aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/power/energy_model.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/power/energy_model.c')
-rw-r--r--kernel/power/energy_model.c86
1 files changed, 68 insertions, 18 deletions
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index a332ccd829e2..0153b0ca7b23 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -2,7 +2,7 @@
/*
* Energy Model of devices
*
- * Copyright (c) 2018-2020, Arm ltd.
+ * Copyright (c) 2018-2021, Arm ltd.
* Written by: Quentin Perret, Arm ltd.
* Improvements provided by: Lukasz Luba, Arm ltd.
*/
@@ -10,6 +10,7 @@
#define pr_fmt(fmt) "energy_model: " fmt
#include <linux/cpu.h>
+#include <linux/cpufreq.h>
#include <linux/cpumask.h>
#include <linux/debugfs.h>
#include <linux/energy_model.h>
@@ -42,6 +43,7 @@ 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("inefficient", 0444, d, &ps->flags);
}
static int em_debug_cpus_show(struct seq_file *s, void *unused)
@@ -55,7 +57,8 @@ DEFINE_SHOW_ATTRIBUTE(em_debug_cpus);
static int em_debug_units_show(struct seq_file *s, void *unused)
{
struct em_perf_domain *pd = s->private;
- char *units = pd->milliwatts ? "milliWatts" : "bogoWatts";
+ char *units = (pd->flags & EM_PERF_DOMAIN_MILLIWATTS) ?
+ "milliWatts" : "bogoWatts";
seq_printf(s, "%s\n", units);
@@ -63,6 +66,17 @@ static int em_debug_units_show(struct seq_file *s, void *unused)
}
DEFINE_SHOW_ATTRIBUTE(em_debug_units);
+static int em_debug_skip_inefficiencies_show(struct seq_file *s, void *unused)
+{
+ struct em_perf_domain *pd = s->private;
+ int enabled = (pd->flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES) ? 1 : 0;
+
+ seq_printf(s, "%d\n", enabled);
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(em_debug_skip_inefficiencies);
+
static void em_debug_create_pd(struct device *dev)
{
struct dentry *d;
@@ -76,6 +90,8 @@ static void em_debug_create_pd(struct device *dev)
&em_debug_cpus_fops);
debugfs_create_file("units", 0444, d, dev->em_pd, &em_debug_units_fops);
+ debugfs_create_file("skip-inefficiencies", 0444, d, dev->em_pd,
+ &em_debug_skip_inefficiencies_fops);
/* Create a sub-directory for each performance state */
for (i = 0; i < dev->em_pd->nr_perf_states; i++)
@@ -107,8 +123,7 @@ static void em_debug_remove_pd(struct device *dev) {}
static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
int nr_states, struct em_data_callback *cb)
{
- unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
- unsigned long power, freq, prev_freq = 0;
+ unsigned long power, freq, prev_freq = 0, prev_cost = ULONG_MAX;
struct em_perf_state *table;
int i, ret;
u64 fmax;
@@ -153,27 +168,22 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
table[i].power = power;
table[i].frequency = prev_freq = freq;
-
- /*
- * The hertz/watts efficiency ratio should decrease as the
- * frequency grows on sane platforms. But this isn't always
- * true in practice so warn the user if a higher OPP is more
- * power efficient than a lower one.
- */
- opp_eff = freq / power;
- if (opp_eff >= prev_opp_eff)
- dev_dbg(dev, "EM: hertz/watts ratio non-monotonically decreasing: em_perf_state %d >= em_perf_state%d\n",
- i, i - 1);
- prev_opp_eff = opp_eff;
}
/* Compute the cost of each performance state. */
fmax = (u64) table[nr_states - 1].frequency;
- for (i = 0; i < nr_states; i++) {
+ for (i = nr_states - 1; i >= 0; i--) {
unsigned long power_res = em_scale_power(table[i].power);
table[i].cost = div64_u64(fmax * power_res,
table[i].frequency);
+ if (table[i].cost >= prev_cost) {
+ table[i].flags = EM_PERF_STATE_INEFFICIENT;
+ dev_dbg(dev, "EM: OPP:%lu is inefficient\n",
+ table[i].frequency);
+ } else {
+ prev_cost = table[i].cost;
+ }
}
pd->table = table;
@@ -222,6 +232,43 @@ static int em_create_pd(struct device *dev, int nr_states,
return 0;
}
+static void em_cpufreq_update_efficiencies(struct device *dev)
+{
+ struct em_perf_domain *pd = dev->em_pd;
+ struct em_perf_state *table;
+ struct cpufreq_policy *policy;
+ int found = 0;
+ int i;
+
+ if (!_is_cpu_device(dev) || !pd)
+ return;
+
+ policy = cpufreq_cpu_get(cpumask_first(em_span_cpus(pd)));
+ if (!policy) {
+ dev_warn(dev, "EM: Access to CPUFreq policy failed");
+ return;
+ }
+
+ table = pd->table;
+
+ for (i = 0; i < pd->nr_perf_states; i++) {
+ if (!(table[i].flags & EM_PERF_STATE_INEFFICIENT))
+ continue;
+
+ if (!cpufreq_table_set_inefficient(policy, table[i].frequency))
+ found++;
+ }
+
+ if (!found)
+ return;
+
+ /*
+ * Efficiencies have been installed in CPUFreq, inefficient frequencies
+ * will be skipped. The EM can do the same.
+ */
+ pd->flags |= EM_PERF_DOMAIN_SKIP_INEFFICIENCIES;
+}
+
/**
* em_pd_get() - Return the performance domain for a device
* @dev : Device to find the performance domain for
@@ -335,7 +382,10 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
if (ret)
goto unlock;
- dev->em_pd->milliwatts = milliwatts;
+ if (milliwatts)
+ dev->em_pd->flags |= EM_PERF_DOMAIN_MILLIWATTS;
+
+ em_cpufreq_update_efficiencies(dev);
em_debug_create_pd(dev);
dev_info(dev, "EM: created perf domain\n");