cpufreq: suspend governors on system suspend/hibernate

This patch adds cpufreq suspend/resume calls to dpm_{suspend|resume}_noirq()
for handling suspend/resume of cpufreq governors.

Lan Tianyu (Intel) & Jinhyuk Choi (Broadcom) found anr issue where
tunables configuration for clusters/sockets with non-boot CPUs was
getting lost after suspend/resume, as we were notifying governors
with CPUFREQ_GOV_POLICY_EXIT on removal of the last cpu for that
policy and so deallocating memory for tunables. This is fixed by
this patch as we don't allow any operation on governors after
device suspend and before device resume now.

Reported-and-tested-by: Lan Tianyu <tianyu.lan@intel.com>
Reported-by: Jinhyuk Choi <jinchoi@broadcom.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
[rjw: Changelog, minor cleanups]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

2 files changed, 46 insertions, 0 deletions

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 9f098a82cf04..10c3510d72a9 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -29,6 +29,7 @@
 #include <linux/async.h>
 #include <linux/suspend.h>
 #include <trace/events/power.h>
+#include <linux/cpufreq.h>
 #include <linux/cpuidle.h>
 #include "../base.h"
 #include "power.h"
@@ -473,6 +474,7 @@ static void dpm_resume_noirq(pm_message_t state)
 	dpm_show_time(starttime, state, "noirq");
 	resume_device_irqs();
 	cpuidle_resume();
+	cpufreq_resume();
 }
 
 /**
@@ -885,6 +887,7 @@ static int dpm_suspend_noirq(pm_message_t state)
 	ktime_t starttime = ktime_get();
 	int error = 0;
 
+	cpufreq_suspend();
 	cpuidle_pause();
 	suspend_device_irqs();
 	mutex_lock(&dpm_list_mtx);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 02d534da22dd..606224a8abc2 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/tick.h>
 #include <trace/events/power.h>
@@ -47,6 +48,9 @@ static LIST_HEAD(cpufreq_policy_list);
 static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
 #endif
 
+/* Flag to suspend/resume CPUFreq governors */
+static bool cpufreq_suspended;
+
 static inline bool has_target(void)
 {
 	return cpufreq_driver->target_index || cpufreq_driver->target;
@@ -1462,6 +1466,41 @@ static struct subsys_interface cpufreq_interface = {
 	.remove_dev	= cpufreq_remove_dev,
 };
 
+void cpufreq_suspend(void)
+{
+	struct cpufreq_policy *policy;
+
+	if (!has_target())
+		return;
+
+	pr_debug("%s: Suspending Governors\n", __func__);
+
+	list_for_each_entry(policy, &cpufreq_policy_list, policy_list)
+		if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP))
+			pr_err("%s: Failed to stop governor for policy: %p\n",
+				__func__, policy);
+
+	cpufreq_suspended = true;
+}
+
+void cpufreq_resume(void)
+{
+	struct cpufreq_policy *policy;
+
+	if (!has_target())
+		return;
+
+	pr_debug("%s: Resuming Governors\n", __func__);
+
+	cpufreq_suspended = false;
+
+	list_for_each_entry(policy, &cpufreq_policy_list, policy_list)
+		if (__cpufreq_governor(policy, CPUFREQ_GOV_START)
+		    || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))
+			pr_err("%s: Failed to start governor for policy: %p\n",
+				__func__, policy);
+}
+
 /**
  * cpufreq_bp_suspend - Prepare the boot CPU for system suspend.
  *
@@ -1764,6 +1803,10 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 	struct cpufreq_governor *gov = NULL;
 #endif
 
+	/* Don't start any governor operations if we are entering suspend */
+	if (cpufreq_suspended)
+		return 0;
+
 	if (policy->governor->max_transition_latency &&
 	    policy->cpuinfo.transition_latency >
 	    policy->governor->max_transition_latency) {