[RFC PATCH v4 03/12] PM: Introduce an Energy Model management framework

[Quentin Perret]

Several subsystems in the kernel (task scheduler and/or thermal at the
time of writing) can benefit from knowing about the energy consumed by
CPUs. Yet, this information can come from different sources (DT or
firmware for example), in different formats, hence making it hard to
exploit without a standard API.

As an attempt to address this, introduce a centralized Energy Model
(EM) management framework which aggregates the power values provided
by drivers into a table for each frequency domain in the system. The
power cost tables are made available to interested clients (e.g. task
scheduler or thermal) via platform-agnostic APIs. The overall design
is represented by the diagram below (focused on Arm-related drivers as
an example, but hopefully applicable to any architecture):

     +---------------+  +-----------------+  +---------+
     | Thermal (IPA) |  | Scheduler (EAS) |  | Other ? |
     +---------------+  +-----------------+  +---------+
             |                 | em_fd_energy()   |
             |                 | em_cpu_get()     |
             +-----------+     |         +--------+
                         |     |         |
                         v     v         v
                      +---------------------+
                      |                     |         +---------------+
                      |    Energy Model     |         | arch_topology |
                      |                     |<--------|    driver     |
                      |     Framework       |         +---------------+
                      |                     | em_rescale_cpu_capacity()
                      +---------------------+
                         ^       ^       ^
                         |       |       | em_register_freq_domain()
              +----------+       |       +---------+
              |                  |                 |
      +---------------+  +---------------+  +--------------+
      |  cpufreq-dt   |  |   arm_scmi    |  |    Other     |
      +---------------+  +---------------+  +--------------+
              ^                  ^                 ^
              |                  |                 |
      +--------------+   +---------------+  +--------------+
      | Device Tree  |   |   Firmware    |  |      ?       |
      +--------------+   +---------------+  +--------------+

Drivers (typically, but not limited to, CPUFreq drivers) can register
data in the EM framework using the em_register_freq_domain() API. The
calling driver must provide a callback function with a standardized
signature that will be used by the EM framework to build the power
cost tables of the frequency domain. This design should offer a lot of
flexibility to calling drivers which are free of reading information
from any location and to use any technique to compute power costs.
Moreover, the capacity states registered by drivers in the EM framework
are not required to match real performance states of the target. This
is particularly important on targets where the performance states are
not known by the OS.

On the client side, the EM framework offers APIs to access the power
cost tables of a CPU (em_cpu_get()), and to estimate the energy
consumed by the CPUs of a frequency domain (em_fd_energy()). Clients
such as the task scheduler can then use these APIs to access the shared
data structures holding the Energy Model of CPUs.

The EM framework also provides an API (em_rescale_cpu_capacity()) to
re-scale the capacity values of the model asynchronously, after it has
been created. This is required for architectures where the capacity
scale factor of CPUs can change at run-time. This is the case for
Arm/Arm64 for example where the arch_topology driver recomputes the
capacity scale factors of the CPUs after the maximum frequency of all
CPUs has been discovered. Although complex, the process of creating and
re-scaling the EM has to be kept in two separate steps to fulfill the
needs of the different users. The thermal subsystem doesn't use the
capacity values and shouldn't have dependencies on subsystems providing
them. On the other hand, the task scheduler needs the capacity values,
and it will benefit from seeing them up-to-date when applicable.

Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: "Rafael J. Wysocki" <rjw@xxxxxxxxxxxxx>
Signed-off-by: Quentin Perret <quentin.perret@xxxxxxx>
---
 include/linux/energy_model.h | 140 ++++++++++++++++++
 kernel/power/Kconfig         |  15 ++
 kernel/power/Makefile        |   2 +
 kernel/power/energy_model.c  | 273 +++++++++++++++++++++++++++++++++++
 4 files changed, 430 insertions(+)
 create mode 100644 include/linux/energy_model.h
 create mode 100644 kernel/power/energy_model.c

