Message-ID: <5a74106a-d9db-4e63-b3e6-3857f30a1190@interia.pl>
Date: Mon, 15 Dec 2025 10:30:07 +0100
From: Bernard Drozd <bernid@...eria.pl>
To: Damien Le Moal <dlemoal@...nel.org>, linux-ide@...r.kernel.org,
 linux-kernel@...r.kernel.org
Cc: Niklas Cassel <cassel@...nel.org>
Subject: Re: [REGRESSION] libata: SATA LPM forcibly disabled on Intel Jasper
 Lake since Linux 6.13

Hi Damien,

thank you for the detailed explanation – that was exactly the missing piece.
You were absolutely right: the issue was caused by all SATA ports being 
reported by the BIOS as external (hot-pluggable).

In my BIOS (AMI Aptio), all SATA ports had Hot Plug enabled by default:
https://www.dropbox.com/scl/fi/9gi68rlxg1mcd37yrwcva/Hot_PLUG_SATA.jpg?rlkey=cse0i5j7qr4va0xjw9o7fv6r4&st=dn6r6q0k&raw=1
After disabling Hot Plug for the SATA ports, LPM works correctly again.

Results:
- Kernel: 6.17.8-1~bpo13+1
- link_power_management_policy can now be set to: med_power_with_dipm
- SATA links enter partial/slumber
- CPU package reaches deep C-states again (PC10)
- Idle power consumption back to ~2.5 W (same as with 6.12)

So this was not a kernel regression, but a correct behavior exposed by 
the libata fix after 6.12, combined with an unfortunate BIOS default.
Thanks again for the clear analysis and for pointing out 
ahci.mask_port_ext as a fallback – very helpful.

Best regards,
Bernard

On 15/12/2025 07:47, Damien Le Moal wrote:
> On 12/15/25 13:28, Bernard Drozd wrote:
>> Hi Damien,
>> Thank you for the explanation – I understand now that pre-6.13 behaviour
>> was relying on a bug allowing userspace to override unsupported LPM.
>> I have collected full diagnostics comparing a *working* kernel (6.12)
>> and a *regressed* kernel (6.17), both tested with **no SATA devices
>> connected**.
>>
>> Important correction:
>> The correct SATA controller PCI ID is:
>> Intel Jasper Lake SATA AHCI Controller [8086:4dd3]
>> This was mistakenly reported earlier as 4d03.
>>
>> Key observation:
>> The LPM disable happens even with no SATA devices attached, so this
>> appears to be a **platform-level decision**, not device capability.
>>
>> Data provided:
>> 1) Full dmesg, Linux 6.12 (LPM works, CPU reaches PC10):
>> https://www.dropbox.com/scl/fi/pwc0bfgoqgb607babczg9/dmesg-6.12-full.txt?rlkey=o8j88lzeq3rw3cbx2q65oyblv&st=u4dwqv0p&raw=1
>>
>> 2) Full dmesg, Linux 6.17 (LPM forced to max_performance, CPU stuck in PC2):
>> https://www.dropbox.com/scl/fi/twbyjm7h5ewgmllit02h8/dmesg-6.17-full.txt?rlkey=p3b97lli6ruo5ypg4c2d4jnc2&st=3o3xo47m&raw=1
> Got it: your AHCI adapter has:
>
> ahci 0000:00:17.0: AHCI vers 0001.0301, 32 command slots, 6 Gbps, SATA mode
> ahci 0000:00:17.0: 2/2 ports implemented (port mask 0x3)
> ahci 0000:00:17.0: flags: 64bit ncq sntf pm led clo only pio slum part deso sadm sds
>
> Partial and slumber are supported, so all good.
>
> BUT ! your ports are...
>
> ata1: SATA max UDMA/133 abar m2048@...0102000 port 0x80102100 irq 142 lpm-pol 1 ext
> ata2: SATA max UDMA/133 abar m2048@...0102000 port 0x80102180 irq 142 lpm-pol 1 ext
>
> ...external. That is, the adapter is saying that these are
> external/hot-pluggable ports, and for these, power management is a bad
> idea/should be disabled, which we do. The reason is that otherwise, we cannot
> catch hot-plug/unplug events (IRQs).
>
> So to enable low-power policies, you need to go into your BIOS settings and
> disable the hot-plugging capability for the ports. Many BIOSes have such setting
> for SATA ports. If your BIOS does not have this, yu can use the mask_port_ext
> AHCI module parameter. Simply add:
>
> ahci.mask_port_ext=0x3 to your kernel command line and the "ext" flag of the
> ports will be ignored and LPM enabled.
>
>

Powered by blists - more mailing lists