irq_migrate_...off_this_cpu(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸ’… irq_migrate_all_off_this_cpu

okay bestie, welcome to the Kernel API Manual β€” yes, that's the whole vibe, we're in the kernel docs now and it's giving ✨ deep magic ✨. Sit down, put your hair up, and let's talk about getting interrupts off a CPU that's clocking out. πŸŽ€


🌸 NAME 🌸

irq_migrate_all_off_this_cpu β€” migrating IRQs away from an offline CPU, no cap πŸ’…

πŸ¦‹ SYNOPSIS πŸ¦‹

void irq_migrate_all_off_this_cpu (void );

πŸ“ ARGUMENTS πŸ“

  • void β€” no arguments, babe. zero. nothing. it takes nothing and it knows it. πŸ™ˆ

✨ DESCRIPTION ✨

So here's the tea β˜•: the current CPU has already been marked offline. Like, it's out, it's done, it's not coming to the function.

This function's whole job is to migrate IRQs off this CPU. Get them gone. Move them somewhere that still has main character energy. πŸ”₯

And if the affinity settings do not allow other CPUs? Then the function forces them onto any available CPU. Yeah. It does not ask. It does not negotiate. It just puts them somewhere 🫢

no cap, that's the entire description β€” but it's an important one, so we're being loud about it πŸ‘‘

πŸ’€ NOTE πŸ’€

we must iterate over all IRQs, whether they have an attached action structure or not, as we need to get chained interrupts too.

like β€” all of them. even the ones with no action structure attached. because chained interrupts exist and we need them, iykyk πŸŒ€

🌈 SEE ALSO 🌈


lowkey aesthetic moment: this whole page lives under the ./kernel/irq section, and the docs are dated October 2026, so yeah β€” we're reading the future, periodt ⭐

stay hydrated, go read cpuhotplug.c, and remember: if the affinity settings don't let you move, someone will just force you onto another CPU anyway πŸ˜­πŸ’– bye bestie 🧚

πŸ“¦ where this page comes from