5 files changed, 77 insertions, 43 deletions

diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 993fa7b89253..721f86f4f008 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -56,10 +56,6 @@ config CPU_FREQ_STAT_DETAILS
 
           If in doubt, say N.
 
-# Note that it is not currently possible to set the other governors (such as ondemand)
-# as the default, since if they fail to initialise, cpufreq will be
-# left in an undefined state.
-
 choice
         prompt "Default CPUFreq governor"
         default CPU_FREQ_DEFAULT_GOV_USERSPACE if CPU_FREQ_SA1100 || CPU_FREQ_SA1110
@@ -85,6 +81,29 @@ config CPU_FREQ_DEFAULT_GOV_USERSPACE
           program shall be able to set the CPU dynamically without having
           to enable the userspace governor manually.
 
+config CPU_FREQ_DEFAULT_GOV_ONDEMAND
+        bool "ondemand"
+        select CPU_FREQ_GOV_ONDEMAND
+        select CPU_FREQ_GOV_PERFORMANCE
+        help
+          Use the CPUFreq governor 'ondemand' as default. This allows
+          you to get a full dynamic frequency capable system by simply
+          loading your cpufreq low-level hardware driver.
+          Be aware that not all cpufreq drivers support the ondemand
+          governor. If unsure have a look at the help section of the
+          driver. Fallback governor will be the performance governor.
+
+config CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
+        bool "conservative"
+        select CPU_FREQ_GOV_CONSERVATIVE
+        select CPU_FREQ_GOV_PERFORMANCE
+        help
+          Use the CPUFreq governor 'conservative' as default. This allows
+          you to get a full dynamic frequency capable system by simply
+          loading your cpufreq low-level hardware driver.
+          Be aware that not all cpufreq drivers support the conservative
+          governor. If unsure have a look at the help section of the
+          driver. Fallback governor will be the performance governor.
 endchoice
 
 config CPU_FREQ_GOV_PERFORMANCE
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 2f6a73c01b71..f7b9d6fce123 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -763,6 +763,8 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
         init_completion(&policy->kobj_unregister);
         INIT_WORK(&policy->update, handle_update);
 
+        /* Set governor before ->init, so that driver could check it */
+        policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
         /* call driver. From then on the cpufreq must be able
          * to accept all calls to ->verify and ->setpolicy for this CPU
          */
@@ -1109,12 +1111,7 @@ unsigned int cpufreq_quick_get(unsigned int cpu)
         unsigned int ret_freq = 0;
 
         if (policy) {
-                if (unlikely(lock_policy_rwsem_read(cpu)))
-                        return ret_freq;
-
                 ret_freq = policy->cur;
-
-                unlock_policy_rwsem_read(cpu);
                 cpufreq_cpu_put(policy);
         }
 
@@ -1483,6 +1480,31 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 {
         int ret;
 
+        /* Only must be defined when default governor is known to have latency
+           restrictions, like e.g. conservative or ondemand.
+           That this is the case is already ensured in Kconfig
+        */
+#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
+        struct cpufreq_governor *gov = &cpufreq_gov_performance;
+#else
+        struct cpufreq_governor *gov = NULL;
+#endif
+
+        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);
+                        policy->governor = gov;
+                }
+        }
+
         if (!try_module_get(policy->governor->owner))
                 return -EINVAL;
 
@@ -1703,7 +1725,7 @@ int cpufreq_update_policy(unsigned int cpu)
 }
 EXPORT_SYMBOL(cpufreq_update_policy);
 
-static int cpufreq_cpu_callback(struct notifier_block *nfb,
+static int __cpuinit cpufreq_cpu_callback(struct notifier_block *nfb,
                                         unsigned long action, void *hcpu)
 {
         unsigned int cpu = (unsigned long)hcpu;
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 26f440ccc3fb..4bd33ce8a6f3 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -58,7 +58,7 @@ static unsigned int 				def_sampling_rate;
 #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER    (1000)
 #define DEF_SAMPLING_DOWN_FACTOR                (1)
 #define MAX_SAMPLING_DOWN_FACTOR                (10)
-#define TRANSITION_LATENCY_LIMIT                (10 * 1000)
+#define TRANSITION_LATENCY_LIMIT                (10 * 1000 * 1000)
 
 static void do_dbs_timer(struct work_struct *work);
 
@@ -466,9 +466,6 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
                     (!policy->cur))
                         return -EINVAL;
 
-                if (policy->cpuinfo.transition_latency >
-                                (TRANSITION_LATENCY_LIMIT * 1000))
-                        return -EINVAL;
                 if (this_dbs_info->enable) /* Already enabled */
                         break;
                  
@@ -551,15 +548,17 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
         return 0;
 }
 
-static struct cpufreq_governor cpufreq_gov_dbs = {
-        .name           = "conservative",
-        .governor       = cpufreq_governor_dbs,
-        .owner          = THIS_MODULE,
+struct cpufreq_governor cpufreq_gov_conservative = {
+        .name                   = "conservative",
+        .governor               = cpufreq_governor_dbs,
+        .max_transition_latency = TRANSITION_LATENCY_LIMIT,
+        .owner                  = THIS_MODULE,
 };
+EXPORT_SYMBOL(cpufreq_gov_conservative);
 
 static int __init cpufreq_gov_dbs_init(void)
 {
-        return cpufreq_register_governor(&cpufreq_gov_dbs);
+        return cpufreq_register_governor(&cpufreq_gov_conservative);
 }
 
 static void __exit cpufreq_gov_dbs_exit(void)
@@ -567,7 +566,7 @@ static void __exit cpufreq_gov_dbs_exit(void)
         /* Make sure that the scheduled work is indeed not running */
         flush_scheduled_work();
 