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
new file mode 100644
index 000000000000..88c2f0b9bcb3
--- /dev/null
+++ b/include/linux/energy_model.h
@@ -0,0 +1,140 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_ENERGY_MODEL_H
+#define _LINUX_ENERGY_MODEL_H
+#include <linux/cpumask.h>
+#include <linux/jump_label.h>
+#include <linux/kobject.h>
+#include <linux/rcupdate.h>
+#include <linux/sched/cpufreq.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_ENERGY_MODEL
+struct em_cap_state {
+	unsigned long capacity;
+	unsigned long frequency; /* Kilo-hertz */
+	unsigned long power; /* Milli-watts */
+};
+
+struct em_cs_table {
+	struct em_cap_state *state; /* Capacity states, in ascending order. */
+	int nr_cap_states;
+	struct rcu_head rcu;
+};
+
+struct em_freq_domain {
+	struct em_cs_table *cs_table; /* Capacity state table, RCU-protected */
+	unsigned long cpus[0]; /* CPUs of the frequency domain. */
+};
+
+#define EM_CPU_MAX_POWER 0xFFFF
+
+struct em_data_callback {
+	/**
+	 * active_power() - Provide power at the next capacity state of a CPU
+	 * @power	: Active power at the capacity state in mW (modified)
+	 * @freq	: Frequency at the capacity state in kHz (modified)
+	 * @cpu		: CPU for which we do this operation
+	 *
+	 * active_power() must find the lowest capacity state of 'cpu' above
+	 * 'freq' and update 'power' and 'freq' to the matching active power
+	 * and frequency.
+	 *
+	 * The power is the one of a single CPU in the domain, expressed in
+	 * milli-watts. It is expected to fit in the [0, EM_CPU_MAX_POWER]
+	 * range.
+	 *
+	 * Return 0 on success.
+	 */
+	int (*active_power) (unsigned long *power, unsigned long *freq, int cpu);
+};
+#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb }
+
+void em_rescale_cpu_capacity(void);
+struct em_freq_domain *em_cpu_get(int cpu);
+int em_register_freq_domain(cpumask_t *span, unsigned int nr_states,
+						struct em_data_callback *cb);
+
+/**
+ * em_fd_energy() - Estimates the energy consumed by the CPUs of a freq. domain
+ * @fd		: frequency domain for which energy has to be estimated
+ * @max_util	: highest utilization among CPUs of the domain
+ * @sum_util	: sum of the utilization of all CPUs in the domain
+ *
+ * em_fd_energy() dereferences the capacity state table of the frequency
+ * domain, so it must be called under RCU read lock.
+ *
+ * Return: the sum of the energy consumed by the CPUs of the domain assuming
+ * a capacity state satisfying the max utilization of the domain.
+ */
+static inline unsigned long em_fd_energy(struct em_freq_domain *fd,
+				unsigned long max_util, unsigned long sum_util)
+{
+	struct em_cs_table *cs_table;
+	struct em_cap_state *cs;
+	unsigned long freq;
+	int i;
+
+	cs_table = rcu_dereference(fd->cs_table);
+	if (!cs_table)
+		return 0;
+
+	/* Map the utilization value to a frequency */
+	cs = &cs_table->state[cs_table->nr_cap_states - 1];
+	freq = map_util_freq(max_util, cs->frequency, cs->capacity);
+
+	/* Find the lowest capacity state above this frequency */
+	for (i = 0; i < cs_table->nr_cap_states; i++) {
+		cs = &cs_table->state[i];
+		if (cs->frequency >= freq)
+			break;
+	}
+
+	return cs->power * sum_util / cs->capacity;
+}
+
+/**
+ * em_fd_nr_cap_states() - Get the number of capacity states of a freq. domain
+ * @fd		: frequency domain for which want to do this
+ *
+ * Return: the number of capacity state in the frequency domain table
+ */
+static inline int em_fd_nr_cap_states(struct em_freq_domain *fd)
+{
+	struct em_cs_table *table;
+	int nr_states;
+
+	rcu_read_lock();
+	table = rcu_dereference(fd->cs_table);
+	nr_states = table->nr_cap_states;
+	rcu_read_unlock();
+
+	return nr_states;
+}
+
+#else
+struct em_freq_domain {};
+struct em_data_callback {};
+#define EM_DATA_CB(_active_power_cb) { }
+
+static inline int em_register_freq_domain(cpumask_t *span,
+			unsigned int nr_states, struct em_data_callback *cb)
+{
+	return -EINVAL;
+}
+static inline struct em_freq_domain *em_cpu_get(int cpu)
+{
+	return NULL;
+}
+static inline unsigned long em_fd_energy(struct em_freq_domain *fd,
+			unsigned long max_util, unsigned long sum_util)
+{
+	return 0;
+}
+static inline int em_fd_nr_cap_states(struct em_freq_domain *fd)
+{
+	return 0;
+}
+static inline void em_rescale_cpu_capacity(void) { }
+#endif
+
+#endif
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index e880ca22c5a5..6f6db452dc7d 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -297,3 +297,18 @@ config PM_GENERIC_DOMAINS_OF
 
