEPT_REVETHIP;
GIF2IFP(sc)->if_addrlen = 0;
GIF2IFP(sc)->if_mtu = GIF_MTU;
GIF2IFP(sc)->if_flags = IFF_POINTOPOINT | IFF_MULTICAST;
#if 0
/* turn off ingress filter */
GIF2IFP(sc)->if_flags |= IFF_LINK2;
#endif
GIF2IFP(sc)->if_ioctl = gif_ioctl;
GIF2IFP(sc)->if_start = gif_start;
GIF2IFP(sc)->if_output = gif_output;
GIF2IFP(sc)->if_snd.ifq_maxlen = ifqmaxlen;
if_attach(GIF2IFP(sc));
bpfattach(GIF2IFP(sc), DLT_NULL, sizeof(u_int32_t));
2001-09-26 23:50:17 +00:00
if (ng_gif_attach_p != NULL)
(*ng_gif_attach_p)(GIF2IFP(sc));
mtx_lock(&gif_mtx);
LIST_INSERT_HEAD(&V_gif_softc_list, sc, gif_list);
mtx_unlock(&gif_mtx);
return (0);
}
static void
gif_clone_destroy(ifp)
struct ifnet *ifp;
{
#if defined(INET) || defined(INET6)
int err;
#endif
struct gif_softc *sc = ifp->if_softc;
mtx_lock(&gif_mtx);
LIST_REMOVE(sc, gif_list);
mtx_unlock(&gif_mtx);
gif_delete_tunnel(ifp);
#ifdef INET6
if (sc->encap_cookie6 != NULL) {
err = encap_detach(sc->encap_cookie6);
KASSERT(err == 0, ("Unexpected error detaching encap_cookie6"));
}
#endif
#ifdef INET
if (sc->encap_cookie4 != NULL) {
err = encap_detach(sc->encap_cookie4);
KASSERT(err == 0, ("Unexpected error detaching encap_cookie4"));
}
#endif
2001-09-26 23:50:17 +00:00
if (ng_gif_detach_p != NULL)
(*ng_gif_detach_p)(ifp);
bpfdetach(ifp);
if_detach(ifp);
if_free(ifp);
GIF_LOCK_DESTROY(sc);
free(sc, M_GIF);
}
static void
vnet_gif_init(const void *unused __unused)
{
LIST_INIT(&V_gif_softc_list);
}
VNET_SYSINIT(vnet_gif_init, SI_SUB_PSEUDO, SI_ORDER_MIDDLE, vnet_gif_init,
NULL);
static int
gifmodevent(mod, type, data)
module_t mod;
int type;
void *data;
{
switch (type) {
case MOD_LOAD:
mtx_init(&gif_mtx, "gif_mtx", NULL, MTX_DEF);
if_clone_attach(&gif_cloner);
break;
case MOD_UNLOAD:
if_clone_detach(&gif_cloner);
mtx_destroy(&gif_mtx);
break;
default:
return EOPNOTSUPP;
}
return 0;
}
static moduledata_t gif_mod = {
"if_gif",
gifmodevent,
0
};
DECLARE_MODULE(if_gif, gif_mod, SI_SUB_PSEUDO, SI_ORDER_ANY);
MODULE_VERSION(if_gif, 1);
int
gif_encapcheck(m, off, proto, arg)
const struct mbuf *m;
int off;
int proto;
void *arg;
{
struct ip ip;
struct gif_softc *sc;
sc = (struct gif_softc *)arg;
if (sc == NULL)
return 0;
if ((GIF2IFP(sc)->if_flags & IFF_UP) == 0)
return 0;
/* no physical address */
if (!sc->gif_psrc || !sc->gif_pdst)
return 0;
switch (proto) {
#ifdef INET
case IPPROTO_IPV4:
break;
#endif
#ifdef INET6
case IPPROTO_IPV6:
break;
#endif
case IPPROTO_ETHERIP:
break;
default:
return 0;
}
/* Bail on short packets */
if (m->m_pkthdr.len < sizeof(ip))
return 0;
m_copydata(m, 0, sizeof(ip), (caddr_t)&ip);
switch (ip.ip_v) {
#ifdef INET
case 4:
if (sc->gif_psrc->sa_family != AF_INET ||
sc->gif_pdst->sa_family != AF_INET)
return 0;
return gif_encapcheck4(m, off, proto, arg);
#endif
#ifdef INET6
case 6:
if (m->m_pkthdr.len < sizeof(struct ip6_hdr))
return 0;
if (sc->gif_psrc->sa_family != AF_INET6 ||
sc->gif_pdst->sa_family != AF_INET6)
return 0;
return gif_encapcheck6(m, off, proto, arg);
#endif
default:
return 0;
}
}
static void
gif_start(struct ifnet *ifp)
{
struct gif_softc *sc;
struct mbuf *m;
sc = ifp->if_softc;
