1 .\" Copyright (c) 1990 The Regents of the University of California.
2 .\" All rights reserved.
4 .\" Redistribution and use in source and binary forms, with or without
5 .\" modification, are permitted provided that: (1) source code distributions
6 .\" retain the above copyright notice and this paragraph in its entirety, (2)
7 .\" distributions including binary code include the above copyright notice and
8 .\" this paragraph in its entirety in the documentation or other materials
9 .\" provided with the distribution, and (3) all advertising materials mentioning
10 .\" features or use of this software display the following acknowledgement:
11 .\" ``This product includes software developed by the University of California,
12 .\" Lawrence Berkeley Laboratory and its contributors.'' Neither the name of
13 .\" the University nor the names of its contributors may be used to endorse
14 .\" or promote products derived from this software without specific prior
15 .\" written permission.
16 .\" THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
17 .\" WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
18 .\" MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
20 .\" This document is derived in part from the enet man page (enet.4)
21 .\" distributed with 4.3BSD Unix.
30 .Nd Berkeley Packet Filter
34 The Berkeley Packet Filter
35 provides a raw interface to data link layers in a protocol
37 All packets on the network, even those destined for other hosts,
38 are accessible through this mechanism.
40 The packet filter appears as a character special device,
44 After opening the device, the file descriptor must be bound to a
45 specific network interface with the
48 A given interface can be shared by multiple listeners, and the filter
49 underlying each descriptor will see an identical packet stream.
51 A separate device file is required for each minor device.
52 If a file is in use, the open will fail and
57 Associated with each open instance of a
59 file is a user-settable packet filter.
60 Whenever a packet is received by an interface,
61 all file descriptors listening on that interface apply their filter.
62 Each descriptor that accepts the packet receives its own copy.
64 Reads from these files return the next group of packets
65 that have matched the filter.
66 To improve performance, the buffer passed to read must be
67 the same size as the buffers used internally by
69 This size is returned by the
71 ioctl (see below), and
74 Note that an individual packet larger than this size is necessarily
77 The packet filter will support any link level protocol that has fixed length
79 Currently, only Ethernet,
83 drivers have been modified to interact with
86 Since packet data is in network byte order, applications should use the
88 macros to extract multi-byte values.
90 A packet can be sent out on the network by writing to a
93 The writes are unbuffered, meaning only one packet can be processed per write.
94 Currently, only writes to Ethernets and
100 command codes below are defined in
105 #include <sys/types.h>
106 #include <sys/time.h>
107 #include <sys/ioctl.h>
124 the following commands may be applied to any open
127 The (third) argument to
129 should be a pointer to the type indicated.
130 .Bl -tag -width BIOCGRTIMEOUT
133 Returns the required buffer length for reads on
138 Sets the buffer length for reads on
141 The buffer must be set before the file is attached to an interface
144 If the requested buffer size cannot be accommodated, the closest
145 allowable size will be set and returned in the argument.
146 A read call will result in
148 if it is passed a buffer that is not this size.
151 Returns the type of the data link layer underlying the attached interface.
153 is returned if no interface has been specified.
154 The device types, prefixed with
159 Forces the interface into promiscuous mode.
160 All packets, not just those destined for the local host, are processed.
161 Since more than one file can be listening on a given interface,
162 a listener that opened its interface non-promiscuously may receive
163 packets promiscuously.
164 This problem can be remedied with an appropriate filter.
166 Flushes the buffer of incoming packets,
167 and resets the statistics that are returned by BIOCGSTATS.
169 .Pq Li "struct ifreq"
170 Returns the name of the hardware interface that the file is listening on.
171 The name is returned in the ifr_name field of
175 All other fields are undefined.
177 .Pq Li "struct ifreq"
178 Sets the hardware interface associate with the file.
180 command must be performed before any packets can be read.
181 The device is indicated by name using the
186 Additionally, performs the actions of
190 .Pq Li "struct timeval"
191 Set or get the read timeout parameter.
193 specifies the length of time to wait before timing
194 out on a read request.
195 This parameter is initialized to zero by
197 indicating no timeout.
199 .Pq Li "struct bpf_stat"
200 Returns the following structure of packet statistics:
203 u_int bs_recv; /* number of packets received */
204 u_int bs_drop; /* number of packets dropped */
209 .Bl -hang -offset indent
211 the number of packets received by the descriptor since opened or reset
212 (including any buffered since the last read call);
215 the number of packets which were accepted by the filter but dropped by the
216 kernel because of buffer overflows
217 (i.e., the application's reads are not keeping up with the packet traffic).
223 based on the truth value of the argument.
