freebsd-nq/sys/net/if_stf.c

760 lines
19 KiB
C
Raw Normal View History

/* $FreeBSD$ */
/* $KAME: if_stf.c,v 1.73 2001/12/03 11:08:30 keiichi Exp $ */
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (C) 2000 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.
*/
/*
* 6to4 interface, based on RFC3056.
*
* 6to4 interface is NOT capable of link-layer (I mean, IPv4) multicasting.
* There is no address mapping defined from IPv6 multicast address to IPv4
* address. Therefore, we do not have IFF_MULTICAST on the interface.
*
* Due to the lack of address mapping for link-local addresses, we cannot
* throw packets toward link-local addresses (fe80::x). Also, we cannot throw
* packets to link-local multicast addresses (ff02::x).
*
* Here are interesting symptoms due to the lack of link-local address:
*
* Unicast routing exchange:
* - RIPng: Impossible. Uses link-local multicast packet toward ff02::9,
* and link-local addresses as nexthop.
* - OSPFv6: Impossible. OSPFv6 assumes that there's link-local address
* assigned to the link, and makes use of them. Also, HELLO packets use
* link-local multicast addresses (ff02::5 and ff02::6).
* - BGP4+: Maybe. You can only use global address as nexthop, and global
* address as TCP endpoint address.
*
* Multicast routing protocols:
* - PIM: Hello packet cannot be used to discover adjacent PIM routers.
* Adjacent PIM routers must be configured manually (is it really spec-wise
* correct thing to do?).
*
* ICMPv6:
* - Redirects cannot be used due to the lack of link-local address.
*
* stf interface does not have, and will not need, a link-local address.
* It seems to have no real benefit and does not help the above symptoms much.
* Even if we assign link-locals to interface, we cannot really
* use link-local unicast/multicast on top of 6to4 cloud (since there's no
* encapsulation defined for link-local address), and the above analysis does
* not change. RFC3056 does not mandate the assignment of link-local address
* either.
*
* 6to4 interface has security issues. Refer to
* http://playground.iijlab.net/i-d/draft-itojun-ipv6-transition-abuse-00.txt
* for details. The code tries to filter out some of malicious packets.
* Note that there is no way to be 100% secure.
*/
#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/lock.h>
2004-05-30 20:27:19 +00:00
#include <sys/module.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/queue.h>
#include <sys/rmlock.h>
#include <sys/sysctl.h>
#include <machine/cpu.h>
#include <sys/malloc.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/if_clone.h>
#include <net/route.h>
#include <net/netisr.h>
#include <net/if_types.h>
#include <net/vnet.h>
#include <netinet/in.h>
2015-12-16 09:18:20 +00:00
#include <netinet/in_fib.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/in_var.h>
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet6/in6_var.h>
#include <netinet/ip_ecn.h>
#include <netinet/ip_encap.h>
#include <machine/stdarg.h>
#include <net/bpf.h>
#include <security/mac/mac_framework.h>
SYSCTL_DECL(_net_link);
static SYSCTL_NODE(_net_link, IFT_STF, stf, CTLFLAG_RW | CTLFLAG_MPSAFE, 0,
"6to4 Interface");
static int stf_permit_rfc1918 = 0;
SYSCTL_INT(_net_link_stf, OID_AUTO, permit_rfc1918, CTLFLAG_RWTUN,
&stf_permit_rfc1918, 0, "Permit the use of private IPv4 addresses");
#define STFUNIT 0
#define IN6_IS_ADDR_6TO4(x) (ntohs((x)->s6_addr16[0]) == 0x2002)
/*
* XXX: Return a pointer with 16-bit aligned. Don't cast it to
* struct in_addr *; use bcopy() instead.
*/
#define GET_V4(x) (&(x)->s6_addr16[1])
struct stf_softc {
struct ifnet *sc_ifp;
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
u_int sc_fibnum;
const struct encaptab *encap_cookie;
};
#define STF2IFP(sc) ((sc)->sc_ifp)
static const char stfname[] = "stf";
static MALLOC_DEFINE(M_STF, stfname, "6to4 Tunnel Interface");
static const int ip_stf_ttl = 40;
Rework IP encapsulation handling code. Currently it has several disadvantages: - it uses single mutex to protect internal structures. It is used by data- and control- path, thus there are no parallelism at all. - it uses single list to keep encap handlers for both INET and INET6 families. - struct encaptab keeps unneeded information (src, dst, masks, protosw), that isn't used by code in the source tree. - matches are prioritized and when many tunneling interfaces are registered, encapcheck handler of each interface is invoked for each packet. The search takes O(n) for n interfaces. All this work is done with exclusive lock held. What this patch includes: - the datapath is converted to be lockless using epoch(9) KPI. - struct encaptab now linked using CK_LIST. - all unused fields removed from struct encaptab. Several new fields addedr: min_length is the minimum packet length, that encapsulation handler expects to see; exact_match is maximum number of bits, that can return an encapsulation handler, when it wants to consume a packet. - IPv6 and IPv4 handlers are stored in separate lists; - added new "encap_lookup_t" method, that will be used later. It is targeted to speedup lookup of needed interface, when gif(4)/gre(4) have many interfaces. - the need to use protosw structure is eliminated. The only pr_input method was used from this structure, so I don't see the need to keep using it. - encap_input_t method changed to avoid using mbuf tags to store softc pointer. Now it is passed directly trough encap_input_t method. encap_getarg() funtions is removed. - all sockaddr structures and code that uses them removed. We don't have any code in the tree that uses them. All consumers use encap_attach_func() method, that relies on invoking of encapcheck() to determine the needed handler. - introduced struct encap_config, it contains parameters of encap handler that is going to be registered by encap_attach() function. - encap handlers are stored in lists ordered by exact_match value, thus handlers that need more bits to match will be checked first, and if encapcheck method returns exact_match value, the search will be stopped. - all current consumers changed to use new KPI. Reviewed by: mmacy Sponsored by: Yandex LLC Differential Revision: https://reviews.freebsd.org/D15617
