2014-09-26 07:16:57 +00:00
|
|
|
/* 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 _LINUX_BPF_H
|
|
|
|
#define _LINUX_BPF_H 1
|
|
|
|
|
|
|
|
#include <uapi/linux/bpf.h>
|
|
|
|
#include <linux/workqueue.h>
|
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 07:16:59 +00:00
|
|
|
#include <linux/file.h>
|
2014-09-26 07:16:57 +00:00
|
|
|
|
|
|
|
struct bpf_map;
|
|
|
|
|
|
|
|
/* map is generic key/value storage optionally accesible by eBPF programs */
|
|
|
|
struct bpf_map_ops {
|
|
|
|
/* funcs callable from userspace (via syscall) */
|
|
|
|
struct bpf_map *(*map_alloc)(union bpf_attr *attr);
|
|
|
|
void (*map_free)(struct bpf_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 07:16:59 +00:00
|
|
|
int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
|
|
|
|
|
|
|
|
/* funcs callable from userspace and from eBPF programs */
|
|
|
|
void *(*map_lookup_elem)(struct bpf_map *map, void *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 01:36:44 +00:00
|
|
|
int (*map_update_elem)(struct bpf_map *map, void *key, void *value, 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 07:16:59 +00:00
|
|
|
int (*map_delete_elem)(struct bpf_map *map, void *key);
|
2014-09-26 07:16:57 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
struct bpf_map {
|
|
|
|
atomic_t refcnt;
|
|
|
|
enum bpf_map_type map_type;
|
|
|
|
u32 key_size;
|
|
|
|
u32 value_size;
|
|
|
|
u32 max_entries;
|
|
|
|
struct bpf_map_ops *ops;
|
|
|
|
struct work_struct work;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct bpf_map_type_list {
|
|
|
|
struct list_head list_node;
|
|
|
|
struct bpf_map_ops *ops;
|
|
|
|
enum bpf_map_type type;
|
|
|
|
};
|
|
|
|
|
|
|
|
void bpf_register_map_type(struct bpf_map_type_list *tl);
|
|
|
|
void bpf_map_put(struct bpf_map *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 07:16:59 +00:00
|
|
|
struct bpf_map *bpf_map_get(struct fd f);
|
2014-09-26 07:16:57 +00:00
|
|
|
|
bpf: verifier (add verifier core)
This patch adds verifier core which simulates execution of every insn and
records the state of registers and program stack. Every branch instruction seen
during simulation is pushed into state stack. When verifier reaches BPF_EXIT,
it pops the state from the stack and continues until it reaches BPF_EXIT again.
For program:
1: bpf_mov r1, xxx
2: if (r1 == 0) goto 5
3: bpf_mov r0, 1
4: goto 6
5: bpf_mov r0, 2
6: bpf_exit
The verifier will walk insns: 1, 2, 3, 4, 6
then it will pop the state recorded at insn#2 and will continue: 5, 6
This way it walks all possible paths through the program and checks all
possible values of registers. While doing so, it checks for:
- invalid instructions
- uninitialized register access
- uninitialized stack access
- misaligned stack access
- out of range stack access
- invalid calling convention
- instruction encoding is not using reserved fields
Kernel subsystem configures the verifier with two callbacks:
- bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
that provides information to the verifer which fields of 'ctx'
are accessible (remember 'ctx' is the first argument to eBPF program)
- const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
returns argument constraints of kernel helper functions that eBPF program
may call, so that verifier can checks that R1-R5 types match the prototype
More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 07:17:06 +00:00
|
|
|
/* function argument constraints */
|
|
|
|
enum bpf_arg_type {
|
|
|
|
ARG_ANYTHING = 0, /* any argument is ok */
|
|
|
|
|
|
|
|
/* the following constraints used to prototype
|
|
|
|
* bpf_map_lookup/update/delete_elem() functions
|
|
|
|
*/
|
|
|
|
ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */
|
|
|
|
ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */
|
|
|
|
ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */
|
|
|
|
|
|
|
|
/* the following constraints used to prototype bpf_memcmp() and other
|
|
|
|
* functions that access data on eBPF program stack
|
|
|
|
*/
|
|
|
|
ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */
|
|
|
|
ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */
|
|
|
|
};
|
|
|
|
|
|
|
|
/* type of values returned from helper functions */
|
|
|
|
enum bpf_return_type {
|
|
|
|
RET_INTEGER, /* function returns integer */
|
|
|
|
RET_VOID, /* function doesn't return anything */
|
|
|
|
RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */
|
|
|
|
};
|
|
|
|
|
2014-09-26 07:17:00 +00:00
|
|
|
/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
|
|
|
|
* to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
|
|
|
|
* instructions after verifying
|
|
|
|
*/
|
|
|
|
struct bpf_func_proto {
|
|
|
|
u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
|
|
|
|
bool gpl_only;
|
bpf: verifier (add verifier core)
This patch adds verifier core which simulates execution of every insn and
records the state of registers and program stack. Every branch instruction seen
during simulation is pushed into state stack. When verifier reaches BPF_EXIT,
it pops the state from the stack and continues until it reaches BPF_EXIT again.
