d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
e5d6bfc3c9
freebsd-nq/sys/netinet/ip_fw.h
Julian Elischer 8b07e49a00 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

667 lines
19 KiB
C
Raw Blame History

/*-
* Copyright (c) 2002 Luigi Rizzo, Universita` di Pisa
*
* 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.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
*
* $FreeBSD$
*/
#ifndef _IPFW2_H
#define _IPFW2_H
/*
* The kernel representation of ipfw rules is made of a list of
* 'instructions' (for all practical purposes equivalent to BPF
* instructions), which specify which fields of the packet
* (or its metadata) should be analysed.
*
* Each instruction is stored in a structure which begins with
* "ipfw_insn", and can contain extra fields depending on the
* instruction type (listed below).
* Note that the code is written so that individual instructions
* have a size which is a multiple of 32 bits. This means that, if
* such structures contain pointers or other 64-bit entities,
* (there is just one instance now) they may end up unaligned on
* 64-bit architectures, so the must be handled with care.
*
* "enum ipfw_opcodes" are the opcodes supported. We can have up
* to 256 different opcodes. When adding new opcodes, they should
* be appended to the end of the opcode list before O_LAST_OPCODE,
* this will prevent the ABI from being broken, otherwise users
* will have to recompile ipfw(8) when they update the kernel.
*/
enum ipfw_opcodes { /* arguments (4 byte each) */
O_NOP,
O_IP_SRC, /* u32 = IP */
O_IP_SRC_MASK, /* ip = IP/mask */
O_IP_SRC_ME, /* none */
O_IP_SRC_SET, /* u32=base, arg1=len, bitmap */
O_IP_DST, /* u32 = IP */
O_IP_DST_MASK, /* ip = IP/mask */
O_IP_DST_ME, /* none */
O_IP_DST_SET, /* u32=base, arg1=len, bitmap */
O_IP_SRCPORT, /* (n)port list:mask 4 byte ea */
O_IP_DSTPORT, /* (n)port list:mask 4 byte ea */
O_PROTO, /* arg1=protocol */
O_MACADDR2, /* 2 mac addr:mask */
O_MAC_TYPE, /* same as srcport */
O_LAYER2, /* none */
O_IN, /* none */
O_FRAG, /* none */
O_RECV, /* none */
O_XMIT, /* none */
O_VIA, /* none */
O_IPOPT, /* arg1 = 2*u8 bitmap */
O_IPLEN, /* arg1 = len */
O_IPID, /* arg1 = id */
O_IPTOS, /* arg1 = id */
O_IPPRECEDENCE, /* arg1 = precedence << 5 */
O_IPTTL, /* arg1 = TTL */
O_IPVER, /* arg1 = version */
O_UID, /* u32 = id */
O_GID, /* u32 = id */
O_ESTAB, /* none (tcp established) */
O_TCPFLAGS, /* arg1 = 2*u8 bitmap */
O_TCPWIN, /* arg1 = desired win */
O_TCPSEQ, /* u32 = desired seq. */
O_TCPACK, /* u32 = desired seq. */
O_ICMPTYPE, /* u32 = icmp bitmap */
O_TCPOPTS, /* arg1 = 2*u8 bitmap */
O_VERREVPATH, /* none */
O_VERSRCREACH, /* none */
O_PROBE_STATE, /* none */
O_KEEP_STATE, /* none */
O_LIMIT, /* ipfw_insn_limit */
O_LIMIT_PARENT, /* dyn_type, not an opcode. */
/*
* These are really 'actions'.
*/
O_LOG, /* ipfw_insn_log */
O_PROB, /* u32 = match probability */
O_CHECK_STATE, /* none */
O_ACCEPT, /* none */
O_DENY, /* none */
O_REJECT, /* arg1=icmp arg (same as deny) */
O_COUNT, /* none */
O_SKIPTO, /* arg1=next rule number */
O_PIPE, /* arg1=pipe number */
O_QUEUE, /* arg1=queue number */
O_DIVERT, /* arg1=port number */
O_TEE, /* arg1=port number */
O_FORWARD_IP, /* fwd sockaddr */
O_FORWARD_MAC, /* fwd mac */
O_NAT, /* nope */
/*
* More opcodes.
