Re: [Patch v5 08/16] smt: Create cpu_smt_enabled static key for SMT specific code

[Tim Chen]

Thomas,


>>  
>> +#ifdef CONFIG_SCHED_SMT
>> +
>> +extern struct static_key_false sched_smt_present;
>> +
>> +static inline bool cpu_smt_present(void)
>> +{
>> +	if (static_branch_unlikely(&sched_smt_present))
>> +		return true;
>> +	else
>> +		return false;
> 
> What's wrong with
> 
>        return static_branch_unlikely(&sched_smt_present);
> 
> ???
> 
> But that's just a stylistic nitpick. The real issue is that you prevent the
> mitigation when CONFIG_SCHED_SMT=n.
> 

Right. The sched_smt_present is just a scheduler construct and the sibling
cpu will still be brought online.  Scratch this.

Tim