When using BPF_PROG_ATTACH to attach a program to a cgroup in
BPF_F_ALLOW_MULTI mode, it is not possible to replace a program
with itself. This is because the check for duplicate programs
doesn't take the replacement program into account.
Replacing a program with itself might seem weird, but it has
some uses: first, it allows resetting the associated cgroup storage.
Second, it makes the API consistent with the non-ALLOW_MULTI usage,
where it is possible to replace a program with itself. Third, it
aligns BPF_PROG_ATTACH with bpf_link, where replacing itself is
also supported.
Sice this code has been refactored a few times this change will
only apply to v5.7 and later. Adjustments could be made to
commit
1f04601c6e1a ("bpf: Simplify __cgroup_bpf_attach") and
commit
143586412d9a ("bpf: allocate cgroup storage entries on attaching bpf programs")
as well as commit
8e506b1a28cb ("bpf: multi program support for cgroup+bpf")
Fixes: 78b5ce1cbefa ("bpf: Implement bpf_link-based cgroup BPF program attachment")
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200608162202.94002-1-lmb@cloudflare.com
}
list_for_each_entry(pl, progs, node) {
- if (prog && pl->prog == prog)
+ if (prog && pl->prog == prog && prog != replace_prog)
/* disallow attaching the same prog twice */
return ERR_PTR(-EINVAL);
if (link && pl->link == link)
"prog_replace", "errno=%d\n", errno))
goto err;
+ /* replace program with itself */
+ attach_opts.replace_prog_fd = allow_prog[6];
+ if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1,
+ BPF_CGROUP_INET_EGRESS, &attach_opts),
+ "prog_replace", "errno=%d\n", errno))
+ goto err;
+
value = 0;
CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0));
CHECK_FAIL(system(PING_CMD));