On Mon, Jan 26, 2026 at 06:44:11PM -0800, Roman Gushchin wrote:
> Introduce bpf_oom_kill_process() bpf kfunc, which is supposed
> to be used by BPF OOM programs. It allows to kill a process
> in exactly the same way the OOM killer does: using the OOM reaper,
> bumping corresponding memcg and global statistics, respecting
> memory.oom.group etc.
>
> On success, it sets the oom_control's bpf_memory_freed field to true,
> enabling the bpf program to bypass the kernel OOM killer.
>
> Signed-off-by: Roman Gushchin <roman.gushchin@linux.dev>
> ---
> mm/oom_kill.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 80 insertions(+)
>
> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 44bbcf033804..09897597907f 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -46,6 +46,7 @@
> #include <linux/cred.h>
> #include <linux/nmi.h>
> #include <linux/bpf_oom.h>
> +#include <linux/btf.h>
>
> #include <asm/tlb.h>
> #include "internal.h"
> @@ -1290,3 +1291,82 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
> return -ENOSYS;
> #endif /* CONFIG_MMU */
> }
> +
> +#ifdef CONFIG_BPF_SYSCALL
> +
> +__bpf_kfunc_start_defs();
> +/**
> + * bpf_oom_kill_process - Kill a process as OOM killer
> + * @oc: pointer to oom_control structure, describes OOM context
> + * @task: task to be killed
> + * @message__str: message to print in dmesg
> + *
> + * Kill a process in a way similar to the kernel OOM killer.
> + * This means dump the necessary information to dmesg, adjust memcg
> + * statistics, leverage the oom reaper, respect memory.oom.group etc.
> + *
> + * bpf_oom_kill_process() marks the forward progress by setting
> + * oc->bpf_memory_freed. If the progress was made, the bpf program
> + * is free to decide if the kernel oom killer should be invoked.
> + * Otherwise it's enforced, so that a bad bpf program can't
> + * deadlock the machine on memory.
> + */
> +__bpf_kfunc int bpf_oom_kill_process(struct oom_control *oc,
> + struct task_struct *task,
> + const char *message__str)
> +{
> + if (oom_unkillable_task(task))
> + return -EPERM;
> +
> + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
> + return -EINVAL;
task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN is also
representative of an unkillable task, so why not fold this up into the
above conditional? Also, why not bother checking states like
mm_flags_test(MMF_OOM_SKIP, task->mm) and in_vfork() here too?
In all fairness I'm a little surprised about constraints like
task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN being enforced
here. You could argue that the whole purpose of BPF OOM is such that
you can implement your own victim selection algorithms entirely in BPF
using your own set of heuristics and what not without needing to
strictly respect properties like oom_score_adj.
In any case, I think we should at least clearly document such
constraints.
> + /* paired with put_task_struct() in oom_kill_process() */
> + get_task_struct(task);
> +
> + oc->chosen = task;
> +
> + oom_kill_process(oc, message__str);
> +
> + oc->chosen = NULL;
> + oc->bpf_memory_freed = true;
> +
> + return 0;
> +}
> +
> +__bpf_kfunc_end_defs();
> +
> +BTF_KFUNCS_START(bpf_oom_kfuncs)
> +BTF_ID_FLAGS(func, bpf_oom_kill_process, KF_SLEEPABLE)
> +BTF_KFUNCS_END(bpf_oom_kfuncs)
> +
> +BTF_ID_LIST_SINGLE(bpf_oom_ops_ids, struct, bpf_oom_ops)
> +
> +static int bpf_oom_kfunc_filter(const struct bpf_prog *prog, u32 kfunc_id)
> +{
> + if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
> + prog->aux->attach_btf_id != bpf_oom_ops_ids[0])
> + return -EACCES;
> + return 0;
> +}
> +
> +static const struct btf_kfunc_id_set bpf_oom_kfunc_set = {
> + .owner = THIS_MODULE,
> + .set = &bpf_oom_kfuncs,
> + .filter = bpf_oom_kfunc_filter,
> +};
> +
> +static int __init bpf_oom_init(void)
> +{
> + int err;
> +
> + err = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
> + &bpf_oom_kfunc_set);
> + if (err)
> + pr_warn("error while registering bpf oom kfuncs: %d", err);
> +
> + return err;
> +}
> +late_initcall(bpf_oom_init);
> +
> +#endif
> --
> 2.52.0
>