*/
O_IPSEC, /* has ipsec history */
O_IP_SRC_LOOKUP, /* arg1=table number, u32=value */
O_IP_DST_LOOKUP, /* arg1=table number, u32=value */
O_ANTISPOOF, /* none */
O_JAIL, /* u32 = id */
O_ALTQ, /* u32 = altq classif. qid */
O_DIVERTED, /* arg1=bitmap (1:loop, 2:out) */
O_TCPDATALEN, /* arg1 = tcp data len */
O_IP6_SRC, /* address without mask */
O_IP6_SRC_ME, /* my addresses */
O_IP6_SRC_MASK, /* address with the mask */
O_IP6_DST,
O_IP6_DST_ME,
O_IP6_DST_MASK,
O_FLOW6ID, /* for flow id tag in the ipv6 pkt */
O_ICMP6TYPE, /* icmp6 packet type filtering */
O_EXT_HDR, /* filtering for ipv6 extension header */
O_IP6,
/*
* actions for ng_ipfw
*/
O_NETGRAPH, /* send to ng_ipfw */
O_NGTEE, /* copy to ng_ipfw */
O_IP4,
O_UNREACH6, /* arg1=icmpv6 code arg (deny) */
O_TAG, /* arg1=tag number */
O_TAGGED, /* arg1=tag number */
O_SETFIB, /* arg1=FIB number */
O_FIB, /* arg1=FIB desired fib number */
O_LAST_OPCODE /* not an opcode! */
};
/*
* The extension header are filtered only for presence using a bit
* vector with a flag for each header.
*/
#define EXT_FRAGMENT 0x1
#define EXT_HOPOPTS 0x2
#define EXT_ROUTING 0x4
#define EXT_AH 0x8
#define EXT_ESP 0x10
#define EXT_DSTOPTS 0x20
#define EXT_RTHDR0 0x40
#define EXT_RTHDR2 0x80
/*
* Template for instructions.
*
* ipfw_insn is used for all instructions which require no operands,
* a single 16-bit value (arg1), or a couple of 8-bit values.
*
* For other instructions which require different/larger arguments
* we have derived structures, ipfw_insn_*.
*
* The size of the instruction (in 32-bit words) is in the low
* 6 bits of "len". The 2 remaining bits are used to implement
* NOT and OR on individual instructions. Given a type, you can
* compute the length to be put in "len" using F_INSN_SIZE(t)
*
* F_NOT negates the match result of the instruction.
*
* F_OR is used to build or blocks. By default, instructions
* are evaluated as part of a logical AND. An "or" block
* { X or Y or Z } contains F_OR set in all but the last
* instruction of the block. A match will cause the code
* to skip past the last instruction of the block.
*
* NOTA BENE: in a couple of places we assume that
* sizeof(ipfw_insn) == sizeof(u_int32_t)
* this needs to be fixed.
*
*/
typedef struct _ipfw_insn { /* template for instructions */
enum ipfw_opcodes opcode:8;
u_int8_t len; /* numer of 32-byte words */
#define F_NOT 0x80
#define F_OR 0x40
#define F_LEN_MASK 0x3f
#define F_LEN(cmd) ((cmd)->len & F_LEN_MASK)
u_int16_t arg1;
} ipfw_insn;
/*
* The F_INSN_SIZE(type) computes the size, in 4-byte words, of
* a given type.
*/
#define F_INSN_SIZE(t) ((sizeof (t))/sizeof(u_int32_t))
#define MTAG_IPFW 1148380143 /* IPFW-tagged cookie */
/*
* This is used to store an array of 16-bit entries (ports etc.)
*/
typedef struct _ipfw_insn_u16 {
ipfw_insn o;
u_int16_t ports[2]; /* there may be more */
} ipfw_insn_u16;
/*
* This is used to store an array of 32-bit entries
* (uid, single IPv4 addresses etc.)
*/
typedef struct _ipfw_insn_u32 {
ipfw_insn o;
u_int32_t d[1]; /* one or more */
} ipfw_insn_u32;
/*
* This is used to store IP addr-mask pairs.
*/
typedef struct _ipfw_insn_ip {
ipfw_insn o;
struct in_addr addr;
struct in_addr mask;
} ipfw_insn_ip;
/*
* This is used to forward to a given address (ip).
*/
typedef struct _ipfw_insn_sa {
ipfw_insn o;
struct sockaddr_in sa;
} ipfw_insn_sa;
/*
* This is used for MAC addr-mask pairs.
*/
typedef struct _ipfw_insn_mac {
ipfw_insn o;
u_char addr[12]; /* dst[6] + src[6] */
u_char mask[12]; /* dst[6] + src[6] */
} ipfw_insn_mac;
/*
* This is used for interface match rules (recv xx, xmit xx).
*/
typedef struct _ipfw_insn_if {
ipfw_insn o;
union {
struct in_addr ip;
int glob;
} p;
char name[IFNAMSIZ];
} ipfw_insn_if;
/*
* This is used for storing an altq queue id number.
