Files
kernel/include/linux
Stanislav Fomichev a9ed15dae0 bpf: Split cgroup_bpf_enabled per attach type
When we attach any cgroup hook, the rest (even if unused/unattached) start
to contribute small overhead. In particular, the one we want to avoid is
__cgroup_bpf_run_filter_skb which does two redirections to get to
the cgroup and pushes/pulls skb.

Let's split cgroup_bpf_enabled to be per-attach to make sure
only used attach types trigger.

I've dropped some existing high-level cgroup_bpf_enabled in some
places because BPF_PROG_CGROUP_XXX_RUN macros usually have another
cgroup_bpf_enabled check.

I also had to copy-paste BPF_CGROUP_RUN_SA_PROG_LOCK for
GETPEERNAME/GETSOCKNAME because type for cgroup_bpf_enabled[type]
has to be constant and known at compile time.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20210115163501.805133-4-sdf@google.com
2021-01-20 14:23:00 -08:00
..
2020-12-09 19:26:02 -06:00
2020-12-02 09:46:55 -07:00
2020-12-02 09:46:55 -07:00
2020-12-19 11:18:38 -08:00
2020-12-14 16:24:19 +01:00
2020-12-11 14:02:14 -08:00
2020-12-02 22:00:22 -08:00
2020-12-10 12:42:59 -06:00
2020-12-02 22:10:35 -08:00
2020-12-08 14:14:48 +00:00
2020-12-15 16:19:31 +01:00
2020-12-15 16:19:31 +01:00
2020-12-07 10:29:57 +01:00
2020-12-04 12:23:25 +01:00
2020-12-15 15:11:08 -06:00
2020-12-03 11:20:52 +01:00
2020-12-15 12:13:39 -08:00
2020-12-07 17:12:49 -07:00
2020-12-10 16:17:15 +01:00
2020-12-15 12:13:37 -08:00
2020-12-10 10:45:36 +01:00
2020-12-04 16:54:35 +01:00
2020-12-15 12:13:41 -08:00