arch_topology: obtain cpu capacity using information from CPPC

Define topology_init_cpu_capacity_cppc() to use highest performance
values from _CPC objects to obtain and set maximum capacity information
for each CPU. acpi_cppc_processor_probe() is a good point at which to
trigger the initialization of CPU (u-arch) capacity values, as at this
point the highest performance values can be obtained from each CPU's
_CPC objects. Architectures can therefore use this functionality
through arch_init_invariance_cppc().

The performance scale used by CPPC is a unified scale for all CPUs in
the system. Therefore, by obtaining the raw highest performance values
from the _CPC objects, and normalizing them on the [0, 1024] capacity
scale, used by the task scheduler, we obtain the CPU capacity of each
CPU.

While an ACPI Notify(0x85) could alert about a change in the highest
performance value, which should in turn retrigger the CPU capacity
computations, this notification is not currently handled by the ACPI
processor driver. When supported, a call to arch_init_invariance_cppc()
would perform the update.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
Tested-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

drivers/base/arch_topology.c

@@ -339,6 +339,46 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu)
 	return !ret;
 }
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+#include <acpi/cppc_acpi.h>
+
+void topology_init_cpu_capacity_cppc(void)
+{
+	struct cppc_perf_caps perf_caps;
+	int cpu;
+
+	if (likely(acpi_disabled || !acpi_cpc_valid()))
+		return;
+
+	raw_capacity = kcalloc(num_possible_cpus(), sizeof(*raw_capacity),
+			       GFP_KERNEL);
+	if (!raw_capacity)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		if (!cppc_get_perf_caps(cpu, &perf_caps) &&
+		    (perf_caps.highest_perf >= perf_caps.nominal_perf) &&
+		    (perf_caps.highest_perf >= perf_caps.lowest_perf)) {
+			raw_capacity[cpu] = perf_caps.highest_perf;
+			pr_debug("cpu_capacity: CPU%d cpu_capacity=%u (raw).\n",
+				 cpu, raw_capacity[cpu]);
+			continue;
+		}
+
+		pr_err("cpu_capacity: CPU%d missing/invalid highest performance.\n", cpu);
+		pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
+		goto exit;
+	}
+
+	topology_normalize_cpu_scale();
+	schedule_work(&update_topology_flags_work);
+	pr_debug("cpu_capacity: cpu_capacity initialization done\n");
+
+exit:
+	free_raw_capacity();
+}
+#endif
+
 #ifdef CONFIG_CPU_FREQ
 static cpumask_var_t cpus_to_visit;
 static void parsing_done_workfn(struct work_struct *work);
@@ -387,9 +427,8 @@ static int __init register_cpufreq_notifier(void)
 	int ret;
 
 	/*
-	 * on ACPI-based systems we need to use the default cpu capacity
-	 * until we have the necessary code to parse the cpu capacity, so
-	 * skip registering cpufreq notifier.
+	 * On ACPI-based systems skip registering cpufreq notifier as cpufreq
+	 * information is not needed for cpu capacity initialization.
 	 */
 	if (!acpi_disabled || !raw_capacity)
 		return -EINVAL;

include/linux/arch_topology.h

@@ -11,6 +11,10 @@
 void topology_normalize_cpu_scale(void);
 int topology_update_cpu_topology(void);
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+void topology_init_cpu_capacity_cppc(void);
+#endif
+
 struct device_node;
 bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu);