Re: 2.6.27rc1 cannot boot more than 8CPUs

["Yinghai Lu" <yhlu.kernel@gmail.com>]

On Wed, Aug 13, 2008 at 10:39 AM, Ingo Molnar <mingo@elte.hu> wrote:
>
> * Jeff Chua <jeff.chua.linux@gmail.com> wrote:
>
>> On Thu, Aug 14, 2008 at 1:10 AM, Jeff Chua <jeff.chua.linux@gmail.com> wrote:
>> > On Wed, Aug 13, 2008 at 10:16 PM, Ingo Molnar <mingo@elte.hu> wrote:
>> >
>> >> btw., could you please check that v2.6.27-rc3 (or later) kernels boot
>> >> fine (with about 8 cpus) even if you have genericarch/bigsmp disabled,
>> >> and do not silently hang as it happened on your box before?
>> >
>> > With 16 CPUs, it still hangs, but now the console is showing the
>> > errors as intended.
>> > ... but it is supposed to hang?
>>
>> I tried with just CONFIG_NR_CPUS=8 and this time it booted, but stange
>> thing is I only see 2 CPUs! To be more precise, it's without both
>> CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.
>>
>> And when I tried to enable the CPUs, it complained about:
>>
>> # cat cpu6/online
>> 0
>> # echo 1 > cpu6/online
>> More than 8 CPUs detected - skipping them.
>> Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.
>> -bash: echo: write error: Input/output error
>>
>> Prior to the patch, the system booted with all 8 CPUs.

that is new regression...

>>
>> Again, if I enable both CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP,
>> I get all 16 CPUs.
>
> Yinghai, could the APIC ID enumeration be nonsequential and we skip CPUs
> starting at the third one already? I think we should accept all CPUs
> that are within our support range.

will try to clear those bits on smp_sanity_check...

YH