ifp->if_drv_flags |= IFF_DRV_OACTIVE;
for (;;) {
IFQ_DEQUEUE(&ifp->if_snd, m);
if (m == 0)
break;
gif_output(ifp, m, sc->gif_pdst, NULL);
}
ifp->if_drv_flags &= ~IFF_DRV_OACTIVE;
return;
}
int
gif_output(ifp, m, dst, ro)
struct ifnet *ifp;
struct mbuf *m;
struct sockaddr *dst;
struct route *ro;
{
struct gif_softc *sc = ifp->if_softc;
struct m_tag *mtag;
int error = 0;
int gif_called;
u_int32_t af;
#ifdef MAC
error = mac_ifnet_check_transmit(ifp, m);
if (error) {
m_freem(m);
goto end;
}
#endif
/*
* gif may cause infinite recursion calls when misconfigured.
* We'll prevent this by detecting loops.
*
* High nesting level may cause stack exhaustion.
* We'll prevent this by introducing upper limit.
*/
gif_called = 1;
mtag = m_tag_locate(m, MTAG_GIF, MTAG_GIF_CALLED, NULL);
while (mtag != NULL) {
if (*(struct ifnet **)(mtag + 1) == ifp) {
log(LOG_NOTICE,
"gif_output: loop detected on %s\n",
(*(struct ifnet **)(mtag + 1))->if_xname);
m_freem(m);
error = EIO; /* is there better errno? */
goto end;
}
mtag = m_tag_locate(m, MTAG_GIF, MTAG_GIF_CALLED, mtag);
gif_called++;
}
if (gif_called > V_max_gif_nesting) {
log(LOG_NOTICE,
"gif_output: recursively called too many times(%d)\n",
gif_called);
m_freem(m);
error = EIO; /* is there better errno? */
goto end;
}
mtag = m_tag_alloc(MTAG_GIF, MTAG_GIF_CALLED, sizeof(struct ifnet *),
M_NOWAIT);
if (mtag == NULL) {
m_freem(m);
error = ENOMEM;
goto end;
}
*(struct ifnet **)(mtag + 1) = ifp;
m_tag_prepend(m, mtag);
m->m_flags &= ~(M_BCAST|M_MCAST);
GIF_LOCK(sc);
if (!(ifp->if_flags & IFF_UP) ||
sc->gif_psrc == NULL || sc->gif_pdst == NULL) {
GIF_UNLOCK(sc);
m_freem(m);
error = ENETDOWN;
goto end;
}
/* BPF writes need to be handled specially. */
if (dst->sa_family == AF_UNSPEC) {
bcopy(dst->sa_data, &af, sizeof(af));
dst->sa_family = af;
}
af = dst->sa_family;
Fix the following bpf(4) race condition which can result in a panic: (1) bpf peer attaches to interface netif0 (2) Packet is received by netif0 (3) ifp->if_bpf pointer is checked and handed off to bpf (4) bpf peer detaches from netif0 resulting in ifp->if_bpf being initialized to NULL. (5) ifp->if_bpf is dereferenced by bpf machinery (6) Kaboom This race condition likely explains the various different kernel panics reported around sending SIGINT to tcpdump or dhclient processes. But really this race can result in kernel panics anywhere you have frequent bpf attach and detach operations with high packet per second load. Summary of changes: - Remove the bpf interface's "driverp" member - When we attach bpf interfaces, we now set the ifp->if_bpf member to the bpf interface structure. Once this is done, ifp->if_bpf should never be NULL. [1] - Introduce bpf_peers_present function, an inline operation which will do a lockless read bpf peer list associated with the interface. It should be noted that the bpf code will pickup the bpf_interface lock before adding or removing bpf peers. This should serialize the access to the bpf descriptor list, removing the race. - Expose the bpf_if structure in bpf.h so that the bpf_peers_present function can use it. This also removes the