2014-09-26 15:16:57 +08:00
|
|
|
/* 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 15:16:59 +08:00
|
|
|
#include <linux/file.h>
|
2016-03-08 13:57:13 +08:00
|
|
|
#include <linux/percpu.h>
|
2014-09-26 15:16:57 +08:00
|
|
|
|
|
|
|
|
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 15:16:59 +08:00
|
|
|
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 09:36:44 +08:00
|
|
|
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 15:16:59 +08:00
|
|
|
int (*map_delete_elem)(struct bpf_map *map, void *key);
|
2015-08-06 15:02:33 +08:00
|
|
|
|
|
|
|
|
/* funcs called by prog_array and perf_event_array map */
|
|
|
|
|
void *(*map_fd_get_ptr) (struct bpf_map *map, int fd);
|
|
|
|
|
void (*map_fd_put_ptr) (void *ptr);
|
2014-09-26 15:16:57 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct bpf_map {
|
|
|
|
|
atomic_t refcnt;
|
|
|
|
|
enum bpf_map_type map_type;
|
|
|
|
|
u32 key_size;
|
|
|
|
|
u32 value_size;
|
|
|
|
|
u32 max_entries;
|
bpf: pre-allocate hash map elements
If kprobe is placed on spin_unlock then calling kmalloc/kfree from
bpf programs is not safe, since the following dead lock is possible:
kfree->spin_lock(kmem_cache_node->lock)...spin_unlock->kprobe->
bpf_prog->map_update->kmalloc->spin_lock(of the same kmem_cache_node->lock)
and deadlocks.
The following solutions were considered and some implemented, but
eventually discarded
- kmem_cache_create for every map
- add recursion check to slow-path of slub
- use reserved memory in bpf_map_update for in_irq or in preempt_disabled
- kmalloc via irq_work
At the end pre-allocation of all map elements turned out to be the simplest
solution and since the user is charged upfront for all the memory, such
pre-allocation doesn't affect the user space visible behavior.
Since it's impossible to tell whether kprobe is triggered in a safe
location from kmalloc point of view, use pre-allocation by default
and introduce new BPF_F_NO_PREALLOC flag.
While testing of per-cpu hash maps it was discovered
that alloc_percpu(GFP_ATOMIC) has odd corner cases and often
fails to allocate memory even when 90% of it is free.
The pre-allocation of per-cpu hash elements solves this problem as well.
Turned out that bpf_map_update() quickly followed by
bpf_map_lookup()+bpf_map_delete() is very common pattern used
in many of iovisor/bcc/tools, so there is additional benefit of
pre-allocation, since such use cases are must faster.
Since all hash map elements are now pre-allocated we can remove
atomic increment of htab->count and save few more cycles.
Also add bpf_map_precharge_memlock() to check rlimit_memlock early to avoid
large malloc/free done by users who don't have sufficient limits.
Pre-allocation is done with vmalloc and alloc/free is done
via percpu_freelist. Here are performance numbers for different
pre-allocation algorithms that were implemented, but discarded
in favor of percpu_freelist:
1 cpu:
pcpu_ida 2.1M
pcpu_ida nolock 2.3M
bt 2.4M
kmalloc 1.8M
hlist+spinlock 2.3M
pcpu_freelist 2.6M
4 cpu:
pcpu_ida 1.5M
pcpu_ida nolock 1.8M
bt w/smp_align 1.7M
bt no/smp_align 1.1M
kmalloc 0.7M
hlist+spinlock 0.2M
pcpu_freelist 2.0M
8 cpu:
pcpu_ida 0.7M
bt w/smp_align 0.8M
kmalloc 0.4M
pcpu_freelist 1.5M
32 cpu:
kmalloc 0.13M
pcpu_freelist 0.49M
pcpu_ida nolock is a modified percpu_ida algorithm without
percpu_ida_cpu locks and without cross-cpu tag stealing.
It's faster than existing percpu_ida, but not as fast as pcpu_freelist.
bt is a variant of block/blk-mq-tag.c simlified and customized
for bpf use case. bt w/smp_align is using cache line for every 'long'
(similar to blk-mq-tag). bt no/smp_align allocates 'long'
bitmasks continuously to save memory. It's comparable to percpu_ida
and in some cases faster, but slower than percpu_freelist
hlist+spinlock is the simplest free list with single spinlock.
As expeceted it has very bad scaling in SMP.
kmalloc is existing implementation which is still available via
BPF_F_NO_PREALLOC flag. It's significantly slower in single cpu and
in 8 cpu setup it's 3 times slower than pre-allocation with pcpu_freelist,
but saves memory, so in cases where map->max_entries can be large
and number of map update/delete per second is low, it may make
sense to use it.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-08 13:57:15 +08:00
|
|
|
u32 map_flags;
|
2015-10-08 13:23:22 +08:00
|
|
|
u32 pages;
|
|
|
|
|
struct user_struct *user;
|
2015-03-01 19:31:42 +08:00
|
|
|
const struct bpf_map_ops *ops;
|
2014-09-26 15:16:57 +08:00
|
|
|
struct work_struct work;
|
bpf: fix clearing on persistent program array maps
Currently, when having map file descriptors pointing to program arrays,
there's still the issue that we unconditionally flush program array
contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens
when such a file descriptor is released and is independent of the map's
refcount.
Having this flush independent of the refcount is for a reason: there
can be arbitrary complex dependency chains among tail calls, also circular
ones (direct or indirect, nesting limit determined during runtime), and
we need to make sure that the map drops all references to eBPF programs
it holds, so that the map's refcount can eventually drop to zero and
initiate its freeing. Btw, a walk of the whole dependency graph would
not be possible for various reasons, one being complexity and another
one inconsistency, i.e. new programs can be added to parts of the graph
at any time, so there's no guaranteed consistent state for the time of
such a walk.
Now, the program array pinning itself works, but the issue is that each
derived file descriptor on close would nevertheless call unconditionally
into bpf_fd_array_map_clear(). Instead, keep track of users and postpone
this flush until the last reference to a user is dropped. As this only
concerns a subset of references (f.e. a prog array could hold a program
that itself has reference on the prog array holding it, etc), we need to
track them separately.
Short analysis on the refcounting: on map creation time usercnt will be
one, so there's no change in behaviour for bpf_map_release(), if unpinned.
If we already fail in map_create(), we are immediately freed, and no
file descriptor has been made public yet. In bpf_obj_pin_user(), we need
to probe for a possible map in bpf_fd_probe_obj() already with a usercnt
reference, so before we drop the reference on the fd with fdput().
