NAME
bbppff - Berkeley Packet Filter
SYNOPSIS
ppsseeuuddoo-ddeevviiccee bbppff
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 bbppff 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 bbppff. This size is returned by the BIOCGBLEN ioctl (see below), and can be set withBIOCSBLEN. 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 PPP drivers have been modified to interact with bbppff. Since packet data is in network byte order, applications should use thebyteorder(3) macros to extract multi-byte values.
A packet can be sent out on the network by writing to a bbppff file descrip-
tor. The writes are unbuffered, meaning only one packet can be processedper 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.
IIOOCCTTLLSSThe ioctl(2) command codes below are defined in
mands require these includes:. All com- #include
#include
#include
#include
Additionally, BIOCGETIF and BIOCSETIF requireand . In addition to FIONREAD the following commands may be applied to any open bbppff 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 bbppff files. BIOCSBLEN (uint) Sets the buffer length for reads on bbppff 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 withthe 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 beforetiming 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). BIOCIMMEDIATE (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 ofinstructions 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 fieldwhile 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 mustcheck 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 BPFMAJORVERSIONand BPFMINORVERSION from
filter may result in undefined behavior (most likely, an error returned by iiooccttll() 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. An incompatible be filled in automatically by the interface output rou-
tine. Set to one if the link level source address will bewritten, as provided, to the wire. This flag is initial-
ized to zero by default. BIOCSSEESENT BIOCGSEESENT (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. BBPPFF HHEEAADDEERR 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 bbppff header, which may not be equal tossiizzeeooff(struct bpfhdr).
The bhhdrlen field exists to account for padding between the header andthe 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 innearest 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:
to facilitate this process. It rounds up its argument to the 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. FFIILLTTEERR MMAACCHHIINNEE A filter program is an array of instructions, with all branches forwardly directed, terminated by a return instruction. Each instruction performssome 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. Theopcodes 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 andmodes are defined in
Below are the semantics for each defined bbppff 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 (BPFIMM), 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+BPFIMM 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+BPFIMM 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+BPFADD+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+BPFADD+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 indexregister (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 distantdestinations. 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 : jfBPFRET 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 thepacket 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 thatdoesn'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 bbppff interface provides the following macros to facilitate array ini-
tializers: BBPPFFSSTTMMTT(opcode, operand) and BBPPFFJJUUMMPP(opcode, operand, trueoffset, falseoffset). EEXXAAMMPPLLEESS 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, IPPROTOTCP, 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/bpfnn 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 RickRashid 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. AUTHORSSteven 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