Linux 6.13-rc2 To Workaround Buggy Intel Lunar Lake Leading To Responsiveness Issues

[elliott]

Did anyone test this? I just installed Ubuntu 24.10 then 6.13-rc2 from mainline and I'm still getting pauses and repeated keystrokes on a LL 258v. It'd be helpful to know if I'm missing something.

Ah, my mistake I installed 6.13-rc1. still waiting on rc2 then.

[elliott]

Did anyone test this? I just installed Ubuntu 24.10 then 6.13-rc2 from mainline and I'm still getting pauses and repeated keystrokes on a LL 258v. It'd be helpful to know if I'm missing something.

[MorrisS.]

Half of work to fix Intel Cpus bugs.

[mlau]

Does the Intel Lunar Lake bug come from the hardware ?? Intel didn't fix its hardware ?

According to LKML posts, its a know issue in the E cores going back 2-3 atom generations.

[Phoronos]

Does the Intel Lunar Lake bug come from the hardware ?? Intel didn't fix its hardware ?

[the-burrito-triangle]

Intel's laptop power management woes have been it's bugaboo for a very long time to the point that some long time PC hardware reviewers were just "wowed" (like Paul Thurrott) by the recent Qualcomm Snapdragon Elite releases actually being instant on/wake, and instant sleep (which Intel has NEVER done properly).

I'm confused. My old Lenovo Kabby Lake laptop was "instant on" with Windows 10... Intel came up with S0ix for "modern standby" so you have "instant wakeup".

My current Lenovo Tiger Lake laptop's firmware takes A LOT longer to boot. This is a trend I've seen lately with newer x86 HW: during cold-boot, the firmware takes it's sweet-ass time to do link training and what not before finally showing POST.

Anyways, wake up is instant for me on Rocket Lake via S3 (suspend to RAM) and on Tiger Lake via S0ix. So I have no idea what you are talking about WRT wake up times.

[the-burrito-triangle]

[...] Intel doesn't need right now immediately on the heels of the quality problems of 12th and 13th gen processors.

You mean 13th and 14th Gen processors? 12th Gen Alderlake was not affected by the self-destructing CPU die syndrome. Intel's incredibly delayed response and blaming of 3rd parties for it is laughable. A microcode update cannot fix an already borked CPU, it can only help CPUs that haven't been damaged yet.

[stormcrow]

To be fair, it took a while for a fix to roll for Windows as well. It's been one of those user visible oops Intel doesn't need right now immediately on the heels of the quality problems of 12th and 13th gen processors. Intel's laptop power management woes have been it's bugaboo for a very long time to the point that some long time PC hardware reviewers were just "wowed" (like Paul Thurrott) by the recent Qualcomm Snapdragon Elite releases actually being instant on/wake, and instant sleep (which Intel has NEVER done properly).

[phoronix]

Phoronix: Linux 6.13-rc2 To Workaround Buggy Intel Lunar Lake Leading To Responsiveness Issues

Sent out this morning were the "x86/urgent" updates ahead of Linux 6.13-rc2 due out later today. There are x86 fixes for both Intel and AMD processors this week. Most notable though is fixing some buggy Intel Core Ultra "Lunar Lake" behavior that could lead to responsiveness/delay issues due to the MONITOR implementation being buggy/broken...

https://www.phoronix.com/news/Linux-6.13-rc2-x86-urgent