Therefore, if actual pinning fails, we need to drop that reference again
in bpf_any_put(), otherwise we keep holding it. When last reference
drops on the inode, the bpf_any_put() in bpf_evict_inode() will take
care of dropping the usercnt again. In the bpf_obj_get_user() case, the
bpf_any_get() will grab a reference on the usercnt, still at a time when
we have the reference on the path. Should we later on fail to grab a new
file descriptor, bpf_any_put() will drop it, otherwise we hold it until
bpf_map_release() time.
Joint work with Alexei.
Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-25 04:28:15 +08:00
|
|
|
atomic_t usercnt;
|
2014-09-26 15:16:57 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct bpf_map_type_list {
|
|
|
|
|
struct list_head list_node;
|
2015-03-01 19:31:42 +08:00
|
|
|
const struct bpf_map_ops *ops;
|
2014-09-26 15:16:57 +08:00
|
|
|
enum bpf_map_type type;
|
|
|
|
|
};
|
|
|
|
|
|
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 15:17:06 +08:00
|
|
|
/* function argument constraints */
|
|
|
|
|
enum bpf_arg_type {
|
2015-03-13 00:21:42 +08:00
|
|
|
ARG_DONTCARE = 0, /* unused argument in helper function */
|
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 15:17:06 +08:00
|
|
|
|
|
|
|
|
/* 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 */
|
bpf: add new arg_type that allows for 0 sized stack buffer
Currently, when we pass a buffer from the eBPF stack into a helper
function, the function proto indicates argument types as ARG_PTR_TO_STACK
and ARG_CONST_STACK_SIZE pair. If R<X> contains the former, then R<X+1>
must be of the latter type. Then, verifier checks whether the buffer
points into eBPF stack, is initialized, etc. The verifier also guarantees
that the constant value passed in R<X+1> is greater than 0, so helper
functions don't need to test for it and can always assume a non-NULL
initialized buffer as well as non-0 buffer size.
This patch adds a new argument types ARG_CONST_STACK_SIZE_OR_ZERO that
allows to also pass NULL as R<X> and 0 as R<X+1> into the helper function.
Such helper functions, of course, need to be able to handle these cases
internally then. Verifier guarantees that either R<X> == NULL && R<X+1> == 0
or R<X> != NULL && R<X+1> != 0 (like the case of ARG_CONST_STACK_SIZE), any
other combinations are not possible to load.
I went through various options of extending the verifier, and introducing
the type ARG_CONST_STACK_SIZE_OR_ZERO seems to have most minimal changes
needed to the verifier.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-20 06:05:22 +08:00
|
|
|
ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack or 0 */
|
2015-03-13 00:21:42 +08:00
|
|
|
|
2015-03-27 10:53:57 +08:00
|
|
|
ARG_PTR_TO_CTX, /* pointer to context */
|
2015-03-13 00:21:42 +08:00
|
|
|
ARG_ANYTHING, /* any (initialized) argument is ok */
|
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 15:17:06 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/* 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 15:17:00 +08:00
|
|
|
/* 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 15:17:06 +08:00
|
|
|
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 15:17:00 +08:00
|
|
|
};
|
|
|
|
|
|
2015-10-08 01:55:41 +08:00
|
|
|
struct bpf_prog;
|
|
|
|
|
|
2014-09-26 15:17:00 +08:00
|
|
|
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 15:17:06 +08:00
|
|
|
|
|
|
|
|
/* 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);
|
2015-03-14 02:57:42 +08:00
|
|
|
|
2015-06-05 01:11:54 +08:00
|
|
|
u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg,
|
|
|
|
|
int src_reg, int ctx_off,
|
2015-10-08 01:55:41 +08:00
|
|
|
struct bpf_insn *insn, struct bpf_prog *prog);
|
2014-09-26 15:17:00 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct bpf_prog_type_list {
|
|
|
|
|
struct list_head list_node;
|
2015-03-01 19:31:42 +08:00
|
|
|
const struct bpf_verifier_ops *ops;
|
2014-09-26 15:17:00 +08:00
|
|
|
enum bpf_prog_type type;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct bpf_prog_aux {
|
|
|
|
|
atomic_t refcnt;
|
2015-03-01 19:31:47 +08:00
|
|
|
u32 used_map_cnt;
|
2016-04-07 09:43:28 +08:00
|
|
|
u32 max_ctx_offset;
|
2015-03-01 19:31:42 +08:00
|
|
|
const struct bpf_verifier_ops *ops;
|
2014-09-26 15:17:00 +08:00
|
|
|
struct bpf_map **used_maps;
|
|
|
|
|
struct bpf_prog *prog;
|
2015-10-08 13:23:22 +08:00
|
|
|
struct user_struct *user;
|
2015-05-29 10:26:02 +08:00
|
|
|
union {
|
|
|
|
|
struct work_struct work;
|
|
|
|
|
struct rcu_head rcu;
|
|
|
|
|
};
|
2014-09-26 15:17:00 +08:00
|
|
|
};
|
|
|
|
|
|
bpf: allow bpf programs to tail-call other bpf programs
introduce bpf_tail_call(ctx, &jmp_table, index) helper function
which can be used from BPF programs like:
int bpf_prog(struct pt_regs *ctx)
{
...
bpf_tail_call(ctx, &jmp_table, index);
...
}
that is roughly equivalent to:
int bpf_prog(struct pt_regs *ctx)
{
...
if (jmp_table[index])
return (*jmp_table[index])(ctx);
...
}
The important detail that it's not a normal call, but a tail call.
The kernel stack is precious, so this helper reuses the current
stack frame and jumps into another BPF program without adding
extra call frame.
It's trivially done in interpreter and a bit trickier in JITs.
In case of x64 JIT the bigger part of generated assembler prologue
is common for all programs, so it is simply skipped while jumping.
Other JITs can do similar prologue-skipping optimization or
do stack unwind before jumping into the next program.
bpf_tail_call() arguments:
ctx - context pointer
jmp_table - one of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table
index - index in the jump table
Since all BPF programs are idenitified by file descriptor, user space
need to populate the jmp_table with FDs of other BPF programs.
If jmp_table[index] is empty the bpf_tail_call() doesn't jump anywhere
and program execution continues as normal.
New BPF_MAP_TYPE_PROG_ARRAY map type is introduced so that user space can
populate this jmp_table array with FDs of other bpf programs.
Programs can share the same jmp_table array or use multiple jmp_tables.
The chain of tail calls can form unpredictable dynamic loops therefore
tail_call_cnt is used to limit the number of calls and currently is set to 32.