struct bpf_if; hack that was there. - Adjust all consumers of the raw if_bpf structure to use bpf_peers_present Now what happens is: (1) Packet is received by netif0 (2) Check to see if bpf descriptor list is empty (3) Pickup the bpf interface lock (4) Hand packet off to process From the attach/detach side: (1) Pickup the bpf interface lock (2) Add/remove from bpf descriptor list Now that we are storing the bpf interface structure with the ifnet, there is is no need to walk the bpf interface list to locate the correct bpf interface. We now simply look up the interface, and initialize the pointer. This has a nice side effect of changing a bpf interface attach operation from O(N) (where N is the number of bpf interfaces), to O(1). [1] From now on, we can no longer check ifp->if_bpf to tell us whether or not we have any bpf peers that might be interested in receiving packets. In collaboration with: sam@ MFC after: 1 month
2006-06-02 19:59:33 +00:00
BPF_MTAP2(ifp, &af, sizeof(af), m);
ifp->if_opackets++;
ifp->if_obytes += m->m_pkthdr.len;
/* override to IPPROTO_ETHERIP for bridged traffic */
if (ifp->if_bridge)
af = AF_LINK;
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);
/* inner AF-specific encapsulation */
/* XXX should we check if our outer source is legal? */
/* dispatch to output logic based on outer AF */
switch (sc->gif_psrc->sa_family) {
#ifdef INET
case AF_INET:
error = in_gif_output(ifp, af, m);
break;
#endif
#ifdef INET6
case AF_INET6:
error = in6_gif_output(ifp, af, m);
break;
#endif
default:
m_freem(m);
error = ENETDOWN;
}
GIF_UNLOCK(sc);
end:
if (error)
ifp->if_oerrors++;
return (error);
}
void
gif_input(m, af, ifp)
struct mbuf *m;
int af;
struct ifnet *ifp;
{
int isr, n;
struct gif_softc *sc;
struct etherip_header *eip;
struct ether_header *eh;
struct ifnet *oldifp;
if (ifp == NULL) {
/* just in case */
m_freem(m);
return;
}
sc = ifp->if_softc;
m->m_pkthdr.rcvif = ifp;
#ifdef MAC
mac_ifnet_create_mbuf(ifp, m);
#endif
Fix the following bpf(4) race condition which can result in a panic: (1) bpf peer attaches to interface netif0 (2) Packet is received by netif0 (3) ifp->if_bpf pointer is checked and handed off to bpf (4) bpf peer detaches from netif0 resulting in ifp->if_bpf being initialized to NULL. (5) ifp->if_bpf is dereferenced by bpf machinery (6) Kaboom This race condition likely explains the various different kernel panics reported around sending SIGINT to tcpdump or dhclient processes. But really this race can result in kernel panics anywhere you have frequent bpf attach and detach operations with high packet per second load. Summary of changes: - Remove the bpf interface's "driverp" member - When we attach bpf interfaces, we now set the ifp->if_bpf member to the bpf interface structure. Once this is done, ifp->if_bpf should never be NULL. [1] - Introduce bpf_peers_present function, an inline operation which will do a lockless read bpf peer list associated with the interface. It should be noted that the bpf code will pickup the bpf_interface lock before adding or removing bpf peers. This should serialize the access