Re: smp_call_function_single lockups

[Rafael David Tinoco]

For the host, we are using "intremap=no_x2apic_optout
intel_idle.max_cstate=0" for cmdline. It looks like that DL360/DL380
Gen8 firmware still asks to optout from x2apic but HP engineering team
said that using x2apic for Gen8 would be ok (intel_idle causes these
servers to generate NMIs when idling, probably related to packed
c-states and this server's dependency on acpi tables for c-state).

Feb 19 08:21:28 derain kernel: [    3.504676] Enabled IRQ remapping in
x2apic mode
Feb 19 08:21:28 derain kernel: [    3.565451] Enabling x2apic
Feb 19 08:21:28 derain kernel: [    3.602134] Enabled x2apic
Feb 19 08:21:28 derain kernel: [    3.637682] Switched APIC routing to
cluster x2apic.

On Thu, Feb 19, 2015 at 2:26 PM, Linus Torvalds
<torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
> On Thu, Feb 19, 2015 at 7:42 AM, Rafael David Tinoco <inaddy@xxxxxxxxxx> wrote:
>>
>> Same environment as before: Nested KVM (2 vcpus) on top of Proliant
>> DL380G8 with acpi_idle and no x2apic optout.
>
> Btw, which apic model does that end up using? Does "no x2apic optout"
> mean you're using the x2apic?
>
> What does "dmesg | grep apic" report? Something like
>
>     Switched APIC routing to cluster x2apic.
>
> or what?
>
> Side note to the apic guys: I think the "single CPU" case ends up
> being one of the most important ones, but the stupid APIC model
> doesn't allow that, so sending an IPI to a single CPU ends up being
> "send a mask with a single bit set", and then we have that horrible
> "for_each_cpu(cpu, mask)" crap.
>
> Would it make sense to perhaps add a "send_IPI_single()" function
> call, and then for the APIC models that always are based on masks, use
> a wrapper that just does that "cpumask_of(cpu)" thing..
>
> Hmm?
>
>                        Linus
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/