2018-06-05 20:51:01 +00:00
static int in_stf_input(struct mbuf *, int, int, void *);
static char *stfnames[] = {"stf0", "stf", "6to4", NULL};
2002-03-19 21:54:18 +00:00
static int stfmodevent(module_t, int, void *);
static int stf_encapcheck(const struct mbuf *, int, int, void *);
static int stf_getsrcifa6(struct ifnet *, struct in6_addr *, struct in6_addr *);
static int stf_output(struct ifnet *, struct mbuf *, const struct sockaddr *,
struct route *);
static int isrfc1918addr(struct in_addr *);
2002-03-19 21:54:18 +00:00
static int stf_checkaddr4(struct stf_softc *, struct in_addr *,
struct ifnet *);
static int stf_checkaddr6(struct stf_softc *, struct in6_addr *,
struct ifnet *);
static int stf_ioctl(struct ifnet *, u_long, caddr_t);
static int stf_clone_match(struct if_clone *, const char *);
static int stf_clone_create(struct if_clone *, char *, size_t, caddr_t);
static int stf_clone_destroy(struct if_clone *, struct ifnet *);
static struct if_clone *stf_cloner;
Rework IP encapsulation handling code. Currently it has several disadvantages: - it uses single mutex to protect internal structures. It is used by data- and control- path, thus there are no parallelism at all. - it uses single list to keep encap handlers for both INET and INET6 families. - struct encaptab keeps unneeded information (src, dst, masks, protosw), that isn't used by code in the source tree. - matches are prioritized and when many tunneling interfaces are registered, encapcheck handler of each interface is invoked for each packet. The search takes O(n) for n interfaces. All this work is done with exclusive lock held. What this patch includes: - the datapath is converted to be lockless using epoch(9) KPI. - struct encaptab now linked using CK_LIST. - all unused fields removed from struct encaptab. Several new fields addedr: min_length is the minimum packet length, that encapsulation handler expects to see; exact_match is maximum number of bits, that can return an encapsulation handler, when it wants to consume a packet. - IPv6 and IPv4 handlers are stored in separate lists; - added new "encap_lookup_t" method, that will be used later. It is targeted to speedup lookup of needed interface, when gif(4)/gre(4) have many interfaces. - the need to use protosw structure is eliminated. The only pr_input method was used from this structure, so I don't see the need to keep using it. - encap_input_t method changed to avoid using mbuf tags to store softc pointer. Now it is passed directly trough encap_input_t method. encap_getarg() funtions is removed. - all sockaddr structures and code that uses them removed. We don't have any code in the tree that uses them. All consumers use encap_attach_func() method, that relies on invoking of encapcheck() to determine the needed handler. - introduced struct encap_config, it contains parameters of encap handler that is going to be registered by encap_attach() function. - encap handlers are stored in lists ordered by exact_match value, thus handlers that need more bits to match will be checked first, and if encapcheck method returns exact_match value, the search will be stopped. - all current consumers changed to use new KPI. Reviewed by: mmacy Sponsored by: Yandex LLC Differential Revision: https://reviews.freebsd.org/D15617
2018-06-05 20:51:01 +00:00
static const struct encap_config ipv4_encap_cfg = {
.proto = IPPROTO_IPV6,
.min_length = sizeof(struct ip),
.exact_match = (sizeof(in_addr_t) << 3) + 8,
.check = stf_encapcheck,
.input = in_stf_input
};
static int
stf_clone_match(struct if_clone *ifc, const char *name)
{
int i;
for(i = 0; stfnames[i] != NULL; i++) {
if (strcmp(stfnames[i], name) == 0)
return (1);
}
return (0);
}
static int
stf_clone_create(struct if_clone *ifc, char *name, size_t len, caddr_t params)
{
char *dp;
int err, unit, wildcard;
struct stf_softc *sc;
struct ifnet *ifp;
err = ifc_name2unit(name, &unit);
if (err != 0)
return (err);
wildcard = (unit < 0);
/*
* We can only have one unit, but since unit allocation is
* already locked, we use it to keep from allocating extra
* interfaces.
*/
unit = STFUNIT;
err = ifc_alloc_unit(ifc, &unit);
if (err != 0)
return (err);
sc = malloc(sizeof(struct stf_softc), M_STF, M_WAITOK | M_ZERO);
ifp = STF2IFP(sc) = if_alloc(IFT_STF);
if (ifp == NULL) {
free(sc, M_STF);
ifc_free_unit(ifc, unit);
return (ENOSPC);
}
ifp->if_softc = sc;
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->sc_fibnum = curthread->td_proc->p_fibnum;
/*
* Set the name manually rather then using if_initname because
* we don't conform to the default naming convention for interfaces.
* In the wildcard case, we need to update the name.
