arm64: parse cpu capacity-dmips-mhz from DT

With the introduction of cpu capacity-dmips-mhz bindings, CPU capacities
can now be calculated from values extracted from DT and information
coming from cpufreq. Add parsing of DT information at boot time, and
complement it with cpufreq information. Also, store such information
using per CPU variables, as we do for arm.

Caveat: the information provided by this patch will start to be used in
the future. We need to #define arch_scale_cpu_capacity to something
provided in arch, so that scheduler's default implementation (which gets
used if arch_scale_cpu_capacity is not defined) is overwritten.

Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/kernel/topology.c

@@ -19,10 +19,162 @@
 #include <linux/nodemask.h>
 #include <linux/of.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/cpufreq.h>
 
 #include <asm/cputype.h>
 #include <asm/topology.h>
 
+static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
+
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(cpu_scale, cpu);
+}
+
+static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
+{
+	per_cpu(cpu_scale, cpu) = capacity;
+}
+
+static u32 capacity_scale;
+static u32 *raw_capacity;
+static bool cap_parsing_failed;
+
+static void __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
+{
+	int ret;
+	u32 cpu_capacity;
+
+	if (cap_parsing_failed)
+		return;
+
+	ret = of_property_read_u32(cpu_node,
+				   "capacity-dmips-mhz",
+				   &cpu_capacity);
+	if (!ret) {
+		if (!raw_capacity) {
+			raw_capacity = kcalloc(num_possible_cpus(),
+					       sizeof(*raw_capacity),
+					       GFP_KERNEL);
+			if (!raw_capacity) {
+				pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
+				cap_parsing_failed = true;
+				return;
+			}
+		}
+		capacity_scale = max(cpu_capacity, capacity_scale);
+		raw_capacity[cpu] = cpu_capacity;
+		pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
+			cpu_node->full_name, raw_capacity[cpu]);
+	} else {
+		if (raw_capacity) {
+			pr_err("cpu_capacity: missing %s raw capacity\n",
+				cpu_node->full_name);
+			pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
+		}
+		cap_parsing_failed = true;
+		kfree(raw_capacity);
+	}
+}
+
+static void normalize_cpu_capacity(void)
+{
+	u64 capacity;
+	int cpu;
+
+	if (!raw_capacity || cap_parsing_failed)
+		return;
+
+	pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
+	for_each_possible_cpu(cpu) {
+		pr_debug("cpu_capacity: cpu=%d raw_capacity=%u\n",
+			 cpu, raw_capacity[cpu]);
+		capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
+			/ capacity_scale;
+		set_capacity_scale(cpu, capacity);
+		pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
+			cpu, arch_scale_cpu_capacity(NULL, cpu));
+	}
+}
+
+#ifdef CONFIG_CPU_FREQ
+static cpumask_var_t cpus_to_visit;
+static bool cap_parsing_done;
+static void parsing_done_workfn(struct work_struct *work);
+static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
+
+static int
+init_cpu_capacity_callback(struct notifier_block *nb,
+			   unsigned long val,
+			   void *data)
+{
+	struct cpufreq_policy *policy = data;
+	int cpu;
+
+	if (cap_parsing_failed || cap_parsing_done)
+		return 0;
+
+	switch (val) {
+	case CPUFREQ_NOTIFY:
+		pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
+				cpumask_pr_args(policy->related_cpus),
+				cpumask_pr_args(cpus_to_visit));
+		cpumask_andnot(cpus_to_visit,
+			       cpus_to_visit,
+			       policy->related_cpus);
+		for_each_cpu(cpu, policy->related_cpus) {
+			raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
+					    policy->cpuinfo.max_freq / 1000UL;
+			capacity_scale = max(raw_capacity[cpu], capacity_scale);
+		}
+		if (cpumask_empty(cpus_to_visit)) {
+			normalize_cpu_capacity();
+			kfree(raw_capacity);
+			pr_debug("cpu_capacity: parsing done\n");
+			cap_parsing_done = true;
+			schedule_work(&parsing_done_work);
+		}
+	}
+	return 0;
+}
+
+static struct notifier_block init_cpu_capacity_notifier = {
+	.notifier_call = init_cpu_capacity_callback,
+};
+
+static int __init register_cpufreq_notifier(void)
+{
+	if (cap_parsing_failed)
+		return -EINVAL;
+
+	if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
+		pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
+		return -ENOMEM;
+	}
+	cpumask_copy(cpus_to_visit, cpu_possible_mask);
+
+	return cpufreq_register_notifier(&init_cpu_capacity_notifier,
+					 CPUFREQ_POLICY_NOTIFIER);
+}
+core_initcall(register_cpufreq_notifier);
+
+static void parsing_done_workfn(struct work_struct *work)
+{
+	cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
+					 CPUFREQ_POLICY_NOTIFIER);
+}
+
+#else
+static int __init free_raw_capacity(void)
+{
+	kfree(raw_capacity);
+
+	return 0;
+}
+core_initcall(free_raw_capacity);
+#endif
+
 static int __init get_cpu_for_node(struct device_node *node)
 {
 	struct device_node *cpu_node;
@@ -34,6 +186,7 @@ static int __init get_cpu_for_node(struct device_node *node)
 
 	for_each_possible_cpu(cpu) {
 		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
+			parse_cpu_capacity(cpu_node, cpu);
 			of_node_put(cpu_node);
 			return cpu;
 		}
@@ -178,13 +331,17 @@ static int __init parse_dt_topology(void)
 	 * cluster with restricted subnodes.
 	 */
 	map = of_get_child_by_name(cn, "cpu-map");
-	if (!map)
+	if (!map) {
+		cap_parsing_failed = true;
 		goto out;
+	}
 
 	ret = parse_cluster(map, 0);
 	if (ret != 0)
 		goto out_map;
 
+	normalize_cpu_capacity();
+
 	/*
 	 * Check that all cores are in the topology; the SMP code will
 	 * only mark cores described in the DT as possible.