Re: [PATCH v2 06/23] mm: introduce BPF struct ops for OOM handling

[Alexei Starovoitov]

On Mon, Oct 27, 2025 at 4:18 PM Roman Gushchin <roman.gushchin@xxxxxxxxx> wrote:
>
> +bool bpf_handle_oom(struct oom_control *oc)
> +{
> +       struct bpf_oom_ops *bpf_oom_ops = NULL;
> +       struct mem_cgroup __maybe_unused *memcg;
> +       int idx, ret = 0;
> +
> +       /* All bpf_oom_ops structures are protected using bpf_oom_srcu */
> +       idx = srcu_read_lock(&bpf_oom_srcu);
> +
> +#ifdef CONFIG_MEMCG
> +       /* Find the nearest bpf_oom_ops traversing the cgroup tree upwards */
> +       for (memcg = oc->memcg; memcg; memcg = parent_mem_cgroup(memcg)) {
> +               bpf_oom_ops = READ_ONCE(memcg->bpf_oom);
> +               if (!bpf_oom_ops)
> +                       continue;
> +
> +               /* Call BPF OOM handler */
> +               ret = bpf_ops_handle_oom(bpf_oom_ops, memcg, oc);
> +               if (ret && oc->bpf_memory_freed)
> +                       goto exit;
> +       }
> +#endif /* CONFIG_MEMCG */
> +
> +       /*
> +        * System-wide OOM or per-memcg BPF OOM handler wasn't successful?
> +        * Try system_bpf_oom.
> +        */
> +       bpf_oom_ops = READ_ONCE(system_bpf_oom);
> +       if (!bpf_oom_ops)
> +               goto exit;
> +
> +       /* Call BPF OOM handler */
> +       ret = bpf_ops_handle_oom(bpf_oom_ops, NULL, oc);
> +exit:
> +       srcu_read_unlock(&bpf_oom_srcu, idx);
> +       return ret && oc->bpf_memory_freed;
> +}

...

> +static int bpf_oom_ops_reg(void *kdata, struct bpf_link *link)
> +{
> +       struct bpf_struct_ops_link *ops_link = container_of(link, struct bpf_struct_ops_link, link);
> +       struct bpf_oom_ops **bpf_oom_ops_ptr = NULL;
> +       struct bpf_oom_ops *bpf_oom_ops = kdata;
> +       struct mem_cgroup *memcg = NULL;
> +       int err = 0;
> +
> +       if (IS_ENABLED(CONFIG_MEMCG) && ops_link->cgroup_id) {
> +               /* Attach to a memory cgroup? */
> +               memcg = mem_cgroup_get_from_ino(ops_link->cgroup_id);
> +               if (IS_ERR_OR_NULL(memcg))
> +                       return PTR_ERR(memcg);
> +               bpf_oom_ops_ptr = bpf_oom_memcg_ops_ptr(memcg);
> +       } else {
> +               /* System-wide OOM handler */
> +               bpf_oom_ops_ptr = &system_bpf_oom;
> +       }

I don't like the fallback and special case of cgroup_id == 0.
imo it would be cleaner to require CONFIG_MEMCG for this feature
and only allow attach to a cgroup.
There is always a root cgroup that can be attached to and that
handler will be acting as "system wide" oom handler.