bpf: add array type of eBPF maps

add new map type BPF_MAP_TYPE_ARRAY and its implementation

- optimized for fastest possible lookup()
  . in the future verifier/JIT may recognize lookup() with constant key
    and optimize it into constant pointer. Can optimize non-constant
    key into direct pointer arithmetic as well, since pointers and
    value_size are constant for the life of the eBPF program.
    In other words array_map_lookup_elem() may be 'inlined' by verifier/JIT
    while preserving concurrent access to this map from user space

- two main use cases for array type:
  . 'global' eBPF variables: array of 1 element with key=0 and value is a
    collection of 'global' variables which programs can use to keep the state
    between events
  . aggregation of tracing events into fixed set of buckets

- all array elements pre-allocated and zero initialized at init time

- key as an index in array and can only be 4 byte

- map_delete_elem() returns EINVAL, since elements cannot be deleted

- map_update_elem() replaces elements in an non-atomic way
  (for atomic updates hashtable type should be used instead)

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Alexei Starovoitov 2014-11-13 17:36:46 -08:00 committed by David S. Miller
parent 0f8e4bd8a1
commit 28fbcfa08d
3 changed files with 153 additions and 1 deletions

View File

@ -112,6 +112,7 @@ enum bpf_cmd {
enum bpf_map_type {
BPF_MAP_TYPE_UNSPEC,
BPF_MAP_TYPE_HASH,
BPF_MAP_TYPE_ARRAY,
};
enum bpf_prog_type {

View File

@ -1,5 +1,5 @@
obj-y := core.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o
ifdef CONFIG_TEST_BPF
obj-$(CONFIG_BPF_SYSCALL) += test_stub.o
endif

151
kernel/bpf/arraymap.c Normal file
View File

@ -0,0 +1,151 @@
/* 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.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <linux/bpf.h>
#include <linux/err.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/mm.h>
struct bpf_array {
struct bpf_map map;
u32 elem_size;
char value[0] __aligned(8);
};
/* Called from syscall */
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
struct bpf_array *array;
u32 elem_size;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
attr->value_size == 0)
return ERR_PTR(-EINVAL);
elem_size = round_up(attr->value_size, 8);
/* allocate all map elements and zero-initialize them */
array = kzalloc(sizeof(*array) + attr->max_entries * elem_size,
GFP_USER | __GFP_NOWARN);
if (!array) {
array = vzalloc(array->map.max_entries * array->elem_size);
if (!array)
return ERR_PTR(-ENOMEM);
}
/* copy mandatory map attributes */
array->map.key_size = attr->key_size;
array->map.value_size = attr->value_size;
array->map.max_entries = attr->max_entries;
array->elem_size = elem_size;
return &array->map;
}
/* Called from syscall or from eBPF program */
static void *array_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
if (index >= array->map.max_entries)
return NULL;
return array->value + array->elem_size * index;
}
/* Called from syscall */
static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
u32 *next = (u32 *)next_key;
if (index >= array->map.max_entries) {
*next = 0;
return 0;
}
if (index == array->map.max_entries - 1)
return -ENOENT;
*next = index + 1;
return 0;
}
/* Called from syscall or from eBPF program */
static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
if (map_flags > BPF_EXIST)
/* unknown flags */
return -EINVAL;
if (index >= array->map.max_entries)
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
if (map_flags == BPF_NOEXIST)
/* all elemenets already exist */
return -EEXIST;
memcpy(array->value + array->elem_size * index, value, array->elem_size);
return 0;
}
/* Called from syscall or from eBPF program */
static int array_map_delete_elem(struct bpf_map *map, void *key)
{
return -EINVAL;
}
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void array_map_free(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the programs (can be more than one that used this map) were
* disconnected from events. Wait for outstanding programs to complete
* and free the array
*/
synchronize_rcu();
kvfree(array);
}
static struct bpf_map_ops array_ops = {
.map_alloc = array_map_alloc,
.map_free = array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
};
static struct bpf_map_type_list tl = {
.ops = &array_ops,
.type = BPF_MAP_TYPE_ARRAY,
};
static int __init register_array_map(void)
{
bpf_register_map_type(&tl);
return 0;
}
late_initcall(register_array_map);