1 files changed, 298 insertions, 115 deletions

diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 0a9326f5f421..f82111837b8d 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -1,44 +1,49 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Energy Model of CPUs
+ * Energy Model of devices
  *
- * Copyright (c) 2018, Arm ltd.
+ * Copyright (c) 2018-2021, Arm ltd.
  * Written by: Quentin Perret, Arm ltd.
+ * Improvements provided by: Lukasz Luba, Arm ltd.
  */
 
 #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>
 #include <linux/sched/topology.h>
 #include <linux/slab.h>
 
-/* Mapping of each CPU to the performance domain to which it belongs. */
-static DEFINE_PER_CPU(struct em_perf_domain *, em_data);
-
 /*
  * Mutex serializing the registrations of performance domains and letting
  * callbacks defined by drivers sleep.
  */
 static DEFINE_MUTEX(em_pd_mutex);
 
+static bool _is_cpu_device(struct device *dev)
+{
+	return (dev->bus == &cpu_subsys);
+}
+
 #ifdef CONFIG_DEBUG_FS
 static struct dentry *rootdir;
 
-static void em_debug_create_cs(struct em_cap_state *cs, struct dentry *pd)
+static void em_debug_create_ps(struct em_perf_state *ps, struct dentry *pd)
 {
 	struct dentry *d;
 	char name[24];
 
-	snprintf(name, sizeof(name), "cs:%lu", cs->frequency);
+	snprintf(name, sizeof(name), "ps:%lu", ps->frequency);
 
-	/* Create per-cs directory */
+	/* Create per-ps directory */
 	d = debugfs_create_dir(name, pd);
-	debugfs_create_ulong("frequency", 0444, d, &cs->frequency);
-	debugfs_create_ulong("power", 0444, d, &cs->power);
-	debugfs_create_ulong("cost", 0444, d, &cs->cost);
+	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)
@@ -49,22 +54,43 @@ static int em_debug_cpus_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(em_debug_cpus);
 
-static void em_debug_create_pd(struct em_perf_domain *pd, int cpu)
+static int em_debug_flags_show(struct seq_file *s, void *unused)
+{
+	struct em_perf_domain *pd = s->private;
+
+	seq_printf(s, "%#lx\n", pd->flags);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(em_debug_flags);
+
+static void em_debug_create_pd(struct device *dev)
 {
 	struct dentry *d;
-	char name[8];
 	int i;
 
-	snprintf(name, sizeof(name), "pd%d", cpu);
-
 	/* Create the directory of the performance domain */
-	d = debugfs_create_dir(name, rootdir);
+	d = debugfs_create_dir(dev_name(dev), rootdir);
 
-	debugfs_create_file("cpus", 0444, d, pd->cpus, &em_debug_cpus_fops);
+	if (_is_cpu_device(dev))
+		debugfs_create_file("cpus", 0444, d, dev->em_pd->cpus,
+				    &em_debug_cpus_fops);
+
+	debugfs_create_file("flags", 0444, d, dev->em_pd,
+			    &em_debug_flags_fops);
+
+	/* Create a sub-directory for each performance state */
+	for (i = 0; i < dev->em_pd->nr_perf_states; i++)
+		em_debug_create_ps(&dev->em_pd->table[i], d);
 
-	/* Create a sub-directory for each capacity state */
-	for (i = 0; i < pd->nr_cap_states; i++)
-		em_debug_create_cs(&pd->table[i], d);
+}
+
+static void em_debug_remove_pd(struct device *dev)
+{
+	struct dentry *debug_dir;
+
+	debug_dir = debugfs_lookup(dev_name(dev), rootdir);
+	debugfs_remove_recursive(debug_dir);
 }
 
 static int __init em_debug_init(void)
@@ -74,136 +100,252 @@ static int __init em_debug_init(void)
 
