d6c4503cc2
The bpf iterators for hash, percpu hash, lru hash and lru percpu hash are implemented. During link time, bpf_iter_reg->check_target() will check map type and ensure the program access key/value region is within the map defined key/value size limit. For percpu hash and lru hash maps, the bpf program will receive values for all cpus. The map element bpf iterator infrastructure will prepare value properly before passing the value pointer to the bpf program. This patch set supports readonly map keys and read/write map values. It does not support deleting map elements, e.g., from hash tables. If there is a user case for this, the following mechanism can be used to support map deletion for hashtab, etc. - permit a new bpf program return value, e.g., 2, to let bpf iterator know the map element should be removed. - since bucket lock is taken, the map element will be queued. - once bucket lock is released after all elements under this bucket are traversed, all to-be-deleted map elements can be deleted. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184114.590470-1-yhs@fb.com
158 lines
3.7 KiB
C
158 lines
3.7 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/* Copyright (c) 2020 Facebook */
|
|
#include <linux/bpf.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/filter.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/btf_ids.h>
|
|
|
|
struct bpf_iter_seq_map_info {
|
|
u32 map_id;
|
|
};
|
|
|
|
static void *bpf_map_seq_start(struct seq_file *seq, loff_t *pos)
|
|
{
|
|
struct bpf_iter_seq_map_info *info = seq->private;
|
|
struct bpf_map *map;
|
|
|
|
map = bpf_map_get_curr_or_next(&info->map_id);
|
|
if (!map)
|
|
return NULL;
|
|
|
|
if (*pos == 0)
|
|
++*pos;
|
|
return map;
|
|
}
|
|
|
|
static void *bpf_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
|
|
{
|
|
struct bpf_iter_seq_map_info *info = seq->private;
|
|
|
|
++*pos;
|
|
++info->map_id;
|
|
bpf_map_put((struct bpf_map *)v);
|
|
return bpf_map_get_curr_or_next(&info->map_id);
|
|
}
|
|
|
|
struct bpf_iter__bpf_map {
|
|
__bpf_md_ptr(struct bpf_iter_meta *, meta);
|
|
__bpf_md_ptr(struct bpf_map *, map);
|
|
};
|
|
|
|
DEFINE_BPF_ITER_FUNC(bpf_map, struct bpf_iter_meta *meta, struct bpf_map *map)
|
|
|
|
static int __bpf_map_seq_show(struct seq_file *seq, void *v, bool in_stop)
|
|
{
|
|
struct bpf_iter__bpf_map ctx;
|
|
struct bpf_iter_meta meta;
|
|
struct bpf_prog *prog;
|
|
int ret = 0;
|
|
|
|
ctx.meta = &meta;
|
|
ctx.map = v;
|
|
meta.seq = seq;
|
|
prog = bpf_iter_get_info(&meta, in_stop);
|
|
if (prog)
|
|
ret = bpf_iter_run_prog(prog, &ctx);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int bpf_map_seq_show(struct seq_file *seq, void *v)
|
|
{
|
|
return __bpf_map_seq_show(seq, v, false);
|
|
}
|
|
|
|
static void bpf_map_seq_stop(struct seq_file *seq, void *v)
|
|
{
|
|
if (!v)
|
|
(void)__bpf_map_seq_show(seq, v, true);
|
|
else
|
|
bpf_map_put((struct bpf_map *)v);
|
|
}
|
|
|
|
static const struct seq_operations bpf_map_seq_ops = {
|
|
.start = bpf_map_seq_start,
|
|
.next = bpf_map_seq_next,
|
|
.stop = bpf_map_seq_stop,
|
|
.show = bpf_map_seq_show,
|
|
};
|
|
|
|
BTF_ID_LIST(btf_bpf_map_id)
|
|
BTF_ID(struct, bpf_map)
|
|
|
|
static const struct bpf_iter_seq_info bpf_map_seq_info = {
|
|
.seq_ops = &bpf_map_seq_ops,
|
|
.init_seq_private = NULL,
|
|
.fini_seq_private = NULL,
|
|
.seq_priv_size = sizeof(struct bpf_iter_seq_map_info),
|
|
};
|
|
|
|
static struct bpf_iter_reg bpf_map_reg_info = {
|
|
.target = "bpf_map",
|
|
.ctx_arg_info_size = 1,
|
|
.ctx_arg_info = {
|
|
{ offsetof(struct bpf_iter__bpf_map, map),
|
|
PTR_TO_BTF_ID_OR_NULL },
|
|
},
|
|
.seq_info = &bpf_map_seq_info,
|
|
};
|
|
|
|
static int bpf_iter_check_map(struct bpf_prog *prog,
|
|
struct bpf_iter_aux_info *aux)
|
|
{
|
|
u32 key_acc_size, value_acc_size, key_size, value_size;
|
|
struct bpf_map *map = aux->map;
|
|
bool is_percpu = false;
|
|
|
|
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
|
|
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH)
|
|
is_percpu = true;
|
|
else if (map->map_type != BPF_MAP_TYPE_HASH &&
|
|
map->map_type != BPF_MAP_TYPE_LRU_HASH)
|
|
return -EINVAL;
|
|
|
|
key_acc_size = prog->aux->max_rdonly_access;
|
|
value_acc_size = prog->aux->max_rdwr_access;
|
|
key_size = map->key_size;
|
|
if (!is_percpu)
|
|
value_size = map->value_size;
|
|
else
|
|
value_size = round_up(map->value_size, 8) * num_possible_cpus();
|
|
|
|
if (key_acc_size > key_size || value_acc_size > value_size)
|
|
return -EACCES;
|
|
|
|
return 0;
|
|
}
|
|
|
|
DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta,
|
|
struct bpf_map *map, void *key, void *value)
|
|
|
|
static const struct bpf_iter_reg bpf_map_elem_reg_info = {
|
|
.target = "bpf_map_elem",
|
|
.check_target = bpf_iter_check_map,
|
|
.req_linfo = BPF_ITER_LINK_MAP_FD,
|
|
.ctx_arg_info_size = 2,
|
|
.ctx_arg_info = {
|
|
{ offsetof(struct bpf_iter__bpf_map_elem, key),
|
|
PTR_TO_RDONLY_BUF_OR_NULL },
|
|
{ offsetof(struct bpf_iter__bpf_map_elem, value),
|
|
PTR_TO_RDWR_BUF_OR_NULL },
|
|
},
|
|
};
|
|
|
|
static int __init bpf_map_iter_init(void)
|
|
{
|
|
int ret;
|
|
|
|
bpf_map_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_map_id;
|
|
ret = bpf_iter_reg_target(&bpf_map_reg_info);
|
|
if (ret)
|
|
return ret;
|
|
|
|
return bpf_iter_reg_target(&bpf_map_elem_reg_info);
|
|
}
|
|
|
|
late_initcall(bpf_map_iter_init);
|