em_adjust_cpu_capacity(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸ’… em_adjust_cpu_capacity(9) β€” the Kernel API Manual, bestie edition

okay so you're reading em_adjust_cpu_capacity(9), which lives in section 9 of the Kernel API Manual (that's the kernel-functions section, iykyk ✨). It's about the EM β€” energy model β€” and yes we're gonna get into it. πŸ¦‹


🌸 NAME 🌸

em_adjust_cpu_capacity β€” literally just going in and adjusting the EM for a CPU after its capacity got updated. that's the whole vibe. πŸ’–


✨ SYNOPSIS ✨

void em_adjust_cpu_capacity (unsigned int cpu );

that's it. that's the call. she's short but she's doing her job. πŸŽ€


🫢 ARGUMENTS 🫢

  • cpu β€” the target CPU. like, which CPU are we doing this to. that one. πŸ‘‘

πŸ”₯ DESCRIPTION πŸ”₯

So here's the situation: you adjust the existing EM for cpu after a capacity update. βœ…

But bestie, there's an assumption baked in here, and you need to know it: this works under the assumption that the capacity has been updated in the same way for all of the CPUs in the same perf domain. same perf domain = same treatment, no cap. it's giving "we're all in this together" energy. πŸ’€βœ¨

So yeah β€” one CPU gets named in cpu, but the mental model is the whole perf domain moving together. got it? perfect. πŸ’œ


🌈 SEE ALSO 🌈

The kernel file lives at ./kernel/power/energy_model.c, and here's the whole friend group you should go meet:

go read them. they're all icons in their own right. πŸ‘‘β­πŸ§š


lowkey reminder: everything above is the actual documented behaviour β€” nothing more, nothing less. no guessing, no extra lore. πŸ™ˆ

and that's the page!! sign-off time: this gem comes from the ./kernel/power source tree, dated October 2026, and yeah β€” she ate. πŸ’…πŸ“πŸŽ€ periodt.

πŸ“¦ where this page comes from