linux/kernel/bpf/map_in_map.c
Kumar Kartikeya Dwivedi c22dfdd215 bpf: Add comments for map BTF matching requirement for bpf_list_head
The old behavior of bpf_map_meta_equal was that it compared timer_off
to be equal (but not spin_lock_off, because that was not allowed), and
did memcmp of kptr_off_tab.

Now, we memcmp the btf_record of two bpf_map structs, which has all
fields.

We preserve backwards compat as we kzalloc the array, so if only spin
lock and timer exist in map, we only compare offset while the rest of
unused members in the btf_field struct are zeroed out.

In case of kptr, btf and everything else is of vmlinux or module, so as
long type is same it will match, since kernel btf, module, dtor pointer
will be same across maps.

Now with list_head in the mix, things are a bit complicated. We
implicitly add a requirement that both BTFs are same, because struct
btf_field_list_head has btf and value_rec members.

We obviously shouldn't force BTFs to be equal by default, as that breaks
backwards compatibility.

Currently it is only implicitly required due to list_head matching
struct btf and value_rec member. value_rec points back into a btf_record
stashed in the map BTF (btf member of btf_field_list_head). So that
pointer and btf member has to match exactly.

Document all these subtle details so that things don't break in the
future when touching this code.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20221118015614.2013203-19-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2022-11-17 19:22:14 -08:00

153 lines
3.9 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2017 Facebook
*/
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include "map_in_map.h"
struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
{
struct bpf_map *inner_map, *inner_map_meta;
u32 inner_map_meta_size;
struct fd f;
int ret;
f = fdget(inner_map_ufd);
inner_map = __bpf_map_get(f);
if (IS_ERR(inner_map))
return inner_map;
/* Does not support >1 level map-in-map */
if (inner_map->inner_map_meta) {
ret = -EINVAL;
goto put;
}
if (!inner_map->ops->map_meta_equal) {
ret = -ENOTSUPP;
goto put;
}
inner_map_meta_size = sizeof(*inner_map_meta);
/* In some cases verifier needs to access beyond just base map. */
if (inner_map->ops == &array_map_ops)
inner_map_meta_size = sizeof(struct bpf_array);
inner_map_meta = kzalloc(inner_map_meta_size, GFP_USER);
if (!inner_map_meta) {
ret = -ENOMEM;
goto put;
}
inner_map_meta->map_type = inner_map->map_type;
inner_map_meta->key_size = inner_map->key_size;
inner_map_meta->value_size = inner_map->value_size;
inner_map_meta->map_flags = inner_map->map_flags;
inner_map_meta->max_entries = inner_map->max_entries;
inner_map_meta->record = btf_record_dup(inner_map->record);
if (IS_ERR(inner_map_meta->record)) {
/* btf_record_dup returns NULL or valid pointer in case of
* invalid/empty/valid, but ERR_PTR in case of errors. During
* equality NULL or IS_ERR is equivalent.
*/
ret = PTR_ERR(inner_map_meta->record);
goto free;
}
if (inner_map_meta->record) {
struct btf_field_offs *field_offs;
/* If btf_record is !IS_ERR_OR_NULL, then field_offs is always
* valid.
*/
field_offs = kmemdup(inner_map->field_offs, sizeof(*inner_map->field_offs), GFP_KERNEL | __GFP_NOWARN);
if (!field_offs) {
ret = -ENOMEM;
goto free_rec;
}
inner_map_meta->field_offs = field_offs;
}
/* Note: We must use the same BTF, as we also used btf_record_dup above
* which relies on BTF being same for both maps, as some members like
* record->fields.list_head have pointers like value_rec pointing into
* inner_map->btf.
*/
if (inner_map->btf) {
btf_get(inner_map->btf);
inner_map_meta->btf = inner_map->btf;
}
/* Misc members not needed in bpf_map_meta_equal() check. */
inner_map_meta->ops = inner_map->ops;
if (inner_map->ops == &array_map_ops) {
inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1;
container_of(inner_map_meta, struct bpf_array, map)->index_mask =
container_of(inner_map, struct bpf_array, map)->index_mask;
}
fdput(f);
return inner_map_meta;
free_rec:
btf_record_free(inner_map_meta->record);
free:
kfree(inner_map_meta);
put:
fdput(f);
return ERR_PTR(ret);
}
void bpf_map_meta_free(struct bpf_map *map_meta)
{
kfree(map_meta->field_offs);
bpf_map_free_record(map_meta);
btf_put(map_meta->btf);
kfree(map_meta);
}
bool bpf_map_meta_equal(const struct bpf_map *meta0,
const struct bpf_map *meta1)
{
/* No need to compare ops because it is covered by map_type */
return meta0->map_type == meta1->map_type &&
meta0->key_size == meta1->key_size &&
meta0->value_size == meta1->value_size &&
meta0->map_flags == meta1->map_flags &&
btf_record_equal(meta0->record, meta1->record);
}
void *bpf_map_fd_get_ptr(struct bpf_map *map,
struct file *map_file /* not used */,
int ufd)
{
struct bpf_map *inner_map, *inner_map_meta;
struct fd f;
f = fdget(ufd);
inner_map = __bpf_map_get(f);
if (IS_ERR(inner_map))
return inner_map;
inner_map_meta = map->inner_map_meta;
if (inner_map_meta->ops->map_meta_equal(inner_map_meta, inner_map))
bpf_map_inc(inner_map);
else
inner_map = ERR_PTR(-EINVAL);
fdput(f);
return inner_map;
}
void bpf_map_fd_put_ptr(void *ptr)
{
/* ptr->ops->map_free() has to go through one
* rcu grace period by itself.
*/
bpf_map_put(ptr);
}
u32 bpf_map_fd_sys_lookup_elem(void *ptr)
{
return ((struct bpf_map *)ptr)->id;
}