*/
if (wildcard) {
for (dp = name; *dp != '\0'; dp++);
if (snprintf(dp, len - (dp-name), "%d", unit) >
len - (dp-name) - 1) {
/*
* This can only be a programmer error and
* there's no straightforward way to recover if
* it happens.
*/
panic("if_clone_create(): interface name too long");
}
}
strlcpy(ifp->if_xname, name, IFNAMSIZ);
ifp->if_dname = stfname;
ifp->if_dunit = IF_DUNIT_NONE;
Rework IP encapsulation handling code. Currently it has several disadvantages: - it uses single mutex to protect internal structures. It is used by data- and control- path, thus there are no parallelism at all. - it uses single list to keep encap handlers for both INET and INET6 families. - struct encaptab keeps unneeded information (src, dst, masks, protosw), that isn't used by code in the source tree. - matches are prioritized and when many tunneling interfaces are registered, encapcheck handler of each interface is invoked for each packet. The search takes O(n) for n interfaces. All this work is done with exclusive lock held. What this patch includes: - the datapath is converted to be lockless using epoch(9) KPI. - struct encaptab now linked using CK_LIST. - all unused fields removed from struct encaptab. Several new fields addedr: min_length is the minimum packet length, that encapsulation handler expects to see; exact_match is maximum number of bits, that can return an encapsulation handler, when it wants to consume a packet. - IPv6 and IPv4 handlers are stored in separate lists; - added new "encap_lookup_t" method, that will be used later. It is targeted to speedup lookup of needed interface, when gif(4)/gre(4) have many interfaces. - the need to use protosw structure is eliminated. The only pr_input method was used from this structure, so I don't see the need to keep using it. - encap_input_t method changed to avoid using mbuf tags to store softc pointer. Now it is passed directly trough encap_input_t method. encap_getarg() funtions is removed. - all sockaddr structures and code that uses them removed. We don't have any code in the tree that uses them. All consumers use encap_attach_func() method, that relies on invoking of encapcheck() to determine the needed handler. - introduced struct encap_config, it contains parameters of encap handler that is going to be registered by encap_attach() function. - encap handlers are stored in lists ordered by exact_match value, thus handlers that need more bits to match will be checked first, and if encapcheck method returns exact_match value, the search will be stopped. - all current consumers changed to use new KPI. Reviewed by: mmacy Sponsored by: Yandex LLC Differential Revision: https://reviews.freebsd.org/D15617
2018-06-05 20:51:01 +00:00
sc->encap_cookie = ip_encap_attach(&ipv4_encap_cfg, sc, M_WAITOK);
if (sc->encap_cookie == NULL) {
if_printf(ifp, "attach failed\n");
free(sc, M_STF);
ifc_free_unit(ifc, unit);
return (ENOMEM);
}
ifp->if_mtu = IPV6_MMTU;
ifp->if_ioctl = stf_ioctl;
ifp->if_output = stf_output;
ifp->if_snd.ifq_maxlen = ifqmaxlen;
if_attach(ifp);
bpfattach(ifp, DLT_NULL, sizeof(u_int32_t));
return (0);
}
static int
stf_clone_destroy(struct if_clone *ifc, struct ifnet *ifp)
{
struct stf_softc *sc = ifp->if_softc;
2018-05-19 05:27:49 +00:00
int err __unused;
Rework IP encapsulation handling code. Currently it has several disadvantages: - it uses single mutex to protect internal structures. It is used by data- and control- path, thus there are no parallelism at all. - it uses single list to keep encap handlers for both INET and INET6 families. - struct encaptab keeps unneeded information (src, dst, masks, protosw), that isn't used by code in the source tree. - matches are prioritized and when many tunneling interfaces are registered, encapcheck handler of each interface is invoked for each packet. The search takes O(n) for n interfaces. All this work is done with exclusive lock held. What this patch includes: - the datapath is converted to be lockless using epoch(9) KPI. - struct encaptab now linked using CK_LIST. - all unused fields removed from struct encaptab. Several new fields addedr: min_length is the minimum packet length, that encapsulation handler expects to see; exact_match is maximum number of bits, that can return an encapsulation handler, when it wants to consume a packet. - IPv6 and IPv4 handlers are stored in separate lists; - added new "encap_lookup_t" method, that will be used later. It is targeted to speedup lookup of needed interface, when gif(4)/gre(4) have many