 config CPU_PM
 	bool
+
+config ENERGY_MODEL
+	bool "Energy Model for CPUs"
+	depends on SMP
+	depends on CPU_FREQ
+	default n
+	help
+	  Several subsystems (thermal and/or the task scheduler for example)
+	  can leverage information about the energy consumed by CPUs to make
+	  smarter decisions. This config option enables the framework from
+	  which subsystems can access the energy models.
+
+	  The exact usage of the energy model is subsystem-dependent.
+
+	  If in doubt, say N.
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index a3f79f0eef36..e7e47d9be1e5 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -15,3 +15,5 @@ obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
 obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
+
+obj-$(CONFIG_ENERGY_MODEL)	+= energy_model.o
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
new file mode 100644
index 000000000000..08ce4035a6d6
--- /dev/null
+++ b/kernel/power/energy_model.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Energy Model of CPUs
+ *
+ * Copyright (c) 2018, Arm ltd.
+ * Written by: Quentin Perret, Arm ltd.
+ */
+
+#define pr_fmt(fmt) "energy_model: " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/energy_model.h>
+#include <linux/sched/topology.h>
+#include <linux/slab.h>
+
+/* Mapping of each CPU to the frequency domain to which it belongs. */
+static DEFINE_PER_CPU(struct em_freq_domain *, em_data);
+
+/*
+ * Mutex serializing the registrations of frequency domains and letting
+ * callbacks defined by drivers sleep.
+ */
+static DEFINE_MUTEX(em_fd_mutex);
+
+static struct em_cs_table *alloc_cs_table(int nr_cs)
+{
+	struct em_cs_table *cs_table;
+
+	cs_table = kzalloc(sizeof(*cs_table), GFP_KERNEL);
+	if (!cs_table)
+		return NULL;
+
+	cs_table->state = kcalloc(nr_cs, sizeof(*cs_table->state), GFP_KERNEL);
+	if (!cs_table->state) {
+		kfree(cs_table);
+		return NULL;
+	}
+
+	cs_table->nr_cap_states = nr_cs;
+
+	return cs_table;
+}
+
+static void free_cs_table(struct em_cs_table *table)
+{
+	if (table) {
+		kfree(table->state);
+		kfree(table);
+	}
+}
+
+/* fd_update_cs_table() - Computes the capacity values of a cs_table
+ *
+ * This assumes a linear relation between capacity and frequency. As such,
+ * the capacity of a CPU at the n^th capacity state is computed as:
+ *           capactity(n) = max_capacity * freq(n) / freq_max
+ */
+static void fd_update_cs_table(struct em_cs_table *cs_table, int cpu)
+{
+	unsigned long cmax = arch_scale_cpu_capacity(NULL, cpu);
+	int max_cap_state = cs_table->nr_cap_states - 1;
+	unsigned long fmax = cs_table->state[max_cap_state].frequency;
+	int i;
+
+	for (i = 0; i < cs_table->nr_cap_states; i++) {
+		u64 cap = (u64)cmax * cs_table->state[i].frequency;
+		do_div(cap, fmax);
+		cs_table->state[i].capacity = (unsigned long)cap;
+	}
+}
+
+static struct em_freq_domain *em_create_fd(cpumask_t *span, int nr_states,
+						struct em_data_callback *cb)
+{
+	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_cs_table *cs_table;
+	struct em_freq_domain *fd;
+
+	if (!cb->active_power)
+		return NULL;
+
+	fd = kzalloc(sizeof(*fd) + cpumask_size(), GFP_KERNEL);
+	if (!fd)
+		return NULL;
+
+	cs_table = alloc_cs_table(nr_states);
+	if (!cs_table)
+		goto free_fd;
+
+	/* Build the list of capacity states for this freq 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 update
+		 * 'power' and 'freq' accordingly.
+		 */
+		ret = cb->active_power(&power, &freq, cpu);
+		if (ret) {
+			pr_err("fd%d: invalid cap. state: %d\n", cpu, ret);
+			goto free_cs_table;
+		}
+
+		/*
+		 * We expect the driver callback to increase the frequency for
+		 * higher capacity states.
+		 */
+		if (freq <= prev_freq) {
+			pr_err("fd%d: non-increasing freq: %lu\n", cpu, freq);
+			goto free_cs_table;
+		}
+
+		/*
+		 * The power returned by active_state() is expected to be in
+		 * milli-watts, and to fit in 16 bits.
+		 */
+		if (power > EM_CPU_MAX_POWER) {
+			pr_err("fd%d: power out of scale: %lu\n", cpu, power);
+			goto free_cs_table;
+		}
+
+		cs_table->state[i].power = power;
