1 files changed, 293 insertions, 257 deletions

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index cb003a6b72c8..abda6609d3e7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -26,7 +26,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/syscore_ops.h>
+#include <linux/suspend.h>
 #include <linux/tick.h>
 #include <trace/events/power.h>
 
@@ -42,10 +42,11 @@ static DEFINE_RWLOCK(cpufreq_driver_lock);
 DEFINE_MUTEX(cpufreq_governor_lock);
 static LIST_HEAD(cpufreq_policy_list);
 
-#ifdef CONFIG_HOTPLUG_CPU
 /* This one keeps track of the previously set governor of a removed CPU */
 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)
 {
@@ -181,8 +182,8 @@ unsigned int cpufreq_generic_get(unsigned int cpu)
 	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
 	if (!policy || IS_ERR(policy->clk)) {
-		pr_err("%s: No %s associated to cpu: %d\n", __func__,
-				policy ? "clk" : "policy", cpu);
+		pr_err("%s: No %s associated to cpu: %d\n",
+		       __func__, policy ? "clk" : "policy", cpu);
 		return 0;
 	}
 
@@ -190,6 +191,12 @@ unsigned int cpufreq_generic_get(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_get);
 
+/* Only for cpufreq core internal use */
+struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
+{
+	return per_cpu(cpufreq_cpu_data, cpu);
+}
+
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = NULL;
@@ -254,15 +261,14 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
 	if (!l_p_j_ref_freq) {
 		l_p_j_ref = loops_per_jiffy;
 		l_p_j_ref_freq = ci->old;
-		pr_debug("saving %lu as reference value for loops_per_jiffy; "
-			"freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq);
+		pr_debug("saving %lu as reference value for loops_per_jiffy; freq is %u kHz\n",
+			 l_p_j_ref, l_p_j_ref_freq);
 	}
-	if ((val == CPUFREQ_POSTCHANGE && ci->old != ci->new) ||
-	    (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) {
+	if (val == CPUFREQ_POSTCHANGE && ci->old != ci->new) {
 		loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq,
 								ci->new);
-		pr_debug("scaling loops_per_jiffy to %lu "
-			"for frequency %u kHz\n", loops_per_jiffy, ci->new);
+		pr_debug("scaling loops_per_jiffy to %lu for frequency %u kHz\n",
+			 loops_per_jiffy, ci->new);
 	}
 }
 #else
@@ -282,7 +288,7 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
 
 	freqs->flags = cpufreq_driver->flags;
 	pr_debug("notification %u of frequency transition to %u kHz\n",
-		state, freqs->new);
+		 state, freqs->new);
 
 	switch (state) {
 
@@ -294,9 +300,8 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
 		if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
 			if ((policy) && (policy->cpu == freqs->cpu) &&
 			    (policy->cur) && (policy->cur != freqs->old)) {
-				pr_debug("Warning: CPU frequency is"
-					" %u, cpufreq assumed %u kHz.\n",
-					freqs->old, policy->cur);
+				pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
+					 freqs->old, policy->cur);
 				freqs->old = policy->cur;
 			}
 		}
@@ -307,8 +312,8 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
 
 	case CPUFREQ_POSTCHANGE:
 		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
-		pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new,
-			(unsigned long)freqs->cpu);
+		pr_debug("FREQ: %lu - CPU: %lu\n",
+			 (unsigned long)freqs->new, (unsigned long)freqs->cpu);
 		trace_cpu_frequency(freqs->new, freqs->cpu);
 		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
 				CPUFREQ_POSTCHANGE, freqs);
@@ -326,16 +331,15 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
  * function. It is called twice on all CPU frequency changes that have
  * external effects.
  */
-void cpufreq_notify_transition(struct cpufreq_policy *policy,
+static void cpufreq_notify_transition(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs, unsigned int state)
 {
 	for_each_cpu(freqs->cpu, policy->cpus)
 		__cpufreq_notify_transition(policy, freqs, state);
 }
-EXPORT_SYMBOL_GPL(cpufreq_notify_transition);
 
