Re: [RFC PATCH v4 8/8] acpi_idle: Disallow play_dead with FFH cstate on AMD platforms

From: Gautham R. Shenoy
Date: Mon Nov 25 2024 - 10:47:47 EST


On Mon, Nov 25, 2024 at 03:56:25PM +0100, Patryk Wlazlyn wrote:
> > So I don't like this. Less exceptions is better.
> >
> > This *SHOULD* never trigger on AMD anyway, because they recommend IO
> > port C[23]. But if their partner BIOS engineer does a wobbly and they
> > end up in MWAIT anyway, it *should* all work regardless.
> Agreed.
> I thought relaying on BIOS to not put FFH states there was a concern.
> I believe Gautham confirmed that AMD would be fine executing that,
> it's just that they prefer ioidle (or hlt?).

Yes, HLT or IOPORT based idle states for CPU Offline are
preferrable. But FFH based idle states work just fine.

--
Thanks and Regards
gautham.