to the bpf descriptor list, removing the race. - Expose the bpf_if structure in bpf.h so that the bpf_peers_present function can use it. This also removes the struct bpf_if; hack that was there. - Adjust all consumers of the raw if_bpf structure to use bpf_peers_present Now what happens is: (1) Packet is received by netif0 (2) Check to see if bpf descriptor list is empty (3) Pickup the bpf interface lock (4) Hand packet off to process From the attach/detach side: (1) Pickup the bpf interface lock (2) Add/remove from bpf descriptor list Now that we are storing the bpf interface structure with the ifnet, there is is no need to walk the bpf interface list to locate the correct bpf interface. We now simply look up the interface, and initialize the pointer. This has a nice side effect of changing a bpf interface attach operation from O(N) (where N is the number of bpf interfaces), to O(1). [1] From now on, we can no longer check ifp->if_bpf to tell us whether or not we have any bpf peers that might be interested in receiving packets. In collaboration with: sam@ MFC after: 1 month
2006-06-02 19:59:33 +00:00
if (bpf_peers_present(ifp->if_bpf)) {
u_int32_t af1 = af;
bpf_mtap2(ifp->if_bpf, &af1, sizeof(af1), m);
}
2001-09-26 23:50:17 +00:00
if (ng_gif_input_p != NULL) {
(*ng_gif_input_p)(ifp, &m, af);
2001-09-26 23:50:17 +00:00
if (m == NULL)
return;
}
/*
* Put the packet to the network layer input queue according to the
* specified address family.
* Note: older versions of gif_input directly called network layer
* input functions, e.g. ip6_input, here. We changed the policy to
* prevent too many recursive calls of such input functions, which
* might cause kernel panic. But the change may introduce another
* problem; if the input queue is full, packets are discarded.
* The kernel stack overflow really happened, and we believed
* queue-full rarely occurs, so we changed the policy.
*/
switch (af) {
#ifdef INET
case AF_INET:
isr = NETISR_IP;
break;
#endif
#ifdef INET6
case AF_INET6:
isr = NETISR_IPV6;
break;
#endif
case AF_LINK:
n = sizeof(struct etherip_header) + sizeof(struct ether_header);
if (n > m->m_len) {
m = m_pullup(m, n);
if (m == NULL) {
ifp->if_ierrors++;
return;
}
}
eip = mtod(m, struct etherip_header *);
/*
* GIF_ACCEPT_REVETHIP (enabled by default) intentionally
* accepts 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_ACCEPT_REVETHIP) {
if (eip->eip_resvl != ETHERIP_VERSION
&& eip->eip_ver != ETHERIP_VERSION) {
/* discard unknown versions */
m_freem(m);
return;
}
} else {
if (eip->eip_ver != ETHERIP_VERSION) {
/* discard unknown versions */
m_freem(m);
return;
}
}
m_adj(m, sizeof(struct etherip_header));
m->m_flags &= ~(M_BCAST|M_MCAST);
m->m_pkthdr.rcvif = ifp;
if (ifp->if_bridge) {
oldifp = ifp;
eh = mtod(m, struct ether_header *);
if (ETHER_IS_MULTICAST(eh->ether_dhost)) {
if (ETHER_IS_BROADCAST(eh->ether_dhost))
m->m_flags |= M_BCAST;
else
m->m_flags |= M_MCAST;
ifp->if_imcasts++;
}
BRIDGE_INPUT(ifp, m);
if (m != NULL && ifp != oldifp) {
/*
* The bridge gave us back itself or one of the
* members for which the frame is addressed.
