2014-09-05 12:17:18 +07:00
|
|
|
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
|
|
* License as published by the Free Software Foundation.
|
|
|
|
*/
|
|
|
|
#ifndef _UAPI__LINUX_BPF_H__
|
|
|
|
#define _UAPI__LINUX_BPF_H__
|
|
|
|
|
|
|
|
#include <linux/types.h>
|
2014-10-14 16:08:54 +07:00
|
|
|
#include <linux/bpf_common.h>
|
2014-09-05 12:17:18 +07:00
|
|
|
|
|
|
|
/* Extended instruction set based on top of classic BPF */
|
|
|
|
|
|
|
|
/* instruction classes */
|
|
|
|
#define BPF_ALU64 0x07 /* alu mode in double word width */
|
|
|
|
|
|
|
|
/* ld/ldx fields */
|
|
|
|
#define BPF_DW 0x18 /* double word */
|
|
|
|
#define BPF_XADD 0xc0 /* exclusive add */
|
|
|
|
|
|
|
|
/* alu/jmp fields */
|
|
|
|
#define BPF_MOV 0xb0 /* mov reg to reg */
|
|
|
|
#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */
|
|
|
|
|
|
|
|
/* change endianness of a register */
|
|
|
|
#define BPF_END 0xd0 /* flags for endianness conversion: */
|
|
|
|
#define BPF_TO_LE 0x00 /* convert to little-endian */
|
|
|
|
#define BPF_TO_BE 0x08 /* convert to big-endian */
|
|
|
|
#define BPF_FROM_LE BPF_TO_LE
|
|
|
|
#define BPF_FROM_BE BPF_TO_BE
|
|
|
|
|
|
|
|
#define BPF_JNE 0x50 /* jump != */
|
|
|
|
#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
|
|
|
|
#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
|
|
|
|
#define BPF_CALL 0x80 /* function call */
|
|
|
|
#define BPF_EXIT 0x90 /* function return */
|
|
|
|
|
|
|
|
/* Register numbers */
|
|
|
|
enum {
|
|
|
|
BPF_REG_0 = 0,
|
|
|
|
BPF_REG_1,
|
|
|
|
BPF_REG_2,
|
|
|
|
BPF_REG_3,
|
|
|
|
BPF_REG_4,
|
|
|
|
BPF_REG_5,
|
|
|
|
BPF_REG_6,
|
|
|
|
BPF_REG_7,
|
|
|
|
BPF_REG_8,
|
|
|
|
BPF_REG_9,
|
|
|
|
BPF_REG_10,
|
|
|
|
__MAX_BPF_REG,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* BPF has 10 general purpose 64-bit registers and stack frame. */
|
|
|
|
#define MAX_BPF_REG __MAX_BPF_REG
|
|
|
|
|
|
|
|
struct bpf_insn {
|
|
|
|
__u8 code; /* opcode */
|
|
|
|
__u8 dst_reg:4; /* dest register */
|
|
|
|
__u8 src_reg:4; /* source register */
|
|
|
|
__s16 off; /* signed offset */
|
|
|
|
__s32 imm; /* signed immediate constant */
|
|
|
|
};
|
|
|
|
|
2014-09-26 14:16:57 +07:00
|
|
|
/* BPF syscall commands */
|
|
|
|
enum bpf_cmd {
|
|
|
|
/* create a map with given type and attributes
|
|
|
|
* fd = bpf(BPF_MAP_CREATE, union bpf_attr *, u32 size)
|
|
|
|
* returns fd or negative error
|
|
|
|
* map is deleted when fd is closed
|
|
|
|
*/
|
|
|
|
BPF_MAP_CREATE,
|
bpf: add lookup/update/delete/iterate methods to BPF maps
'maps' is a generic storage of different types for sharing data between kernel
and userspace.