interfaces. - the need to use protosw structure is eliminated. The only pr_input method was used from this structure, so I don't see the need to keep using it. - encap_input_t method changed to avoid using mbuf tags to store softc pointer. Now it is passed directly trough encap_input_t method. encap_getarg() funtions is removed. - all sockaddr structures and code that uses them removed. We don't have any code in the tree that uses them. All consumers use encap_attach_func() method, that relies on invoking of encapcheck() to determine the needed handler. - introduced struct encap_config, it contains parameters of encap handler that is going to be registered by encap_attach() function. - encap handlers are stored in lists ordered by exact_match value, thus handlers that need more bits to match will be checked first, and if encapcheck method returns exact_match value, the search will be stopped. - all current consumers changed to use new KPI. Reviewed by: mmacy Sponsored by: Yandex LLC Differential Revision: https://reviews.freebsd.org/D15617
2018-06-05 20:51:01 +00:00
err = ip_encap_detach(sc->encap_cookie);
KASSERT(err == 0, ("Unexpected error detaching encap_cookie"));
bpfdetach(ifp);
if_detach(ifp);
if_free(ifp);
free(sc, M_STF);
ifc_free_unit(ifc, STFUNIT);
return (0);
}
static int
2015-07-31 09:04:22 +00:00
stfmodevent(module_t mod, int type, void *data)
{
switch (type) {
case MOD_LOAD:
stf_cloner = if_clone_advanced(stfname, 0, stf_clone_match,
stf_clone_create, stf_clone_destroy);
break;
case MOD_UNLOAD:
if_clone_detach(stf_cloner);
break;
default:
return (EOPNOTSUPP);
}
return (0);
}
static moduledata_t stf_mod = {
"if_stf",
stfmodevent,
0
};
DECLARE_MODULE(if_stf, stf_mod, SI_SUB_PSEUDO, SI_ORDER_ANY);
static int
2015-07-31 09:04:22 +00:00
stf_encapcheck(const struct mbuf *m, int off, int proto, void *arg)
{
struct ip ip;
struct stf_softc *sc;
struct in_addr a, b, mask;
struct in6_addr addr6, mask6;
sc = (struct stf_softc *)arg;
if (sc == NULL)
return 0;
if ((STF2IFP(sc)->if_flags & IFF_UP) == 0)
return 0;
/* IFF_LINK0 means "no decapsulation" */
if ((STF2IFP(sc)->if_flags & IFF_LINK0) != 0)
return 0;
if (proto != IPPROTO_IPV6)
return 0;
2017-03-08 08:09:41 +00:00
m_copydata(m, 0, sizeof(ip), (caddr_t)&ip);
if (ip.ip_v != 4)
return 0;
if (stf_getsrcifa6(STF2IFP(sc), &addr6, &mask6) != 0)
return (0);
/*
* check if IPv4 dst matches the IPv4 address derived from the
* local 6to4 address.
* success on: dst = 10.1.1.1, ia6->ia_addr = 2002:0a01:0101:...
*/
if (bcmp(GET_V4(&addr6), &ip.ip_dst, sizeof(ip.ip_dst)) != 0)
return 0;
/*
* check if IPv4 src matches the IPv4 address derived from the
* local 6to4 address masked by prefixmask.
* success on: src = 10.1.1.1, ia6->ia_addr = 2002:0a00:.../24
* fail on: src = 10.1.1.1, ia6->ia_addr = 2002:0b00:.../24
*/
bzero(&a, sizeof(a));
bcopy(GET_V4(&addr6), &a, sizeof(a));
bcopy(GET_V4(&mask6), &mask, sizeof(mask));
a.s_addr &= mask.s_addr;
b = ip.ip_src;
b.s_addr &= mask.s_addr;
if (a.s_addr != b.s_addr)
return 0;
/* stf interface makes single side match only */
return 32;
}
static int
stf_getsrcifa6(struct ifnet *ifp, struct in6_addr *addr, struct in6_addr *mask)
{
struct rm_priotracker in_ifa_tracker;
struct ifaddr *ia;
struct in_ifaddr *ia4;
struct in6_ifaddr *ia6;
struct sockaddr_in6 *sin6;
struct in_addr in;
NET_EPOCH_ASSERT();
ifnet: Replace if_addr_lock rwlock with epoch + mutex Run on LLNW canaries and tested by pho@ gallatin: Using a 14-core, 28-HTT single socket E5-2697 v3 with a 40GbE MLX5 based ConnectX 4-LX NIC, I see an almost 12% improvement in received packet rate, and a larger improvement in bytes delivered all the way to userspace. When the host receiving 64 streams of netperf -H $DUT -t UDP_STREAM -- -m 1, I see, using nstat -I mce0 1 before the patch: InMpps OMpps InGbs OGbs err TCP Est %CPU syscalls csw irq GBfree 4.98 0.00 4.42 0.00 4235592 33 83.80 4720653 2149771 1235 247.32 4.73 0.00 4.20 0.00 4025260 33 82.99 4724900 2139833 1204 247.32 4.72 0.00 4.20 0.00 4035252 33 82.14 4719162 2132023 1264 247.32 4.71 0.00 4.21 0.00 4073206 33 83.68 4744973 2123317 1347 247.32 4.72 0.00 4.21 0.00 4061118 33 80.82 4713615 2188091 1490 247.32 4.72 0.00 4.21 0.00 4051675 33 85.29 4727399 2109011 1205 247.32 4.73 0.00 4.21 0.00 4039056 33 84.65 4724735 2102603 1053 247.32 After the patch InMpps OMpps InGbs OGbs err TCP Est %CPU syscalls csw irq GBfree 5.43 0.00 4.20 0.00 3313143 33 84.96 5434214 1900162 2656 245.51 5.43 0.00 4.20 0.00 3308527 33 85.24 5439695 1809382 2521 245.51 5.42 0.00 4.19 0.00 3316778 33 87.54 5416028 1805835 2256 245.51 5.42 0.00 4.19 0.00 3317673 33 90.44 5426044 1763056 2332 245.51 5.42 0.00 4.19 0.00 3314839 33 88.11 5435732 1792218 2499 245.52 5.44 0.00 4.19 0.00 3293228 33 91.84 5426301 1668597 2121 245.52 Similarly, netperf reports 230Mb/s before the patch, and 270Mb/s after the patch Reviewed by: gallatin Sponsored by: Limelight Networks Differential Revision: https://reviews.freebsd.org/D15366
