Re: [PATCH v3 2/3] x86/smp native_play_dead: Prefer cpuidle_play_dead() over mwait_play_dead()
From: Patryk Wlazlyn
Date: Tue Nov 12 2024 - 06:19:31 EST
> I don't think the bug has anything to do with this patch, really.
> There's no need to rehash it here.
>
> The issue here is that the only way to call mwait today is via
> mwait_play_dead() directly, using its internally-calculated hint.
>
> What you want is for a cpuidle-driver-calculated hint to be used. So,
> you're using the new hint function via the cpuidle driver. But you just
> need the cpuidle driver to be called first, not the old
> mwait_play_dead()-calculated hint. The new code will still do mwait,
> just via a different path and with a different hint.
Ok. I'll just say that we change the order because idle driver may know better.
> The thing this doesn't mention is what the impact on everyone else is.
> I _think_ the ACPI cpuidle driver is the only worry. Today, if there's
> a system that supports mwait and ACPI cpuidle, it'll use mwait. After
> this patch, it'll use ACPI cpuidle.
>
> The changelog doesn't mention that behavior change or why that's OK.
True, but I think the mwait_play_dead() is exclusively for Intel. Other target
platforms get an early return. I'll include that in the commit message.
> Also, looking at this:
>
>> - mwait_play_dead();
>> if (cpuidle_play_dead())
>> - hlt_play_dead();
>> + mwait_play_dead();
>> + hlt_play_dead();
>
> None of those return on success, right?
>
> Is there any reason this couldn't just be:
>
> /* The first successful play_dead() will not return: */
> cpuidle_play_dead();
> mwait_play_dead();
> hlt_play_dead();
>
> That has the added bonus of not needing to return anything from
> mwait_play_dead() and the resulting churn from the last patch.
mwait_play_dead may return if mwait_play_dead_with_hint returns and it only does
on non-smp builds. That being said, we do ignore the return value right now,
because in either case we want to enter hlt_play_dead() as a fallback, so I
guess we can make mwait_play_dead return void, but leave
mwait_play_dead_with_hint returning int or add ifdef CONFIG_SMP guards in
intel_idle.
When going with the return types proposed in this patch set, on non-smp builds
intel_idle would call mwait_play_dead_with_hint() which would "return 1"; and
propagate through cpuidle_play_dead().