BPF(4) BSD Kernel Interfaces Manual BPF(4)
NAME
bpf -- Berkeley Packet Filter
SYNOPSIS
pseudo-device bpf
DESCRIPTION
The Berkeley Packet Filter provides a raw interface to data link layers
in a protocol independent fashion. All packets on the network, even
those destined for other hosts, are accessible through this mechanism.
The packet filter appears as a character special device, /dev/bpf0,
/dev/bpf1, etc. After opening the device, the file descriptor must be
bound to a specific network interface with the BIOCSETIF ioctl. A given
interface can be shared be multiple listeners, and the filter underlying
each descriptor will see an identical packet stream.
A separate device file is required for each minor device. If a file is
in use, the open will fail and errno will be set to EBUSY.
Associated with each open instance of a bpf file is a user-settable
packet filter. Whenever a packet is received by an interface, all file
descriptors listening on that interface apply their filter. Each
descriptor that accepts the packet receives its own copy.
Reads from these files return the next group of packets that have matched
the filter. To improve performance, the buffer passed to read must be
the same size as the buffers used internally by bpf. This size is
returned by the BIOCGBLEN ioctl (see below), and can be set with
BIOCSBLEN. Note that an individual packet larger than this size is nec-
essarily truncated.
The packet filter will support any link level protocol that has fixed
length headers. Currently, only Ethernet, SLIP, and P drivers have
been modified to interact with bpf.
Since packet data is in network byte order, applications should use the
byteorder(3) macros to extract multi-byte values.
A packet can be sent out on the network by writing to a bpf file descrip-
tor. The writes are unbuffered, meaning only one packet can be processed
per write. Currently, only writes to Ethernets and SLIP links are sup-
ported.
When the last minor device is opened, an additional minor device is cre-
ated on demand. The maximum number of devices that can be created is con-
trolled by the sysctl debug.bpfmaxdevices.
IOCTLS
The ioctl(2) command codes below are defined in . All com-
mands require these includes:
#include
#include
#include
#include
Additionally, BIOCGETIF and BIOCSETIF require and
.
In addition to FIONREAD the following commands may be applied to any open
bpf file. The (third) argument to ioctl(2) should be a pointer to the
type indicated.
BIOCGBLEN (uint) Returns the required buffer length for reads on
bpf files.
BIOCSBLEN (uint) Sets the buffer length for reads on bpf files.
The buffer must be set before the file is attached to an
interface with BIOCSETIF. If the requested buffer size
cannot be accommodated, the closest allowable size will be
set and returned in the argument. A read call will result
in EIO if it is passed a buffer that is not this size.
BIOCGDLT (uint) Returns the type of the data link layer underlying
the attached interface. EINVAL is returned if no inter-
face has been specified. The device types, prefixed with
``DLT'', are defined in .
BIOCPROMISC Forces the interface into promiscuous mode. All packets,
not just those destined for the local host, are processed.
Since more than one file can be listening on a given
interface, a listener that opened its interface non-
promiscuously may receive packets promiscuously. This
problem can be remedied with an appropriate filter.
BIOCFLUSH Flushes the buffer of incoming packets, and resets the
statistics that are returned by BIOCGSTATS.
BIOCGETIF (struct ifreq) Returns the name of the hardware interface
that the file is listening on. The name is returned in
the ifrname field of the ifreq structure. All other
fields are undefined.
BIOCSETIF (struct ifreq) Sets the hardware interface associate with
the file. This command must be performed before any pack-
ets can be read. The device is indicated by name using
the ifrname field of the ifreq structure. Additionally,
performs the actions of BIOCFLUSH.
BIOCSRTIMEOUT
BIOCGRTIMEOUT (struct timeval) Set or get the read timeout parameter.
The argument specifies the length of time to wait before
timing out on a read request. This parameter is initial-
ized to zero by open(2), indicating no timeout.
BIOCGSTATS (struct bpfstat) Returns the following structure of
packet statistics:
struct bpfstat {
uint bsrecv; /* number of packets received */
uint bsdrop; /* number of packets dropped */
};
The fields are:
bsrecv the number of packets received by the
descriptor since opened or reset (including
any buffered since the last read call); and
bsdrop the number of packets which were accepted by
the filter but dropped by the kernel because
of buffer overflows (i.e., the application's
reads aren't keeping up with the packet
traffic).
BIOCIMEDIATE (uint) Enable or disable ``immediate mode'', based on the
truth value of the argument. When immediate mode is
enabled, reads return immediately upon packet reception.