*/
typedef struct _ipfw_insn_altq {
ipfw_insn o;
u_int32_t qid;
} ipfw_insn_altq;
/*
* This is used for limit rules.
*/
typedef struct _ipfw_insn_limit {
ipfw_insn o;
u_int8_t _pad;
u_int8_t limit_mask; /* combination of DYN_* below */
#define DYN_SRC_ADDR 0x1
#define DYN_SRC_PORT 0x2
#define DYN_DST_ADDR 0x4
#define DYN_DST_PORT 0x8
u_int16_t conn_limit;
} ipfw_insn_limit;
/*
* This is used for log instructions.
*/
typedef struct _ipfw_insn_log {
ipfw_insn o;
u_int32_t max_log; /* how many do we log -- 0 = all */
u_int32_t log_left; /* how many left to log */
} ipfw_insn_log;
/*
* Data structures required by both ipfw(8) and ipfw(4) but not part of the
* management API are protected by IPFW_INTERNAL.
*/
#ifdef IPFW_INTERNAL
/* Server pool support (LSNAT). */
struct cfg_spool {
LIST_ENTRY(cfg_spool) _next; /* chain of spool instances */
struct in_addr addr;
u_short port;
};
#endif
/* Redirect modes id. */
#define REDIR_ADDR 0x01
#define REDIR_PORT 0x02
#define REDIR_PROTO 0x04
#ifdef IPFW_INTERNAL
/* Nat redirect configuration. */
struct cfg_redir {
LIST_ENTRY(cfg_redir) _next; /* chain of redir instances */
u_int16_t mode; /* type of redirect mode */
struct in_addr laddr; /* local ip address */
struct in_addr paddr; /* public ip address */
struct in_addr raddr; /* remote ip address */
u_short lport; /* local port */
u_short pport; /* public port */
u_short rport; /* remote port */
u_short pport_cnt; /* number of public ports */
u_short rport_cnt; /* number of remote ports */
int proto; /* protocol: tcp/udp */
struct alias_link **alink;
/* num of entry in spool chain */
u_int16_t spool_cnt;
/* chain of spool instances */
LIST_HEAD(spool_chain, cfg_spool) spool_chain;
};
#endif
#define NAT_BUF_LEN 1024
#ifdef IPFW_INTERNAL
/* Nat configuration data struct. */
struct cfg_nat {
/* chain of nat instances */
LIST_ENTRY(cfg_nat) _next;
int id; /* nat id */
struct in_addr ip; /* nat ip address */
char if_name[IF_NAMESIZE]; /* interface name */
int mode; /* aliasing mode */
struct libalias *lib; /* libalias instance */
/* number of entry in spool chain */
int redir_cnt;
/* chain of redir instances */
LIST_HEAD(redir_chain, cfg_redir) redir_chain;
};
#endif
#define SOF_NAT sizeof(struct cfg_nat)
#define SOF_REDIR sizeof(struct cfg_redir)
#define SOF_SPOOL sizeof(struct cfg_spool)
/* Nat command. */
typedef struct _ipfw_insn_nat {
ipfw_insn o;
struct cfg_nat *nat;
} ipfw_insn_nat;
/* Apply ipv6 mask on ipv6 addr */
#define APPLY_MASK(addr,mask) \
(addr)->__u6_addr.__u6_addr32[0] &= (mask)->__u6_addr.__u6_addr32[0]; \
(addr)->__u6_addr.__u6_addr32[1] &= (mask)->__u6_addr.__u6_addr32[1]; \
(addr)->__u6_addr.__u6_addr32[2] &= (mask)->__u6_addr.__u6_addr32[2]; \
(addr)->__u6_addr.__u6_addr32[3] &= (mask)->__u6_addr.__u6_addr32[3];
/* Structure for ipv6 */
typedef struct _ipfw_insn_ip6 {
ipfw_insn o;
struct in6_addr addr6;
struct in6_addr mask6;
} ipfw_insn_ip6;
/* Used to support icmp6 types */
typedef struct _ipfw_insn_icmp6 {
ipfw_insn o;
uint32_t d[7]; /* XXX This number si related to the netinet/icmp6.h
* define ICMP6_MAXTYPE
* as follows: n = ICMP6_MAXTYPE/32 + 1
* Actually is 203
*/
} ipfw_insn_icmp6;
/*
* Here we have the structure representing an ipfw rule.
*
* It starts with a general area (with link fields and counters)
* followed by an array of one or more instructions, which the code
* accesses as an array of 32-bit values.
*
* Given a rule pointer r:
*
* r->cmd is the start of the first instruction.