The maps are accessed from user space via BPF syscall, which has commands:
- create a map with given type and attributes
fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
returns fd or negative error
- lookup key in a given map referenced by fd
err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero and stores found elem into value or negative error
- create or update key/value pair in a given map
err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero or negative error
- find and delete element by key in a given map
err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key
- iterate map elements (based on input key return next_key)
err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->next_key
- close(fd) deletes the map
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 14:16:59 +07:00
|
|
|
|
|
|
|
/* lookup key in a given map
|
|
|
|
* err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
|
|
|
|
* Using attr->map_fd, attr->key, attr->value
|
|
|
|
* returns zero and stores found elem into value
|
|
|
|
* or negative error
|
|
|
|
*/
|
|
|
|
BPF_MAP_LOOKUP_ELEM,
|
|
|
|
|
|
|
|
/* create or update key/value pair in a given map
|
|
|
|
* err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
|
bpf: add 'flags' attribute to BPF_MAP_UPDATE_ELEM command
the current meaning of BPF_MAP_UPDATE_ELEM syscall command is:
either update existing map element or create a new one.
Initially the plan was to add a new command to handle the case of
'create new element if it didn't exist', but 'flags' style looks
cleaner and overall diff is much smaller (more code reused), so add 'flags'
attribute to BPF_MAP_UPDATE_ELEM command with the following meaning:
#define BPF_ANY 0 /* create new element or update existing */
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
bpf_update_elem(fd, key, value, BPF_NOEXIST) call can fail with EEXIST
if element already exists.
bpf_update_elem(fd, key, value, BPF_EXIST) can fail with ENOENT
if element doesn't exist.
Userspace will call it as:
int bpf_update_elem(int fd, void *key, void *value, __u64 flags)
{
union bpf_attr attr = {
.map_fd = fd,
.key = ptr_to_u64(key),
.value = ptr_to_u64(value),
.flags = flags;
};
return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}
First two bits of 'flags' are used to encode style of bpf_update_elem() command.
Bits 2-63 are reserved for future use.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-14 08:36:44 +07:00
|
|
|
* Using attr->map_fd, attr->key, attr->value, attr->flags
|
bpf: add lookup/update/delete/iterate methods to BPF maps
'maps' is a generic storage of different types for sharing data between kernel
and userspace.
The maps are accessed from user space via BPF syscall, which has commands:
- create a map with given type and attributes
fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
returns fd or negative error
- lookup key in a given map referenced by fd
err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero and stores found elem into value or negative error
- create or update key/value pair in a given map
err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero or negative error
- find and delete element by key in a given map
err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key
- iterate map elements (based on input key return next_key)
err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->next_key
- close(fd) deletes the map
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 14:16:59 +07:00
|
|
|
* returns zero or negative error
|
|
|
|
*/
|
|
|
|
BPF_MAP_UPDATE_ELEM,
|
|
|
|
|
|
|
|
/* find and delete elem by key in a given map
|
|
|
|
* err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
|
|
|
|
* Using attr->map_fd, attr->key
|
|
|
|
* returns zero or negative error
|
|
|
|
*/
|
|
|
|
BPF_MAP_DELETE_ELEM,
|
|
|
|
|
|
|
|
/* lookup key in a given map and return next key
|
|
|
|
* err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
|
|
|
|
* Using attr->map_fd, attr->key, attr->next_key
|
|
|
|
* returns zero and stores next key or negative error
|
|
|
|
*/
|
|
|
|
BPF_MAP_GET_NEXT_KEY,
|
2014-09-26 14:17:00 +07:00
|
|
|
|
|
|
|
/* verify and load eBPF program
|
|
|
|
* prog_fd = bpf(BPF_PROG_LOAD, union bpf_attr *attr, u32 size)
|
|
|
|
* Using attr->prog_type, attr->insns, attr->license
|
|
|
|
* returns fd or negative error
|
|
|
|
*/
|
|
|
|
BPF_PROG_LOAD,
|
2014-09-26 14:16:57 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
enum bpf_map_type {
|
|
|
|
BPF_MAP_TYPE_UNSPEC,
|
2014-11-14 08:36:45 +07:00
|
|
|
BPF_MAP_TYPE_HASH,
|
2014-11-14 08:36:46 +07:00
|
|
|
BPF_MAP_TYPE_ARRAY,
|
2014-09-26 14:16:57 +07:00
|
|
|
};
|
|
|
|
|
2014-09-26 14:17:00 +07:00
|
|
|
enum bpf_prog_type {
|
|
|
|
BPF_PROG_TYPE_UNSPEC,
|
2014-12-02 06:06:34 +07:00
|
|
|
BPF_PROG_TYPE_SOCKET_FILTER,
|
ebpf: add sched_cls_type and map it to sk_filter's verifier ops
As discussed recently and at netconf/netdev01, we want to prevent making
bpf_verifier_ops registration available for modules, but have them at a
controlled place inside the kernel instead.