 	return 0;
 }
-core_initcall(em_debug_init);
+fs_initcall(em_debug_init);
 #else /* CONFIG_DEBUG_FS */
-static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) {}
+static void em_debug_create_pd(struct device *dev) {}
+static void em_debug_remove_pd(struct device *dev) {}
 #endif
-static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
-						struct em_data_callback *cb)
+
+static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
+				int nr_states, struct em_data_callback *cb,
+				unsigned long flags)
 {
-	unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
-	unsigned long power, freq, prev_freq = 0;
-	int i, ret, cpu = cpumask_first(span);
-	struct em_cap_state *table;
-	struct em_perf_domain *pd;
+	unsigned long power, freq, prev_freq = 0, prev_cost = ULONG_MAX;
+	struct em_perf_state *table;
+	int i, ret;
 	u64 fmax;
 
-	if (!cb->active_power)
-		return NULL;
-
-	pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
-	if (!pd)
-		return NULL;
-
 	table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL);
 	if (!table)
-		goto free_pd;
+		return -ENOMEM;
 
-	/* Build the list of capacity states for this performance domain */
+	/* Build the list of performance states for this performance domain */
 	for (i = 0, freq = 0; i < nr_states; i++, freq++) {
 		/*
 		 * active_power() is a driver callback which ceils 'freq' to
-		 * lowest capacity state of 'cpu' above 'freq' and updates
+		 * lowest performance state of 'dev' above 'freq' and updates
 		 * 'power' and 'freq' accordingly.
 		 */
-		ret = cb->active_power(&power, &freq, cpu);
+		ret = cb->active_power(dev, &power, &freq);
 		if (ret) {
-			pr_err("pd%d: invalid cap. state: %d\n", cpu, ret);
-			goto free_cs_table;
+			dev_err(dev, "EM: invalid perf. state: %d\n",
+				ret);
+			goto free_ps_table;
 		}
 
 		/*
 		 * We expect the driver callback to increase the frequency for
-		 * higher capacity states.
+		 * higher performance states.
 		 */
 		if (freq <= prev_freq) {
-			pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq);
-			goto free_cs_table;
+			dev_err(dev, "EM: non-increasing freq: %lu\n",
+				freq);
+			goto free_ps_table;
 		}
 
 		/*
 		 * The power returned by active_state() is expected to be
-		 * positive, in milli-watts and to fit into 16 bits.
+		 * positive and be in range.
 		 */
-		if (!power || power > EM_CPU_MAX_POWER) {
-			pr_err("pd%d: invalid power: %lu\n", cpu, power);
-			goto free_cs_table;
+		if (!power || power > EM_MAX_POWER) {
+			dev_err(dev, "EM: invalid power: %lu\n",
+				power);
+			goto free_ps_table;
 		}
 
 		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)
-			pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n",
-					cpu, i, i - 1);
-		prev_opp_eff = opp_eff;
 	}
 
-	/* Compute the cost of each capacity_state. */
+	/* Compute the cost of each performance state. */
 	fmax = (u64) table[nr_states - 1].frequency;
-	for (i = 0; i < nr_states; i++) {
-		table[i].cost = div64_u64(fmax * table[i].power,
-					  table[i].frequency);
+	for (i = nr_states - 1; i >= 0; i--) {
+		unsigned long power_res, cost;
+
+		if (flags & EM_PERF_DOMAIN_ARTIFICIAL) {
+			ret = cb->get_cost(dev, table[i].frequency, &cost);
+			if (ret || !cost || cost > EM_MAX_POWER) {
+				dev_err(dev, "EM: invalid cost %lu %d\n",
+					cost, ret);
+				goto free_ps_table;
+			}
+		} else {
+			power_res = table[i].power;
+			cost = div64_u64(fmax * power_res, table[i].frequency);
+		}
+
+		table[i].cost = cost;
+
+		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;
-	pd->nr_cap_states = nr_states;
-	cpumask_copy(to_cpumask(pd->cpus), span);
-
-	em_debug_create_pd(pd, cpu);
+	pd->nr_perf_states = nr_states;
 
-	return pd;
+	return 0;
 