 /* Do post notifications when there are chances that transition has failed */
-void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
+static void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs, int transition_failed)
 {
 	cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE);
@@ -346,13 +350,47 @@ void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
 	cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE);
 	cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE);
 }
-EXPORT_SYMBOL_GPL(cpufreq_notify_post_transition);
+
+void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
+		struct cpufreq_freqs *freqs)
+{
+wait:
+	wait_event(policy->transition_wait, !policy->transition_ongoing);
+
+	spin_lock(&policy->transition_lock);
+
+	if (unlikely(policy->transition_ongoing)) {
+		spin_unlock(&policy->transition_lock);
+		goto wait;
+	}
+
+	policy->transition_ongoing = true;
+
+	spin_unlock(&policy->transition_lock);
+
+	cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE);
+}
+EXPORT_SYMBOL_GPL(cpufreq_freq_transition_begin);
+
+void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
+		struct cpufreq_freqs *freqs, int transition_failed)
+{
+	if (unlikely(WARN_ON(!policy->transition_ongoing)))
+		return;
+
+	cpufreq_notify_post_transition(policy, freqs, transition_failed);
+
+	policy->transition_ongoing = false;
+
+	wake_up(&policy->transition_wait);
+}
+EXPORT_SYMBOL_GPL(cpufreq_freq_transition_end);
 
 
 /*********************************************************************
  *                          SYSFS INTERFACE                          *
  *********************************************************************/
-ssize_t show_boost(struct kobject *kobj,
+static ssize_t show_boost(struct kobject *kobj,
 				 struct attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled);
@@ -368,13 +406,13 @@ static ssize_t store_boost(struct kobject *kobj, struct attribute *attr,
 		return -EINVAL;
 
 	if (cpufreq_boost_trigger_state(enable)) {
-		pr_err("%s: Cannot %s BOOST!\n", __func__,
-		       enable ? "enable" : "disable");
+		pr_err("%s: Cannot %s BOOST!\n",
+		       __func__, enable ? "enable" : "disable");
 		return -EINVAL;
 	}
 
-	pr_debug("%s: cpufreq BOOST %s\n", __func__,
-		 enable ? "enabled" : "disabled");
+	pr_debug("%s: cpufreq BOOST %s\n",
+		 __func__, enable ? "enabled" : "disabled");
 
 	return count;
 }
@@ -879,18 +917,25 @@ err_out_kobj_put:
 
 static void cpufreq_init_policy(struct cpufreq_policy *policy)
 {
+	struct cpufreq_governor *gov = NULL;
 	struct cpufreq_policy new_policy;
 	int ret = 0;
 
 	memcpy(&new_policy, policy, sizeof(*policy));
 
+	/* Update governor of new_policy to the governor used before hotplug */
+	gov = __find_governor(per_cpu(cpufreq_cpu_governor, policy->cpu));
+	if (gov)
+		pr_debug("Restoring governor %s for cpu %d\n",
+				policy->governor->name, policy->cpu);
+	else
+		gov = CPUFREQ_DEFAULT_GOVERNOR;
+
+	new_policy.governor = gov;
+
 	/* Use the default policy if its valid. */
 	if (cpufreq_driver->setpolicy)
-		cpufreq_parse_governor(policy->governor->name,
-					&new_policy.policy, NULL);
-
-	/* assure that the starting sequence is run in cpufreq_set_policy */
-	policy->governor = NULL;
+		cpufreq_parse_governor(gov->name, &new_policy.policy, NULL);
 
 	/* set default policy */
 	ret = cpufreq_set_policy(policy, &new_policy);
@@ -927,8 +972,11 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 	up_write(&policy->rwsem);
 
 	if (has_target()) {
-		if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) ||
-			(ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) {
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		if (!ret)
+			ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+
+		if (ret) {
 			pr_err("%s: Failed to start governor\n", __func__);
 			return ret;
 		}
@@ -949,6 +997,8 @@ static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
 
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
+	policy->governor = NULL;
+
 	return policy;
 }
 
@@ -968,6 +1018,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)
 
 	INIT_LIST_HEAD(&policy->policy_list);
 	init_rwsem(&policy->rwsem);
+	spin_lock_init(&policy->transition_lock);
+	init_waitqueue_head(&policy->transition_wait);
 
 	return policy;
 
@@ -1022,21 +1074,19 @@ static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
 
 	up_write(&policy->rwsem);
 
-	cpufreq_frequency_table_update_policy_cpu(policy);
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 			CPUFREQ_UPDATE_POLICY_CPU, policy);
 }
 
