[PATCH V3 1/6] cpufreq: suspend governors on system suspend/hibernate

[Viresh Kumar <viresh.kumar@linaro.org>]

This patch adds cpufreq callbacks to dpm_{suspend|resume}() for handling
suspend/resume of cpufreq governors. This is required for early suspend and late
resume of governors and cpufreq core.

There are multiple problems that are fixed by this patch:
- Nishanth Menon (TI) found an interesting problem on his platform, OMAP. His board
  wasn't working well with suspend/resume as calls for removing non-boot CPUs
  was turning out into a call to drivers ->target() which then tries to play
  with regulators. But regulators and their I2C bus were already suspended and
  this resulted in a failure. Many platforms have such problems, samsung, tegra,
  etc.. They solved it with driver specific PM notifiers where they used to
  disable their driver's ->target() routine.
- Lan Tianyu (Intel) & Jinhyuk Choi (Broadcom) found another 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 also fixed with this patch as don't
  allow any operation on Governors during suspend/resume now.

Reported-by: Lan Tianyu <tianyu.lan@intel.com>
Reported-by: Nishanth Menon <nm@ti.com>
Reported-by: Jinhyuk Choi <jinchoi@broadcom.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/base/power/main.c |  5 +++++
 drivers/cpufreq/cpufreq.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/cpufreq.h   |  3 +++
 3 files changed, 58 insertions(+)

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 1b41fca..c9fbb9d 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 <linux/timer.h>
 
@@ -789,6 +790,8 @@ void dpm_resume(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
 	dpm_show_time(starttime, state, NULL);
+
+	cpufreq_resume();
 }
 
 /**
@@ -1259,6 +1262,8 @@ int dpm_suspend(pm_message_t state)
 
 	might_sleep();
 
+	cpufreq_suspend();
+
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 	async_error = 0;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 02d534d..b6c7821 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 +1466,48 @@ static struct subsys_interface cpufreq_interface = {
 	.remove_dev	= cpufreq_remove_dev,
 };
 
+/*
+ * Callbacks for suspending/resuming governors as some platforms can't change
+ * frequency after this point in suspend cycle. Because some of the devices
+ * (like: i2c, regulators, etc) they use for changing frequency are suspended
+ * quickly after this point.
+ */
+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 +1810,10 @@ 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) {
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index dc196bb..6d93f91 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -255,6 +255,9 @@ struct cpufreq_driver {
 int cpufreq_register_driver(struct cpufreq_driver *driver_data);
 int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
 
+void cpufreq_suspend(void);
+void cpufreq_resume(void);
+
 const char *cpufreq_get_current_driver(void);
 
 static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy,
-- 
1.7.12.rc2.18.g61b472e