Re: [PATCH v3 8/8] cpufreq: intel_pstate: Use CPPC to get max performance

From: Thomas Gleixner
Date: Sat Sep 10 2016 - 12:25:31 EST


On Thu, 8 Sep 2016, Srinivas Pandruvada wrote:
> +
> +/* Call set_sched_itmt from a work function to be able to use hotplug locks */

And why can't the function below not do that? Is the reader required to
figure that out himslf?

> +static void intel_pstste_sched_itmt_work_fn(struct work_struct *work)
> +{
> + set_sched_itmt(true);
> +}
> +
> +static DECLARE_WORK(sched_itmt_work, intel_pstste_sched_itmt_work_fn);
>
> static bool intel_pstate_get_ppc_enable_status(void)
> {
> @@ -377,14 +391,63 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
> int ret;
> int i;
>
> - if (hwp_active)
> + cpu = all_cpu_data[policy->cpu];
> +
> + if (hwp_active) {

Please split this out into a seperate function.

> + struct cppc_perf_caps *perf_caps;
> +
> + cpu->cppc_data = kzalloc(sizeof(struct cppc_cpudata),
> + GFP_KERNEL);
> + if (!cpu->cppc_data)
> + return;
> +
> + perf_caps = &cpu->cppc_data->perf_caps;
> + ret = cppc_get_perf_caps(policy->cpu, perf_caps);
> + if (ret) {
> + kfree(cpu->cppc_data);
> + return;
> + }
> +
> + cpu->valid_cppc_table = true;
> + pr_debug("cpu:%d H:0x%x N:0x%x L:0x%x\n", policy->cpu,
> + perf_caps->highest_perf, perf_caps->nominal_perf,
> + perf_caps->lowest_perf);
> +
> + cpumask_set_cpu(policy->cpu, &cppc_rd_cpu_mask);
> + if (cpumask_subset(topology_core_cpumask(policy->cpu),
> + &cppc_rd_cpu_mask)) {
> + int cpu_index;
> + int max_prio;
> + bool itmt_support = false;
> +
> + cpu = all_cpu_data[0];
> + max_prio = cpu->cppc_data->perf_caps.highest_perf;
> + for_each_cpu(cpu_index, &cppc_rd_cpu_mask) {
> + cpu = all_cpu_data[cpu_index];
> + perf_caps = &cpu->cppc_data->perf_caps;
> + if (max_prio != perf_caps->highest_perf) {
> + itmt_support = true;
> + break;
> + }
> + }

20 lines of magic logic w/o a userful comment. Darn, you yourself will have
forgotten the magic within 3 month ....

Thanks,

tglx