cpufreq/sched: Move cpufreq-specific EAS checks to cpufreq

Doing cpufreq-specific EAS checks that require accessing policy
internals directly from sched_is_eas_possible() is a bit unfortunate,
so introduce cpufreq_ready_for_eas() in cpufreq, move those checks
into that new function and make sched_is_eas_possible() call it.

While at it, address a possible race between the EAS governor check
and governor change by doing the former under the policy rwsem.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Tested-by: Christian Loehle <christian.loehle@arm.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://patch.msgid.link/2317800.iZASKD2KPV@rjwysocki.net

3 files changed, 39 insertions, 20 deletions

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 21fa733a2fe8..731ecfc178d8 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -3056,6 +3056,38 @@ static int __init cpufreq_core_init(void)
 
 	return 0;
 }
+
+static bool cpufreq_policy_is_good_for_eas(unsigned int cpu)
+{
+	struct cpufreq_policy *policy __free(put_cpufreq_policy);
+
+	policy = cpufreq_cpu_get(cpu);
+	if (!policy) {
+		pr_debug("cpufreq policy not set for CPU: %d\n", cpu);
+		return false;
+	}
+
+	guard(cpufreq_policy_read)(policy);
+
+	return sugov_is_governor(policy);
+}
+
+bool cpufreq_ready_for_eas(const struct cpumask *cpu_mask)
+{
+	unsigned int cpu;
+
+	/* Do not attempt EAS if schedutil is not being used. */
+	for_each_cpu(cpu, cpu_mask) {
+		if (!cpufreq_policy_is_good_for_eas(cpu)) {
+			pr_debug("rd %*pbl: schedutil is mandatory for EAS\n",
+				 cpumask_pr_args(cpu_mask));
+			return false;
+		}
+	}
+
+	return true;
+}
+
 module_param(off, int, 0444);
 module_param_string(default_governor, default_governor, CPUFREQ_NAME_LEN, 0444);
 core_initcall(cpufreq_core_init);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1d2c6c6d8952..95f3807c8c55 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1237,6 +1237,8 @@ void cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency);
 
+bool cpufreq_ready_for_eas(const struct cpumask *cpu_mask);
+
 static inline void cpufreq_register_em_with_opp(struct cpufreq_policy *policy)
 {
 	dev_pm_opp_of_register_em(get_cpu_device(policy->cpu),
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 902d37f922b4..580c28fed539 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -212,8 +212,6 @@ static bool sched_energy_update;
 static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
 {
 	bool any_asym_capacity = false;
-	struct cpufreq_policy *policy;
-	bool policy_is_ready;
 	int i;
 
 	/* EAS is enabled for asymmetric CPU capacity topologies. */
@@ -248,25 +246,12 @@ static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
 		return false;
 	}
 
-	/* Do not attempt EAS if schedutil is not being used. */
-	for_each_cpu(i, cpu_mask) {
-		policy = cpufreq_cpu_get(i);
-		if (!policy) {
-			if (sched_debug()) {
-				pr_info("rd %*pbl: Checking EAS, cpufreq policy not set for CPU: %d",
-					cpumask_pr_args(cpu_mask), i);
-			}
-			return false;
-		}
-		policy_is_ready = sugov_is_governor(policy);
-		cpufreq_cpu_put(policy);
-		if (!policy_is_ready) {
-			if (sched_debug()) {
-				pr_info("rd %*pbl: Checking EAS, schedutil is mandatory\n",
-					cpumask_pr_args(cpu_mask));
-			}
-			return false;
+	if (!cpufreq_ready_for_eas(cpu_mask)) {
+		if (sched_debug()) {
+			pr_info("rd %*pbl: Checking EAS: cpufreq is not ready\n",
+				cpumask_pr_args(cpu_mask));
 		}
+		return false;
 	}
 
 	return true;