-static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
-			     bool frozen)
+static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 {
 	unsigned int j, cpu = dev->id;
 	int ret = -ENOMEM;
 	struct cpufreq_policy *policy;
 	unsigned long flags;
+	bool recover_policy = cpufreq_suspended;
 #ifdef CONFIG_HOTPLUG_CPU
 	struct cpufreq_policy *tpolicy;
-	struct cpufreq_governor *gov;
 #endif
 
 	if (cpu_is_offline(cpu))
@@ -1075,9 +1125,9 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 	 * Restore the saved policy when doing light-weight init and fall back
 	 * to the full init if that fails.
 	 */
-	policy = frozen ? cpufreq_policy_restore(cpu) : NULL;
+	policy = recover_policy ? cpufreq_policy_restore(cpu) : NULL;
 	if (!policy) {
-		frozen = false;
+		recover_policy = false;
 		policy = cpufreq_policy_alloc();
 		if (!policy)
 			goto nomem_out;
@@ -1089,12 +1139,11 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 	 * the creation of a brand new one. So we need to perform this update
 	 * by invoking update_policy_cpu().
 	 */
-	if (frozen && cpu != policy->cpu)
+	if (recover_policy && cpu != policy->cpu)
 		update_policy_cpu(policy, cpu);
 	else
 		policy->cpu = cpu;
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
 
 	init_completion(&policy->kobj_unregister);
@@ -1109,12 +1158,27 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 		goto err_set_policy_cpu;
 	}
 
+	/* related cpus should atleast have policy->cpus */
+	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
+
+	/*
+	 * affected cpus must always be the one, which are online. We aren't
+	 * managing offline cpus here.
+	 */
+	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
+
+	if (!recover_policy) {
+		policy->user_policy.min = policy->min;
+		policy->user_policy.max = policy->max;
+	}
+
+	down_write(&policy->rwsem);
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	for_each_cpu(j, policy->cpus)
 		per_cpu(cpufreq_cpu_data, j) = policy;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	if (cpufreq_driver->get) {
+	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
 		policy->cur = cpufreq_driver->get(policy->cpu);
 		if (!policy->cur) {
 			pr_err("%s: ->get() failed\n", __func__);
@@ -1162,33 +1226,10 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 		}
 	}
 
-	/* related cpus should atleast have policy->cpus */
-	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
-
-	/*
-	 * affected cpus must always be the one, which are online. We aren't
-	 * managing offline cpus here.
-	 */
-	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
-
-	if (!frozen) {
-		policy->user_policy.min = policy->min;
-		policy->user_policy.max = policy->max;
-	}
-
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				     CPUFREQ_START, policy);
 
-#ifdef CONFIG_HOTPLUG_CPU
-	gov = __find_governor(per_cpu(cpufreq_cpu_governor, cpu));
-	if (gov) {
-		policy->governor = gov;
-		pr_debug("Restoring governor %s for cpu %d\n",
-		       policy->governor->name, cpu);
-	}
-#endif
-
-	if (!frozen) {
+	if (!recover_policy) {
 		ret = cpufreq_add_dev_interface(policy, dev);
 		if (ret)
 			goto err_out_unregister;
@@ -1202,10 +1243,11 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 
 	cpufreq_init_policy(policy);
 
-	if (!frozen) {
+	if (!recover_policy) {
 		policy->user_policy.policy = policy->policy;
 		policy->user_policy.governor = policy->governor;
 	}
+	up_write(&policy->rwsem);
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
 	up_read(&cpufreq_rwsem);
@@ -1224,7 +1266,7 @@ err_get_freq:
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 err_set_policy_cpu:
-	if (frozen) {
+	if (recover_policy) {
 		/* Do not leave stale fallback data behind. */
 		per_cpu(cpufreq_cpu_data_fallback, cpu) = NULL;
 		cpufreq_policy_put_kobj(policy);
@@ -1248,7 +1290,7 @@ nomem_out:
  */
 static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 {
-	return __cpufreq_add_dev(dev, sif, false);
+	return __cpufreq_add_dev(dev, sif);
 }
 
 static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,
@@ -1263,7 +1305,7 @@ static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,
 	sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
 	ret = kobject_move(&policy->kobj, &cpu_dev->kobj);
 	if (ret) {
-		pr_err("%s: Failed to move kobj: %d", __func__, ret);
+		pr_err("%s: Failed to move kobj: %d\n", __func__, ret);
 