+		cs_table->state[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 some of the high
+		 * OPPs are more power efficient than some of the lower ones.
+		 */
+		opp_eff = freq / power;
+		if (opp_eff >= prev_opp_eff)
+			pr_warn("fd%d: hertz/watts ratio non-monotonically "
+				"decreasing: OPP%d >= OPP%d\n", cpu, i, i - 1);
+		prev_opp_eff = opp_eff;
+	}
+	fd_update_cs_table(cs_table, cpu);
+	rcu_assign_pointer(fd->cs_table, cs_table);
+
+	/* Copy the span of the frequency domain */
+	cpumask_copy(to_cpumask(fd->cpus), span);
+
+	return fd;
+
+free_cs_table:
+	free_cs_table(cs_table);
+free_fd:
+	kfree(fd);
+
+	return NULL;
+}
+
+static void rcu_free_cs_table(struct rcu_head *rp)
+{
+	struct em_cs_table *table;
+
+	table = container_of(rp, struct em_cs_table, rcu);
+	free_cs_table(table);
+}
+
+/**
+ * em_rescale_cpu_capacity() - Re-scale capacity values of the Energy Model
+ *
+ * This re-scales the capacity values for all capacity states of all frequency
+ * domains of the Energy Model. This should be used when the capacity values
+ * of the CPUs are updated at run-time, after the EM was registered.
+ */
+void em_rescale_cpu_capacity(void)
+{
+	struct em_cs_table *old_table, *new_table;
+	struct em_freq_domain *fd;
+	int nr_states, cpu;
+
+	mutex_lock(&em_fd_mutex);
+	rcu_read_lock();
+	for_each_possible_cpu(cpu) {
+		/* Re-scale only once per frequency domain. */
+		fd = READ_ONCE(per_cpu(em_data, cpu));
+		if (!fd || cpu != cpumask_first(to_cpumask(fd->cpus)))
+			continue;
+
+		/* Copy the existing table. */
+		old_table = rcu_dereference(fd->cs_table);
+		nr_states = old_table->nr_cap_states;
+		new_table = alloc_cs_table(nr_states);
+		if (!new_table)
+			goto out;
+		memcpy(new_table->state, old_table->state,
+					nr_states * sizeof(*new_table->state));
+
+		/* Re-scale the capacity values of the copy. */
+		fd_update_cs_table(new_table,
+					cpumask_first(to_cpumask(fd->cpus)));
+
+		/* Replace the fd table with the re-scaled version. */
+		rcu_assign_pointer(fd->cs_table, new_table);
+		call_rcu(&old_table->rcu, rcu_free_cs_table);
+	}
+out:
+	rcu_read_unlock();
+	mutex_unlock(&em_fd_mutex);
+}
+EXPORT_SYMBOL_GPL(em_rescale_cpu_capacity);
+
+/**
+ * em_cpu_get() - Return the frequency domain for a CPU
+ * @cpu : CPU to find the frequency domain for
+ *
+ * Return: the frequency domain to which 'cpu' belongs, or NULL if it doesn't
+ * exist.
+ */
+struct em_freq_domain *em_cpu_get(int cpu)
+{
+	return READ_ONCE(per_cpu(em_data, cpu));
+}
+EXPORT_SYMBOL_GPL(em_cpu_get);
+
+/**
+ * em_register_freq_domain() - Register the Energy Model of a frequency domain
+ * @span	: Mask of CPUs in the frequency domain
+ * @nr_states	: Number of capacity states to register
+ * @cb		: Callback functions providing the data of the Energy Model
+ *
+ * Create Energy Model tables for a frequency domain using the callbacks
+ * defined in cb.
+ *
+ * If multiple clients register the same frequency domain, all but the first
+ * registration will be ignored.
+ *
+ * Return 0 on success
+ */
+int em_register_freq_domain(cpumask_t *span, unsigned int nr_states,
+						struct em_data_callback *cb)
+{
+	struct em_freq_domain *fd;
+	int cpu, ret = 0;
+
+	if (!span || !nr_states || !cb)
+		return -EINVAL;
+
+	/*
+	 * Registration of frequency domains needs to be serialized. Since
+	 * em_create_fd() calls into the driver-defined callback functions
+	 * which might sleep, we use a mutex.
+	 */
+	mutex_lock(&em_fd_mutex);
+
+	/* Make sure we don't register again an existing domain. */
+	for_each_cpu(cpu, span) {
+		if (READ_ONCE(per_cpu(em_data, cpu))) {
+			ret = -EEXIST;
+			goto unlock;
+		}
+	}
+
+	/* Create the frequency domain and add it to the Energy Model. */
+	fd = em_create_fd(span, nr_states, cb);
+	if (!fd) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	for_each_cpu(cpu, span)
+		smp_store_release(per_cpu_ptr(&em_data, cpu), fd);
+
+	pr_debug("Created freq domain %*pbl\n", cpumask_pr_args(span));
+unlock:
+	mutex_unlock(&em_fd_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(em_register_freq_domain);
-- 
2.17.1