scx_bpf_get_idle_smtmask(9)

💅 scx_bpf_get_idle_smtmask — like, the whole manual page, bestie

Okay so real talk: this is scx_bpf_get_idle_smtmask(9) from the Kernel API Manual, and it's lowkey one of the cutest little kfuncs in the sched-ext universe. It hands you a referenced kptr to the idle-tracking, per-physical-core cpumask — which means you can actually check whether an entire physical core is free. Iconic behaviour, honestly. 🦋

---

✨ NAME ✨

scx_bpf_get_idle_smtmask — get a referenced kptr to the idle-tracking, per-physical-core cpumask. Can be used to determine if an entire physical core is free. 💖

---

✨ SYNOPSIS ✨

__bpf_kfunc const struct cpumask * scx_bpf_get_idle_smtmask (const
struct bpf_prog_aux *aux );

---

✨ ARGUMENTS ✨

• aux — the implicit BPF argument that gives you access to bpf_prog_aux. It's hidden from BPF progs, so like… don't go looking for it, it's not for you bestie 🙈

---

✨ DESCRIPTION ✨

Returns an empty mask if idle tracking is not enabled, or if you're running on a UP kernel. That's the whole vibe check — no mask for you in those cases. 🎀

fr fr, "empty mask" is a real answer here, not an error. Don't panic when you get nothing back, it's giving intentional. 😭

---

✨ SEE ALSO ✨

Kernel file ./kernel/sched/ext/idle.c — plus the whole friend group:

• scx_bpf_cpu_node(9)
• scx_bpf_select_cpu_dfl(9)
• __scx_bpf_select_cpu_and(9)
• scx_bpf_get_idle_cpumask_node(9)
• scx_bpf_get_idle_cpumask(9)
• scx_bpf_get_idle_smtmask_node(9)
• scx_bpf_put_idle_cpumask(9)
• scx_bpf_test_and_clear_cpu_idle(9)
• scx_bpf_pick_idle_cpu_node(9)
• scx_bpf_pick_idle_cpu(9)
• scx_bpf_pick_any_cpu_node(9)
• scx_bpf_pick_any_cpu(9)

---

🌸 Okay that's the whole page, you ate that. Source/version lives at ./kernel/sched/ext, and this bad girl is dated October 2026 — scx_bpf_get_idle_smtmask(9), periodt. 💅✨