 		down_write(&policy->rwsem);
 		cpumask_set_cpu(old_cpu, policy->cpus);
@@ -1279,8 +1321,7 @@ static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,
 }
 
 static int __cpufreq_remove_dev_prepare(struct device *dev,
-					struct subsys_interface *sif,
-					bool frozen)
+					struct subsys_interface *sif)
 {
 	unsigned int cpu = dev->id, cpus;
 	int new_cpu, ret;
@@ -1294,7 +1335,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 	policy = per_cpu(cpufreq_cpu_data, cpu);
 
 	/* Save the policy somewhere when doing a light-weight tear-down */
-	if (frozen)
+	if (cpufreq_suspended)
 		per_cpu(cpufreq_cpu_data_fallback, cpu) = policy;
 
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
@@ -1312,11 +1353,9 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 		}
 	}
 
-#ifdef CONFIG_HOTPLUG_CPU
 	if (!cpufreq_driver->setpolicy)
 		strncpy(per_cpu(cpufreq_cpu_governor, cpu),
 			policy->governor->name, CPUFREQ_NAME_LEN);
-#endif
 
 	down_read(&policy->rwsem);
 	cpus = cpumask_weight(policy->cpus);
@@ -1329,19 +1368,19 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 		if (new_cpu >= 0) {
 			update_policy_cpu(policy, new_cpu);
 
-			if (!frozen) {
+			if (!cpufreq_suspended)
 				pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
-						__func__, new_cpu, cpu);
-			}
+					 __func__, new_cpu, cpu);
 		}
+	} else if (cpufreq_driver->stop_cpu && cpufreq_driver->setpolicy) {
+		cpufreq_driver->stop_cpu(policy);
 	}
 
 	return 0;
 }
 
 static int __cpufreq_remove_dev_finish(struct device *dev,
-				       struct subsys_interface *sif,
-				       bool frozen)
+				       struct subsys_interface *sif)
 {
 	unsigned int cpu = dev->id, cpus;
 	int ret;
@@ -1371,12 +1410,12 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 					CPUFREQ_GOV_POLICY_EXIT);
 			if (ret) {
 				pr_err("%s: Failed to exit governor\n",
-						__func__);
+				       __func__);
 				return ret;
 			}
 		}
 
-		if (!frozen)
+		if (!cpufreq_suspended)
 			cpufreq_policy_put_kobj(policy);
 
 		/*
@@ -1392,16 +1431,16 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 		list_del(&policy->policy_list);
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-		if (!frozen)
+		if (!cpufreq_suspended)
 			cpufreq_policy_free(policy);
-	} else {
-		if (has_target()) {
-			if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) ||
-					(ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) {
-				pr_err("%s: Failed to start governor\n",
-						__func__);
-				return ret;
-			}
+	} else if (has_target()) {
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		if (!ret)
+			ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+
+		if (ret) {
+			pr_err("%s: Failed to start governor\n", __func__);
+			return ret;
 		}
 	}
 
@@ -1422,10 +1461,10 @@ static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	if (cpu_is_offline(cpu))
 		return 0;
 
-	ret = __cpufreq_remove_dev_prepare(dev, sif, false);
+	ret = __cpufreq_remove_dev_prepare(dev, sif);
 
 	if (!ret)
-		ret = __cpufreq_remove_dev_finish(dev, sif, false);
+		ret = __cpufreq_remove_dev_finish(dev, sif);
 
 	return ret;
 }
@@ -1456,8 +1495,8 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq,
 	struct cpufreq_freqs freqs;
 	unsigned long flags;
 
-	pr_debug("Warning: CPU frequency out of sync: cpufreq and timing "
-	       "core thinks of %u, is %u kHz.\n", old_freq, new_freq);
+	pr_debug("Warning: CPU frequency out of sync: cpufreq and timing core thinks of %u, is %u kHz\n",
+		 old_freq, new_freq);
 
 	freqs.old = old_freq;
 	freqs.new = new_freq;
@@ -1466,8 +1505,8 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq,
 	policy = per_cpu(cpufreq_cpu_data, cpu);
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
-	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
+	cpufreq_freq_transition_begin(policy, &freqs);
+	cpufreq_freq_transition_end(policy, &freqs, 0);
 }
 
