PF(4) | Device Drivers Manual | PF(4) |
pf
— packet
filter
pseudo-device pf
Packet filtering takes place in the kernel. A pseudo-device, /dev/pf, allows userland processes to control the behavior of the packet filter through an ioctl(2) interface. There are commands to enable and disable the filter, load rulesets, add and remove individual rules or state table entries, and retrieve statistics. The most commonly used functions are covered by pfctl(8).
Manipulations like loading a ruleset that involve more than a single ioctl(2) call require a so-called ticket, which prevents the occurrence of multiple concurrent manipulations.
Fields of ioctl(2) parameter structures that refer to packet data (like addresses and ports) are generally expected in network byte-order.
Rules and address tables are contained in so-called
anchors. When
servicing an ioctl(2) request,
if the anchor field of the argument structure is empty, the kernel will use
the default anchor (i.e., the main ruleset) in operations. Anchors are
specified by name and may be nested, with components separated by
‘/’ characters, similar to how file system hierarchies are
laid out. The final component of the anchor path is the anchor under which
operations will be performed. Anchor names with characters after the
terminating null byte are considered invalid; if used in an ioctl,
EINVAL
will be returned.
pf
supports the following
ioctl(2) commands, available
through <net/pfvar.h>
:
DIOCSTART
DIOCSTOP
DIOCADDRULE
struct pfioc_rule *prstruct pfioc_rule { u_int32_t action; u_int32_t ticket; u_int32_t nr; char anchor[PATH_MAX]; char anchor_call[PATH_MAX]; struct pf_rule rule; };
Add rule at the end of the inactive
ruleset. This call requires a ticket obtained
through a preceding DIOCXBEGIN
call. The
optional anchor name indicates the anchor in which
to append the rule. nr and
action are ignored.
DIOCADDQUEUE
struct pfioc_queue *qstruct pfioc_queue { u_int32_t ticket; u_int nr; struct pf_queuespec queue; };
DIOCGETRULES
struct pfioc_rule *prDIOCGETRULE
calls and the number
nr of rules in the active ruleset.DIOCGETRULE
struct pfioc_rule *prDIOCGETRULES
call. If action
is set to PF_GET_CLR_CNTR
, the per-rule statistics
on the requested rule are cleared.DIOCGETQUEUES
struct pfioc_queue *pqDIOCGETQUEUE
calls and the number
nr of queues in the active list.DIOCGETQUEUE
struct pfioc_queue *pqDIOCGETQUEUES
call.DIOCGETQSTATS
struct pfioc_qstats *pqstruct pfioc_qstats { u_int32_t ticket; u_int32_t nr; struct pf_queuespec queue; void *buf; int nbytes; };
This call fills in a pointer to the buffer of statistics buf, of length nbytes, for the queue specified by nr.
DIOCGETRULESETS
struct pfioc_ruleset *prstruct pfioc_ruleset { u_int32_t nr; char path[PATH_MAX]; char name[PF_ANCHOR_NAME_SIZE]; };
Get the number nr of rulesets (i.e.,
anchors) directly attached to the anchor named by
path for use in subsequent
DIOCGETRULESET
calls. Nested anchors, since they
are not directly attached to the given anchor, will not be included.
This ioctl returns EINVAL
if the given anchor
does not exist.