-        cpufreq_unregister_governor(&cpufreq_gov_dbs);
+        cpufreq_unregister_governor(&cpufreq_gov_conservative);
 }
 
 
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index e794527e4925..369f44595150 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -47,7 +47,7 @@ static unsigned int def_sampling_rate;
                         (def_sampling_rate / MIN_SAMPLING_RATE_RATIO)
 #define MAX_SAMPLING_RATE                       (500 * def_sampling_rate)
 #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER    (1000)
-#define TRANSITION_LATENCY_LIMIT                (10 * 1000)
+#define TRANSITION_LATENCY_LIMIT                (10 * 1000 * 1000)
 
 static void do_dbs_timer(struct work_struct *work);
 
@@ -508,12 +508,6 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
                 if ((!cpu_online(cpu)) || (!policy->cur))
                         return -EINVAL;
 
-                if (policy->cpuinfo.transition_latency >
-                                (TRANSITION_LATENCY_LIMIT * 1000)) {
-                        printk(KERN_WARNING "ondemand governor failed to load "
-                               "due to too long transition latency\n");
-                        return -EINVAL;
-                }
                 if (this_dbs_info->enable) /* Already enabled */
                         break;
 
@@ -585,11 +579,13 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
         return 0;
 }
 
-static struct cpufreq_governor cpufreq_gov_dbs = {
-        .name = "ondemand",
-        .governor = cpufreq_governor_dbs,
-        .owner = THIS_MODULE,
+struct cpufreq_governor cpufreq_gov_ondemand = {
+        .name                   = "ondemand",
+        .governor               = cpufreq_governor_dbs,
+        .max_transition_latency = TRANSITION_LATENCY_LIMIT,
+        .owner                  = THIS_MODULE,
 };
+EXPORT_SYMBOL(cpufreq_gov_ondemand);
 
 static int __init cpufreq_gov_dbs_init(void)
 {
@@ -598,12 +594,12 @@ static int __init cpufreq_gov_dbs_init(void)
                 printk(KERN_ERR "Creation of kondemand failed\n");
                 return -EFAULT;
         }
-        return cpufreq_register_governor(&cpufreq_gov_dbs);
+        return cpufreq_register_governor(&cpufreq_gov_ondemand);
 }
 
 static void __exit cpufreq_gov_dbs_exit(void)
 {
-        cpufreq_unregister_governor(&cpufreq_gov_dbs);
+        cpufreq_unregister_governor(&cpufreq_gov_ondemand);
         destroy_workqueue(kondemand_wq);
 }
 
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 917b9bab9ccb..8a45d0f93e26 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -164,8 +164,7 @@ freq_table_get_index(struct cpufreq_stats *stat, unsigned int freq)
         return -1;
 }
 
-static void
-cpufreq_stats_free_table (unsigned int cpu)
+static void __cpuexit cpufreq_stats_free_table(unsigned int cpu)
 {
         struct cpufreq_stats *stat = cpufreq_stats_table[cpu];
         struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
@@ -305,8 +304,9 @@ cpufreq_stat_notifier_trans (struct notifier_block *nb, unsigned long val,
         return 0;
 }
 
-static int cpufreq_stat_cpu_callback(struct notifier_block *nfb,
-                                        unsigned long action, void *hcpu)
+static int __cpuinit cpufreq_stat_cpu_callback(struct notifier_block *nfb,
+                                               unsigned long action,
+                                               void *hcpu)
 {
         unsigned int cpu = (unsigned long)hcpu;
 
@@ -323,7 +323,7 @@ static int cpufreq_stat_cpu_callback(struct notifier_block *nfb,
         return NOTIFY_OK;
 }
 
-static struct notifier_block cpufreq_stat_cpu_notifier =
+static struct notifier_block cpufreq_stat_cpu_notifier __cpuinitdata =
 {
         .notifier_call = cpufreq_stat_cpu_callback,
 };
@@ -356,8 +356,7 @@ __init cpufreq_stats_init(void)
 
         register_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
         for_each_online_cpu(cpu) {
-                cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier,
-                                CPU_ONLINE, (void *)(long)cpu);
+                cpufreq_update_policy(cpu);
         }
         return 0;
 }
@@ -372,13 +371,12 @@ __exit cpufreq_stats_exit(void)
                         CPUFREQ_TRANSITION_NOTIFIER);
         unregister_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
         for_each_online_cpu(cpu) {
-                cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier,
-                                                CPU_DEAD, (void *)(long)cpu);
+                cpufreq_stats_free_table(cpu);
         }
 }
 
 MODULE_AUTHOR ("Zou Nan hai <nanhai.zou@intel.com>");
-MODULE_DESCRIPTION ("'cpufreq_stats' - A driver to export cpufreq stats"
+MODULE_DESCRIPTION ("'cpufreq_stats' - A driver to export cpufreq stats "
                                 "through sysfs filesystem");
 MODULE_LICENSE ("GPL");