Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Introduce "Energy Aware Scheduling" - by Quentin Perret.

     This is a coherent topology description of CPUs in cooperation with
     the PM subsystem, with the goal to schedule more energy-efficiently
     on asymetric SMP platform - such as waking up tasks to the more
     energy-efficient CPUs first, as long as the system isn't
     oversubscribed.

     For details of the design, see:

        https://lore.kernel.org/lkml/20180724122521.22109-1-quentin.perret@arm.com/

   - Misc cleanups and smaller enhancements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  sched/fair: Select an energy-efficient CPU on task wake-up
  sched/fair: Introduce an energy estimation helper function
  sched/fair: Add over-utilization/tipping point indicator
  sched/fair: Clean-up update_sg_lb_stats parameters
  sched/toplogy: Introduce the 'sched_energy_present' static key
  sched/topology: Make Energy Aware Scheduling depend on schedutil
  sched/topology: Disable EAS on inappropriate platforms
  sched/topology: Add lowest CPU asymmetry sched_domain level pointer
  sched/topology: Reference the Energy Model of CPUs when available
  PM: Introduce an Energy Model management framework
  sched/cpufreq: Prepare schedutil for Energy Aware Scheduling
  sched/topology: Relocate arch_scale_cpu_capacity() to the internal header
  sched/core: Remove unnecessary unlikely() in push_*_task()
  sched/topology: Remove the ::smt_gain field from 'struct sched_domain'
  sched: Fix various typos in comments
  sched/core: Clean up the #ifdef block in add_nr_running()
  sched/fair: Make some variables static
  sched/core: Create task_has_idle_policy() helper
  sched/fair: Add lsub_positive() and use it consistently
  sched/fair: Mask UTIL_AVG_UNCHANGED usages
  ...

3 files changed, 218 insertions, 0 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 3a6c2f87699e..f8fe57d1022e 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -298,3 +298,18 @@ 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..d9dc2c38764a
--- /dev/null
+++ b/kernel/power/energy_model.c
@@ -0,0 +1,201 @@
+// 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 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 struct em_perf_domain *em_create_pd(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_cap_state *table;
+	struct em_perf_domain *pd;
+	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;
+
+	/* Build the list of capacity 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
+		 * 'power' and 'freq' accordingly.
+		 */
+		ret = cb->active_power(&power, &freq, cpu);
+		if (ret) {
+			pr_err("pd%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("pd%d: non-increasing freq: %lu\n", cpu, freq);
+			goto free_cs_table;
+		}
+
+		/*
+		 * The power returned by active_state() is expected to be
+		 * positive, in milli-watts and to fit into 16 bits.
+		 */
+		if (!power || power > EM_CPU_MAX_POWER) {
+			pr_err("pd%d: invalid power: %lu\n", cpu, power);
+			goto free_cs_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. */
+	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);
+	}
+
+	pd->table = table;
+	pd->nr_cap_states = nr_states;
+	cpumask_copy(to_cpumask(pd->cpus), span);
+
+	return pd;
+
+free_cs_table:
+	kfree(table);
+free_pd:
+	kfree(pd);
+
+	return NULL;
+}
+
+/**
+ * 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
+ * exist.
+ */
+struct em_perf_domain *em_cpu_get(int cpu)
+{
+	return READ_ONCE(per_cpu(em_data, cpu));
+}
+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
+ * @cb		: Callback functions providing the data of the Energy Model
+ *
+ * Create Energy Model tables for a performance domain using the callbacks
+ * defined in cb.
+ *
+ * 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)
+{
+	unsigned long cap, prev_cap = 0;
+	struct em_perf_domain *pd;
+	int cpu, ret = 0;
+
+	if (!span || !nr_states || !cb)
+		return -EINVAL;
+
+	/*
+	 * Use a mutex to serialize the registration of performance domains and
+	 * let the driver-defined callback functions sleep.
+	 */
+	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;
+		}
+
+		/*
+		 * All CPUs of a domain must have the same micro-architecture
+		 * since they all share the same table.
+		 */
+		cap = arch_scale_cpu_capacity(NULL, cpu);
+		if (prev_cap && prev_cap != cap) {
+			pr_err("CPUs of %*pbl must have the same capacity\n",
+							cpumask_pr_args(span));
+			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;
+		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);
+	}
+
+	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);