DIOCGETRULESET
struct pfioc_ruleset *prDIOCGETRULESETS
call. This ioctl returns
EINVAL
if the given anchor does not exist or
EBUSY
if another process is concurrently updating
a ruleset.DIOCADDSTATE
struct pfioc_state *psstruct pfioc_state { struct pfsync_state state; };
DIOCGETSTATE
struct pfioc_state *psDIOCKILLSTATES
struct pfioc_state_kill *pskstruct pfioc_state_kill { struct pf_state_cmp psk_pfcmp; sa_family_t psk_af; int psk_proto; struct pf_rule_addr psk_src; struct pf_rule_addr psk_dst; char psk_ifname[IFNAMSIZ]; char psk_label[PF_RULE_LABEL_SIZE]; u_int psk_killed; u_int16_t psk_rdomain; };
DIOCCLRSTATES
struct pfioc_state_kill *pskDIOCKILLSTATES
,
but ignores all fields of the pfioc_state_kill
structure, except psk_ifname.DIOCGETSTATUS
struct pf_status *sstruct pf_status { u_int64_t counters[PFRES_MAX]; u_int64_t lcounters[LCNT_MAX]; /* limit counters */ u_int64_t fcounters[FCNT_MAX]; u_int64_t scounters[SCNT_MAX]; u_int64_t pcounters[2][2][3]; u_int64_t bcounters[2][2]; u_int64_t stateid; u_int64_t syncookies_inflight[2]; /* unACKed SYNcookies */ time_t since; u_int32_t running; u_int32_t states; u_int32_t states_halfopen; u_int32_t src_nodes; u_int32_t debug; u_int32_t hostid; u_int32_t reass; /* reassembly */ u_int8_t syncookies_active; u_int8_t syncookies_mode; /* never/always/adaptive */ u_int8_t pad[2]; char ifname[IFNAMSIZ]; u_int8_t pf_chksum[PF_MD5_DIGEST_LENGTH]; };
DIOCCLRSTATUS
DIOCNATLOOK
struct pfioc_natlook *pnlstruct pfioc_natlook { struct pf_addr saddr; struct pf_addr daddr; struct pf_addr rsaddr; struct pf_addr rdaddr; u_int16_t rdomain; u_int16_t rrdomain; u_int16_t sport; u_int16_t dport; u_int16_t rsport; u_int16_t rdport; sa_family_t af; u_int8_t proto; u_int8_t direction; };
This was primarily used to support transparent proxies with
rdr-to rules. New proxies should use divert-to rules instead. These do
not require access to the privileged /dev/pf
device and preserve the original destination address for
getsockname(2). For
SOCK_DGRAM
sockets, the
ip(4) socket options
IP_RECVDSTADDR
and
IP_RECVDSTPORT
can be used to retrieve the
destination address and port.
DIOCSETDEBUG
u_int32_t *levelDIOCGETSTATES
struct pfioc_states *psstruct pfioc_states { size_t ps_len; union { caddr_t psu_buf; struct pfsync_state *psu_states; } ps_u; #define ps_buf ps_u.psu_buf #define ps_states ps_u.psu_states };
If ps_len is non-zero on entry, as many
states as possible that can fit into this size will be copied into the
supplied buffer ps_states. On exit,
ps_len is always set to the total size required to
hold all state table entries (i.e., it is set to
sizeof(struct pfsync_state) * nr
).
DIOCCHANGERULE
struct pfioc_rule *pcrThe type of operation to be performed is indicated by action, which can be any of the following:
enum { PF_CHANGE_NONE, PF_CHANGE_ADD_HEAD, PF_CHANGE_ADD_TAIL, PF_CHANGE_ADD_BEFORE, PF_CHANGE_ADD_AFTER, PF_CHANGE_REMOVE, PF_CHANGE_GET_TICKET };
ticket must be set to the value obtained
with PF_CHANGE_GET_TICKET
for all actions except
PF_CHANGE_GET_TICKET
.
anchor indicates to which anchor the operation
applies. nr indicates the rule number against
which PF_CHANGE_ADD_BEFORE
,
PF_CHANGE_ADD_AFTER
, or
PF_CHANGE_REMOVE
actions are applied.
DIOCSETTIMEOUT
struct pfioc_tm *ptstruct pfioc_tm { int timeout; int seconds; };
Set the state timeout of timeout to
seconds. The old value will be placed into
seconds. For possible values of
timeout, consult the
PFTM_*
values in
<net/pfvar.h>
.
DIOCGETTIMEOUT
struct pfioc_tm *ptDIOCSETLIMIT
struct pfioc_limit *plstruct pfioc_limit { int index; unsigned limit; }; enum { PF_LIMIT_STATES, PF_LIMIT_SRC_NODES, PF_LIMIT_FRAGS, PF_LIMIT_TABLES, PF_LIMIT_TABLE_ENTRIES, PF_LIMIT_PKTDELAY_PKTS, PF_LIMIT_MAX };
DIOCGETLIMIT
struct pfioc_limit *plDIOCRCLRTABLES
struct pfioc_table *ioDIOCRCLRTABLES
,
pfrio_ndel contains on exit the number of tables
deleted.