-free_cs_table:
+free_ps_table:
 	kfree(table);
-free_pd:
-	kfree(pd);
+	return -EINVAL;
+}
+
+static int em_create_pd(struct device *dev, int nr_states,
+			struct em_data_callback *cb, cpumask_t *cpus,
+			unsigned long flags)
+{
+	struct em_perf_domain *pd;
+	struct device *cpu_dev;
+	int cpu, ret, num_cpus;
 
-	return NULL;
+	if (_is_cpu_device(dev)) {
+		num_cpus = cpumask_weight(cpus);
+
+		/* Prevent max possible energy calculation to not overflow */
+		if (num_cpus > EM_MAX_NUM_CPUS) {
+			dev_err(dev, "EM: too many CPUs, overflow possible\n");
+			return -EINVAL;
+		}
+
+		pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
+		if (!pd)
+			return -ENOMEM;
+
+		cpumask_copy(em_span_cpus(pd), cpus);
+	} else {
+		pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+		if (!pd)
+			return -ENOMEM;
+	}
+
+	ret = em_create_perf_table(dev, pd, nr_states, cb, flags);
+	if (ret) {
+		kfree(pd);
+		return ret;
+	}
+
+	if (_is_cpu_device(dev))
+		for_each_cpu(cpu, cpus) {
+			cpu_dev = get_cpu_device(cpu);
+			cpu_dev->em_pd = pd;
+		}
+
+	dev->em_pd = pd;
+
+	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++;
+	}
+
+	cpufreq_cpu_put(policy);
+
+	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
+ *
+ * Returns the performance domain to which @dev belongs, or NULL if it doesn't
+ * exist.
+ */
+struct em_perf_domain *em_pd_get(struct device *dev)
+{
+	if (IS_ERR_OR_NULL(dev))
+		return NULL;
+
+	return dev->em_pd;
+}
+EXPORT_SYMBOL_GPL(em_pd_get);
+
+/**
  * em_cpu_get() - Return the performance domain for a CPU
  * @cpu : CPU to find the performance domain for
  *
- * Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't
+ * Returns the performance domain to which @cpu belongs, or NULL if it doesn't
  * exist.
  */
 struct em_perf_domain *em_cpu_get(int cpu)
 {
-	return READ_ONCE(per_cpu(em_data, cpu));
+	struct device *cpu_dev;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev)
+		return NULL;
+
+	return em_pd_get(cpu_dev);
 }
 EXPORT_SYMBOL_GPL(em_cpu_get);
 
 /**
- * em_register_perf_domain() - Register the Energy Model of a performance domain
- * @span	: Mask of CPUs in the performance domain
- * @nr_states	: Number of capacity states to register
+ * em_dev_register_perf_domain() - Register the Energy Model (EM) for a device
+ * @dev		: Device for which the EM is to register
+ * @nr_states	: Number of performance states to register
  * @cb		: Callback functions providing the data of the Energy Model
+ * @cpus	: Pointer to cpumask_t, which in case of a CPU device is
+ *		obligatory. It can be taken from i.e. 'policy->cpus'. For other
+ *		type of devices this should be set to NULL.
+ * @microwatts	: Flag indicating that the power values are in micro-Watts or
+ *		in some other scale. It must be set properly.
  *
  * Create Energy Model tables for a performance domain using the callbacks
  * defined in cb.
  *
+ * The @microwatts is important to set with correct value. Some kernel
+ * sub-systems might rely on this flag and check if all devices in the EM are
+ * using the same scale.
+ *
  * If multiple clients register the same performance domain, all but the first
  * registration will be ignored.
  *
  * Return 0 on success
  */
-int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
-						struct em_data_callback *cb)
+int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
+				struct em_data_callback *cb, cpumask_t *cpus,
+				bool microwatts)
 {
 	unsigned long cap, prev_cap = 0;
-	struct em_perf_domain *pd;
-	int cpu, ret = 0;
+	unsigned long flags = 0;
+	int cpu, ret;
 
-	if (!span || !nr_states || !cb)
+	if (!dev || !nr_states || !cb)
 		return -EINVAL;
 
