PM: EM: Add performance field to struct em_perf_state and optimize

The performance doesn't scale linearly with the frequency. Also, it may
be different in different workloads. Some CPUs are designed to be
particularly good at some applications e.g. images or video processing
and other CPUs in different. When those different types of CPUs are
combined in one SoC they should be properly modeled to get max of the HW
in Energy Aware Scheduler (EAS). The Energy Model (EM) provides the
power vs. performance curves to the EAS, but assumes the CPUs capacity
is fixed and scales linearly with the frequency. This patch allows to
adjust the curve on the 'performance' axis as well.

Code speed optimization:
Removing map_util_freq() allows to avoid one division and one
multiplication operations from the EAS hot code path.

Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

1 files changed, 27 insertions, 0 deletions

diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 667619b70be7..41418aa6daa6 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -46,6 +46,7 @@ static void em_debug_create_ps(struct em_perf_state *ps, struct dentry *pd)
 	debugfs_create_ulong("frequency", 0444, d, &ps->frequency);
 	debugfs_create_ulong("power", 0444, d, &ps->power);
 	debugfs_create_ulong("cost", 0444, d, &ps->cost);
+	debugfs_create_ulong("performance", 0444, d, &ps->performance);
 	debugfs_create_ulong("inefficient", 0444, d, &ps->flags);
 }
 
@@ -159,6 +160,30 @@ struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd)
 	return table;
 }
 
+static void em_init_performance(struct device *dev, struct em_perf_domain *pd,
+				struct em_perf_state *table, int nr_states)
+{
+	u64 fmax, max_cap;
+	int i, cpu;
+
+	/* This is needed only for CPUs and EAS skip other devices */
+	if (!_is_cpu_device(dev))
+		return;
+
+	cpu = cpumask_first(em_span_cpus(pd));
+
+	/*
+	 * Calculate the performance value for each frequency with
+	 * linear relationship. The final CPU capacity might not be ready at
+	 * boot time, but the EM will be updated a bit later with correct one.
+	 */
+	fmax = (u64) table[nr_states - 1].frequency;
+	max_cap = (u64) arch_scale_cpu_capacity(cpu);
+	for (i = 0; i < nr_states; i++)
+		table[i].performance = div64_u64(max_cap * table[i].frequency,
+						 fmax);
+}
+
 static int em_compute_costs(struct device *dev, struct em_perf_state *table,
 			    struct em_data_callback *cb, int nr_states,
 			    unsigned long flags)
@@ -318,6 +343,8 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 		table[i].frequency = prev_freq = freq;
 	}
 
+	em_init_performance(dev, pd, table, nr_states);
+
 	ret = em_compute_costs(dev, table, cb, nr_states, flags);
 	if (ret)
 		return -EINVAL;