 /**
@@ -1546,23 +1585,16 @@ static unsigned int __cpufreq_get(unsigned int cpu)
  */
 unsigned int cpufreq_get(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	unsigned int ret_freq = 0;
 
-	if (cpufreq_disabled() || !cpufreq_driver)
-		return -ENOENT;
-
-	BUG_ON(!policy);
-
-	if (!down_read_trylock(&cpufreq_rwsem))
-		return 0;
-
-	down_read(&policy->rwsem);
-
-	ret_freq = __cpufreq_get(cpu);
+	if (policy) {
+		down_read(&policy->rwsem);
+		ret_freq = __cpufreq_get(cpu);
+		up_read(&policy->rwsem);
 
-	up_read(&policy->rwsem);
-	up_read(&cpufreq_rwsem);
+		cpufreq_cpu_put(policy);
+	}
 
 	return ret_freq;
 }
@@ -1575,83 +1607,103 @@ static struct subsys_interface cpufreq_interface = {
 	.remove_dev	= cpufreq_remove_dev,
 };
 
+/*
+ * In case platform wants some specific frequency to be configured
+ * during suspend..
+ */
+int cpufreq_generic_suspend(struct cpufreq_policy *policy)
+{
+	int ret;
+
+	if (!policy->suspend_freq) {
+		pr_err("%s: suspend_freq can't be zero\n", __func__);
+		return -EINVAL;
+	}
+
+	pr_debug("%s: Setting suspend-freq: %u\n", __func__,
+			policy->suspend_freq);
+
+	ret = __cpufreq_driver_target(policy, policy->suspend_freq,
+			CPUFREQ_RELATION_H);
+	if (ret)
+		pr_err("%s: unable to set suspend-freq: %u. err: %d\n",
+				__func__, policy->suspend_freq, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL(cpufreq_generic_suspend);
+
 /**
- * cpufreq_bp_suspend - Prepare the boot CPU for system suspend.
+ * cpufreq_suspend() - Suspend CPUFreq governors
  *
- * This function is only executed for the boot processor.  The other CPUs
- * have been put offline by means of CPU hotplug.
+ * Called during system wide Suspend/Hibernate cycles for suspending 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.
  */
-static int cpufreq_bp_suspend(void)
+void cpufreq_suspend(void)
 {
-	int ret = 0;
-
-	int cpu = smp_processor_id();
 	struct cpufreq_policy *policy;
 
-	pr_debug("suspending cpu %u\n", cpu);
+	if (!cpufreq_driver)
+		return;
 
-	/* If there's no policy for the boot CPU, we have nothing to do. */
-	policy = cpufreq_cpu_get(cpu);
-	if (!policy)
-		return 0;
+	if (!has_target())
+		return;
 
-	if (cpufreq_driver->suspend) {
-		ret = cpufreq_driver->suspend(policy);
-		if (ret)
-			printk(KERN_ERR "cpufreq: suspend failed in ->suspend "
-					"step on CPU %u\n", policy->cpu);
+	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);
+		else if (cpufreq_driver->suspend
+		    && cpufreq_driver->suspend(policy))
+			pr_err("%s: Failed to suspend driver: %p\n", __func__,
+				policy);
 	}
 
-	cpufreq_cpu_put(policy);
-	return ret;
+	cpufreq_suspended = true;
 }
 
 /**
- * cpufreq_bp_resume - Restore proper frequency handling of the boot CPU.
- *
- *	1.) resume CPUfreq hardware support (cpufreq_driver->resume())
- *	2.) schedule call cpufreq_update_policy() ASAP as interrupts are
- *	    restored. It will verify that the current freq is in sync with
- *	    what we believe it to be. This is a bit later than when it
- *	    should be, but nonethteless it's better than calling
- *	    cpufreq_driver->get() here which might re-enable interrupts...
+ * cpufreq_resume() - Resume CPUFreq governors
  *
- * This function is only executed for the boot CPU.  The other CPUs have not
- * been turned on yet.
+ * Called during system wide Suspend/Hibernate cycle for resuming governors that
+ * are suspended with cpufreq_suspend().
  */
-static void cpufreq_bp_resume(void)
+void cpufreq_resume(void)
 {
-	int ret = 0;
-
-	int cpu = smp_processor_id();
 	struct cpufreq_policy *policy;
 