*/
ether_demux(ifp, m);
return;
}
}
if (m != NULL)
m_freem(m);
return;
default:
2001-09-26 23:50:17 +00:00
if (ng_gif_input_orphan_p != NULL)
(*ng_gif_input_orphan_p)(ifp, m, af);
2001-09-26 23:50:17 +00:00
else
m_freem(m);
return;
}
ifp->if_ipackets++;
ifp->if_ibytes += m->m_pkthdr.len;
netisr_dispatch(isr, m);
}
/* XXX how should we handle IPv6 scope on SIOC[GS]IFPHYADDR? */
int
gif_ioctl(ifp, cmd, data)
struct ifnet *ifp;
u_long cmd;
caddr_t data;
{
struct gif_softc *sc = ifp->if_softc;
struct ifreq *ifr = (struct ifreq*)data;
int error = 0, size;
u_int options;
struct sockaddr *dst, *src;
#ifdef SIOCSIFMTU /* xxx */
u_long mtu;
#endif
switch (cmd) {
case SIOCSIFADDR:
ifp->if_flags |= IFF_UP;
break;
case SIOCSIFDSTADDR:
break;
case SIOCADDMULTI:
case SIOCDELMULTI:
break;
#ifdef SIOCSIFMTU /* xxx */
case SIOCGIFMTU:
break;
case SIOCSIFMTU:
mtu = ifr->ifr_mtu;
if (mtu < GIF_MTU_MIN || mtu > GIF_MTU_MAX)
return (EINVAL);
ifp->if_mtu = mtu;
break;
#endif /* SIOCSIFMTU */
#ifdef INET
case SIOCSIFPHYADDR:
#endif
#ifdef INET6
case SIOCSIFPHYADDR_IN6:
#endif /* INET6 */
case SIOCSLIFPHYADDR:
switch (cmd) {
#ifdef INET
case SIOCSIFPHYADDR:
src = (struct sockaddr *)
&(((struct in_aliasreq *)data)->ifra_addr);
dst = (struct sockaddr *)
&(((struct in_aliasreq *)data)->ifra_dstaddr);
break;
#endif
#ifdef INET6
case SIOCSIFPHYADDR_IN6:
src = (struct sockaddr *)
&(((struct in6_aliasreq *)data)->ifra_addr);
dst = (struct sockaddr *)
&(((struct in6_aliasreq *)data)->ifra_dstaddr);
break;
#endif
case SIOCSLIFPHYADDR:
src = (struct sockaddr *)
&(((struct if_laddrreq *)data)->addr);
dst = (struct sockaddr *)
&(((struct if_laddrreq *)data)->dstaddr);
break;
default:
return EINVAL;
}
/* sa_family must be equal */
if (src->sa_family != dst->sa_family)
return EINVAL;
/* validate sa_len */
switch (src->sa_family) {
#ifdef INET
case AF_INET:
if (src->sa_len != sizeof(struct sockaddr_in))
return EINVAL;
break;
#endif
#ifdef INET6
case AF_INET6:
if (src->sa_len != sizeof(struct sockaddr_in6))
return EINVAL;
break;
#endif
default:
return EAFNOSUPPORT;
}
switch (dst->sa_family) {
#ifdef INET
case AF_INET:
if (dst->sa_len != sizeof(struct sockaddr_in))
return EINVAL;
break;
#endif
#ifdef INET6
case AF_INET6:
if (dst->sa_len != sizeof(struct sockaddr_in6))
return EINVAL;
break;
#endif
default:
return EAFNOSUPPORT;
}
/* check sa_family looks sane for the cmd */
switch (cmd) {
case SIOCSIFPHYADDR:
if (src->sa_family == AF_INET)
break;
return EAFNOSUPPORT;
#ifdef INET6
case SIOCSIFPHYADDR_IN6:
if (src->sa_family == AF_INET6)
break;
return EAFNOSUPPORT;
#endif /* INET6 */
case SIOCSLIFPHYADDR:
/* checks done in the above */
break;
}
error = gif_set_tunnel(GIF2IFP(sc), src, dst);
break;
#ifdef SIOCDIFPHYADDR
case SIOCDIFPHYADDR:
gif_delete_tunnel(GIF2IFP(sc));
break;
#endif
case SIOCGIFPSRCADDR:
#ifdef INET6
