mirror of
https://github.com/torvalds/linux.git
synced 2024-11-29 07:31:29 +00:00
61df10c779
This commit introduces a new pointer type 'kptr' which can be embedded
in a map value to hold a PTR_TO_BTF_ID stored by a BPF program during
its invocation. When storing such a kptr, BPF program's PTR_TO_BTF_ID
register must have the same type as in the map value's BTF, and loading
a kptr marks the destination register as PTR_TO_BTF_ID with the correct
kernel BTF and BTF ID.
Such kptr are unreferenced, i.e. by the time another invocation of the
BPF program loads this pointer, the object which the pointer points to
may not longer exist. Since PTR_TO_BTF_ID loads (using BPF_LDX) are
patched to PROBE_MEM loads by the verifier, it would safe to allow user
to still access such invalid pointer, but passing such pointers into
BPF helpers and kfuncs should not be permitted. A future patch in this
series will close this gap.
The flexibility offered by allowing programs to dereference such invalid
pointers while being safe at runtime frees the verifier from doing
complex lifetime tracking. As long as the user may ensure that the
object remains valid, it can ensure data read by it from the kernel
object is valid.
The user indicates that a certain pointer must be treated as kptr
capable of accepting stores of PTR_TO_BTF_ID of a certain type, by using
a BTF type tag 'kptr' on the pointed to type of the pointer. Then, this
information is recorded in the object BTF which will be passed into the
kernel by way of map's BTF information. The name and kind from the map
value BTF is used to look up the in-kernel type, and the actual BTF and
BTF ID is recorded in the map struct in a new kptr_off_tab member. For
now, only storing pointers to structs is permitted.
An example of this specification is shown below:
#define __kptr __attribute__((btf_type_tag("kptr")))
struct map_value {
...
struct task_struct __kptr *task;
...
};
Then, in a BPF program, user may store PTR_TO_BTF_ID with the type
task_struct into the map, and then load it later.
Note that the destination register is marked PTR_TO_BTF_ID_OR_NULL, as
the verifier cannot know whether the value is NULL or not statically, it
must treat all potential loads at that map value offset as loading a
possibly NULL pointer.
Only BPF_LDX, BPF_STX, and BPF_ST (with insn->imm = 0 to denote NULL)
are allowed instructions that can access such a pointer. On BPF_LDX, the
destination register is updated to be a PTR_TO_BTF_ID, and on BPF_STX,
it is checked whether the source register type is a PTR_TO_BTF_ID with
same BTF type as specified in the map BTF. The access size must always
be BPF_DW.
For the map in map support, the kptr_off_tab for outer map is copied
from the inner map's kptr_off_tab. It was chosen to do a deep copy
instead of introducing a refcount to kptr_off_tab, because the copy only
needs to be done when paramterizing using inner_map_fd in the map in map
case, hence would be unnecessary for all other users.
It is not permitted to use MAP_FREEZE command and mmap for BPF map
having kptrs, similar to the bpf_timer case. A kptr also requires that
BPF program has both read and write access to the map (hence both
BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG are disallowed).
Note that check_map_access must be called from both
check_helper_mem_access and for the BPF instructions, hence the kptr
check must distinguish between ACCESS_DIRECT and ACCESS_HELPER, and
reject ACCESS_HELPER cases. We rename stack_access_src to bpf_access_src
and reuse it for this purpose.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-2-memxor@gmail.com
126 lines
3.1 KiB
C
126 lines
3.1 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;
|
|
|
|
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) {
|
|
fdput(f);
|
|
return ERR_PTR(-EINVAL);
|
|
}
|
|
|
|
if (!inner_map->ops->map_meta_equal) {
|
|
fdput(f);
|
|
return ERR_PTR(-ENOTSUPP);
|
|
}
|
|
|
|
if (map_value_has_spin_lock(inner_map)) {
|
|
fdput(f);
|
|
return ERR_PTR(-ENOTSUPP);
|
|
}
|
|
|
|
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) {
|
|
fdput(f);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
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->spin_lock_off = inner_map->spin_lock_off;
|
|
inner_map_meta->timer_off = inner_map->timer_off;
|
|
inner_map_meta->kptr_off_tab = bpf_map_copy_kptr_off_tab(inner_map);
|
|
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;
|
|
}
|
|
|
|
void bpf_map_meta_free(struct bpf_map *map_meta)
|
|
{
|
|
bpf_map_free_kptr_off_tab(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->timer_off == meta1->timer_off &&
|
|
meta0->map_flags == meta1->map_flags &&
|
|
bpf_map_equal_kptr_off_tab(meta0, meta1);
|
|
}
|
|
|
|
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;
|
|
}
|