The reason for this is, that out-of-tree modules can go crazy and define
and register any verfifier ops they want, doing all sorts of crap, even
bypassing available GPLed eBPF helper functions. We don't want to offer
such a shiny playground, of course, but keep strict control to ourselves
inside the core kernel.
This also encourages us to design eBPF user helpers carefully and
generically, so they can be shared among various subsystems using eBPF.
For the eBPF traffic classifier (cls_bpf), it's a good start to share
the same helper facilities as we currently do in eBPF for socket filters.
That way, we have BPF_PROG_TYPE_SCHED_CLS look like it's own type, thus
one day if there's a good reason to diverge the set of helper functions
from the set available to socket filters, we keep ABI compatibility.
In future, we could place all bpf_prog_type_list at a central place,
perhaps.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-01 18:31:46 +07:00
|
|
|
BPF_PROG_TYPE_SCHED_CLS,
|
2014-09-26 14:17:00 +07:00
|
|
|
};
|
|
|
|
|
2015-03-01 18:31:43 +07:00
|
|
|
#define BPF_PSEUDO_MAP_FD 1
|
|
|
|
|
bpf: add 'flags' attribute to BPF_MAP_UPDATE_ELEM command
the current meaning of BPF_MAP_UPDATE_ELEM syscall command is:
either update existing map element or create a new one.
Initially the plan was to add a new command to handle the case of
'create new element if it didn't exist', but 'flags' style looks
cleaner and overall diff is much smaller (more code reused), so add 'flags'
attribute to BPF_MAP_UPDATE_ELEM command with the following meaning:
#define BPF_ANY 0 /* create new element or update existing */
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
bpf_update_elem(fd, key, value, BPF_NOEXIST) call can fail with EEXIST
if element already exists.
bpf_update_elem(fd, key, value, BPF_EXIST) can fail with ENOENT
if element doesn't exist.
Userspace will call it as:
int bpf_update_elem(int fd, void *key, void *value, __u64 flags)
{
union bpf_attr attr = {
.map_fd = fd,
.key = ptr_to_u64(key),
.value = ptr_to_u64(value),
.flags = flags;
};
return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}
First two bits of 'flags' are used to encode style of bpf_update_elem() command.
Bits 2-63 are reserved for future use.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-14 08:36:44 +07:00
|
|
|
/* flags for BPF_MAP_UPDATE_ELEM command */
|
|
|
|
#define BPF_ANY 0 /* create new element or update existing */
|
|
|
|
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
|
|
|
|
#define BPF_EXIST 2 /* update existing element */
|
|
|
|
|
2014-09-26 14:16:57 +07:00
|
|
|
union bpf_attr {
|
|
|
|
struct { /* anonymous struct used by BPF_MAP_CREATE command */
|
|
|
|
__u32 map_type; /* one of enum bpf_map_type */
|
|
|
|
__u32 key_size; /* size of key in bytes */
|
|
|
|
__u32 value_size; /* size of value in bytes */
|
|
|
|
__u32 max_entries; /* max number of entries in a map */
|
|
|
|
};
|
bpf: add lookup/update/delete/iterate methods to BPF maps
'maps' is a generic storage of different types for sharing data between kernel
and userspace.
The maps are accessed from user space via BPF syscall, which has commands:
- create a map with given type and attributes
fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
returns fd or negative error
- lookup key in a given map referenced by fd
err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero and stores found elem into value or negative error
- create or update key/value pair in a given map
err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero or negative error
- find and delete element by key in a given map
err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key
- iterate map elements (based on input key return next_key)
err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->next_key
- close(fd) deletes the map
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 14:16:59 +07:00
|
|
|
|
|
|
|
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
|
|
|
|
__u32 map_fd;
|
|
|
|
__aligned_u64 key;
|
|
|
|
union {
|
|
|
|
__aligned_u64 value;
|
|
|
|
__aligned_u64 next_key;
|
|
|
|
};
|
bpf: add 'flags' attribute to BPF_MAP_UPDATE_ELEM command
the current meaning of BPF_MAP_UPDATE_ELEM syscall command is:
either update existing map element or create a new one.