2018-05-18 20:13:34 +00:00
CK_STAILQ_FOREACH(ia, &ifp->if_addrhead, ifa_link) {
if (ia->ifa_addr->sa_family != AF_INET6)
continue;
sin6 = (struct sockaddr_in6 *)ia->ifa_addr;
if (!IN6_IS_ADDR_6TO4(&sin6->sin6_addr))
continue;
bcopy(GET_V4(&sin6->sin6_addr), &in, sizeof(in));
IN_IFADDR_RLOCK(&in_ifa_tracker);
LIST_FOREACH(ia4, INADDR_HASH(in.s_addr), ia_hash)
if (ia4->ia_addr.sin_addr.s_addr == in.s_addr)
break;
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
if (ia4 == NULL)
continue;
ia6 = (struct in6_ifaddr *)ia;
*addr = sin6->sin6_addr;
*mask = ia6->ia_prefixmask.sin6_addr;
return (0);
}
return (ENOENT);
}
static int
stf_output(struct ifnet *ifp, struct mbuf *m, const struct sockaddr *dst,
2015-07-31 09:04:22 +00:00
struct route *ro)
{
struct stf_softc *sc;
const struct sockaddr_in6 *dst6;
struct in_addr in4;
const void *ptr;
u_int8_t tos;
struct ip *ip;
struct ip6_hdr *ip6;
struct in6_addr addr6, mask6;
int error;
#ifdef MAC
error = mac_ifnet_check_transmit(ifp, m);
if (error) {
m_freem(m);
return (error);
}
#endif
sc = ifp->if_softc;
dst6 = (const struct sockaddr_in6 *)dst;
/* just in case */
if ((ifp->if_flags & IFF_UP) == 0) {
m_freem(m);
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
return ENETDOWN;
}
/*
* If we don't have an ip4 address that match my inner ip6 address,
* we shouldn't generate output. Without this check, we'll end up
* using wrong IPv4 source.
*/
if (stf_getsrcifa6(ifp, &addr6, &mask6) != 0) {
m_freem(m);
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
return ENETDOWN;
}
if (m->m_len < sizeof(*ip6)) {
m = m_pullup(m, sizeof(*ip6));
if (!m) {
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
return ENOBUFS;
}
}
ip6 = mtod(m, struct ip6_hdr *);
tos = (ntohl(ip6->ip6_flow) >> 20) & 0xff;
/*
* Pickup the right outer dst addr from the list of candidates.
* ip6_dst has priority as it may be able to give us shorter IPv4 hops.
*/
ptr = NULL;
if (IN6_IS_ADDR_6TO4(&ip6->ip6_dst))
ptr = GET_V4(&ip6->ip6_dst);
else if (IN6_IS_ADDR_6TO4(&dst6->sin6_addr))
ptr = GET_V4(&dst6->sin6_addr);
else {
m_freem(m);
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
return ENETUNREACH;
}
bcopy(ptr, &in4, sizeof(in4));
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)) {
/*
* We need to prepend the address family as
* a four byte field. Cons up a dummy header
* to pacify bpf. This is safe because bpf
* will only read from the mbuf (i.e., it won't
* try to free it or keep a pointer a to it).
*/
u_int af = AF_INET6;
bpf_mtap2(ifp->if_bpf, &af, sizeof(af), m);
}
M_PREPEND(m, sizeof(struct ip), M_NOWAIT);
if (m == NULL) {
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
return ENOBUFS;
}
ip = mtod(m, struct ip *);
bzero(ip, sizeof(*ip));
bcopy(GET_V4(&addr6), &ip->ip_src, sizeof(ip->ip_src));
bcopy(&in4, &ip->ip_dst, sizeof(ip->ip_dst));
ip->ip_p = IPPROTO_IPV6;
ip->ip_ttl = ip_stf_ttl;
ip->ip_len = htons(m->m_pkthdr.len);
if (ifp->if_flags & IFF_LINK1)
ip_ecn_ingress(ECN_ALLOWED, &ip->ip_tos, &tos);
else
ip_ecn_ingress(ECN_NOCARE, &ip->ip_tos, &tos);
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->sc_fibnum);
if_inc_counter(ifp, IFCOUNTER_OPACKETS, 1);
error = ip_output(m, NULL, NULL, 0, NULL, NULL);
return error;
}
static int
2015-07-31 09:04:22 +00:00
isrfc1918addr(struct in_addr *in)
{
/*
* returns 1 if private address range:
* 10.0.0.0/8 172.16.0.0/12 192.168.0.0/16
*/
if (stf_permit_rfc1918 == 0 && (
(ntohl(in->s_addr) & 0xff000000) >> 24 == 10 ||
(ntohl(in->s_addr) & 0xfff00000) >> 16 == 172 * 256 + 16 ||
(ntohl(in->s_addr) & 0xffff0000) >> 16 == 192 * 256 + 168))
return 1;
return 0;
}
static int
2015-07-31 09:04:22 +00:00
stf_checkaddr4(struct stf_softc *sc, struct in_addr *in, struct ifnet *inifp)
{
struct rm_priotracker in_ifa_tracker;
struct in_ifaddr *ia4;
/*
* reject packets with the following address:
* 224.0.0.0/4 0.0.0.0/8 127.0.0.0/8 255.0.0.0/8
*/
if (IN_MULTICAST(ntohl(in->s_addr)))
return -1;
switch ((ntohl(in->s_addr) & 0xff000000) >> 24) {
case 0: case 127: case 255:
return -1;
}
/*
* reject packets with private address range.