Use cases:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
==========
- simplify complex programs by splitting them into a sequence of small programs
- dispatch routine
For tracing and future seccomp the program may be triggered on all system
calls, but processing of syscall arguments will be different. It's more
efficient to implement them as:
int syscall_entry(struct seccomp_data *ctx)
{
bpf_tail_call(ctx, &syscall_jmp_table, ctx->nr /* syscall number */);
... default: process unknown syscall ...
}
int sys_write_event(struct seccomp_data *ctx) {...}
int sys_read_event(struct seccomp_data *ctx) {...}
syscall_jmp_table[__NR_write] = sys_write_event;
syscall_jmp_table[__NR_read] = sys_read_event;
For networking the program may call into different parsers depending on
packet format, like:
int packet_parser(struct __sk_buff *skb)
{
... parse L2, L3 here ...
__u8 ipproto = load_byte(skb, ... offsetof(struct iphdr, protocol));
bpf_tail_call(skb, &ipproto_jmp_table, ipproto);
... default: process unknown protocol ...
}
int parse_tcp(struct __sk_buff *skb) {...}
int parse_udp(struct __sk_buff *skb) {...}
ipproto_jmp_table[IPPROTO_TCP] = parse_tcp;
ipproto_jmp_table[IPPROTO_UDP] = parse_udp;
- for TC use case, bpf_tail_call() allows to implement reclassify-like logic
- bpf_map_update_elem/delete calls into BPF_MAP_TYPE_PROG_ARRAY jump table
are atomic, so user space can build chains of BPF programs on the fly
Implementation details:
=======================
- high performance of bpf_tail_call() is the goal.
It could have been implemented without JIT changes as a wrapper on top of
BPF_PROG_RUN() macro, but with two downsides:
. all programs would have to pay performance penalty for this feature and
tail call itself would be slower, since mandatory stack unwind, return,
stack allocate would be done for every tailcall.
. tailcall would be limited to programs running preempt_disabled, since
generic 'void *ctx' doesn't have room for 'tail_call_cnt' and it would
need to be either global per_cpu variable accessed by helper and by wrapper
or global variable protected by locks.
In this implementation x64 JIT bypasses stack unwind and jumps into the
callee program after prologue.
- bpf_prog_array_compatible() ensures that prog_type of callee and caller
are the same and JITed/non-JITed flag is the same, since calling JITed
program from non-JITed is invalid, since stack frames are different.
Similarly calling kprobe type program from socket type program is invalid.
- jump table is implemented as BPF_MAP_TYPE_PROG_ARRAY to reuse 'map'
abstraction, its user space API and all of verifier logic.
It's in the existing arraymap.c file, since several functions are
shared with regular array map.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-20 07:59:03 +08:00
|
|
|
struct bpf_array {
|
|
|
|
|
struct bpf_map map;
|
|
|
|
|
u32 elem_size;
|
|
|
|
|
/* 'ownership' of prog_array is claimed by the first program that
|
|
|
|
|
* is going to use this map or by the first program which FD is stored
|
|
|
|
|
* in the map to make sure that all callers and callees have the same
|
|
|
|
|
* prog_type and JITed flag
|
|
|
|
|
*/
|
|
|
|
|
enum bpf_prog_type owner_prog_type;
|
|
|
|
|
bool owner_jited;
|
|
|
|
|
union {
|
|
|
|
|
char value[0] __aligned(8);
|
2015-08-06 15:02:33 +08:00
|
|
|
void *ptrs[0] __aligned(8);
|
2016-02-02 14:39:54 +08:00
|
|
|
void __percpu *pptrs[0] __aligned(8);
|
bpf: allow bpf programs to tail-call other bpf programs
introduce bpf_tail_call(ctx, &jmp_table, index) helper function
which can be used from BPF programs like:
int bpf_prog(struct pt_regs *ctx)
{
...
bpf_tail_call(ctx, &jmp_table, index);
...
}
that is roughly equivalent to:
int bpf_prog(struct pt_regs *ctx)
{
...
if (jmp_table[index])
return (*jmp_table[index])(ctx);
...
}
The important detail that it's not a normal call, but a tail call.
The kernel stack is precious, so this helper reuses the current
stack frame and jumps into another BPF program without adding
extra call frame.
It's trivially done in interpreter and a bit trickier in JITs.
In case of x64 JIT the bigger part of generated assembler prologue
is common for all programs, so it is simply skipped while jumping.
Other JITs can do similar prologue-skipping optimization or
do stack unwind before jumping into the next program.
bpf_tail_call() arguments:
ctx - context pointer
jmp_table - one of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table
index - index in the jump table
Since all BPF programs are idenitified by file descriptor, user space
need to populate the jmp_table with FDs of other BPF programs.
If jmp_table[index] is empty the bpf_tail_call() doesn't jump anywhere
and program execution continues as normal.
New BPF_MAP_TYPE_PROG_ARRAY map type is introduced so that user space can
populate this jmp_table array with FDs of other bpf programs.
Programs can share the same jmp_table array or use multiple jmp_tables.
The chain of tail calls can form unpredictable dynamic loops therefore
tail_call_cnt is used to limit the number of calls and currently is set to 32.
Use cases:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
==========
- simplify complex programs by splitting them into a sequence of small programs
- dispatch routine
For tracing and future seccomp the program may be triggered on all system
calls, but processing of syscall arguments will be different. It's more
efficient to implement them as:
int syscall_entry(struct seccomp_data *ctx)
{
bpf_tail_call(ctx, &syscall_jmp_table, ctx->nr /* syscall number */);
... default: process unknown syscall ...
}
int sys_write_event(struct seccomp_data *ctx) {...}
int sys_read_event(struct seccomp_data *ctx) {...}
syscall_jmp_table[__NR_write] = sys_write_event;
syscall_jmp_table[__NR_read] = sys_read_event;
For networking the program may call into different parsers depending on
packet format, like:
int packet_parser(struct __sk_buff *skb)
{
... parse L2, L3 here ...
__u8 ipproto = load_byte(skb, ... offsetof(struct iphdr, protocol));
bpf_tail_call(skb, &ipproto_jmp_table, ipproto);
... default: process unknown protocol ...
}
int parse_tcp(struct __sk_buff *skb) {...}
int parse_udp(struct __sk_buff *skb) {...}
ipproto_jmp_table[IPPROTO_TCP] = parse_tcp;
ipproto_jmp_table[IPPROTO_UDP] = parse_udp;
- for TC use case, bpf_tail_call() allows to implement reclassify-like logic
- bpf_map_update_elem/delete calls into BPF_MAP_TYPE_PROG_ARRAY jump table
are atomic, so user space can build chains of BPF programs on the fly
Implementation details:
=======================
- high performance of bpf_tail_call() is the goal.