struct pfioc_table { struct pfr_table pfrio_table; void *pfrio_buffer; int pfrio_esize; int pfrio_size; int pfrio_size2; int pfrio_nadd; int pfrio_ndel; int pfrio_nchange; int pfrio_flags; u_int32_t pfrio_ticket; }; #define pfrio_exists pfrio_nadd #define pfrio_nzero pfrio_nadd #define pfrio_nmatch pfrio_nadd #define pfrio_naddr pfrio_size2 #define pfrio_setflag pfrio_size2 #define pfrio_clrflag pfrio_nadd
DIOCRADDTABLES
struct pfioc_table *iostruct pfr_table { char pfrt_anchor[PATH_MAX]; char pfrt_name[PF_TABLE_NAME_SIZE]; u_int32_t pfrt_flags; u_int8_t pfrt_fback; };
DIOCRDELTABLES
struct pfioc_table *ioDIOCRGETTABLES
struct pfioc_table *ioDIOCRGETTSTATS
struct pfioc_table *ioDIOCRGETTABLES
but is used to
get an array of pfr_tstats structures.
struct pfr_tstats { struct pfr_table pfrts_t; u_int64_t pfrts_packets [PFR_DIR_MAX][PFR_OP_TABLE_MAX]; u_int64_t pfrts_bytes [PFR_DIR_MAX][PFR_OP_TABLE_MAX]; u_int64_t pfrts_match; u_int64_t pfrts_nomatch; time_t pfrts_tzero; int pfrts_cnt; int pfrts_refcnt[PFR_REFCNT_MAX]; }; #define pfrts_name pfrts_t.pfrt_name #define pfrts_flags pfrts_t.pfrt_flags
DIOCRCLRTSTATS
struct pfioc_table *ioDIOCRCLRADDRS
struct pfioc_table *ioDIOCRADDADDRS
struct pfioc_table *iostruct pfr_addr { union { struct in_addr _pfra_ip4addr; struct in6_addr _pfra_ip6addr; } pfra_u; char pfra_ifname[IFNAMSIZ]; u_int32_t pfra_states; u_int16_t pfra_weight; u_int8_t pfra_af; u_int8_t pfra_net; u_int8_t pfra_not; u_int8_t pfra_fback; u_int8_t pfra_type; u_int8_t pad[7]; }; #define pfra_ip4addr pfra_u._pfra_ip4addr #define pfra_ip6addr pfra_u._pfra_ip6addr
DIOCRDELADDRS
struct pfioc_table *ioDIOCRSETADDRS
struct pfioc_table *ioOn entry, pfrio_table contains the table
ID and pfrio_buffer must point to an array of
struct pfr_addr containing at least
pfrio_size elements which become the new contents
of the table. pfrio_esize must be the size of
struct pfr_addr. Additionally, if
pfrio_size2 is non-zero,
pfrio_buffer[pfrio_size..pfrio_size2] must be a
writeable buffer, into which the kernel can copy the addresses that have
been deleted during the replace operation. On exit,
pfrio_ndel, pfrio_nadd, and
pfrio_nchange contain the number of addresses
deleted, added, and changed by the kernel. If
pfrio_size2 was set on entry,
pfrio_size2 will point to the size of the buffer
used, exactly like DIOCRGETADDRS
.
DIOCRGETADDRS
struct pfioc_table *ioDIOCRGETASTATS
struct pfioc_table *ioDIOCRGETADDRS
but is used to get
an array of pfr_astats structures.
struct pfr_astats { struct pfr_addr pfras_a; u_int64_t pfras_packets [PFR_DIR_MAX][PFR_OP_ADDR_MAX]; u_int64_t pfras_bytes [PFR_DIR_MAX][PFR_OP_ADDR_MAX]; time_t pfras_tzero; };
DIOCRCLRASTATS
struct pfioc_table *ioDIOCRTSTADDRS
struct pfioc_table *ioDIOCRSETTFLAGS
struct pfioc_table *ioPFR_TFLAG_CONST
or
PFR_TFLAG_PERSIST
flags of a table. On entry,
pfrio_buffer must point to an array of
struct pfr_table containing at least
pfrio_size elements.
pfrio_esize must be the size of
struct pfr_table.
pfrio_setflag must contain the flags to add, while
pfrio_clrflag must contain the flags to remove. On
exit, pfrio_nchange and
pfrio_ndel contain the number of tables altered or
deleted by the kernel. Yes, tables can be deleted if one removes the
PFR_TFLAG_PERSIST
flag of an unreferenced
table.DIOCRINADEFINE
struct pfioc_table *ioDIOCXBEGIN
struct pfioc_trans *iostruct pfioc_trans { int size; /* number of elements */ int esize; /* size of each element in bytes */ struct pfioc_trans_e { int type; char anchor[PATH_MAX]; u_int32_t ticket; } *array; };
Clear all the inactive rulesets specified in the
pfioc_trans_e array. For each ruleset, a ticket is
returned for subsequent "add rule" ioctls, as well as for the
DIOCXCOMMIT
and
DIOCXROLLBACK
calls.