-	pr_debug("resuming cpu %u\n", cpu);
+	if (!cpufreq_driver)
+		return;
 
-	/* If there's no policy for the boot CPU, we have nothing to do. */
-	policy = cpufreq_cpu_get(cpu);
-	if (!policy)
+	if (!has_target())
 		return;
 
-	if (cpufreq_driver->resume) {
-		ret = cpufreq_driver->resume(policy);
-		if (ret) {
-			printk(KERN_ERR "cpufreq: resume failed in ->resume "
-					"step on CPU %u\n", policy->cpu);
-			goto fail;
-		}
-	}
+	pr_debug("%s: Resuming Governors\n", __func__);
 
-	schedule_work(&policy->update);
+	cpufreq_suspended = false;
 
-fail:
-	cpufreq_cpu_put(policy);
-}
+	list_for_each_entry(policy, &cpufreq_policy_list, policy_list) {
+		if (cpufreq_driver->resume && cpufreq_driver->resume(policy))
+			pr_err("%s: Failed to resume driver: %p\n", __func__,
+				policy);
+		else 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);
 
-static struct syscore_ops cpufreq_syscore_ops = {
-	.suspend	= cpufreq_bp_suspend,
-	.resume		= cpufreq_bp_resume,
-};
+		/*
+		 * schedule call cpufreq_update_policy() for boot CPU, i.e. last
+		 * policy in list. It will verify that the current freq is in
+		 * sync with what we believe it to be.
+		 */
+		if (list_is_last(&policy->policy_list, &cpufreq_policy_list))
+			schedule_work(&policy->update);
+	}
+}
 
 /**
  *	cpufreq_get_current_driver - return current driver's name
@@ -1767,7 +1819,7 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 		target_freq = policy->min;
 
 	pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
-			policy->cpu, target_freq, relation, old_target_freq);
+		 policy->cpu, target_freq, relation, old_target_freq);
 
 	/*
 	 * This might look like a redundant call as we are checking it again
@@ -1812,20 +1864,18 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 			freqs.flags = 0;
 
 			pr_debug("%s: cpu: %d, oldfreq: %u, new freq: %u\n",
-					__func__, policy->cpu, freqs.old,
-					freqs.new);
+				 __func__, policy->cpu, freqs.old, freqs.new);
 
-			cpufreq_notify_transition(policy, &freqs,
-					CPUFREQ_PRECHANGE);
+			cpufreq_freq_transition_begin(policy, &freqs);
 		}
 
 		retval = cpufreq_driver->target_index(policy, index);
 		if (retval)
 			pr_err("%s: Failed to change cpu frequency: %d\n",
-					__func__, retval);
+			       __func__, retval);
 
 		if (notify)
-			cpufreq_notify_post_transition(policy, &freqs, retval);
+			cpufreq_freq_transition_end(policy, &freqs, retval);
 	}
 
 out:
@@ -1868,17 +1918,18 @@ 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) {
 		if (!gov)
 			return -EINVAL;
 		else {
-			printk(KERN_WARNING "%s governor failed, too long"
-			       " transition latency of HW, fallback"
-			       " to %s governor\n",
-			       policy->governor->name,
-			       gov->name);
+			pr_warn("%s governor failed, too long transition latency of HW, fallback to %s governor\n",
+				policy->governor->name, gov->name);
 			policy->governor = gov;
 		}
 	}
@@ -1888,7 +1939,7 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 			return -EINVAL;
 
 	pr_debug("__cpufreq_governor for CPU %u, event %u\n",
-						policy->cpu, event);
+		 policy->cpu, event);
 
 	mutex_lock(&cpufreq_governor_lock);
 	if ((policy->governor_enabled && event == CPUFREQ_GOV_START)
@@ -1955,9 +2006,7 @@ EXPORT_SYMBOL_GPL(cpufreq_register_governor);
 
 void cpufreq_unregister_governor(struct cpufreq_governor *governor)
 {
-#ifdef CONFIG_HOTPLUG_CPU
 	int cpu;
-#endif
 
 	if (!governor)
 		return;
@@ -1965,14 +2014,12 @@ void cpufreq_unregister_governor(struct cpufreq_governor *governor)
 	if (cpufreq_disabled())
 		return;
 