224 When immediate mode is enabled, reads return immediately upon packet
226 Otherwise, a read will block until either the kernel buffer
227 becomes full or a timeout occurs.
228 This is useful for programs like
230 which must respond to messages in real time.
231 The default for a new file is off.
233 .Pq Li "struct bpf_program"
234 Sets the read filter program used by the kernel to discard uninteresting
236 An array of instructions and its length is passed in using
237 the following structure:
241 struct bpf_insn *bf_insns;
245 The filter program is pointed to by the
247 field while its length in units of
248 .Sq Li struct bpf_insn
257 for an explanation of the filter language.
259 .Pq Li "struct bpf_program"
260 Sets the write filter program used by the kernel to control what type of
261 packets can be written to the interface.
269 .Pq Li "struct bpf_version"
270 Returns the major and minor version numbers of the filter language currently
271 recognized by the kernel.
272 Before installing a filter, applications must check
273 that the current version is compatible with the running kernel.
274 Version numbers are compatible if the major numbers match and the application minor
275 is less than or equal to the kernel minor.
276 The kernel version number is returned in the following structure:
284 The current version numbers are given by
285 .Dv BPF_MAJOR_VERSION
287 .Dv BPF_MINOR_VERSION
290 An incompatible filter
291 may result in undefined behavior (most likely, an error returned by
293 or haphazard packet matching).
297 Set or get the status of the
300 Set to zero if the link level source address should be filled in automatically
301 by the interface output routine.
302 Set to one if the link level source
303 address will be written, as provided, to the wire.
304 This flag is initialized to zero by default.
308 Set or get the flag determining whether locally generated packets on the
309 interface should be returned by BPF.
310 Set to zero to see only incoming packets on the interface.
311 Set to one to see packets originating locally and remotely on the interface.
312 This flag is initialized to one by
315 Set the locked flag on the
318 This prevents the execution of
319 ioctl commands which could change the underlying operating parameters of
323 The following structure is prepended to each packet returned by
327 struct timeval bh_tstamp; /* time stamp */
328 u_long bh_caplen; /* length of captured portion */
329 u_long bh_datalen; /* original length of packet */
330 u_short bh_hdrlen; /* length of bpf header (this struct
331 plus alignment padding */
335 The fields, whose values are stored in host order, and are:
337 .Bl -tag -compact -width bh_datalen
339 The time at which the packet was processed by the packet filter.
341 The length of the captured portion of the packet.
342 This is the minimum of
343 the truncation amount specified by the filter and the length of the packet.
345 The length of the packet off the wire.
346 This value is independent of the truncation amount specified by the filter.
350 header, which may not be equal to
351 .\" XXX - not really a function call
352 .Fn sizeof "struct bpf_hdr" .
357 field exists to account for
358 padding between the header and the link level protocol.
359 The purpose here is to guarantee proper alignment of the packet
360 data structures, which is required on alignment sensitive
361 architectures and improves performance on many other architectures.
362 The packet filter insures that the
364 and the network layer
365 header will be word aligned.
367 must be taken when accessing the link layer protocol fields on alignment
369 (This is not a problem on an Ethernet, since
370 the type field is a short falling on an even offset,
371 and the addresses are probably accessed in a bytewise fashion).
373 Additionally, individual packets are padded so that each starts
375 This requires that an application
376 has some knowledge of how to get from packet to packet.
383 It rounds up its argument to the nearest word aligned value (where a word is
389 points to the start of a packet, this expression
390 will advance it to the next packet:
391 .Dl p = (char *)p + BPF_WORDALIGN(p->bh_hdrlen + p->bh_caplen)
393 For the alignment mechanisms to work properly, the
396 must itself be word aligned.
400 will always return an aligned buffer.
402 A filter program is an array of instructions, with all branches forwardly
403 directed, terminated by a
406 Each instruction performs some action on the pseudo-machine state,
407 which consists of an accumulator, index register, scratch memory store,
408 and implicit program counter.
410 The following structure defines the instruction format:
422 field is used in different ways by different instructions,
427 fields are used as offsets
428 by the branch instructions.
429 The opcodes are encoded in a semi-hierarchical fashion.
430 There are eight classes of instructions:
440 Various other mode and
441 operator bits are or'd into the class to give the actual instructions.
442 The classes and modes are defined in
445 Below are the semantics for each defined
448 We use the convention that A is the accumulator, X is the index register,
449 P[] packet data, and M[] scratch memory store.
450 P[i:n] gives the data at byte offset
453 interpreted as a word (n=4),
454 unsigned halfword (n=2), or unsigned byte (n=1).
