dev_pm_doma...rmance_state(9)

📦 version 7.3.1, in nixpkgs unstable

💅 dev_pm_domain_set_performance_state — aka "bestie, request a new performance state"

okay so real talk, this page lives in the Kernel API Manual and it's lowkey one of those lil functions that does exactly what the name says. no cap. let's get into it 🫶

✨ NAME ✨

dev_pm_domain_set_performance_state — Request a new performance state.

like... that's the whole gig. it requests a new performance state. iconic behavior fr 💅

🌸 SYNOPSIS 🌸

int dev_pm_domain_set_performance_state(struct device *dev, unsigned int state);

she returns an int, she takes a struct device *dev and an unsigned int state, and she's out. main character energy honestly ✨

🎀 ARGUMENTS 🎀

  • dev — The device to make the request for. 👈 like, this is the device you're doing the whole thing for, bestie.
  • state — Target performance state for the device. 🎯 the vibe you want the device to be at.

🦋 DESCRIPTION 🦋

so basically: this function should be called when a new performance state needs to be requested for a device that is attached to a PM domain. that's the moment. that's the assignment. 💖

heads up bestie: the support for performance scaling for PM domains is optional. so like, it's not guaranteed every PM domain is gonna be into it, yk? 🙈

returns 0 on success and when performance scaling isn't supported — yes she returns 0 in both of those cases, no drama — and a negative error code on failure. 💀

🔥 SEE ALSO 🔥

this function lives in the Kernel file ./drivers/base/power/common.c and it runs with this whole friend group:

like, read the whole group chat, iykyk 💜

okay that's the page!! sending u off with love — this one's brought to you by the source at ./drivers/base/power, dated October 2026, and it's literally the same function name on the way out as on the way in (dev_pm_doma...rmance_state(9), the truncated queen 👑). stan her, she's just doing PM domain things. 🌈🎀✨

📦 where this page comes from