It could have been implemented without JIT changes as a wrapper on top of
BPF_PROG_RUN() macro, but with two downsides:
. all programs would have to pay performance penalty for this feature and
tail call itself would be slower, since mandatory stack unwind, return,
stack allocate would be done for every tailcall.
. tailcall would be limited to programs running preempt_disabled, since
generic 'void *ctx' doesn't have room for 'tail_call_cnt' and it would
need to be either global per_cpu variable accessed by helper and by wrapper
or global variable protected by locks.
In this implementation x64 JIT bypasses stack unwind and jumps into the
callee program after prologue.
- bpf_prog_array_compatible() ensures that prog_type of callee and caller
are the same and JITed/non-JITed flag is the same, since calling JITed
program from non-JITed is invalid, since stack frames are different.
Similarly calling kprobe type program from socket type program is invalid.
- jump table is implemented as BPF_MAP_TYPE_PROG_ARRAY to reuse 'map'
abstraction, its user space API and all of verifier logic.
It's in the existing arraymap.c file, since several functions are
shared with regular array map.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-20 07:59:03 +08:00
|
|
|
};
|
|
|
|
|
};
|
|
|
|
|
#define MAX_TAIL_CALL_CNT 32
|
|
|
|
|
|
|
|
|
|
u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
|
2016-04-07 09:43:27 +08:00
|
|
|
u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
|
2015-08-06 15:02:33 +08:00
|
|
|
void bpf_fd_array_map_clear(struct bpf_map *map);
|
bpf: allow bpf programs to tail-call other bpf programs
introduce bpf_tail_call(ctx, &jmp_table, index) helper function
which can be used from BPF programs like:
int bpf_prog(struct pt_regs *ctx)
{
...
bpf_tail_call(ctx, &jmp_table, index);
...
}
that is roughly equivalent to:
int bpf_prog(struct pt_regs *ctx)
{
...
if (jmp_table[index])
return (*jmp_table[index])(ctx);
...
}
The important detail that it's not a normal call, but a tail call.
The kernel stack is precious, so this helper reuses the current
stack frame and jumps into another BPF program without adding
extra call frame.
It's trivially done in interpreter and a bit trickier in JITs.
In case of x64 JIT the bigger part of generated assembler prologue
is common for all programs, so it is simply skipped while jumping.
Other JITs can do similar prologue-skipping optimization or
do stack unwind before jumping into the next program.
bpf_tail_call() arguments:
ctx - context pointer
jmp_table - one of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table
index - index in the jump table
Since all BPF programs are idenitified by file descriptor, user space
need to populate the jmp_table with FDs of other BPF programs.
If jmp_table[index] is empty the bpf_tail_call() doesn't jump anywhere
and program execution continues as normal.
New BPF_MAP_TYPE_PROG_ARRAY map type is introduced so that user space can
populate this jmp_table array with FDs of other bpf programs.
Programs can share the same jmp_table array or use multiple jmp_tables.
The chain of tail calls can form unpredictable dynamic loops therefore
tail_call_cnt is used to limit the number of calls and currently is set to 32.
Use cases:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
==========
- simplify complex programs by splitting them into a sequence of small programs
- dispatch routine
For tracing and future seccomp the program may be triggered on all system
calls, but processing of syscall arguments will be different. It's more
efficient to implement them as:
int syscall_entry(struct seccomp_data *ctx)
{
bpf_tail_call(ctx, &syscall_jmp_table, ctx->nr /* syscall number */);
... default: process unknown syscall ...
}
int sys_write_event(struct seccomp_data *ctx) {...}
int sys_read_event(struct seccomp_data *ctx) {...}
syscall_jmp_table[__NR_write] = sys_write_event;
syscall_jmp_table[__NR_read] = sys_read_event;
For networking the program may call into different parsers depending on
packet format, like:
int packet_parser(struct __sk_buff *skb)
{
... parse L2, L3 here ...
__u8 ipproto = load_byte(skb, ... offsetof(struct iphdr, protocol));
bpf_tail_call(skb, &ipproto_jmp_table, ipproto);
... default: process unknown protocol ...
}
int parse_tcp(struct __sk_buff *skb) {...}
int parse_udp(struct __sk_buff *skb) {...}
ipproto_jmp_table[IPPROTO_TCP] = parse_tcp;
ipproto_jmp_table[IPPROTO_UDP] = parse_udp;
- for TC use case, bpf_tail_call() allows to implement reclassify-like logic
- bpf_map_update_elem/delete calls into BPF_MAP_TYPE_PROG_ARRAY jump table
are atomic, so user space can build chains of BPF programs on the fly
Implementation details:
=======================
- high performance of bpf_tail_call() is the goal.
It could have been implemented without JIT changes as a wrapper on top of
BPF_PROG_RUN() macro, but with two downsides:
. all programs would have to pay performance penalty for this feature and
tail call itself would be slower, since mandatory stack unwind, return,
stack allocate would be done for every tailcall.
. tailcall would be limited to programs running preempt_disabled, since
generic 'void *ctx' doesn't have room for 'tail_call_cnt' and it would
need to be either global per_cpu variable accessed by helper and by wrapper
or global variable protected by locks.
In this implementation x64 JIT bypasses stack unwind and jumps into the
callee program after prologue.
- bpf_prog_array_compatible() ensures that prog_type of callee and caller
are the same and JITed/non-JITed flag is the same, since calling JITed
program from non-JITed is invalid, since stack frames are different.
Similarly calling kprobe type program from socket type program is invalid.
- jump table is implemented as BPF_MAP_TYPE_PROG_ARRAY to reuse 'map'
abstraction, its user space API and all of verifier logic.
It's in the existing arraymap.c file, since several functions are
shared with regular array map.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-20 07:59:03 +08:00
|
|
|
bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
|
2015-06-13 10:39:13 +08:00
|
|
|
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
|
bpf: allow bpf programs to tail-call other bpf programs
introduce bpf_tail_call(ctx, &jmp_table, index) helper function
which can be used from BPF programs like:
int bpf_prog(struct pt_regs *ctx)
{
...
bpf_tail_call(ctx, &jmp_table, index);
...
}
that is roughly equivalent to:
int bpf_prog(struct pt_regs *ctx)
{
...
if (jmp_table[index])
return (*jmp_table[index])(ctx);
...
}
The important detail that it's not a normal call, but a tail call.
The kernel stack is precious, so this helper reuses the current
stack frame and jumps into another BPF program without adding
extra call frame.