case SIOCGIFPSRCADDR_IN6:
#endif /* INET6 */
if (sc->gif_psrc == NULL) {
error = EADDRNOTAVAIL;
goto bad;
}
src = sc->gif_psrc;
switch (cmd) {
#ifdef INET
case SIOCGIFPSRCADDR:
dst = &ifr->ifr_addr;
size = sizeof(ifr->ifr_addr);
break;
#endif /* INET */
#ifdef INET6
case SIOCGIFPSRCADDR_IN6:
dst = (struct sockaddr *)
&(((struct in6_ifreq *)data)->ifr_addr);
size = sizeof(((struct in6_ifreq *)data)->ifr_addr);
break;
#endif /* INET6 */
default:
error = EADDRNOTAVAIL;
goto bad;
}
if (src->sa_len > size)
return EINVAL;
bcopy((caddr_t)src, (caddr_t)dst, src->sa_len);
#ifdef INET6
if (dst->sa_family == AF_INET6) {
error = sa6_recoverscope((struct sockaddr_in6 *)dst);
if (error != 0)
return (error);
}
#endif
break;
case SIOCGIFPDSTADDR:
#ifdef INET6
case SIOCGIFPDSTADDR_IN6:
#endif /* INET6 */
if (sc->gif_pdst == NULL) {
error = EADDRNOTAVAIL;
goto bad;
}
src = sc->gif_pdst;
switch (cmd) {
#ifdef INET
case SIOCGIFPDSTADDR:
dst = &ifr->ifr_addr;
size = sizeof(ifr->ifr_addr);
break;
#endif /* INET */
#ifdef INET6
case SIOCGIFPDSTADDR_IN6:
dst = (struct sockaddr *)
&(((struct in6_ifreq *)data)->ifr_addr);
size = sizeof(((struct in6_ifreq *)data)->ifr_addr);
break;
#endif /* INET6 */
default:
error = EADDRNOTAVAIL;
goto bad;
}
if (src->sa_len > size)
return EINVAL;
bcopy((caddr_t)src, (caddr_t)dst, src->sa_len);
#ifdef INET6
if (dst->sa_family == AF_INET6) {
error = sa6_recoverscope((struct sockaddr_in6 *)dst);
if (error != 0)
return (error);
}
#endif
break;
case SIOCGLIFPHYADDR:
if (sc->gif_psrc == NULL || sc->gif_pdst == NULL) {
error = EADDRNOTAVAIL;
goto bad;
}
/* copy src */
src = sc->gif_psrc;
dst = (struct sockaddr *)
&(((struct if_laddrreq *)data)->addr);
size = sizeof(((struct if_laddrreq *)data)->addr);
if (src->sa_len > size)
return EINVAL;
bcopy((caddr_t)src, (caddr_t)dst, src->sa_len);
/* copy dst */
src = sc->gif_pdst;
dst = (struct sockaddr *)
&(((struct if_laddrreq *)data)->dstaddr);
size = sizeof(((struct if_laddrreq *)data)->dstaddr);
if (src->sa_len > size)
return EINVAL;
bcopy((caddr_t)src, (caddr_t)dst, src->sa_len);
break;
case SIOCSIFFLAGS:
/* if_ioctl() takes care of it */
break;
case GIFGOPTS:
options = sc->gif_options;
error = copyout(&options, ifr->ifr_data,
sizeof(options));
break;
case GIFSOPTS:
if ((error = priv_check(curthread, PRIV_NET_GIF)) != 0)
break;
2009-06-09 08:09:30 +00:00
error = copyin(ifr->ifr_data, &options, sizeof(options));
if (error)
break;
if (options & ~GIF_OPTMASK)
error = EINVAL;
else
sc->gif_options = options;
break;
default:
error = EINVAL;
break;
}
bad:
return error;
}
/*
* XXXRW: There's a general event-ordering issue here: the code to check
* if a given tunnel is already present happens before we perform a
* potentially blocking setup of the tunnel. This code needs to be
* re-ordered so that the check and replacement can be atomic using
* a mutex.