* ACTION_PTR(r) is the start of the first action (things to do
* once a rule matched).
*
* When assembling instruction, remember the following:
*
* + if a rule has a "keep-state" (or "limit") option, then the
* first instruction (at r->cmd) MUST BE an O_PROBE_STATE
* + if a rule has a "log" option, then the first action
* (at ACTION_PTR(r)) MUST be O_LOG
* + if a rule has an "altq" option, it comes after "log"
* + if a rule has an O_TAG option, it comes after "log" and "altq"
*
* NOTE: we use a simple linked list of rules because we never need
* to delete a rule without scanning the list. We do not use
* queue(3) macros for portability and readability.
*/
struct ip_fw {
struct ip_fw *next; /* linked list of rules */
struct ip_fw *next_rule; /* ptr to next [skipto] rule */
/* 'next_rule' is used to pass up 'set_disable' status */
u_int16_t act_ofs; /* offset of action in 32-bit units */
u_int16_t cmd_len; /* # of 32-bit words in cmd */
u_int16_t rulenum; /* rule number */
u_int8_t set; /* rule set (0..31) */
#define RESVD_SET 31 /* set for default and persistent rules */
u_int8_t _pad; /* padding */
/* These fields are present in all rules. */
u_int64_t pcnt; /* Packet counter */
u_int64_t bcnt; /* Byte counter */
u_int32_t timestamp; /* tv_sec of last match */
ipfw_insn cmd[1]; /* storage for commands */
};
#define ACTION_PTR(rule) \
(ipfw_insn *)( (u_int32_t *)((rule)->cmd) + ((rule)->act_ofs) )
#define RULESIZE(rule) (sizeof(struct ip_fw) + \
((struct ip_fw *)(rule))->cmd_len * 4 - 4)
/*
* This structure is used as a flow mask and a flow id for various
* parts of the code.
*/
struct ipfw_flow_id {
u_int32_t dst_ip;
u_int32_t src_ip;
u_int16_t dst_port;
u_int16_t src_port;
u_int8_t fib;
u_int8_t proto;
u_int8_t flags; /* protocol-specific flags */
uint8_t addr_type; /* 4 = ipv4, 6 = ipv6, 1=ether ? */
struct in6_addr dst_ip6; /* could also store MAC addr! */
struct in6_addr src_ip6;
u_int32_t flow_id6;
u_int32_t frag_id6;
};
#define IS_IP6_FLOW_ID(id) ((id)->addr_type == 6)
/*
* Dynamic ipfw rule.
*/
typedef struct _ipfw_dyn_rule ipfw_dyn_rule;
struct _ipfw_dyn_rule {
ipfw_dyn_rule *next; /* linked list of rules. */
struct ip_fw *rule; /* pointer to rule */
/* 'rule' is used to pass up the rule number (from the parent) */
ipfw_dyn_rule *parent; /* pointer to parent rule */
u_int64_t pcnt; /* packet match counter */
u_int64_t bcnt; /* byte match counter */
struct ipfw_flow_id id; /* (masked) flow id */
u_int32_t expire; /* expire time */
u_int32_t bucket; /* which bucket in hash table */
u_int32_t state; /* state of this rule (typically a
* combination of TCP flags)
*/
u_int32_t ack_fwd; /* most recent ACKs in forward */
u_int32_t ack_rev; /* and reverse directions (used */
/* to generate keepalives) */
u_int16_t dyn_type; /* rule type */
u_int16_t count; /* refcount */
};
/*
* Definitions for IP option names.
*/
#define IP_FW_IPOPT_LSRR 0x01
#define IP_FW_IPOPT_SSRR 0x02
#define IP_FW_IPOPT_RR 0x04
#define IP_FW_IPOPT_TS 0x08
/*
* Definitions for TCP option names.
*/
#define IP_FW_TCPOPT_MSS 0x01
#define IP_FW_TCPOPT_WINDOW 0x02
#define IP_FW_TCPOPT_SACK 0x04
#define IP_FW_TCPOPT_TS 0x08
#define IP_FW_TCPOPT_CC 0x10
#define ICMP_REJECT_RST 0x100 /* fake ICMP code (send a TCP RST) */
#define ICMP6_UNREACH_RST 0x100 /* fake ICMPv6 code (send a TCP RST) */
/*
* These are used for lookup tables.
*/
typedef struct _ipfw_table_entry {
in_addr_t addr; /* network address */
u_int32_t value; /* value */
u_int16_t tbl; /* table number */
u_int8_t masklen; /* mask length */
} ipfw_table_entry;
typedef struct _ipfw_table {
u_int32_t size; /* size of entries in bytes */
u_int32_t cnt; /* # of entries */
u_int16_t tbl; /* table number */
ipfw_table_entry ent[0]; /* entries */
} ipfw_table;
#define IP_FW_TABLEARG 65535
/*
* Main firewall chains definitions and global var's definitions.