455 M[i] gives the i'th word in the scratch memory store, which is only
456 addressed in word units.
457 The memory store is indexed from 0 to
464 are the corresponding fields in the
465 instruction definition.
467 refers to the length of the packet.
469 .Bl -tag -width BPF_STXx
471 These instructions copy a value into the accumulator.
472 The type of the source operand is specified by an
474 and can be a constant
476 packet data at a fixed offset
478 packet data at a variable offset
482 or a word in the scratch memory store
488 the data size must be specified as a word
494 The semantics of all the recognized
499 BPF_LD+BPF_W+BPF_ABS A <- P[k:4]
500 BPF_LD+BPF_H+BPF_ABS A <- P[k:2]
501 BPF_LD+BPF_B+BPF_ABS A <- P[k:1]
502 BPF_LD+BPF_W+BPF_IND A <- P[X+k:4]
503 BPF_LD+BPF_H+BPF_IND A <- P[X+k:2]
504 BPF_LD+BPF_B+BPF_IND A <- P[X+k:1]
505 BPF_LD+BPF_W+BPF_LEN A <- len
506 BPF_LD+BPF_IMM A <- k
507 BPF_LD+BPF_MEM A <- M[k]
510 These instructions load a value into the index register.
512 the addressing modes are more restrictive than those of the accumulator loads,
515 a hack for efficiently loading the IP header length.
518 BPF_LDX+BPF_W+BPF_IMM X <- k
519 BPF_LDX+BPF_W+BPF_MEM X <- M[k]
520 BPF_LDX+BPF_W+BPF_LEN X <- len
521 BPF_LDX+BPF_B+BPF_MSH X <- 4*(P[k:1]&0xf)
524 This instruction stores the accumulator into the scratch memory.
525 We do not need an addressing mode since there is only one possibility
532 This instruction stores the index register in the scratch memory store.
538 The alu instructions perform operations between the accumulator and
539 index register or constant, and store the result back in the accumulator.
540 For binary operations, a source mode is required
546 BPF_ALU+BPF_ADD+BPF_K A <- A + k
547 BPF_ALU+BPF_SUB+BPF_K A <- A - k
548 BPF_ALU+BPF_MUL+BPF_K A <- A * k
549 BPF_ALU+BPF_DIV+BPF_K A <- A / k
550 BPF_ALU+BPF_AND+BPF_K A <- A & k
551 BPF_ALU+BPF_OR+BPF_K A <- A | k
552 BPF_ALU+BPF_LSH+BPF_K A <- A << k
553 BPF_ALU+BPF_RSH+BPF_K A <- A >> k
554 BPF_ALU+BPF_ADD+BPF_X A <- A + X
555 BPF_ALU+BPF_SUB+BPF_X A <- A - X
556 BPF_ALU+BPF_MUL+BPF_X A <- A * X
557 BPF_ALU+BPF_DIV+BPF_X A <- A / X
558 BPF_ALU+BPF_AND+BPF_X A <- A & X
559 BPF_ALU+BPF_OR+BPF_X A <- A | X
560 BPF_ALU+BPF_LSH+BPF_X A <- A << X
561 BPF_ALU+BPF_RSH+BPF_X A <- A >> X
562 BPF_ALU+BPF_NEG A <- -A
565 The jump instructions alter flow of control.
567 compare the accumulator against a constant
569 or the index register
571 If the result is true (or non-zero),
572 the true branch is taken, otherwise the false branch is taken.
573 Jump offsets are encoded in 8 bits so the longest jump is 256 instructions.
574 However, the jump always
576 opcode uses the 32 bit
578 field as the offset, allowing arbitrarily distant destinations.
579 All conditionals use unsigned comparison conventions.
582 BPF_JMP+BPF_JA pc += k
583 BPF_JMP+BPF_JGT+BPF_K pc += (A > k) ? jt : jf
584 BPF_JMP+BPF_JGE+BPF_K pc += (A >= k) ? jt : jf
585 BPF_JMP+BPF_JEQ+BPF_K pc += (A == k) ? jt : jf
586 BPF_JMP+BPF_JSET+BPF_K pc += (A & k) ? jt : jf
587 BPF_JMP+BPF_JGT+BPF_X pc += (A > X) ? jt : jf
588 BPF_JMP+BPF_JGE+BPF_X pc += (A >= X) ? jt : jf
589 BPF_JMP+BPF_JEQ+BPF_X pc += (A == X) ? jt : jf
590 BPF_JMP+BPF_JSET+BPF_X pc += (A & X) ? jt : jf
593 The return instructions terminate the filter program and specify the amount
594 of packet to accept (i.e., they return the truncation amount).