It's trivially done in interpreter and a bit trickier in JITs.
In case of x64 JIT the bigger part of generated assembler prologue
is common for all programs, so it is simply skipped while jumping.
Other JITs can do similar prologue-skipping optimization or
do stack unwind before jumping into the next program.
bpf_tail_call() arguments:
ctx - context pointer
jmp_table - one of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table
index - index in the jump table
Since all BPF programs are idenitified by file descriptor, user space
need to populate the jmp_table with FDs of other BPF programs.
If jmp_table[index] is empty the bpf_tail_call() doesn't jump anywhere
and program execution continues as normal.
New BPF_MAP_TYPE_PROG_ARRAY map type is introduced so that user space can
populate this jmp_table array with FDs of other bpf programs.
Programs can share the same jmp_table array or use multiple jmp_tables.
The chain of tail calls can form unpredictable dynamic loops therefore
tail_call_cnt is used to limit the number of calls and currently is set to 32.
Use cases:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
==========
- simplify complex programs by splitting them into a sequence of small programs
- dispatch routine
For tracing and future seccomp the program may be triggered on all system
calls, but processing of syscall arguments will be different. It's more
efficient to implement them as:
int syscall_entry(struct seccomp_data *ctx)
{
bpf_tail_call(ctx, &syscall_jmp_table, ctx->nr /* syscall number */);
... default: process unknown syscall ...
}
int sys_write_event(struct seccomp_data *ctx) {...}
int sys_read_event(struct seccomp_data *ctx) {...}
syscall_jmp_table[__NR_write] = sys_write_event;
syscall_jmp_table[__NR_read] = sys_read_event;
For networking the program may call into different parsers depending on
packet format, like:
int packet_parser(struct __sk_buff *skb)
{
... parse L2, L3 here ...
__u8 ipproto = load_byte(skb, ... offsetof(struct iphdr, protocol));
bpf_tail_call(skb, &ipproto_jmp_table, ipproto);
... default: process unknown protocol ...
}
int parse_tcp(struct __sk_buff *skb) {...}
int parse_udp(struct __sk_buff *skb) {...}
ipproto_jmp_table[IPPROTO_TCP] = parse_tcp;
ipproto_jmp_table[IPPROTO_UDP] = parse_udp;
- for TC use case, bpf_tail_call() allows to implement reclassify-like logic
- bpf_map_update_elem/delete calls into BPF_MAP_TYPE_PROG_ARRAY jump table
are atomic, so user space can build chains of BPF programs on the fly
Implementation details:
=======================
- high performance of bpf_tail_call() is the goal.
It could have been implemented without JIT changes as a wrapper on top of
BPF_PROG_RUN() macro, but with two downsides:
. all programs would have to pay performance penalty for this feature and
tail call itself would be slower, since mandatory stack unwind, return,
stack allocate would be done for every tailcall.
. tailcall would be limited to programs running preempt_disabled, since
generic 'void *ctx' doesn't have room for 'tail_call_cnt' and it would
need to be either global per_cpu variable accessed by helper and by wrapper
or global variable protected by locks.
In this implementation x64 JIT bypasses stack unwind and jumps into the
callee program after prologue.
- bpf_prog_array_compatible() ensures that prog_type of callee and caller
are the same and JITed/non-JITed flag is the same, since calling JITed
program from non-JITed is invalid, since stack frames are different.
Similarly calling kprobe type program from socket type program is invalid.
- jump table is implemented as BPF_MAP_TYPE_PROG_ARRAY to reuse 'map'
abstraction, its user space API and all of verifier logic.
It's in the existing arraymap.c file, since several functions are
shared with regular array map.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-20 07:59:03 +08:00
|
|
|
|
2014-12-02 07:06:35 +08:00
|
|
|
#ifdef CONFIG_BPF_SYSCALL
|
2016-03-08 13:57:13 +08:00
|
|
|
DECLARE_PER_CPU(int, bpf_prog_active);
|
|
|
|
|
|
2015-03-01 19:31:44 +08:00
|
|
|
void bpf_register_prog_type(struct bpf_prog_type_list *tl);
|
2015-03-02 22:21:55 +08:00
|
|
|
void bpf_register_map_type(struct bpf_map_type_list *tl);
|
2015-03-01 19:31:44 +08:00
|
|
|
|
|
|
|
|
struct bpf_prog *bpf_prog_get(u32 ufd);
|
2015-03-02 22:21:55 +08:00
|
|
|
void bpf_prog_put(struct bpf_prog *prog);
|
2015-05-29 10:26:02 +08:00
|
|
|
void bpf_prog_put_rcu(struct bpf_prog *prog);
|
2015-03-02 22:21:55 +08:00
|
|
|
|
bpf: fix clearing on persistent program array maps
Currently, when having map file descriptors pointing to program arrays,
there's still the issue that we unconditionally flush program array
contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens
when such a file descriptor is released and is independent of the map's
refcount.
Having this flush independent of the refcount is for a reason: there
can be arbitrary complex dependency chains among tail calls, also circular
ones (direct or indirect, nesting limit determined during runtime), and
we need to make sure that the map drops all references to eBPF programs
it holds, so that the map's refcount can eventually drop to zero and
initiate its freeing. Btw, a walk of the whole dependency graph would
not be possible for various reasons, one being complexity and another
one inconsistency, i.e. new programs can be added to parts of the graph
at any time, so there's no guaranteed consistent state for the time of
such a walk.
Now, the program array pinning itself works, but the issue is that each
derived file descriptor on close would nevertheless call unconditionally
into bpf_fd_array_map_clear(). Instead, keep track of users and postpone
this flush until the last reference to a user is dropped. As this only
concerns a subset of references (f.e. a prog array could hold a program
that itself has reference on the prog array holding it, etc), we need to
track them separately.
Short analysis on the refcounting: on map creation time usercnt will be
one, so there's no change in behaviour for bpf_map_release(), if unpinned.
If we already fail in map_create(), we are immediately freed, and no
file descriptor has been made public yet. In bpf_obj_pin_user(), we need
to probe for a possible map in bpf_fd_probe_obj() already with a usercnt
reference, so before we drop the reference on the fd with fdput().
Therefore, if actual pinning fails, we need to drop that reference again
in bpf_any_put(), otherwise we keep holding it. When last reference
drops on the inode, the bpf_any_put() in bpf_evict_inode() will take
care of dropping the usercnt again. In the bpf_obj_get_user() case, the
bpf_any_get() will grab a reference on the usercnt, still at a time when
we have the reference on the path. Should we later on fail to grab a new
file descriptor, bpf_any_put() will drop it, otherwise we hold it until
bpf_map_release() time.
