diff options
| author | Daniel Borkmann <daniel@iogearbox.net> | 2019-12-16 17:49:00 +0100 |
|---|---|---|
| committer | Alexei Starovoitov <ast@kernel.org> | 2019-12-16 10:59:29 -0800 |
| commit | a2ea07465c8d7984cc6b8b1f0b3324f9b138094a (patch) | |
| tree | ffc04818616b047ecbd2b64f1ae3d9c33108a727 /include/linux | |
| parent | 5133498f4ad1123a5ffd4c08df6431dab882cc32 (diff) | |
bpf: Fix missing prog untrack in release_maps
Commit da765a2f5993 ("bpf: Add poke dependency tracking for prog array
maps") wrongly assumed that in case of prog load errors, we're cleaning
up all program tracking via bpf_free_used_maps().
However, it can happen that we're still at the point where we didn't copy
map pointers into the prog's aux section such that env->prog->aux->used_maps
is still zero, running into a UAF. In such case, the verifier has similar
release_maps() helper that drops references to used maps from its env.
Consolidate the release code into __bpf_free_used_maps() and call it from
all sides to fix it.
Fixes: da765a2f5993 ("bpf: Add poke dependency tracking for prog array maps")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/1c2909484ca524ae9f55109b06f22b6213e76376.1576514756.git.daniel@iogearbox.net
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/bpf.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ac7de5291509..085a59afba85 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -818,6 +818,8 @@ struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); |