Ruleset types, identified by type, can be one of the following:
PF_TRANS_RULESET
PF_TRANS_TABLE
DIOCXCOMMIT
struct pfioc_trans *ioEBUSY
if another process is
concurrently updating some of the same rulesets.DIOCXROLLBACK
struct pfioc_trans *ioDIOCXBEGIN
.
DIOCXROLLBACK
will silently ignore rulesets for
which the ticket is invalid.DIOCSETHOSTID
u_int32_t *hostidDIOCOSFPFLUSH
DIOCOSFPADD
struct pf_osfp_ioctl *iostruct pf_osfp_ioctl { struct pf_osfp_entry fp_os; pf_tcpopts_t fp_tcpopts; /* packed TCP options */ u_int16_t fp_wsize; /* TCP window size */ u_int16_t fp_psize; /* ip->ip_len */ u_int16_t fp_mss; /* TCP MSS */ u_int16_t fp_flags; u_int8_t fp_optcnt; /* TCP option count */ u_int8_t fp_wscale; /* TCP window scaling */ u_int8_t fp_ttl; /* IPv4 TTL */ int fp_getnum; /* DIOCOSFPGET number */ }; struct pf_osfp_entry { SLIST_ENTRY(pf_osfp_entry) fp_entry; pf_osfp_t fp_os; int fp_enflags; #define PF_OSFP_EXPANDED 0x001 /* expanded entry */ #define PF_OSFP_GENERIC 0x002 /* generic signature */ #define PF_OSFP_NODETAIL 0x004 /* no p0f details */ #define PF_OSFP_LEN 32 u_char fp_class_nm[PF_OSFP_LEN]; u_char fp_version_nm[PF_OSFP_LEN]; u_char fp_subtype_nm[PF_OSFP_LEN]; };
Add a passive OS fingerprint to the table. Set fp_os.fp_os to the packed fingerprint, fp_os.fp_class_nm to the name of the class (Linux, Windows, etc), fp_os.fp_version_nm to the name of the version (NT, 95, 98), and fp_os.fp_subtype_nm to the name of the subtype or patchlevel. The members fp_mss, fp_wsize, fp_psize, fp_ttl, fp_optcnt, and fp_wscale are set to the TCP MSS, the TCP window size, the IP length, the IP TTL, the number of TCP options, and the TCP window scaling constant of the TCP SYN packet, respectively.
The fp_flags member is filled according
to the <net/pfvar.h>
include file PF_OSFP_*
defines. The
fp_tcpopts member contains packed TCP options.
Each option uses PF_OSFP_TCPOPT_BITS
bits in the
packed value. Options include any of
PF_OSFP_TCPOPT_NOP
,
PF_OSFP_TCPOPT_SACK
,
PF_OSFP_TCPOPT_WSCALE
,
PF_OSFP_TCPOPT_MSS
, or
PF_OSFP_TCPOPT_TS
.
The fp_getnum member is not used with this ioctl.
The structure's slack space must be zeroed for correct operation; memset(3) the whole structure to zero before filling and sending to the kernel.
DIOCOSFPGET
struct pf_osfp_ioctl *ioEBUSY
.DIOCGETSRCNODES
struct pfioc_src_nodes *psnstruct pfioc_src_nodes { size_t psn_len; union { caddr_t psu_buf; struct pf_src_node *psu_src_nodes; } psn_u; #define psn_buf psn_u.psu_buf #define psn_src_nodes psn_u.psu_src_nodes };
Get the list of source nodes kept by sticky addresses and source tracking. The ioctl must be called once with psn_len set to 0. If the ioctl returns without error, psn_len will be set to the size of the buffer required to hold all the pf_src_node structures held in the table. A buffer of this size should then be allocated, and a pointer to this buffer placed in psn_buf. The ioctl must then be called again to fill this buffer with the actual source node data. After that call, psn_len will be set to the length of the buffer actually used.