Initially the plan was to add a new command to handle the case of
'create new element if it didn't exist', but 'flags' style looks
cleaner and overall diff is much smaller (more code reused), so add 'flags'
attribute to BPF_MAP_UPDATE_ELEM command with the following meaning:
#define BPF_ANY 0 /* create new element or update existing */
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
bpf_update_elem(fd, key, value, BPF_NOEXIST) call can fail with EEXIST
if element already exists.
bpf_update_elem(fd, key, value, BPF_EXIST) can fail with ENOENT
if element doesn't exist.
Userspace will call it as:
int bpf_update_elem(int fd, void *key, void *value, __u64 flags)
{
union bpf_attr attr = {
.map_fd = fd,
.key = ptr_to_u64(key),
.value = ptr_to_u64(value),
.flags = flags;
};
return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}
First two bits of 'flags' are used to encode style of bpf_update_elem() command.
Bits 2-63 are reserved for future use.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-14 08:36:44 +07:00
|
|
|
__u64 flags;
|
bpf: add lookup/update/delete/iterate methods to BPF maps
'maps' is a generic storage of different types for sharing data between kernel
and userspace.
The maps are accessed from user space via BPF syscall, which has commands:
- create a map with given type and attributes
fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
returns fd or negative error
- lookup key in a given map referenced by fd
err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero and stores found elem into value or negative error
- create or update key/value pair in a given map
err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero or negative error
- find and delete element by key in a given map
err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key
- iterate map elements (based on input key return next_key)
err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->next_key
- close(fd) deletes the map
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 14:16:59 +07:00
|
|
|
};
|
2014-09-26 14:17:00 +07:00
|
|
|
|
|
|
|
struct { /* anonymous struct used by BPF_PROG_LOAD command */
|
|
|
|
__u32 prog_type; /* one of enum bpf_prog_type */
|
|
|
|
__u32 insn_cnt;
|
|
|
|
__aligned_u64 insns;
|
|
|
|
__aligned_u64 license;
|
bpf: verifier (add ability to receive verification log)
add optional attributes for BPF_PROG_LOAD syscall:
union bpf_attr {
struct {
...
__u32 log_level; /* verbosity level of eBPF verifier */
__u32 log_size; /* size of user buffer */
__aligned_u64 log_buf; /* user supplied 'char *buffer' */
};
};
when log_level > 0 the verifier will return its verification log in the user
supplied buffer 'log_buf' which can be used by program author to analyze why
verifier rejected given program.
'Understanding eBPF verifier messages' section of Documentation/networking/filter.txt
provides several examples of these messages, like the program:
BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_CALL_FUNC(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0),
BPF_EXIT_INSN(),
will be rejected with the following multi-line message in log_buf:
0: (7a) *(u64 *)(r10 -8) = 0
1: (bf) r2 = r10
2: (07) r2 += -8
3: (b7) r1 = 0
4: (85) call 1
5: (15) if r0 == 0x0 goto pc+1
R0=map_ptr R10=fp
6: (7a) *(u64 *)(r0 +4) = 0
misaligned access off 4 size 8
The format of the output can change at any time as verifier evolves.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 14:17:03 +07:00
|
|
|
__u32 log_level; /* verbosity level of verifier */
|
|
|
|
__u32 log_size; /* size of user buffer */
|
|
|
|
__aligned_u64 log_buf; /* user supplied buffer */
|
2014-09-26 14:17:00 +07:00
|
|
|
};
|
2014-09-26 14:16:57 +07:00
|
|
|
} __attribute__((aligned(8)));
|
|
|
|
|
2014-09-26 14:17:00 +07:00
|
|
|
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
|
|
|
|
* function eBPF program intends to call
|
|
|
|
*/
|
|
|
|
enum bpf_func_id {
|
|
|
|
BPF_FUNC_unspec,
|
2014-11-14 08:36:49 +07:00
|
|
|
BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
|
|
|
|
BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
|
|
|
|
BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
|
2015-03-14 08:27:16 +07:00
|
|
|
BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */
|
2015-03-14 08:27:17 +07:00
|
|
|
BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */
|
2014-09-26 14:17:00 +07:00
|
|
|
__BPF_FUNC_MAX_ID,
|
|
|
|
};
|
|
|
|
|
2014-09-05 12:17:18 +07:00
|
|
|
#endif /* _UAPI__LINUX_BPF_H__ */
|