resctrl_arch...disable_bits(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

okay bestie, welcome to resctrl_arch...disable_bits(9) from the Kernel API Manual β€” we're about to get into prefetch disable bits and pseudo-locking, and honestly it's giving very specific kernel energy πŸ’…βœ¨

πŸŽ€ NAME πŸŽ€

  • resctrl_arch_get_prefetch_disable_bits β€” prefetch disable bits of supported platforms

πŸ¦‹ SYNOPSIS πŸ¦‹

u64 resctrl_arch_get_prefetch_disable_bits (void );

🌸 ARGUMENTS 🌸

  • void β€” no arguments, like literally none, zero, nada 🫢

✨ DESCRIPTION ✨

So this one captures the list of platforms that have been validated to support pseudo-locking. That validation includes testing to make sure pseudo-locked regions with low cache miss rates can be created under a variety of load conditions, and also that those pseudo-locked regions can maintain their low cache miss rates under a variety of load conditions for significant lengths of time. iconic testing behavior, no cap πŸ”₯

After a platform has been validated to support pseudo-locking, its hardware prefetch disable bits are included here as they are documented in the SDM. periodt.

When you add a platform here, also add support for its cache events to resctrl_arch_measure_l*_residency β€” don't leave your girl hanging πŸ™ˆ

πŸ’– RETURN πŸ’–

If the platform is supported: the bits to disable hardware prefetchers. If the platform is not supported: 0. that's the whole vibe check πŸ’€

🌈 SEE ALSO 🌈


byeee πŸ’… this little page lives in the ./arch/x86/kernel/cpu/resctrl source/version corner, dated October 2026, and it's the resctrl_arch...disable_bits(9) page β€” mwah πŸŽ€πŸ‘‘

πŸ“¦ where this page comes from