For program:
1: bpf_mov r1, xxx
2: if (r1 == 0) goto 5
3: bpf_mov r0, 1
4: goto 6
5: bpf_mov r0, 2
6: bpf_exit
The verifier will walk insns: 1, 2, 3, 4, 6
then it will pop the state recorded at insn#2 and will continue: 5, 6
This way it walks all possible paths through the program and checks all
possible values of registers. While doing so, it checks for:
- invalid instructions
- uninitialized register access
- uninitialized stack access
- misaligned stack access
- out of range stack access
- invalid calling convention
- instruction encoding is not using reserved fields
Kernel subsystem configures the verifier with two callbacks:
- bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
that provides information to the verifer which fields of 'ctx'
are accessible (remember 'ctx' is the first argument to eBPF program)
- const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
returns argument constraints of kernel helper functions that eBPF program
may call, so that verifier can checks that R1-R5 types match the prototype
More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 07:17:06 +00:00
|
|
|
enum bpf_return_type ret_type;
|
|
|
|
enum bpf_arg_type arg1_type;
|
|
|
|
enum bpf_arg_type arg2_type;
|
|
|
|
enum bpf_arg_type arg3_type;
|
|
|
|
enum bpf_arg_type arg4_type;
|
|
|
|
enum bpf_arg_type arg5_type;
|
|
|
|
};
|
|
|
|
|
|
|
|
/* bpf_context is intentionally undefined structure. Pointer to bpf_context is
|
|
|
|
* the first argument to eBPF programs.
|
|
|
|
* For socket filters: 'struct bpf_context *' == 'struct sk_buff *'
|
|
|
|
*/
|
|
|
|
struct bpf_context;
|
|
|
|
|
|
|
|
enum bpf_access_type {
|
|
|
|
BPF_READ = 1,
|
|
|
|
BPF_WRITE = 2
|
2014-09-26 07:17:00 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
struct bpf_verifier_ops {
|
|
|
|
/* return eBPF function prototype for verification */
|
|
|
|
const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
|
bpf: verifier (add verifier core)
This patch adds verifier core which simulates execution of every insn and
records the state of registers and program stack. Every branch instruction seen
during simulation is pushed into state stack. When verifier reaches BPF_EXIT,
it pops the state from the stack and continues until it reaches BPF_EXIT again.
For program:
1: bpf_mov r1, xxx
2: if (r1 == 0) goto 5
3: bpf_mov r0, 1
4: goto 6
5: bpf_mov r0, 2
6: bpf_exit
The verifier will walk insns: 1, 2, 3, 4, 6
then it will pop the state recorded at insn#2 and will continue: 5, 6
This way it walks all possible paths through the program and checks all
possible values of registers. While doing so, it checks for:
- invalid instructions
- uninitialized register access
- uninitialized stack access
- misaligned stack access
- out of range stack access
- invalid calling convention
- instruction encoding is not using reserved fields
Kernel subsystem configures the verifier with two callbacks:
- bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
that provides information to the verifer which fields of 'ctx'
are accessible (remember 'ctx' is the first argument to eBPF program)
- const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
returns argument constraints of kernel helper functions that eBPF program
may call, so that verifier can checks that R1-R5 types match the prototype
More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 07:17:06 +00:00
|
|
|
|
|
|
|
/* return true if 'size' wide access at offset 'off' within bpf_context
|
|
|
|
* with 'type' (read or write) is allowed
|
|
|
|
*/
|
|
|
|
bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
|
2014-09-26 07:17:00 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
struct bpf_prog_type_list {
|
|
|
|
struct list_head list_node;
|
|
|
|
struct bpf_verifier_ops *ops;
|
|
|
|
enum bpf_prog_type type;
|
|
|
|
};
|
|
|
|
|
|
|
|
void bpf_register_prog_type(struct bpf_prog_type_list *tl);
|
|
|
|
|
|
|
|
struct bpf_prog;
|
|
|
|
|
|
|
|
struct bpf_prog_aux {
|
|
|
|
atomic_t refcnt;
|
|
|
|
bool is_gpl_compatible;
|
|
|
|
enum bpf_prog_type prog_type;
|
|
|
|
struct bpf_verifier_ops *ops;
|
|
|
|
struct bpf_map **used_maps;
|
|
|
|
u32 used_map_cnt;
|
|
|
|
struct bpf_prog *prog;
|
|
|
|
struct work_struct work;
|
|
|
|
};
|
|
|
|
|
2014-12-01 23:06:35 +00:00
|
|
|
#ifdef CONFIG_BPF_SYSCALL
|
2014-09-26 07:17:00 +00:00
|
|
|
void bpf_prog_put(struct bpf_prog *prog);
|
2014-12-01 23:06:35 +00:00
|
|
|
#else
|
|
|
|
static inline void bpf_prog_put(struct bpf_prog *prog) {}
|
|
|
|
#endif
|
2014-09-26 07:17:00 +00:00
|
|
|
struct bpf_prog *bpf_prog_get(u32 ufd);
|
2014-09-26 07:17:02 +00:00
|
|
|
/* verify correctness of eBPF program */
|
|
|
|
int bpf_check(struct bpf_prog *fp, union bpf_attr *attr);
|
2014-09-26 07:17:00 +00:00
|
|
|
|
2014-11-14 01:36:49 +00:00
|
|
|
/* verifier prototypes for helper functions called from eBPF programs */
|
|
|
|
extern struct bpf_func_proto bpf_map_lookup_elem_proto;
|
|
|
|
extern struct bpf_func_proto bpf_map_update_elem_proto;
|
|
|
|
extern struct bpf_func_proto bpf_map_delete_elem_proto;
|
|
|
|
|
2014-09-26 07:16:57 +00:00
|
|
|
#endif /* _LINUX_BPF_H */
|