-#ifdef CONFIG_HOTPLUG_CPU
 	for_each_present_cpu(cpu) {
 		if (cpu_online(cpu))
 			continue;
 		if (!strcmp(per_cpu(cpufreq_cpu_governor, cpu), governor->name))
 			strcpy(per_cpu(cpufreq_cpu_governor, cpu), "\0");
 	}
-#endif
 
 	mutex_lock(&cpufreq_governor_mutex);
 	list_del(&governor->governor_list);
@@ -2017,22 +2064,21 @@ EXPORT_SYMBOL(cpufreq_get_policy);
 static int cpufreq_set_policy(struct cpufreq_policy *policy,
 				struct cpufreq_policy *new_policy)
 {
-	int ret = 0, failed = 1;
+	struct cpufreq_governor *old_gov;
+	int ret;
 
-	pr_debug("setting new policy for CPU %u: %u - %u kHz\n", new_policy->cpu,
-		new_policy->min, new_policy->max);
+	pr_debug("setting new policy for CPU %u: %u - %u kHz\n",
+		 new_policy->cpu, new_policy->min, new_policy->max);
 
 	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));
 
-	if (new_policy->min > policy->max || new_policy->max < policy->min) {
-		ret = -EINVAL;
-		goto error_out;
-	}
+	if (new_policy->min > policy->max || new_policy->max < policy->min)
+		return -EINVAL;
 
 	/* verify the cpu speed can be set within this limit */
 	ret = cpufreq_driver->verify(new_policy);
 	if (ret)
-		goto error_out;
+		return ret;
 
 	/* adjust if necessary - all reasons */
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
@@ -2048,7 +2094,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	 */
 	ret = cpufreq_driver->verify(new_policy);
 	if (ret)
-		goto error_out;
+		return ret;
 
 	/* notification of the new policy */
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
@@ -2058,63 +2104,53 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	policy->max = new_policy->max;
 
 	pr_debug("new min and max freqs are %u - %u kHz\n",
-					policy->min, policy->max);
+		 policy->min, policy->max);
 
 	if (cpufreq_driver->setpolicy) {
 		policy->policy = new_policy->policy;
 		pr_debug("setting range\n");
-		ret = cpufreq_driver->setpolicy(new_policy);
-	} else {
-		if (new_policy->governor != policy->governor) {
-			/* save old, working values */
-			struct cpufreq_governor *old_gov = policy->governor;
-
-			pr_debug("governor switch\n");
-
-			/* end old governor */
-			if (policy->governor) {
-				__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
-				up_write(&policy->rwsem);
-				__cpufreq_governor(policy,
-						CPUFREQ_GOV_POLICY_EXIT);
-				down_write(&policy->rwsem);
-			}
+		return cpufreq_driver->setpolicy(new_policy);
+	}
 
-			/* start new governor */
-			policy->governor = new_policy->governor;
-			if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) {
-				if (!__cpufreq_governor(policy, CPUFREQ_GOV_START)) {
-					failed = 0;
-				} else {
-					up_write(&policy->rwsem);
-					__cpufreq_governor(policy,
-							CPUFREQ_GOV_POLICY_EXIT);
-					down_write(&policy->rwsem);
-				}
-			}
+	if (new_policy->governor == policy->governor)
+		goto out;
 
-			if (failed) {
-				/* new governor failed, so re-start old one */
-				pr_debug("starting governor %s failed\n",
-							policy->governor->name);
-				if (old_gov) {
-					policy->governor = old_gov;
-					__cpufreq_governor(policy,
-							CPUFREQ_GOV_POLICY_INIT);
-					__cpufreq_governor(policy,
-							   CPUFREQ_GOV_START);
-				}
-				ret = -EINVAL;
-				goto error_out;
-			}
-			/* might be a policy change, too, so fall through */
-		}
-		pr_debug("governor: change or update limits\n");
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+	pr_debug("governor switch\n");
+
+	/* save old, working values */
+	old_gov = policy->governor;
+	/* end old governor */
+	if (old_gov) {
+		__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		up_write(&policy->rwsem);
+		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		down_write(&policy->rwsem);
 	}
 
