powercap/drivers/dtpm: Scale the power with the load

Currently the power consumption is based on the current OPP power
assuming the entire performance domain is fully loaded.

That gives very gross power estimation and we can do much better by
using the load to scale the power consumption.

Use the utilization to normalize and scale the power usage over the
max possible power.

Tested on a rock960 with 2 big CPUS, the power consumption estimation
conforms with the expected one.

Before this change:

~$ ~/dhrystone -t 1 -l 10000&
~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw
2260000

After this change:

~$ ~/dhrystone -t 1 -l 10000&
~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw
1130000

~$ ~/dhrystone -t 2 -l 10000&
~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw
2260000

Signed-off-by: Daniel Lezcano <[email protected]>
Reviewed-by: Lukasz Luba <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: dlezcano

drivers/powercap/dtpm_cpu.c

@@ -68,27 +68,59 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 	return power_limit;
 }
 
+static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power)
+{
+	unsigned long max = 0, sum_util = 0;
+	int cpu;
+
+	for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {
+
+		/*
+		 * The capacity is the same for all CPUs belonging to
+		 * the same perf domain, so a single call to
+		 * arch_scale_cpu_capacity() is enough. However, we
+		 * need the CPU parameter to be initialized by the
+		 * loop, so the call ends up in this block.
+		 *
+		 * We can initialize 'max' with a cpumask_first() call
+		 * before the loop but the bits computation is not
+		 * worth given the arch_scale_cpu_capacity() just
+		 * returns a value where the resulting assembly code
+		 * will be optimized by the compiler.
+		 */
+		max = arch_scale_cpu_capacity(cpu);
+		sum_util += sched_cpu_util(cpu, max);
+	}
+
+	/*
+	 * In the improbable case where all the CPUs of the perf
+	 * domain are offline, 'max' will be zero and will lead to an
+	 * illegal operation with a zero division.
+	 */
+	return max ? (power * ((sum_util << 10) / max)) >> 10 : 0;
+}
+
 static u64 get_pd_power_uw(struct dtpm *dtpm)
 {
 	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
 	struct em_perf_domain *pd;
-	struct cpumask cpus;
+	struct cpumask *pd_mask;
 	unsigned long freq;
-	int i, nr_cpus;
+	int i;
 
 	pd = em_cpu_get(dtpm_cpu->cpu);
-	freq = cpufreq_quick_get(dtpm_cpu->cpu);
 
-	cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
-	nr_cpus = cpumask_weight(&cpus);
+	pd_mask = em_span_cpus(pd);
+
+	freq = cpufreq_quick_get(dtpm_cpu->cpu);
 
 	for (i = 0; i < pd->nr_perf_states; i++) {
 
 		if (pd->table[i].frequency < freq)
 			continue;
 
-		return pd->table[i].power *
-			MICROWATT_PER_MILLIWATT * nr_cpus;
+		return scale_pd_power_uw(pd_mask, pd->table[i].power *
+					 MICROWATT_PER_MILLIWATT);
 	}
 
 	return 0;