Re: [PATCH v3] Documentation: real-time: Add boot parameters and task isolation section
From: Sebastian Andrzej Siewior
Date: Fri Nov 20 2026 - 10:48:29 EST
On 2026-11-20 23:28:36 [+0800], Zixin Wang wrote:
> One open question about the idle state limits section: I could not
> exercise processor.max_cstate or intel_idle.max_cstate locally. QEMU
> exposes no ACPI _CST states, so the kernel registers no cpuidle states,
> and intel_idle is not built for this AMD test host. Should the section
> stay as documentation-only guidance, or would you prefer that I drop or
> rework it (for example, by pointing to
> Documentation/admin-guide/pm/cpuidle.rst)? I am happy to adjust it.
processor.max_cstate should work on AMD unless it does not expose
certain things. But then it might be an embedded board, not having this?
Does cpupower report anything?
And I don't thing this is exposed on qemu since the guest goes only idle
and the host decides what to do.
The CONFIG_CPU_IDLE section already mentions processor.max_cstate=1 and
refers to cpupower among other points.
I don't know how you want to structure this information but parts of it
are already there. You could go on an add some settings for i915 for
instance. But then it feels like it should be within the DRM section
because it somehow belongs together.
And there is a CONFIG_NO_HZ/ CONFIG_NO_HZ_FULL section for instance.
It also says that the transition is a bit more expensive. This repeated
again later on.
Maybe it wouldn't be that bad if the config switches would have a
suggestion for the comandline argument that might be helpful/
considered. That way the information pieces stay together.
What do you think?
Sebastian