Joint work with Alexei.
Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-25 04:28:15 +08:00
|
|
|
struct bpf_map *bpf_map_get_with_uref(u32 ufd);
|
2015-10-29 21:58:07 +08:00
|
|
|
struct bpf_map *__bpf_map_get(struct fd f);
|
bpf: fix clearing on persistent program array maps
Currently, when having map file descriptors pointing to program arrays,
there's still the issue that we unconditionally flush program array
contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens
when such a file descriptor is released and is independent of the map's
refcount.
Having this flush independent of the refcount is for a reason: there
can be arbitrary complex dependency chains among tail calls, also circular
ones (direct or indirect, nesting limit determined during runtime), and
we need to make sure that the map drops all references to eBPF programs
it holds, so that the map's refcount can eventually drop to zero and
initiate its freeing. Btw, a walk of the whole dependency graph would
not be possible for various reasons, one being complexity and another
one inconsistency, i.e. new programs can be added to parts of the graph
at any time, so there's no guaranteed consistent state for the time of
such a walk.
Now, the program array pinning itself works, but the issue is that each
derived file descriptor on close would nevertheless call unconditionally
into bpf_fd_array_map_clear(). Instead, keep track of users and postpone
this flush until the last reference to a user is dropped. As this only
concerns a subset of references (f.e. a prog array could hold a program
that itself has reference on the prog array holding it, etc), we need to
track them separately.
Short analysis on the refcounting: on map creation time usercnt will be
one, so there's no change in behaviour for bpf_map_release(), if unpinned.
If we already fail in map_create(), we are immediately freed, and no
file descriptor has been made public yet. In bpf_obj_pin_user(), we need
to probe for a possible map in bpf_fd_probe_obj() already with a usercnt
reference, so before we drop the reference on the fd with fdput().
Therefore, if actual pinning fails, we need to drop that reference again
in bpf_any_put(), otherwise we keep holding it. When last reference
drops on the inode, the bpf_any_put() in bpf_evict_inode() will take
care of dropping the usercnt again. In the bpf_obj_get_user() case, the
bpf_any_get() will grab a reference on the usercnt, still at a time when
we have the reference on the path. Should we later on fail to grab a new
file descriptor, bpf_any_put() will drop it, otherwise we hold it until
bpf_map_release() time.
Joint work with Alexei.
Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-25 04:28:15 +08:00
|
|
|
void bpf_map_inc(struct bpf_map *map, bool uref);
|
|
|
|
|
void bpf_map_put_with_uref(struct bpf_map *map);
|
2015-03-02 22:21:55 +08:00
|
|
|
void bpf_map_put(struct bpf_map *map);
|
bpf: pre-allocate hash map elements
If kprobe is placed on spin_unlock then calling kmalloc/kfree from
bpf programs is not safe, since the following dead lock is possible:
kfree->spin_lock(kmem_cache_node->lock)...spin_unlock->kprobe->
bpf_prog->map_update->kmalloc->spin_lock(of the same kmem_cache_node->lock)
and deadlocks.
The following solutions were considered and some implemented, but
eventually discarded
- kmem_cache_create for every map
- add recursion check to slow-path of slub
- use reserved memory in bpf_map_update for in_irq or in preempt_disabled
- kmalloc via irq_work
At the end pre-allocation of all map elements turned out to be the simplest
solution and since the user is charged upfront for all the memory, such
pre-allocation doesn't affect the user space visible behavior.
Since it's impossible to tell whether kprobe is triggered in a safe
location from kmalloc point of view, use pre-allocation by default
and introduce new BPF_F_NO_PREALLOC flag.
While testing of per-cpu hash maps it was discovered
that alloc_percpu(GFP_ATOMIC) has odd corner cases and often
fails to allocate memory even when 90% of it is free.
The pre-allocation of per-cpu hash elements solves this problem as well.
Turned out that bpf_map_update() quickly followed by
bpf_map_lookup()+bpf_map_delete() is very common pattern used
in many of iovisor/bcc/tools, so there is additional benefit of
pre-allocation, since such use cases are must faster.
Since all hash map elements are now pre-allocated we can remove
atomic increment of htab->count and save few more cycles.
Also add bpf_map_precharge_memlock() to check rlimit_memlock early to avoid
large malloc/free done by users who don't have sufficient limits.
Pre-allocation is done with vmalloc and alloc/free is done
via percpu_freelist. Here are performance numbers for different
pre-allocation algorithms that were implemented, but discarded
in favor of percpu_freelist:
1 cpu:
pcpu_ida 2.1M
pcpu_ida nolock 2.3M
bt 2.4M
kmalloc 1.8M
hlist+spinlock 2.3M
pcpu_freelist 2.6M
4 cpu:
pcpu_ida 1.5M
pcpu_ida nolock 1.8M
bt w/smp_align 1.7M
bt no/smp_align 1.1M
kmalloc 0.7M
hlist+spinlock 0.2M
pcpu_freelist 2.0M
8 cpu:
pcpu_ida 0.7M
bt w/smp_align 0.8M
kmalloc 0.4M
pcpu_freelist 1.5M
32 cpu:
kmalloc 0.13M
pcpu_freelist 0.49M
pcpu_ida nolock is a modified percpu_ida algorithm without
percpu_ida_cpu locks and without cross-cpu tag stealing.
It's faster than existing percpu_ida, but not as fast as pcpu_freelist.
bt is a variant of block/blk-mq-tag.c simlified and customized
for bpf use case. bt w/smp_align is using cache line for every 'long'
(similar to blk-mq-tag). bt no/smp_align allocates 'long'
bitmasks continuously to save memory. It's comparable to percpu_ida
and in some cases faster, but slower than percpu_freelist
hlist+spinlock is the simplest free list with single spinlock.
As expeceted it has very bad scaling in SMP.
kmalloc is existing implementation which is still available via
BPF_F_NO_PREALLOC flag. It's significantly slower in single cpu and
in 8 cpu setup it's 3 times slower than pre-allocation with pcpu_freelist,
but saves memory, so in cases where map->max_entries can be large
and number of map update/delete per second is low, it may make
sense to use it.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-08 13:57:15 +08:00
|
|
|
int bpf_map_precharge_memlock(u32 pages);
|
2015-03-02 22:21:55 +08:00
|
|
|
|
bpf: enable non-root eBPF programs
In order to let unprivileged users load and execute eBPF programs
teach verifier to prevent pointer leaks.
