It’s typically rare these days for the ATA subsystem updates in the Linux kernel to contain anything really noteworthy. But today some important fixes were merged for the ATA code to deal with a reported power management regression affecting the past number of Linux kernel releases over the last year. ATAPI devices with dummy ports weren’t hitting their low-power state and in turn preventing the CPU from reaching low-power C-states but thankfully that is now resolved with this code.
Merged today were a few ATA patches to fix this power management issue for those relying on ATAPI devices like CD /…
It’s typically rare these days for the ATA subsystem updates in the Linux kernel to contain anything really noteworthy. But today some important fixes were merged for the ATA code to deal with a reported power management regression affecting the past number of Linux kernel releases over the last year. ATAPI devices with dummy ports weren’t hitting their low-power state and in turn preventing the CPU from reaching low-power C-states but thankfully that is now resolved with this code.
Merged today were a few ATA patches to fix this power management issue for those relying on ATAPI devices like CD / DVD / Blu-ray drives and more:
"A set of fixes for link power management as the recent changes/fixes introduced regressions with ATAPI devices and with adapters that have DUMMY ports, preventing an adapter to fully reach a low power state and thus preventing the system CPU from reaching low power C-states."
These fixes stem from this bug report two weeks ago over SATA Link Power Management (LPM) being disabled since Linux 6.14. The user reported that for their Intel Core i5 "Raptor Lake" system with its SATA AHCI controller, on post-6.14 kernels SATA Link Power Management is forcibly disabled and the Intel CPU is then unable to enter the deeper package C-states. The idle power consumption on this Intel Core i5 desktop went up by around 4 Watts due to this power management regression.
This patch series by Niklas Cassel is what made up today’s ATA pull request to fix this power management regression and some other issues uncovered:
"we had a recent bug report on the mailing list related to LPM, which made me review the LPM related code.
While doing so, I found some issues. This series fixes those issues.
The most serious issue is that ATA_QUIRK_NOLPM was not getting applied for ATAPI devices and that we read the per port area for unimplemented ports, even though the AHCI specification explicitly forbids this."
The code is merged today to Linux 6.19 Git while these fixes will likely be back-ported to prior supported kernel versions in the near future.