595 A return value of zero indicates that the packet should be ignored.
596 The return value is either a constant
602 BPF_RET+BPF_A accept A bytes
603 BPF_RET+BPF_K accept k bytes
606 The miscellaneous category was created for anything that does not
607 fit into the above classes, and for any new instructions that might need to
609 Currently, these are the register transfer instructions
610 that copy the index register to the accumulator or vice versa.
613 BPF_MISC+BPF_TAX X <- A
614 BPF_MISC+BPF_TXA A <- X
620 interface provides the following macros to facilitate
622 .Fn BPF_STMT opcode operand
624 .Fn BPF_JUMP opcode operand true_offset false_offset .
626 .Bl -tag -compact -width /dev/bpfXXX
627 .It Pa /dev/bpf Ns Sy n
628 the packet filter device
631 The following filter is taken from the Reverse ARP Daemon.
632 It accepts only Reverse ARP requests.
634 struct bpf_insn insns[] = {
635 BPF_STMT(BPF_LD+BPF_H+BPF_ABS, 12),
636 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, ETHERTYPE_REVARP, 0, 3),
637 BPF_STMT(BPF_LD+BPF_H+BPF_ABS, 20),
638 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, REVARP_REQUEST, 0, 1),
639 BPF_STMT(BPF_RET+BPF_K, sizeof(struct ether_arp) +
640 sizeof(struct ether_header)),
641 BPF_STMT(BPF_RET+BPF_K, 0),
645 This filter accepts only IP packets between host 128.3.112.15 and
648 struct bpf_insn insns[] = {
649 BPF_STMT(BPF_LD+BPF_H+BPF_ABS, 12),
650 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, ETHERTYPE_IP, 0, 8),
651 BPF_STMT(BPF_LD+BPF_W+BPF_ABS, 26),
652 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, 0x8003700f, 0, 2),
653 BPF_STMT(BPF_LD+BPF_W+BPF_ABS, 30),
654 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, 0x80037023, 3, 4),
655 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, 0x80037023, 0, 3),
656 BPF_STMT(BPF_LD+BPF_W+BPF_ABS, 30),
657 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, 0x8003700f, 0, 1),
658 BPF_STMT(BPF_RET+BPF_K, (u_int)-1),
659 BPF_STMT(BPF_RET+BPF_K, 0),
663 Finally, this filter returns only TCP finger packets.
664 We must parse the IP header to reach the TCP header.
668 checks that the IP fragment offset is 0 so we are sure
669 that we have a TCP header.
671 struct bpf_insn insns[] = {
672 BPF_STMT(BPF_LD+BPF_H+BPF_ABS, 12),
673 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, ETHERTYPE_IP, 0, 10),
674 BPF_STMT(BPF_LD+BPF_B+BPF_ABS, 23),
675 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, IPPROTO_TCP, 0, 8),
676 BPF_STMT(BPF_LD+BPF_H+BPF_ABS, 20),
677 BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, 0x1fff, 6, 0),
678 BPF_STMT(BPF_LDX+BPF_B+BPF_MSH, 14),
679 BPF_STMT(BPF_LD+BPF_H+BPF_IND, 14),
680 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, 79, 2, 0),
681 BPF_STMT(BPF_LD+BPF_H+BPF_IND, 16),
682 BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, 79, 0, 1),
683 BPF_STMT(BPF_RET+BPF_K, (u_int)-1),
684 BPF_STMT(BPF_RET+BPF_K, 0),
696 .%T "An efficient, extensible, and portable network monitor"
699 The Enet packet filter was created in 1980 by Mike Accetta and
700 Rick Rashid at Carnegie-Mellon University.
702 Stanford, ported the code to
704 and continued its development from
706 Since then, it has evolved into the Ultrix Packet Filter at
718 of Lawrence Berkeley Laboratory, implemented BPF in
720 Much of the design is due to
723 The read buffer must be of a fixed size (returned by the
727 A file that does not request promiscuous mode may receive promiscuously
728 received packets as a side effect of another file requesting this
729 mode on the same hardware interface.
730 This could be fixed in the kernel with additional processing overhead.
731 However, we favor the model where
732 all files must assume that the interface is promiscuous, and if
733 so desired, must utilize a filter to reject foreign packets.
735 Data link protocols with variable length headers are not currently supported.
739 flag has been observed to work incorrectly on some interface
740 types, including those with hardware loopback rather than software loopback,
741 and point-to-point interfaces.
742 It appears to function correctly on a
743 broad range of Ethernet-style interfaces.