From a2ea07465c8d7984cc6b8b1f0b3324f9b138094a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 16 Dec 2019 17:49:00 +0100
Subject: 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
---
include/linux/bpf.h | 2 ++
1 file changed, 2 insertions(+)
(limited to 'include/linux')
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);
--
cgit v1.2.3-70-g09d2