mcpm_wait_for_cpu_powerdown(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸ’– mcpm_wait_for_cpu_powerdown(9) πŸ’–

okay so bestie, welcome to the Kernel API Manual β€” this one's about mcpm_wait_for_cpu_powerdown, and it does exactly what it says on the tin: it waits for a specified CPU to halt, and makes sure it is powered off. no cap. πŸŽ€


✨ NAME ✨

mcpm_wait_for_cpu_powerdown β€” wait for a specified CPU to halt, and make sure it is powered off 🫢


🌸 SYNOPSIS 🌸

int mcpm_wait_for_cpu_powerdown (unsigned int cpu , unsigned int cluster );

like, that's the whole vibe. two args, one int back. πŸ’…


πŸ¦‹ ARGUMENTS πŸ¦‹

  • cpu β€” the CPU number, within the given cluster. yes, within the cluster, bestie, don't come at me with a global CPU number. πŸ™ˆ
  • cluster β€” the cluster number for that CPU. it's giving "which friend group is this CPU in" energy. πŸ‘‘

πŸ’œ DESCRIPTION πŸ’œ

so here's the tea β˜• β€” you call this function to make sure that a pending powerdown has actually taken effect, and that the CPU is safely parked, before you go doing non-mcpm operations that may affect that CPU. the example the page gives is kexec trashing the kernel text β€” which, yeah, that's a whole situation. πŸ’€

real talk: it is *not* necessary to call this function if all you need is to serialise a pending powerdown with mcpm_cpu_power_up or a wakeup event. so don't be extra for no reason. 😌
do NOT call this function unless the specified CPU has already called mcpm_cpu_power_down or has committed to doing so. like, fr fr, don't skip that part. 🚨

⭐ RETURN ⭐

  • zero if the CPU is in a safely parked state πŸ…ΏοΈβœ¨
  • nonzero otherwise (e.g., timeout) 😭

🌈 SEE ALSO 🌈

kernel file ./arch/arm/include/asm/mcpm.h β€” and honestly the whole mcpm friend group:


and that's the page, bestie πŸ§šπŸ’– β€” brought to you by ./arch/arm/include/asm, October 2026, and this absolute icon of a manpage, mcpm_wait_for_cpu_powerdown(9). periodt. πŸ’…πŸŽ€

πŸ“¦ where this page comes from