Re: [PATCH v4 07/17] x86/split_lock: Enumerate #AC for split lock by MSR IA32_CORE_CAPABILITY

[Dave Hansen]

On 3/4/19 10:59 AM, Fenghua Yu wrote:
>> But, it goes unmentioned why you do the boot-cpu-only restriction here.
>>  It doesn't match the behavior of the two functions called before
>> init_core_capability():
>>
>>         init_scattered_cpuid_features(c);
>>         init_speculation_control(c);
>>
>> So why is this new function special?
> The function sets the split_lock_detect feature which needs to be
> applied before BSP calls apply_enforced_caps() in get_cpu_cap(). 

Why does it need to be applied that way?

> And I want to enable split lock detection in earlier phase to detect
> split lock earlier.

Why do you want to do this?  Why is this *required* as part of this
implementation?

... and how is this different than the other features that are processed
for cpus other than the boot CPU?