Re: [PATCH 1/5] fs/resctrl: Drop support for different bandwidth delay mappings

[Reinette Chatre]

Hi Chenyu,

On 9/3/26 8:33 PM, Chen Yu wrote:
> On Thu, Sep 03, 2026 at 09:57:03AM -0700, Reinette Chatre wrote:
>>  
>> -/*
>> - * Map the memory b/w percentage value to delay values
>> - * that can be written to QOS_MSRs.
>> - * There are currently no SKUs which support non linear delay values.
>> - */
>> -static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
>> -{
>> -	if (r->membw.delay_linear)
>> -		return MAX_MBA_BW - bw;
>> -
>> -	pr_warn_once("Non Linear delay-bw map not supported but queried\n");
>> -	return MAX_MBA_BW;
>> -}
>> -
>>  static void mba_wrmsr_intel(struct msr_param *m)
>>  {
>>  	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom);
>>  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
>>  	unsigned int i;
>>  
>> -	/*  Write the delay values for mba. */
>> +	if (!m->res->membw.delay_linear) {
>> +		pr_warn_once("Non-linear bandwidth delay not supported\n");
>> +		return;
> 
> Previously if linear delay is not supported, we still write MAX_MBA_BW
> to MSR, and here we return with MSR untouched, this should be the expected
> behavior?

I believe so, yes. Two reasons:
a) This is not a supported scenario. This code path should never execute
   and already complains loudly if encountered.
b) In the unlikely case that this unsupported scenario is encountered I
   find leaving the hardware as-is to be the safer option.

> Besides, in patch 2, __get_mem_config_intel() returns false for
> non-linear-delay platform thus MB resource's alloc_capable is false,
> do we still need to do the linear check in mba_wrmsr_intel() in patch 1
> as the code path will not be triggered?

You are right that the check is not required. I view this check more like
why we use "lockdep_assert_held()". More specifically, it uses the code to
document the requirements instead of comments. For Intel this is valuable
since the transition to controls and their flags means that when a developer
builds on the new resctrl capabilities to initialize multiple controls it is
required for *each* control to have the "this scalar is linear" flag set. This
test makes that requirement clear.

Reinette