*/
int
gif_set_tunnel(ifp, src, dst)
struct ifnet *ifp;
struct sockaddr *src;
struct sockaddr *dst;
{
struct gif_softc *sc = ifp->if_softc;
struct gif_softc *sc2;
struct sockaddr *osrc, *odst, *sa;
int error = 0;
mtx_lock(&gif_mtx);
LIST_FOREACH(sc2, &V_gif_softc_list, gif_list) {
if (sc2 == sc)
continue;
if (!sc2->gif_pdst || !sc2->gif_psrc)
continue;
if (sc2->gif_pdst->sa_family != dst->sa_family ||
sc2->gif_pdst->sa_len != dst->sa_len ||
sc2->gif_psrc->sa_family != src->sa_family ||
sc2->gif_psrc->sa_len != src->sa_len)
continue;
/*
* Disallow parallel tunnels unless instructed
* otherwise.
*/
if (!V_parallel_tunnels &&
bcmp(sc2->gif_pdst, dst, dst->sa_len) == 0 &&
bcmp(sc2->gif_psrc, src, src->sa_len) == 0) {
error = EADDRNOTAVAIL;
mtx_unlock(&gif_mtx);
goto bad;
}
/* XXX both end must be valid? (I mean, not 0.0.0.0) */
}
mtx_unlock(&gif_mtx);
/* XXX we can detach from both, but be polite just in case */
if (sc->gif_psrc)
switch (sc->gif_psrc->sa_family) {
#ifdef INET
case AF_INET:
(void)in_gif_detach(sc);
break;
#endif
#ifdef INET6
case AF_INET6:
(void)in6_gif_detach(sc);
break;
#endif
}
osrc = sc->gif_psrc;
sa = (struct sockaddr *)malloc(src->sa_len, M_IFADDR, M_WAITOK);
bcopy((caddr_t)src, (caddr_t)sa, src->sa_len);
sc->gif_psrc = sa;
odst = sc->gif_pdst;
sa = (struct sockaddr *)malloc(dst->sa_len, M_IFADDR, M_WAITOK);
bcopy((caddr_t)dst, (caddr_t)sa, dst->sa_len);
sc->gif_pdst = sa;
switch (sc->gif_psrc->sa_family) {
#ifdef INET
case AF_INET:
error = in_gif_attach(sc);
break;
#endif
#ifdef INET6
case AF_INET6:
/*
* Check validity of the scope zone ID of the addresses, and
* convert it into the kernel internal form if necessary.
*/
error = sa6_embedscope((struct sockaddr_in6 *)sc->gif_psrc, 0);
if (error != 0)
break;
error = sa6_embedscope((struct sockaddr_in6 *)sc->gif_pdst, 0);
if (error != 0)
break;
error = in6_gif_attach(sc);
break;
#endif
}
if (error) {
/* rollback */
free((caddr_t)sc->gif_psrc, M_IFADDR);
free((caddr_t)sc->gif_pdst, M_IFADDR);
sc->gif_psrc = osrc;
sc->gif_pdst = odst;
goto bad;
}
if (osrc)
free((caddr_t)osrc, M_IFADDR);
if (odst)
free((caddr_t)odst, M_IFADDR);
bad:
if (sc->gif_psrc && sc->gif_pdst)
ifp->if_drv_flags |= IFF_DRV_RUNNING;
else
ifp->if_drv_flags &= ~IFF_DRV_RUNNING;
return error;
}
void
gif_delete_tunnel(ifp)
struct ifnet *ifp;
{
struct gif_softc *sc = ifp->if_softc;
if (sc->gif_psrc) {
free((caddr_t)sc->gif_psrc, M_IFADDR);
sc->gif_psrc = NULL;
}
if (sc->gif_pdst) {
free((caddr_t)sc->gif_pdst, M_IFADDR);
sc->gif_pdst = NULL;
}
/* it is safe to detach from both */
#ifdef INET
(void)in_gif_detach(sc);
#endif
#ifdef INET6
(void)in6_gif_detach(sc);
#endif
2006-06-29 07:23:49 +00:00
ifp->if_drv_flags &= ~IFF_DRV_RUNNING;
}