Pedro Tammela wrote:
> Suggested-by: Jamal Hadi Salim <jhs@xxxxxxxxxxxx>
> Signed-off-by: Pedro Tammela <pctammela@xxxxxxxxxxxx>
> ---
A commit message describing some of the change details and a note it uses
the for-each cpu copies (same as normal syscall on percpu map) and not the
per-cpu ones would be nice. I at least had to go and check the generic_map*
batch operations.
Also something about why generic_map_delete_batch is omitted?
> kernel/bpf/arraymap.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
> index 463d25e1e67e..3c4105603f9d 100644
> --- a/kernel/bpf/arraymap.c
> +++ b/kernel/bpf/arraymap.c
> @@ -698,6 +698,8 @@ const struct bpf_map_ops percpu_array_map_ops = {
> .map_delete_elem = array_map_delete_elem,
> .map_seq_show_elem = percpu_array_map_seq_show_elem,
> .map_check_btf = array_map_check_btf,
> + .map_lookup_batch = generic_map_lookup_batch,
> + .map_update_batch = generic_map_update_batch,
> .map_set_for_each_callback_args = map_set_for_each_callback_args,
> .map_for_each_callback = bpf_for_each_array_elem,
> .map_btf_name = "bpf_array",
> --
> 2.25.1
>
