scx_bpf_kick_cid(9)

๐Ÿ“ฆ version 7.3.1, in nixpkgs unstable

okay so bestie, welcome to scx_bpf_kick_cid(9) from the Kernel API Manual โœจ this one is literally here to trigger a reschedule on the CPU mapped to @cid, and it's giving scheduler main-character energy ๐Ÿ’….

๐ŸŽ€ NAME ๐ŸŽ€

scx_bpf_kick_cid โ€” trigger reschedule on the CPU mapped to @cid ๐Ÿฆ‹

โœจ SYNOPSIS โœจ

__bpf_kfunc void scx_bpf_kick_cid (s32 cid , u64 flags , const struct
       bpf_prog_aux *aux );

๐ŸŒธ ARGUMENTS ๐ŸŒธ

  • cid โ€” the cid to kick ๐Ÿ’–
  • flags โ€” the SCX_KICK_* flags, periodt.
  • aux โ€” implicit BPF argument to access bpf_prog_aux hidden from BPF progs ๐Ÿ™ˆ

๐Ÿ’… DESCRIPTION ๐Ÿ’…

This is the cid-addressed equivalent of scx_bpf_kick_cpu, fr fr. An invalid cid aborts the scheduler via scx_cid_to_cpu โ€” not cute, very real ๐Ÿ˜ญ.

Caps are enforced on the delivery path: a kick is dropped if the caller lacks baseline access on cid, and a SCX_KICK_PREEMPT degrades to a plain reschedule if the caller lacks SCX_CAP_PREEMPT for a task outside its subtree. That's the whole rulebook, bestie ๐Ÿซถ.

lowkey important: an invalid cid aborts the scheduler via scx_cid_to_cpu ๐Ÿ’€ do not test this for fun.

๐Ÿ”ฎ SEE ALSO ๐Ÿ”ฎ

not me dropping the entire SEE ALSO roster, because bestie we do not skip names ๐Ÿ˜ค:

xoxo, source/version: ./kernel/sched/ext, dated October 2026 โ€” mwah ๐Ÿ’‹โœจ

๐Ÿ“ฆ where this page comes from