Otherwise, a read will block until either the kernel
buffer becomes full or a timeout occurs. This is useful
for programs like rarpd(8) which must respond to messages
in real time. The default for a new file is off.
BIOCSETF (struct bpfprogram) Sets the filter program used by the
kernel to discard uninteresting packets. An array of
instructions and its length is passed in using the follow-
ing structure:
struct bpfprogram {
int bflen;
struct bpfinsn *bfinsns;
};
The filter program is pointed to by the bfinsns field
while its length in units of `struct bpfinsn' is given by
the bflen field. Also, the actions of BIOCFLUSH are per-
formed. See section FILTER MACHINE for an explanation of
the filter language.
BIOCVERSION (struct bpfversion) Returns the major and minor version
numbers of the filter language currently recognized by the
kernel. Before installing a filter, applications must
check that the current version is compatible with the run-
ning kernel. Version numbers are compatible if the major
numbers match and the application minor is less than or
equal to the kernel minor. The kernel version number is
returned in the following structure:
struct bpfversion {
ushort bvmajor;
ushort bvminor;
};
The current version numbers are given by BPFMAJORVERSION
and BPFMINORVERSION from . An incompatible
filter may result in undefined behavior (most likely, an
error returned by ioctl() or haphazard packet matching).
BIOCSHDRCMPLT
BIOCGHDRCMPLT (uint) Set or get the status of the ``header complete''
flag. Set to zero if the link level source address should
be filled in automatically by the interface output rou-
tine. Set to one if the link level source address will be
written, as provided, to the wire. This flag is initial-
ized to zero by default.
BIOCSESENT
BIOCGSESENT (uint) Set or get the flag determining whether locally
generated packets on the interface should be returned by
BPF. Set to zero to see only incoming packets on the
interface. Set to one to see packets originating locally
and remotely on the interface. This flag is initialized
to one by default.
BPF HEADER
The following structure is prepended to each packet returned by read(2):
struct bpfhdr {
struct timeval bhtstamp; /* time stamp */
ulong bhcaplen; /* length of captured portion */
ulong bhdatalen; /* original length of packet */
ushort bhhdrlen; /* length of bpf header (this struct
plus alignment padding */
};
The fields, whose values are stored in host order, and are:
bhtstamp The time at which the packet was processed by the packet fil-
ter.
bhcaplen The length of the captured portion of the packet. This is
the minimum of the truncation amount specified by the filter
and the length of the packet.
bhdatalen The length of the packet off the wire. This value is inde-
pendent of the truncation amount specified by the filter.
bhhdrlen The length of the bpf header, which may not be equal to
sizeof(struct bpfhdr).
The bhhdrlen field exists to account for padding between the header and
the link level protocol. The purpose here is to guarantee proper align-
ment of the packet data structures, which is required on alignment sensi-
tive architectures and improves performance on many other architectures.
The packet filter insures that the bpfhdr and the network layer header
will be word aligned. Suitable precautions must be taken when accessing
the link layer protocol fields on alignment restricted machines. (This
isn't a problem on an Ethernet, since the type field is a short falling
on an even offset, and the addresses are probably accessed in a bytewise
fashion).
Additionally, individual packets are padded so that each starts on a word
boundary. This requires that an application has some knowledge of how to
get from packet to packet. The macro BPFWORDALIGN is defined in
to facilitate this process. It rounds up its argument to the
nearest word aligned value (where a word is BPFALIGNMENT bytes wide).
For example, if `p' points to the start of a packet, this expression will
advance it to the next packet:
p = (char *)p ] BPFWORDALIGN(p->bhhdrlen ] p->bhcaplen)
For the alignment mechanisms to work properly, the buffer passed to
read(2) must itself be word aligned. The malloc(3) function will always
return an aligned buffer.
FILTER MACHINE
A filter program is an array of instructions, with all branches forwardly
directed, terminated by a return instruction. Each instruction performs
some action on the pseudo-machine state, which consists of an accumula-
tor, index register, scratch memory store, and implicit program counter.
The following structure defines the instruction format:
struct bpfinsn {
ushort code;
uchar jt;
uchar jf;
ulong k;
};
The k field is used in different ways by different instructions, and the
jt and jf fields are used as offsets by the branch instructions. The
opcodes are encoded in a semi-hierarchical fashion. There are eight
classes of instructions: BPFLD, BPFLDX, BPFST, BPFSTX, BPFALU,
BPFJMP, BPFRET, and BPFMISC. Various other mode and operator bits are
or'd into the class to give the actual instructions. The classes and
modes are defined in .
