scx_cmask_ref_copy(9)

💅 scx_cmask_ref_copy(9)

okay so first things first, this is a page from the Kernel API Manual, section 9, and the star of the show is scx_cmask_ref_copy. bestie, we're in the kernel scheduler files rn, so hydrate and pay attention 💖

---

✨ NAME ✨

scx_cmask_ref_copy — literally copies @src into the arena cmask that @ref is pointing at 🫶

---

🎀 SYNOPSIS 🎀

void scx_cmask_ref_copy (const struct scx_cmask_ref *ref , const struct
scx_cmask *src );

that's it, that's the whole signature, no cap ✨

---

🌸 ARGUMENTS 🌸

• ref — a validated ref. like, it's already been checked, so it's good to go 💅
• src — a stable kernel cmask. this is the source of truth we're copying from 🦋

---

🧚 DESCRIPTION 🧚

so here's the vibe check 🔥 — the bits that live inside the intersection of ref's snapshotted range and src's range take src's values. everything outside that intersection? left completely untouched, exactly as it was 🙈

and the stores on ref->src use WRITE_ONCE, because BPF may be reading and writing at the same time 😭 so like... concurrency is real, we're being safe about it, periodt.

---

👑 SEE ALSO 👑

okay so there's a whole friend group here, iykyk:

• Kernel file ./kernel/sched/ext/cid.c
• scx_cid_publish_tables(9)
• scx_cid_retire_tables(9)
• scx_cid_init(9)
• scx_cmask_clear(9)
• scx_cmask_fill(9)
• scx_bpf_cid_override(9)
• scx_bpf_cid_to_cpu(9)
• scx_bpf_cpu_to_cid(9)
• scx_cmask_subset(9)
• scx_cmask_empty(9)
• scx_bpf_cid_topo(9)
• scx_cmask_ref_init(9)
• scx_cmask_ref_init_kern(9)
• scx_cmask_ref_shard(9)
• scx_cmask_ref_or(9)
• scx_cmask_ref_from_cpumask(9)

---

🌈 and that's the whole page bestie! this one's straight out of ./kernel/sched/ext, dated October 2026, and the page is scx_cmask_ref_copy(9) — go forth and copy those cmasks 💜🎀⭐