-error_out:
-	return ret;
+	/* start new governor */
+	policy->governor = new_policy->governor;
+	if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) {
+		if (!__cpufreq_governor(policy, CPUFREQ_GOV_START))
+			goto out;
+
+		up_write(&policy->rwsem);
+		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		down_write(&policy->rwsem);
+	}
+
+	/* new governor failed, so re-start old one */
+	pr_debug("starting governor %s failed\n", policy->governor->name);
+	if (old_gov) {
+		policy->governor = old_gov;
+		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
+		__cpufreq_governor(policy, CPUFREQ_GOV_START);
+	}
+
+	return -EINVAL;
+
+ out:
+	pr_debug("governor: change or update limits\n");
+	return __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 }
 
 /**
@@ -2148,10 +2184,15 @@ int cpufreq_update_policy(unsigned int cpu)
 	 * BIOS might change freq behind our back
 	 * -> ask driver for current freq and notify governors about a change
 	 */
-	if (cpufreq_driver->get) {
+	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
 		new_policy.cur = cpufreq_driver->get(cpu);
+		if (WARN_ON(!new_policy.cur)) {
+			ret = -EIO;
+			goto no_policy;
+		}
+
 		if (!policy->cur) {
-			pr_debug("Driver did not initialize current freq");
+			pr_debug("Driver did not initialize current freq\n");
 			policy->cur = new_policy.cur;
 		} else {
 			if (policy->cur != new_policy.cur && has_target())
@@ -2175,30 +2216,24 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 {
 	unsigned int cpu = (unsigned long)hcpu;
 	struct device *dev;
-	bool frozen = false;
 
 	dev = get_cpu_device(cpu);
 	if (dev) {
-
-		if (action & CPU_TASKS_FROZEN)
-			frozen = true;
-
 		switch (action & ~CPU_TASKS_FROZEN) {
 		case CPU_ONLINE:
-			__cpufreq_add_dev(dev, NULL, frozen);
-			cpufreq_update_policy(cpu);
+			__cpufreq_add_dev(dev, NULL);
 			break;
 
 		case CPU_DOWN_PREPARE:
-			__cpufreq_remove_dev_prepare(dev, NULL, frozen);
+			__cpufreq_remove_dev_prepare(dev, NULL);
 			break;
 
 		case CPU_POST_DEAD:
-			__cpufreq_remove_dev_finish(dev, NULL, frozen);
+			__cpufreq_remove_dev_finish(dev, NULL);
 			break;
 
 		case CPU_DOWN_FAILED:
-			__cpufreq_add_dev(dev, NULL, frozen);
+			__cpufreq_add_dev(dev, NULL);
 			break;
 		}
 	}
@@ -2254,8 +2289,8 @@ int cpufreq_boost_trigger_state(int state)
 		cpufreq_driver->boost_enabled = !state;
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-		pr_err("%s: Cannot %s BOOST\n", __func__,
-		       state ? "enable" : "disable");
+		pr_err("%s: Cannot %s BOOST\n",
+		       __func__, state ? "enable" : "disable");
 	}
 
 	return ret;
@@ -2300,7 +2335,9 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 
 	if (!driver_data || !driver_data->verify || !driver_data->init ||
 	    !(driver_data->setpolicy || driver_data->target_index ||
-		    driver_data->target))
+		    driver_data->target) ||
+	     (driver_data->setpolicy && (driver_data->target_index ||
+		    driver_data->target)))
 		return -EINVAL;
 
 	pr_debug("trying to register driver %s\n", driver_data->name);
@@ -2327,7 +2364,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 		ret = cpufreq_sysfs_create_file(&boost.attr);
 		if (ret) {
 			pr_err("%s: cannot register global BOOST sysfs file\n",
-				__func__);
+			       __func__);
 			goto err_null_driver;
 		}
 	}
@@ -2350,7 +2387,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 		/* if all ->init() calls failed, unregister */
 		if (ret) {
 			pr_debug("no CPU initialized for driver %s\n",
-							driver_data->name);
+				 driver_data->name);
 			goto err_if_unreg;
 		}
 	}
@@ -2414,7 +2451,6 @@ static int __init cpufreq_core_init(void)
 
 	cpufreq_global_kobject = kobject_create();
 	BUG_ON(!cpufreq_global_kobject);
-	register_syscore_ops(&cpufreq_syscore_ops);
 
 	return 0;
 }