* (requirement from RFC3056 section 2 1st paragraph)
*/
if (isrfc1918addr(in))
return -1;
/*
* reject packets with broadcast
*/
IN_IFADDR_RLOCK(&in_ifa_tracker);
ifnet: Replace if_addr_lock rwlock with epoch + mutex Run on LLNW canaries and tested by pho@ gallatin: Using a 14-core, 28-HTT single socket E5-2697 v3 with a 40GbE MLX5 based ConnectX 4-LX NIC, I see an almost 12% improvement in received packet rate, and a larger improvement in bytes delivered all the way to userspace. When the host receiving 64 streams of netperf -H $DUT -t UDP_STREAM -- -m 1, I see, using nstat -I mce0 1 before the patch: InMpps OMpps InGbs OGbs err TCP Est %CPU syscalls csw irq GBfree 4.98 0.00 4.42 0.00 4235592 33 83.80 4720653 2149771 1235 247.32 4.73 0.00 4.20 0.00 4025260 33 82.99 4724900 2139833 1204 247.32 4.72 0.00 4.20 0.00 4035252 33 82.14 4719162 2132023 1264 247.32 4.71 0.00 4.21 0.00 4073206 33 83.68 4744973 2123317 1347 247.32 4.72 0.00 4.21 0.00 4061118 33 80.82 4713615 2188091 1490 247.32 4.72 0.00 4.21 0.00 4051675 33 85.29 4727399 2109011 1205 247.32 4.73 0.00 4.21 0.00 4039056 33 84.65 4724735 2102603 1053 247.32 After the patch InMpps OMpps InGbs OGbs err TCP Est %CPU syscalls csw irq GBfree 5.43 0.00 4.20 0.00 3313143 33 84.96 5434214 1900162 2656 245.51 5.43 0.00 4.20 0.00 3308527 33 85.24 5439695 1809382 2521 245.51 5.42 0.00 4.19 0.00 3316778 33 87.54 5416028 1805835 2256 245.51 5.42 0.00 4.19 0.00 3317673 33 90.44 5426044 1763056 2332 245.51 5.42 0.00 4.19 0.00 3314839 33 88.11 5435732 1792218 2499 245.52 5.44 0.00 4.19 0.00 3293228 33 91.84 5426301 1668597 2121 245.52 Similarly, netperf reports 230Mb/s before the patch, and 270Mb/s after the patch Reviewed by: gallatin Sponsored by: Limelight Networks Differential Revision: https://reviews.freebsd.org/D15366
2018-05-18 20:13:34 +00:00
CK_STAILQ_FOREACH(ia4, &V_in_ifaddrhead, ia_link) {
if ((ia4->ia_ifa.ifa_ifp->if_flags & IFF_BROADCAST) == 0)
continue;
if (in->s_addr == ia4->ia_broadaddr.sin_addr.s_addr) {
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
return -1;
}
}
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
/*
* perform ingress filter
*/
if (sc && (STF2IFP(sc)->if_flags & IFF_LINK2) == 0 && inifp) {
2015-12-16 09:18:20 +00:00
struct nhop4_basic nh4;
if (fib4_lookup_nh_basic(sc->sc_fibnum, *in, 0, 0, &nh4) != 0)
return (-1);
if (nh4.nh_ifp != inifp)
return (-1);
}
return 0;
}
static int
2015-07-31 09:04:22 +00:00
stf_checkaddr6(struct stf_softc *sc, struct in6_addr *in6, struct ifnet *inifp)
{
/*
* check 6to4 addresses
*/
if (IN6_IS_ADDR_6TO4(in6)) {
struct in_addr in4;
bcopy(GET_V4(in6), &in4, sizeof(in4));
return stf_checkaddr4(sc, &in4, inifp);
}
/*
* reject anything that look suspicious. the test is implemented
* in ip6_input too, but we check here as well to
* (1) reject bad packets earlier, and
* (2) to be safe against future ip6_input change.