 	/*
@@ -212,47 +354,88 @@ int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
 	 */
 	mutex_lock(&em_pd_mutex);
 
-	for_each_cpu(cpu, span) {
-		/* Make sure we don't register again an existing domain. */
-		if (READ_ONCE(per_cpu(em_data, cpu))) {
-			ret = -EEXIST;
-			goto unlock;
-		}
+	if (dev->em_pd) {
+		ret = -EEXIST;
+		goto unlock;
+	}
 
-		/*
-		 * All CPUs of a domain must have the same micro-architecture
-		 * since they all share the same table.
-		 */
-		cap = arch_scale_cpu_capacity(cpu);
-		if (prev_cap && prev_cap != cap) {
-			pr_err("CPUs of %*pbl must have the same capacity\n",
-							cpumask_pr_args(span));
+	if (_is_cpu_device(dev)) {
+		if (!cpus) {
+			dev_err(dev, "EM: invalid CPU mask\n");
 			ret = -EINVAL;
 			goto unlock;
 		}
-		prev_cap = cap;
+
+		for_each_cpu(cpu, cpus) {
+			if (em_cpu_get(cpu)) {
+				dev_err(dev, "EM: exists for CPU%d\n", cpu);
+				ret = -EEXIST;
+				goto unlock;
+			}
+			/*
+			 * All CPUs of a domain must have the same
+			 * micro-architecture since they all share the same
+			 * table.
+			 */
+			cap = arch_scale_cpu_capacity(cpu);
+			if (prev_cap && prev_cap != cap) {
+				dev_err(dev, "EM: CPUs of %*pbl must have the same capacity\n",
+					cpumask_pr_args(cpus));
+
+				ret = -EINVAL;
+				goto unlock;
+			}
+			prev_cap = cap;
+		}
 	}
 
-	/* Create the performance domain and add it to the Energy Model. */
-	pd = em_create_pd(span, nr_states, cb);
-	if (!pd) {
-		ret = -EINVAL;
+	if (microwatts)
+		flags |= EM_PERF_DOMAIN_MICROWATTS;
+	else if (cb->get_cost)
+		flags |= EM_PERF_DOMAIN_ARTIFICIAL;
+
+	ret = em_create_pd(dev, nr_states, cb, cpus, flags);
+	if (ret)
 		goto unlock;
-	}
 
-	for_each_cpu(cpu, span) {
-		/*
-		 * The per-cpu array can be read concurrently from em_cpu_get().
-		 * The barrier enforces the ordering needed to make sure readers
-		 * can only access well formed em_perf_domain structs.
-		 */
-		smp_store_release(per_cpu_ptr(&em_data, cpu), pd);
-	}
+	dev->em_pd->flags |= flags;
+
+	em_cpufreq_update_efficiencies(dev);
+
+	em_debug_create_pd(dev);
+	dev_info(dev, "EM: created perf domain\n");
 
-	pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span));
 unlock:
 	mutex_unlock(&em_pd_mutex);
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(em_register_perf_domain);
+EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
+
+/**
+ * em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device
+ * @dev		: Device for which the EM is registered
+ *
+ * Unregister the EM for the specified @dev (but not a CPU device).
+ */
+void em_dev_unregister_perf_domain(struct device *dev)
+{
+	if (IS_ERR_OR_NULL(dev) || !dev->em_pd)
+		return;
+
+	if (_is_cpu_device(dev))
+		return;
+
+	/*
+	 * The mutex separates all register/unregister requests and protects
+	 * from potential clean-up/setup issues in the debugfs directories.
+	 * The debugfs directory name is the same as device's name.
+	 */
+	mutex_lock(&em_pd_mutex);
+	em_debug_remove_pd(dev);
+
+	kfree(dev->em_pd->table);
+	kfree(dev->em_pd);
+	dev->em_pd = NULL;
+	mutex_unlock(&em_pd_mutex);
+}
+EXPORT_SYMBOL_GPL(em_dev_unregister_perf_domain);