*/
#ifdef _KERNEL
/* Return values from ipfw_chk() */
enum {
IP_FW_PASS = 0,
IP_FW_DENY,
IP_FW_DIVERT,
IP_FW_TEE,
IP_FW_DUMMYNET,
IP_FW_NETGRAPH,
IP_FW_NGTEE,
IP_FW_NAT,
};
/* flags for divert mtag */
#define IP_FW_DIVERT_LOOPBACK_FLAG 0x00080000
#define IP_FW_DIVERT_OUTPUT_FLAG 0x00100000
/*
* Structure for collecting parameters to dummynet for ip6_output forwarding
*/
struct _ip6dn_args {
struct ip6_pktopts *opt_or;
struct route_in6 ro_or;
int flags_or;
struct ip6_moptions *im6o_or;
struct ifnet *origifp_or;
struct ifnet *ifp_or;
struct sockaddr_in6 dst_or;
u_long mtu_or;
struct route_in6 ro_pmtu_or;
};
/*
* Arguments for calling ipfw_chk() and dummynet_io(). We put them
* all into a structure because this way it is easier and more
* efficient to pass variables around and extend the interface.
*/
struct ip_fw_args {
struct mbuf *m; /* the mbuf chain */
struct ifnet *oif; /* output interface */
struct sockaddr_in *next_hop; /* forward address */
struct ip_fw *rule; /* matching rule */
struct ether_header *eh; /* for bridged packets */
struct ipfw_flow_id f_id; /* grabbed from IP header */
u_int32_t cookie; /* a cookie depending on rule action */
struct inpcb *inp;
struct _ip6dn_args dummypar; /* dummynet->ip6_output */
struct sockaddr_in hopstore; /* store here if cannot use a pointer */
};
/*
* Function definitions.
*/
/* Firewall hooks */
struct sockopt;
struct dn_flow_set;
int ipfw_check_in(void *, struct mbuf **, struct ifnet *, int, struct inpcb *inp);
int ipfw_check_out(void *, struct mbuf **, struct ifnet *, int, struct inpcb *inp);
int ipfw_chk(struct ip_fw_args *);
int ipfw_init(void);
void ipfw_destroy(void);
typedef int ip_fw_ctl_t(struct sockopt *);
extern ip_fw_ctl_t *ip_fw_ctl_ptr;
extern int fw_one_pass;
extern int fw_enable;
#ifdef INET6
extern int fw6_enable;
#endif
/* For kernel ipfw_ether and ipfw_bridge. */
typedef int ip_fw_chk_t(struct ip_fw_args *args);
extern ip_fw_chk_t *ip_fw_chk_ptr;
#define IPFW_LOADED (ip_fw_chk_ptr != NULL)
#ifdef IPFW_INTERNAL
#define IPFW_TABLES_MAX 128
struct ip_fw_chain {
struct ip_fw *rules; /* list of rules */
struct ip_fw *reap; /* list of rules to reap */
LIST_HEAD(, cfg_nat) nat; /* list of nat entries */
struct radix_node_head *tables[IPFW_TABLES_MAX];
struct rwlock rwmtx;
};
#define IPFW_LOCK_INIT(_chain) \
rw_init(&(_chain)->rwmtx, "IPFW static rules")
#define IPFW_LOCK_DESTROY(_chain) rw_destroy(&(_chain)->rwmtx)
#define IPFW_WLOCK_ASSERT(_chain) rw_assert(&(_chain)->rwmtx, RA_WLOCKED)
#define IPFW_RLOCK(p) rw_rlock(&(p)->rwmtx)
#define IPFW_RUNLOCK(p) rw_runlock(&(p)->rwmtx)
#define IPFW_WLOCK(p) rw_wlock(&(p)->rwmtx)
#define IPFW_WUNLOCK(p) rw_wunlock(&(p)->rwmtx)
#define LOOKUP_NAT(l, i, p) do { \
LIST_FOREACH((p), &(l.nat), _next) { \
if ((p)->id == (i)) { \
break; \
} \
} \
} while (0)
typedef int ipfw_nat_t(struct ip_fw_args *, struct cfg_nat *, struct mbuf *);
typedef int ipfw_nat_cfg_t(struct sockopt *);
#endif
#endif /* _KERNEL */
#endif /* _IPFW2_H */
Reference in New Issue View Git Blame Copy Permalink