DIOCCLRSRCNODES
DIOCIGETIFACES
struct pfioc_iface *iopf
. All the ioctls that manipulate interfaces use
the same structure described below:
struct pfioc_iface { char pfiio_name[IFNAMSIZ]; void *pfiio_buffer; int pfiio_esize; int pfiio_size; int pfiio_nzero; int pfiio_flags; };
If not empty, pfiio_name can be used to
restrict the search to a specific interface or group.
pfiio_buffer[pfiio_size] is the user-supplied
buffer for returning the data. On entry,
pfiio_size contains the number of
pfi_kif entries that can fit into the buffer. The
kernel will replace this value by the real number of entries it wants to
return. pfiio_esize should be set to
sizeof(struct pfi_kif)
.
The data is returned in the pfi_kif structure described below:
struct pfi_kif { char pfik_name[IFNAMSIZ]; RB_ENTRY(pfi_kif) pfik_tree; u_int64_t pfik_packets[2][2][2]; u_int64_t pfik_bytes[2][2][2]; time_t pfik_tzero; int pfik_flags; int pfik_flags_new; void *pfik_ah_cookie; struct ifnet *pfik_ifp; struct ifg_group *pfik_group; int pfik_states; int pfik_rules; int pfik_routes; TAILQ_HEAD(, pfi_dynaddr) pfik_dynaddrs; };
DIOCSETSTATUSIF
struct pfioc_iface *piDIOCSETIFFLAG
struct pfioc_iface *iopf
internal interface description. The filtering
process is the same as for DIOCIGETIFACES
.
#define PFI_IFLAG_SKIP 0x0100 /* skip filtering on interface */
DIOCCLRIFFLAG
struct pfioc_iface *ioDIOCSETIFFLAG
above but clears the
flags.DIOCKILLSRCNODES
struct pfioc_src_node_kill *psnkstruct pfioc_src_node_kill { sa_family_t psnk_af; struct pf_rule_addr psnk_src; struct pf_rule_addr psnk_dst; u_int psnk_killed; };
The following example demonstrates how to use the
DIOCGETLIMIT
command to show the hard limit of a
memory pool used by the packet filter:
#include <sys/types.h> #include <sys/socket.h> #include <sys/ioctl.h> #include <sys/fcntl.h> #include <netinet/in.h> #include <net/if.h> #include <net/pfvar.h> #include <err.h> #include <limits.h> #include <stdio.h> #include <stdlib.h> #include <string.h> static const struct { const char *name; int index; } pf_limits[] = { { "states", PF_LIMIT_STATES }, { "src-nodes", PF_LIMIT_SRC_NODES }, { "frags", PF_LIMIT_FRAGS }, { "tables", PF_LIMIT_TABLES }, { "table-entries", PF_LIMIT_TABLE_ENTRIES }, { NULL, 0 } }; void usage(void) { int i; fprintf(stderr, "usage: %s [", getprogname()); for (i = 0; pf_limits[i].name; i++) fprintf(stderr, "%s%s", (i > 0 ? "|" : ""), pf_limits[i].name); fprintf(stderr, "]\n"); exit(1); } int main(int argc, char *argv[]) { struct pfioc_limit pl; int i, dev; int pool_index = -1; if (argc != 2) usage(); for (i = 0; pf_limits[i].name; i++) if (strcmp(argv[1], pf_limits[i].name) == 0) { pool_index = pf_limits[i].index; break; } if (pool_index == -1) { warnx("no such memory pool: %s", argv[1]); usage(); } dev = open("/dev/pf", O_RDWR); if (dev == -1) err(1, "open(\"/dev/pf\") failed"); memset(&pl, 0, sizeof(struct pfioc_limit)); pl.index = pool_index; if (ioctl(dev, DIOCGETLIMIT, &pl) == -1) err(1, "DIOCGETLIMIT"); printf("The %s memory pool has ", pf_limits[i].name); if (pl.limit == UINT_MAX) printf("unlimited entries.\n"); else printf("a hard limit of %u entries.\n", pl.limit); return 0; }
ioctl(2), bridge(4), pflog(4), pflow(4), pfsync(4), pf.conf(5), pfctl(8)
The pf
packet filtering mechanism first
appeared in OpenBSD 3.0.
May 26, 2019 | OpenBSD-6.8 |