*/
if (IN6_IS_ADDR_V4COMPAT(in6) || IN6_IS_ADDR_V4MAPPED(in6))
return -1;
return 0;
}
static int
Rework IP encapsulation handling code. Currently it has several disadvantages: - it uses single mutex to protect internal structures. It is used by data- and control- path, thus there are no parallelism at all. - it uses single list to keep encap handlers for both INET and INET6 families. - struct encaptab keeps unneeded information (src, dst, masks, protosw), that isn't used by code in the source tree. - matches are prioritized and when many tunneling interfaces are registered, encapcheck handler of each interface is invoked for each packet. The search takes O(n) for n interfaces. All this work is done with exclusive lock held. What this patch includes: - the datapath is converted to be lockless using epoch(9) KPI. - struct encaptab now linked using CK_LIST. - all unused fields removed from struct encaptab. Several new fields addedr: min_length is the minimum packet length, that encapsulation handler expects to see; exact_match is maximum number of bits, that can return an encapsulation handler, when it wants to consume a packet. - IPv6 and IPv4 handlers are stored in separate lists; - added new "encap_lookup_t" method, that will be used later. It is targeted to speedup lookup of needed interface, when gif(4)/gre(4) have many interfaces. - the need to use protosw structure is eliminated. The only pr_input method was used from this structure, so I don't see the need to keep using it. - encap_input_t method changed to avoid using mbuf tags to store softc pointer. Now it is passed directly trough encap_input_t method. encap_getarg() funtions is removed. - all sockaddr structures and code that uses them removed. We don't have any code in the tree that uses them. All consumers use encap_attach_func() method, that relies on invoking of encapcheck() to determine the needed handler. - introduced struct encap_config, it contains parameters of encap handler that is going to be registered by encap_attach() function. - encap handlers are stored in lists ordered by exact_match value, thus handlers that need more bits to match will be checked first, and if encapcheck method returns exact_match value, the search will be stopped. - all current consumers changed to use new KPI. Reviewed by: mmacy Sponsored by: Yandex LLC Differential Revision: https://reviews.freebsd.org/D15617
2018-06-05 20:51:01 +00:00
in_stf_input(struct mbuf *m, int off, int proto, void *arg)
{
Rework IP encapsulation handling code. Currently it has several disadvantages: - it uses single mutex to protect internal structures. It is used by data- and control- path, thus there are no parallelism at all. - it uses single list to keep encap handlers for both INET and INET6 families. - struct encaptab keeps unneeded information (src, dst, masks, protosw), that isn't used by code in the source tree. - matches are prioritized and when many tunneling interfaces are registered, encapcheck handler of each interface is invoked for each packet. The search takes O(n) for n interfaces. All this work is done with exclusive lock held. What this patch includes: - the datapath is converted to be lockless using epoch(9) KPI. - struct encaptab now linked using CK_LIST. - all unused fields removed from struct encaptab. Several new fields addedr: min_length is the minimum packet length, that encapsulation handler expects to see; exact_match is maximum number of bits, that can return an encapsulation handler, when it wants to consume a packet. - IPv6 and IPv4 handlers are stored in separate lists; - added new "encap_lookup_t" method, that will be used later. It is targeted to speedup lookup of needed interface, when gif(4)/gre(4) have many interfaces. - the need to use protosw structure is eliminated. The only pr_input method was used from this structure, so I don't see the need to keep using it. - encap_input_t method changed to avoid using mbuf tags to store softc pointer. Now it is passed directly trough encap_input_t method. encap_getarg() funtions is removed. - all sockaddr structures and code that uses them removed. We don't have any code in the tree that uses them. All consumers use encap_attach_func() method, that relies on invoking of encapcheck() to determine the needed handler. - introduced struct encap_config, it contains parameters of encap handler that is going to be registered by encap_attach() function. - encap handlers are stored in lists ordered by exact_match value, thus handlers that need more bits to match will be checked first, and if encapcheck method returns exact_match value, the search will be stopped. - all current consumers changed to use new KPI. Reviewed by: mmacy Sponsored by: Yandex LLC Differential Revision: https://reviews.freebsd.org/D15617
2018-06-05 20:51:01 +00:00
struct stf_softc *sc = arg;
struct ip *ip;
struct ip6_hdr *ip6;
u_int8_t otos, itos;
struct ifnet *ifp;
Widen NET_EPOCH coverage. When epoch(9) was introduced to network stack, it was basically dropped in place of existing locking, which was mutexes and rwlocks. For the sake of performance mutex covered areas were as small as possible, so became epoch covered areas. However, epoch doesn't introduce any contention, it just delays memory reclaim. So, there is no point to minimise epoch covered areas in sense of performance. Meanwhile entering/exiting epoch also has non-zero CPU usage, so doing this less often is a win. Not the least is also code maintainability. In the new paradigm we can assume that at any stage of processing a packet, we are inside network epoch. This makes coding both input and output path way easier. On output path we already enter epoch quite early - in the ip_output(), in the ip6_output(). This patch does the same for the input path. All ISR processing, network related callouts, other ways of packet injection to the network stack shall be performed in net_epoch. Any leaf function that walks network configuration now asserts epoch. Tricky part is configuration code paths - ioctls, sysctls. They also call into leaf functions, so some need to be changed. This patch would introduce more epoch recursions (see EPOCH_TRACE) than we had before. They will be cleaned up separately, as several of them aren't trivial. Note, that unlike a lock recursion the epoch recursion is safe and just wastes a bit of resources. Reviewed by: gallatin, hselasky, cy, adrian, kristof Differential Revision: https://reviews.freebsd.org/D19111
2019-10-07 22:40:05 +00:00
NET_EPOCH_ASSERT();
if (proto != IPPROTO_IPV6) {
m_freem(m);
return (IPPROTO_DONE);
}
ip = mtod(m, struct ip *);
if (sc == NULL || (STF2IFP(sc)->if_flags & IFF_UP) == 0) {
m_freem(m);
return (IPPROTO_DONE);
}
ifp = STF2IFP(sc);
#ifdef MAC
mac_ifnet_create_mbuf(ifp, m);
#endif
/*
* perform sanity check against outer src/dst.
* for source, perform ingress filter as well.
*/
if (stf_checkaddr4(sc, &ip->ip_dst, NULL) < 0 ||
stf_checkaddr4(sc, &ip->ip_src, m->m_pkthdr.rcvif) < 0) {
m_freem(m);
return (IPPROTO_DONE);
}
otos = ip->ip_tos;
m_adj(m, off);
if (m->m_len < sizeof(*ip6)) {
m = m_pullup(m, sizeof(*ip6));
if (!m)
return (IPPROTO_DONE);
}
ip6 = mtod(m, struct ip6_hdr *);
/*
* perform sanity check against inner src/dst.