Below are the semantics for each defined bpf instruction. We use the
convention that A is the accumulator, X is the index register, P[] packet
data, and M[] scratch memory store. P[i:n] gives the data at byte offset
``i'' in the packet, interpreted as a word (n=4), unsigned halfword
(n=2), or unsigned byte (n=1). M[i] gives the i'th word in the scratch
memory store, which is only addressed in word units. The memory store is
indexed from 0 to BPFMEMWORDS - 1. k, jt, and jf are the corresponding
fields in the instruction definition. ``len'' refers to the length of
the packet.
BPFLD These instructions copy a value into the accumulator. The type
of the source operand is specified by an ``addressing mode''
and can be a constant (BPFIM), packet data at a fixed offset
(BPFABS), packet data at a variable offset (BPFIND), the
packet length (BPFLEN), or a word in the scratch memory store
(BPFMEM). For BPFIND and BPFABS, the data size must be
specified as a word (BPFW), halfword (BPFH), or byte (BPFB).
The semantics of all the recognized BPFLD instructions follow.
BPFLD]BPFW]BPFABS A <- P[k:4]
BPFLD]BPFH]BPFABS A <- P[k:2]
BPFLD]BPFB]BPFABS A <- P[k:1]
BPFLD]BPFW]BPFIND A <- P[X]k:4]
BPFLD]BPFH]BPFIND A <- P[X]k:2]
BPFLD]BPFB]BPFIND A <- P[X]k:1]
BPFLD]BPFW]BPFLEN A <- len
BPFLD]BPFIM A <- k
BPFLD]BPFMEM A <- M[k]
BPFLDX These instructions load a value into the index register. Note
that the addressing modes are more restrictive than those of
the accumulator loads, but they include BPFMSH, a hack for
efficiently loading the IP header length.
BPFLDX]BPFW]BPFIM X <- k
BPFLDX]BPFW]BPFMEM X <- M[k]
BPFLDX]BPFW]BPFLEN X <- len
BPFLDX]BPFB]BPFMSH X <- 4*(P[k:1]&0xf)
BPFST This instruction stores the accumulator into the scratch mem-
ory. We do not need an addressing mode since there is only one
possibility for the destination.
BPFST M[k] <- A
BPFSTX This instruction stores the index register in the scratch mem-
ory store.
BPFSTX M[k] <- X
BPFALU The alu instructions perform operations between the accumulator
and index register or constant, and store the result back in
the accumulator. For binary operations, a source mode is
required (BPFK or BPFX).
BPFALU]BPFAD]BPFK A <- A ] k
BPFALU]BPFSUB]BPFK A <- A - k
BPFALU]BPFMUL]BPFK A <- A * k
BPFALU]BPFDIV]BPFK A <- A / k
BPFALU]BPFAND]BPFK A <- A & k
BPFALU]BPFOR]BPFK A <- A k
BPFALU]BPFLSH]BPFK A <- A << k
BPFALU]BPFRSH]BPFK A <- A >> k
BPFALU]BPFAD]BPFX A <- A ] X
BPFALU]BPFSUB]BPFX A <- A - X
BPFALU]BPFMUL]BPFX A <- A * X
BPFALU]BPFDIV]BPFX A <- A / X
BPFALU]BPFAND]BPFX A <- A & X
BPFALU]BPFOR]BPFX A <- A X
BPFALU]BPFLSH]BPFX A <- A << X
BPFALU]BPFRSH]BPFX A <- A >> X
BPFALU]BPFNEG A <- -A
BPFJMP The jump instructions alter flow of control. Conditional jumps
compare the accumulator against a constant (BPFK) or the index
register (BPFX). If the result is true (or non-zero), the
true branch is taken, otherwise the false branch is taken.
Jump offsets are encoded in 8 bits so the longest jump is 256
instructions. However, the jump always (BPFJA) opcode uses
the 32 bit k field as the offset, allowing arbitrarily distant
destinations. All conditionals use unsigned comparison conven-
tions.
BPFJMP]BPFJA pc ]= k
BPFJMP]BPFJGT]BPFK pc ]= (A > k) ? jt : jf
BPFJMP]BPFJGE]BPFK pc ]= (A >= k) ? jt : jf
BPFJMP]BPFJEQ]BPFK pc ]= (A == k) ? jt : jf
BPFJMP]BPFJSET]BPFK pc ]= (A & k) ? jt : jf
BPFJMP]BPFJGT]BPFX pc ]= (A > X) ? jt : jf
BPFJMP]BPFJGE]BPFX pc ]= (A >= X) ? jt : jf
BPFJMP]BPFJEQ]BPFX pc ]= (A == X) ? jt : jf
BPFJMP]BPFJSET]BPFX pc ]= (A & X) ? jt : jf
BPFRET The return instructions terminate the filter program and spec-
ify the amount of packet to accept (i.e., they return the trun-
cation amount). A return value of zero indicates that the
packet should be ignored. The return value is either a con-
stant (BPFK) or the accumulator (BPFA).