Verifier will prevent
- any arithmetic on pointers
(except R10+Imm which is used to compute stack addresses)
- comparison of pointers
(except if (map_value_ptr == 0) ... )
- passing pointers to helper functions
- indirectly passing pointers in stack to helper functions
- returning pointer from bpf program
- storing pointers into ctx or maps
Spill/fill of pointers into stack is allowed, but mangling
of pointers stored in the stack or reading them byte by byte is not.
Within bpf programs the pointers do exist, since programs need to
be able to access maps, pass skb pointer to LD_ABS insns, etc
but programs cannot pass such pointer values to the outside
or obfuscate them.
Only allow BPF_PROG_TYPE_SOCKET_FILTER unprivileged programs,
so that socket filters (tcpdump), af_packet (quic acceleration)
and future kcm can use it.
tracing and tc cls/act program types still require root permissions,
since tracing actually needs to be able to see all kernel pointers
and tc is for root only.
For example, the following unprivileged socket filter program is allowed:
int bpf_prog1(struct __sk_buff *skb)
{
u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol));
u64 *value = bpf_map_lookup_elem(&my_map, &index);
if (value)
*value += skb->len;
return 0;
}
but the following program is not:
int bpf_prog1(struct __sk_buff *skb)
{
u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol));
u64 *value = bpf_map_lookup_elem(&my_map, &index);
if (value)
*value += (u64) skb;
return 0;
}
since it would leak the kernel address into the map.
Unprivileged socket filter bpf programs have access to the
following helper functions:
- map lookup/update/delete (but they cannot store kernel pointers into them)
- get_random (it's already exposed to unprivileged user space)
- get_smp_processor_id
- tail_call into another socket filter program
- ktime_get_ns
The feature is controlled by sysctl kernel.unprivileged_bpf_disabled.
This toggle defaults to off (0), but can be set true (1). Once true,
bpf programs and maps cannot be accessed from unprivileged process,
and the toggle cannot be set back to false.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-08 13:23:21 +08:00
|
|
|
extern int sysctl_unprivileged_bpf_disabled;
|
|
|
|
|
|
2015-10-29 21:58:09 +08:00
|
|
|
int bpf_map_new_fd(struct bpf_map *map);
|
|
|
|
|
int bpf_prog_new_fd(struct bpf_prog *prog);
|
|
|
|
|
|
|
|
|
|
int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
|
|
|
|
|
int bpf_obj_get_user(const char __user *pathname);
|
|
|
|
|
|
bpf: add lookup/update support for per-cpu hash and array maps
The functions bpf_map_lookup_elem(map, key, value) and
bpf_map_update_elem(map, key, value, flags) need to get/set
values from all-cpus for per-cpu hash and array maps,
so that user space can aggregate/update them as necessary.
Example of single counter aggregation in user space:
unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
long values[nr_cpus];
long value = 0;
bpf_lookup_elem(fd, key, values);
for (i = 0; i < nr_cpus; i++)
value += values[i];
The user space must provide round_up(value_size, 8) * nr_cpus
array to get/set values, since kernel will use 'long' copy
of per-cpu values to try to copy good counters atomically.
It's a best-effort, since bpf programs and user space are racing
to access the same memory.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-02 14:39:55 +08:00
|
|
|
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
|
|
|
|
|
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
|
|
|
|
|
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
|
|
|
|
|
u64 flags);
|
|
|
|
|
int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
|
|
|
|
|
u64 flags);
|
2016-03-08 13:57:17 +08:00
|
|
|
int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
|
bpf: add lookup/update support for per-cpu hash and array maps
The functions bpf_map_lookup_elem(map, key, value) and
bpf_map_update_elem(map, key, value, flags) need to get/set
values from all-cpus for per-cpu hash and array maps,
so that user space can aggregate/update them as necessary.
Example of single counter aggregation in user space:
unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
long values[nr_cpus];
long value = 0;
bpf_lookup_elem(fd, key, values);
for (i = 0; i < nr_cpus; i++)
value += values[i];
The user space must provide round_up(value_size, 8) * nr_cpus
array to get/set values, since kernel will use 'long' copy
of per-cpu values to try to copy good counters atomically.
It's a best-effort, since bpf programs and user space are racing
to access the same memory.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-02 14:39:55 +08:00
|
|
|
|
|
|
|
|
/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
|
|
|
|
|
* forced to use 'long' read/writes to try to atomically copy long counters.
|
|
|
|
|
* Best-effort only. No barriers here, since it _will_ race with concurrent
|
|
|
|
|
* updates from BPF programs. Called from bpf syscall and mostly used with
|
|
|
|
|
* size 8 or 16 bytes, so ask compiler to inline it.
|
|
|
|
|
*/
|
|
|
|
|
static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
|
|
|
|
|
{
|
|
|
|
|
const long *lsrc = src;
|
|
|
|
|
long *ldst = dst;
|
|
|
|
|
|
|
|
|
|
size /= sizeof(long);
|
|
|
|
|
while (size--)
|
|
|
|
|
*ldst++ = *lsrc++;
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-02 22:21:55 +08:00
|
|
|
/* verify correctness of eBPF program */
|
2015-03-14 02:57:42 +08:00
|
|
|
int bpf_check(struct bpf_prog **fp, union bpf_attr *attr);
|
2014-12-02 07:06:35 +08:00
|
|
|
#else
|
2015-03-01 19:31:44 +08:00
|
|
|
static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
|
|
|
|
|
{
|
|
|
|
|
return ERR_PTR(-EOPNOTSUPP);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void bpf_prog_put(struct bpf_prog *prog)
|
|
|
|
|
{
|
|
|
|
|
}
|
2015-03-02 22:21:55 +08:00
|
|
|
#endif /* CONFIG_BPF_SYSCALL */
|
2014-09-26 15:17:00 +08:00
|
|
|
|
2014-11-14 09:36:49 +08:00
|
|
|
/* verifier prototypes for helper functions called from eBPF programs */
|
2015-03-01 19:31:42 +08:00
|
|
|
extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
|
|
|
|
|
extern const struct bpf_func_proto bpf_map_update_elem_proto;
|
|
|
|
|
extern const struct bpf_func_proto bpf_map_delete_elem_proto;
|
2014-11-14 09:36:49 +08:00
|
|
|
|
2015-03-14 09:27:16 +08:00
|
|
|
extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
|
2015-03-14 09:27:17 +08:00
|
|
|
extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
|
bpf: allow bpf programs to tail-call other bpf programs
introduce bpf_tail_call(ctx, &jmp_table, index) helper function
which can be used from BPF programs like:
int bpf_prog(struct pt_regs *ctx)
{
...
bpf_tail_call(ctx, &jmp_table, index);
...