* for source, perform ingress filter as well.
*/
if (stf_checkaddr6(sc, &ip6->ip6_dst, NULL) < 0 ||
stf_checkaddr6(sc, &ip6->ip6_src, m->m_pkthdr.rcvif) < 0) {
m_freem(m);
return (IPPROTO_DONE);
}
itos = (ntohl(ip6->ip6_flow) >> 20) & 0xff;
if ((ifp->if_flags & IFF_LINK1) != 0)
ip_ecn_egress(ECN_ALLOWED, &otos, &itos);
else
ip_ecn_egress(ECN_NOCARE, &otos, &itos);
ip6->ip6_flow &= ~htonl(0xff << 20);
ip6->ip6_flow |= htonl((u_int32_t)itos << 20);
m->m_pkthdr.rcvif = ifp;
Rework IP encapsulation handling code. Currently it has several disadvantages: - it uses single mutex to protect internal structures. It is used by data- and control- path, thus there are no parallelism at all. - it uses single list to keep encap handlers for both INET and INET6 families. - struct encaptab keeps unneeded information (src, dst, masks, protosw), that isn't used by code in the source tree. - matches are prioritized and when many tunneling interfaces are registered, encapcheck handler of each interface is invoked for each packet. The search takes O(n) for n interfaces. All this work is done with exclusive lock held. What this patch includes: - the datapath is converted to be lockless using epoch(9) KPI. - struct encaptab now linked using CK_LIST. - all unused fields removed from struct encaptab. Several new fields addedr: min_length is the minimum packet length, that encapsulation handler expects to see; exact_match is maximum number of bits, that can return an encapsulation handler, when it wants to consume a packet. - IPv6 and IPv4 handlers are stored in separate lists; - added new "encap_lookup_t" method, that will be used later. It is targeted to speedup lookup of needed interface, when gif(4)/gre(4) have many interfaces. - the need to use protosw structure is eliminated. The only pr_input method was used from this structure, so I don't see the need to keep using it. - encap_input_t method changed to avoid using mbuf tags to store softc pointer. Now it is passed directly trough encap_input_t method. encap_getarg() funtions is removed. - all sockaddr structures and code that uses them removed. We don't have any code in the tree that uses them. All consumers use encap_attach_func() method, that relies on invoking of encapcheck() to determine the needed handler. - introduced struct encap_config, it contains parameters of encap handler that is going to be registered by encap_attach() function. - encap handlers are stored in lists ordered by exact_match value, thus handlers that need more bits to match will be checked first, and if encapcheck method returns exact_match value, the search will be stopped. - all current consumers changed to use new KPI. Reviewed by: mmacy Sponsored by: Yandex LLC Differential Revision: https://reviews.freebsd.org/D15617
2018-06-05 20:51:01 +00:00
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)) {
/*
* We need to prepend the address family as
* a four byte field. Cons up a dummy header
* to pacify bpf. This is safe because bpf
* will only read from the mbuf (i.e., it won't
* try to free it or keep a pointer a to it).
*/
u_int32_t af = AF_INET6;
2005-01-11 07:05:56 +00:00
bpf_mtap2(ifp->if_bpf, &af, sizeof(af), m);
}
/*
* Put the packet to the network layer input queue according to the
* specified address family.
* See net/if_gif.c for possible issues with packet processing
* reorder due to extra queueing.
*/
if_inc_counter(ifp, IFCOUNTER_IPACKETS, 1);
if_inc_counter(ifp, IFCOUNTER_IBYTES, m->m_pkthdr.len);
M_SETFIB(m, ifp->if_fib);
netisr_dispatch(NETISR_IPV6, m);
return (IPPROTO_DONE);
}
static int
2015-07-31 09:04:22 +00:00
stf_ioctl(struct ifnet *ifp, u_long cmd, caddr_t data)
{
struct ifaddr *ifa;
struct ifreq *ifr;
struct sockaddr_in6 *sin6;
struct in_addr addr;
int error, mtu;
error = 0;
switch (cmd) {
case SIOCSIFADDR:
ifa = (struct ifaddr *)data;
if (ifa == NULL || ifa->ifa_addr->sa_family != AF_INET6) {
error = EAFNOSUPPORT;
break;
}
sin6 = (struct sockaddr_in6 *)ifa->ifa_addr;
if (!IN6_IS_ADDR_6TO4(&sin6->sin6_addr)) {
error = EINVAL;
break;
}
bcopy(GET_V4(&sin6->sin6_addr), &addr, sizeof(addr));
if (isrfc1918addr(&addr)) {
error = EINVAL;
break;
}
ifp->if_flags |= IFF_UP;
ifp->if_drv_flags |= IFF_DRV_RUNNING;
break;
case SIOCADDMULTI:
case SIOCDELMULTI:
ifr = (struct ifreq *)data;
if (ifr && ifr->ifr_addr.sa_family == AF_INET6)
;
else
error = EAFNOSUPPORT;
break;
case SIOCGIFMTU:
break;
case SIOCSIFMTU:
ifr = (struct ifreq *)data;
mtu = ifr->ifr_mtu;
/* RFC 4213 3.2 ideal world MTU */
if (mtu < IPV6_MINMTU || mtu > IF_MAXMTU - 20)
return (EINVAL);
ifp->if_mtu = mtu;
break;
default:
error = EINVAL;
break;
}
return error;
}