BPFRET]BPFA accept A bytes
BPFRET]BPFK accept k bytes
BPFMISC The miscellaneous category was created for anything that
doesn't fit into the above classes, and for any new instruc-
tions that might need to be added. Currently, these are the
register transfer instructions that copy the index register to
the accumulator or vice versa.
BPFMISC]BPFTAX X <- A
BPFMISC]BPFTXA A <- X
The bpf interface provides the following macros to facilitate array ini-
tializers: BPFSTMT(opcode, operand) and BPFJUMP(opcode, operand,
trueoffset, falseoffset).
EXAMPLES
The following filter is taken from the Reverse ARP Daemon. It accepts
only Reverse ARP requests.
struct bpfinsn insns[] = {
BPFSTMT(BPFLD]BPFH]BPFABS, 12),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, ETHERTYPEREVARP, 0, 3),
BPFSTMT(BPFLD]BPFH]BPFABS, 20),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, REVARPREQUEST, 0, 1),
BPFSTMT(BPFRET]BPFK, sizeof(struct etherarp) ]
sizeof(struct etherheader)),
BPFSTMT(BPFRET]BPFK, 0),
};
This filter accepts only IP packets between host 128.3.112.15 and
128.3.112.35.
struct bpfinsn insns[] = {
BPFSTMT(BPFLD]BPFH]BPFABS, 12),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, ETHERTYPEIP, 0, 8),
BPFSTMT(BPFLD]BPFW]BPFABS, 26),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, 0x8003700f, 0, 2),
BPFSTMT(BPFLD]BPFW]BPFABS, 30),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, 0x80037023, 3, 4),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, 0x80037023, 0, 3),
BPFSTMT(BPFLD]BPFW]BPFABS, 30),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, 0x8003700f, 0, 1),
BPFSTMT(BPFRET]BPFK, (uint)-1),
BPFSTMT(BPFRET]BPFK, 0),
};
Finally, this filter returns only TCP finger packets. We must parse the
IP header to reach the TCP header. The BPFJSET instruction checks that
the IP fragment offset is 0 so we are sure that we have a TCP header.
struct bpfinsn insns[] = {
BPFSTMT(BPFLD]BPFH]BPFABS, 12),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, ETHERTYPEIP, 0, 10),
BPFSTMT(BPFLD]BPFB]BPFABS, 23),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, IPROTOTCP, 0, 8),
BPFSTMT(BPFLD]BPFH]BPFABS, 20),
BPFJUMP(BPFJMP]BPFJSET]BPFK, 0x1fff, 6, 0),
BPFSTMT(BPFLDX]BPFB]BPFMSH, 14),
BPFSTMT(BPFLD]BPFH]BPFIND, 14),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, 79, 2, 0),
BPFSTMT(BPFLD]BPFH]BPFIND, 16),
BPFJUMP(BPFJMP]BPFJEQ]BPFK, 79, 0, 1),
BPFSTMT(BPFRET]BPFK, (uint)-1),
BPFSTMT(BPFRET]BPFK, 0),
};
SEE ALSO
tcpdump(1), ioctl(2), byteorder(3), ngbpf(4)
McCanne, S. and Jacobson V., An efficient, extensible, and portable
network monitor.
FILES
/dev/bpfn the packet filter device
BUGS
The read buffer must be of a fixed size (returned by the BIOCGBLEN
ioctl).
A file that does not request promiscuous mode may receive promiscuously
received packets as a side effect of another file requesting this mode on
the same hardware interface. This could be fixed in the kernel with
additional processing overhead. However, we favor the model where all
files must assume that the interface is promiscuous, and if so desired,
must utilize a filter to reject foreign packets.
Data link protocols with variable length headers are not currently sup-
ported.
HISTORY
The Enet packet filter was created in 1980 by Mike Accetta and Rick
Rashid at Carnegie-Mellon University. Jeffrey Mogul, at Stanford, ported
the code to BSD and continued its development from 1983 on. Since then,
it has evolved into the Ultrix Packet Filter at DEC, a STREAMS NIT module
under SunOS 4.1, and BPF.
AUTHORS
Steven McCanne, of Lawrence Berkeley Laboratory, implemented BPF in Sum-
mer 1990. Much of the design is due to Van Jacobson.
BSD January 16, 1996 BSD
|