}
that is roughly equivalent to:
int bpf_prog(struct pt_regs *ctx)
{
...
if (jmp_table[index])
return (*jmp_table[index])(ctx);
...
}
The important detail that it's not a normal call, but a tail call.
The kernel stack is precious, so this helper reuses the current
stack frame and jumps into another BPF program without adding
extra call frame.
It's trivially done in interpreter and a bit trickier in JITs.
In case of x64 JIT the bigger part of generated assembler prologue
is common for all programs, so it is simply skipped while jumping.
Other JITs can do similar prologue-skipping optimization or
do stack unwind before jumping into the next program.
bpf_tail_call() arguments:
ctx - context pointer
jmp_table - one of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table
index - index in the jump table
Since all BPF programs are idenitified by file descriptor, user space
need to populate the jmp_table with FDs of other BPF programs.
If jmp_table[index] is empty the bpf_tail_call() doesn't jump anywhere
and program execution continues as normal.
New BPF_MAP_TYPE_PROG_ARRAY map type is introduced so that user space can
populate this jmp_table array with FDs of other bpf programs.
Programs can share the same jmp_table array or use multiple jmp_tables.
The chain of tail calls can form unpredictable dynamic loops therefore
tail_call_cnt is used to limit the number of calls and currently is set to 32.
Use cases:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
==========
- simplify complex programs by splitting them into a sequence of small programs
- dispatch routine
For tracing and future seccomp the program may be triggered on all system
calls, but processing of syscall arguments will be different. It's more
efficient to implement them as:
int syscall_entry(struct seccomp_data *ctx)
{
bpf_tail_call(ctx, &syscall_jmp_table, ctx->nr /* syscall number */);
... default: process unknown syscall ...
}
int sys_write_event(struct seccomp_data *ctx) {...}
int sys_read_event(struct seccomp_data *ctx) {...}
syscall_jmp_table[__NR_write] = sys_write_event;
syscall_jmp_table[__NR_read] = sys_read_event;
For networking the program may call into different parsers depending on
packet format, like:
int packet_parser(struct __sk_buff *skb)
{
... parse L2, L3 here ...
__u8 ipproto = load_byte(skb, ... offsetof(struct iphdr, protocol));
bpf_tail_call(skb, &ipproto_jmp_table, ipproto);
... default: process unknown protocol ...
}
int parse_tcp(struct __sk_buff *skb) {...}
int parse_udp(struct __sk_buff *skb) {...}
ipproto_jmp_table[IPPROTO_TCP] = parse_tcp;
ipproto_jmp_table[IPPROTO_UDP] = parse_udp;
- for TC use case, bpf_tail_call() allows to implement reclassify-like logic
- bpf_map_update_elem/delete calls into BPF_MAP_TYPE_PROG_ARRAY jump table
are atomic, so user space can build chains of BPF programs on the fly
Implementation details:
=======================
- high performance of bpf_tail_call() is the goal.
It could have been implemented without JIT changes as a wrapper on top of
BPF_PROG_RUN() macro, but with two downsides:
. all programs would have to pay performance penalty for this feature and
tail call itself would be slower, since mandatory stack unwind, return,
stack allocate would be done for every tailcall.
. tailcall would be limited to programs running preempt_disabled, since
generic 'void *ctx' doesn't have room for 'tail_call_cnt' and it would
need to be either global per_cpu variable accessed by helper and by wrapper
or global variable protected by locks.
In this implementation x64 JIT bypasses stack unwind and jumps into the
callee program after prologue.
- bpf_prog_array_compatible() ensures that prog_type of callee and caller
are the same and JITed/non-JITed flag is the same, since calling JITed
program from non-JITed is invalid, since stack frames are different.
Similarly calling kprobe type program from socket type program is invalid.
- jump table is implemented as BPF_MAP_TYPE_PROG_ARRAY to reuse 'map'
abstraction, its user space API and all of verifier logic.
It's in the existing arraymap.c file, since several functions are
shared with regular array map.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-20 07:59:03 +08:00
|
|
|
extern const struct bpf_func_proto bpf_tail_call_proto;
|
2015-05-30 05:23:06 +08:00
|
|
|
extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
|
2015-06-13 10:39:12 +08:00
|
|
|
extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
|
|
|
|
|
extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
|
|
|
|
|
extern const struct bpf_func_proto bpf_get_current_comm_proto;
|
2015-07-21 11:34:18 +08:00
|
|
|
extern const struct bpf_func_proto bpf_skb_vlan_push_proto;
|
|
|
|
|
extern const struct bpf_func_proto bpf_skb_vlan_pop_proto;
|
2016-02-18 11:58:58 +08:00
|
|
|
extern const struct bpf_func_proto bpf_get_stackid_proto;
|
2015-03-14 09:27:16 +08:00
|
|
|
|
bpf: split state from prandom_u32() and consolidate {c, e}BPF prngs
While recently arguing on a seccomp discussion that raw prandom_u32()
access shouldn't be exposed to unpriviledged user space, I forgot the
fact that SKF_AD_RANDOM extension actually already does it for some time
in cBPF via commit 4cd3675ebf74 ("filter: added BPF random opcode").
Since prandom_u32() is being used in a lot of critical networking code,
lets be more conservative and split their states. Furthermore, consolidate
eBPF and cBPF prandom handlers to use the new internal PRNG. For eBPF,
bpf_get_prandom_u32() was only accessible for priviledged users, but
should that change one day, we also don't want to leak raw sequences
through things like eBPF maps.
One thought was also to have own per bpf_prog states, but due to ABI
reasons this is not easily possible, i.e. the program code currently
cannot access bpf_prog itself, and copying the rnd_state to/from the
stack scratch space whenever a program uses the prng seems not really
worth the trouble and seems too hacky. If needed, taus113 could in such
cases be implemented within eBPF using a map entry to keep the state
space, or get_random_bytes() could become a second helper in cases where
performance would not be critical.
Both sides can trigger a one-time late init via prandom_init_once() on
the shared state. Performance-wise, there should even be a tiny gain
as bpf_user_rnd_u32() saves one function call. The PRNG needs to live
inside the BPF core since kernels could have a NET-less config as well.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Chema Gonzalez <chema@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-08 07:20:39 +08:00
|
|
|
/* Shared helpers among cBPF and eBPF. */
|
|
|
|
|
void bpf_user_rnd_init_once(void);
|
|
|
|
|
u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
|
|
|
|
|
|
2014-09-26 15:16:57 +08:00
|
|
|
#endif /* _LINUX_BPF_H */
|