Re: [PATCH bpf-next 4/4] bpf: export bpf_jit_current

From: Jakub Sitnicki
Date: Mon Sep 27 2021 - 10:02:06 EST

On Mon, Sep 27, 2021 at 03:34 PM CEST, Daniel Borkmann wrote:
> On 9/24/21 11:55 AM, Lorenz Bauer wrote:
>> Expose bpf_jit_current as a read only value via sysctl.
>> Signed-off-by: Lorenz Bauer <lmb@xxxxxxxxxxxxxx>
>> ---

I find exposing stats via system configuration variables a bit
unexpected. Not sure if there is any example today that we're following.

Maybe an entry under /sys/kernel/debug would be a better fit?

That way we don't have to commit to a sysctl that might go away if we
start charging JIT allocs against memory cgroup quota.

Although that brings up question against which cgroup iptables xt_bpf
allocations should be charged? Root cgroup?