3 files changed, 99 insertions, 128 deletions

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index aed80e6aec6d..9b6ae7dc8b8a 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -52,9 +52,8 @@ static void handle_update(void *data);
  * changes to devices when the CPU clock speed changes.
  * The mutex locks both lists.
  */
-static struct notifier_block *cpufreq_policy_notifier_list;
-static struct notifier_block *cpufreq_transition_notifier_list;
-static DECLARE_RWSEM (cpufreq_notifier_rwsem);
+static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
+static BLOCKING_NOTIFIER_HEAD(cpufreq_transition_notifier_list);
 
 
 static LIST_HEAD(cpufreq_governor_list);
@@ -247,8 +246,6 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
         dprintk("notification %u of frequency transition to %u kHz\n",
                 state, freqs->new);
 
-        down_read(&cpufreq_notifier_rwsem);
-
         policy = cpufreq_cpu_data[freqs->cpu];
         switch (state) {
 
@@ -266,20 +263,19 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
                                 freqs->old = policy->cur;
                         }
                 }
-                notifier_call_chain(&cpufreq_transition_notifier_list,
-                                        CPUFREQ_PRECHANGE, freqs);
+                blocking_notifier_call_chain(&cpufreq_transition_notifier_list,
+                                CPUFREQ_PRECHANGE, freqs);
                 adjust_jiffies(CPUFREQ_PRECHANGE, freqs);
                 break;
 
         case CPUFREQ_POSTCHANGE:
                 adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
-                notifier_call_chain(&cpufreq_transition_notifier_list,
-                                        CPUFREQ_POSTCHANGE, freqs);
+                blocking_notifier_call_chain(&cpufreq_transition_notifier_list,
+                                CPUFREQ_POSTCHANGE, freqs);
                 if (likely(policy) && likely(policy->cpu == freqs->cpu))
                         policy->cur = freqs->new;
                 break;
         }
-        up_read(&cpufreq_notifier_rwsem);
 }
 EXPORT_SYMBOL_GPL(cpufreq_notify_transition);
 
@@ -1007,7 +1003,7 @@ static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg)
                 freqs.old = cpu_policy->cur;
                 freqs.new = cur_freq;
 
-                notifier_call_chain(&cpufreq_transition_notifier_list,
+                blocking_notifier_call_chain(&cpufreq_transition_notifier_list,
                                     CPUFREQ_SUSPENDCHANGE, &freqs);
                 adjust_jiffies(CPUFREQ_SUSPENDCHANGE, &freqs);
 
@@ -1088,7 +1084,8 @@ static int cpufreq_resume(struct sys_device * sysdev)
                         freqs.old = cpu_policy->cur;
                         freqs.new = cur_freq;
 
-                        notifier_call_chain(&cpufreq_transition_notifier_list,
+                        blocking_notifier_call_chain(
+                                        &cpufreq_transition_notifier_list,
                                         CPUFREQ_RESUMECHANGE, &freqs);
                         adjust_jiffies(CPUFREQ_RESUMECHANGE, &freqs);
 
@@ -1125,24 +1122,24 @@ static struct sysdev_driver cpufreq_sysdev_driver = {
  *      changes in cpufreq policy.
  *
  *      This function may sleep, and has the same return conditions as
- *      notifier_chain_register.
+ *      blocking_notifier_chain_register.
  */
 int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
 {
         int ret;
 
-        down_write(&cpufreq_notifier_rwsem);
         switch (list) {
         case CPUFREQ_TRANSITION_NOTIFIER:
-                ret = notifier_chain_register(&cpufreq_transition_notifier_list, nb);
+                ret = blocking_notifier_chain_register(
+                                &cpufreq_transition_notifier_list, nb);
                 break;
         case CPUFREQ_POLICY_NOTIFIER:
-                ret = notifier_chain_register(&cpufreq_policy_notifier_list, nb);
+                ret = blocking_notifier_chain_register(
+                                &cpufreq_policy_notifier_list, nb);
                 break;
         default:
                 ret = -EINVAL;
         }
-        up_write(&cpufreq_notifier_rwsem);
 
         return ret;
 }
@@ -1157,24 +1154,24 @@ EXPORT_SYMBOL(cpufreq_register_notifier);
  *      Remove a driver from the CPU frequency notifier list.
  *
  *      This function may sleep, and has the same return conditions as
- *      notifier_chain_unregister.
+ *      blocking_notifier_chain_unregister.
  */
 int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list)
 {
         int ret;
 
-        down_write(&cpufreq_notifier_rwsem);
         switch (list) {
         case CPUFREQ_TRANSITION_NOTIFIER:
-                ret = notifier_chain_unregister(&cpufreq_transition_notifier_list, nb);
+                ret = blocking_notifier_chain_unregister(
+                                &cpufreq_transition_notifier_list, nb);
                 break;
         case CPUFREQ_POLICY_NOTIFIER:
-                ret = notifier_chain_unregister(&cpufreq_policy_notifier_list, nb);
+                ret = blocking_notifier_chain_unregister(
+                                &cpufreq_policy_notifier_list, nb);
                 break;
         default:
                 ret = -EINVAL;
         }
-        up_write(&cpufreq_notifier_rwsem);
 
         return ret;
 }
@@ -1346,29 +1343,23 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_poli
         if (ret)
                 goto error_out;
 
-        down_read(&cpufreq_notifier_rwsem);
-
         /* adjust if necessary - all reasons */
-        notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_ADJUST,
-                            policy);
+        blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+                        CPUFREQ_ADJUST, policy);
 
         /* adjust if necessary - hardware incompatibility*/
-        notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_INCOMPATIBLE,
-                            policy);
+        blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+                        CPUFREQ_INCOMPATIBLE, policy);
 
         /* verify the cpu speed can be set within this limit,
            which might be different to the first one */
         ret = cpufreq_driver->verify(policy);
-        if (ret) {
-                up_read(&cpufreq_notifier_rwsem);
+        if (ret)
                 goto error_out;
-        }
 
         /* notification of the new policy */
-        notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_NOTIFY,
-                            policy);
-
-        up_read(&cpufreq_notifier_rwsem);
+        blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+                        CPUFREQ_NOTIFY, policy);
 
         data->min = policy->min;
         data->max = policy->max;
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index ac38766b2583..037f6bf4543c 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -35,12 +35,7 @@
  */
 
 #define DEF_FREQUENCY_UP_THRESHOLD              (80)
-#define MIN_FREQUENCY_UP_THRESHOLD              (0)
-#define MAX_FREQUENCY_UP_THRESHOLD              (100)
-
 #define DEF_FREQUENCY_DOWN_THRESHOLD            (20)
-#define MIN_FREQUENCY_DOWN_THRESHOLD            (0)
-#define MAX_FREQUENCY_DOWN_THRESHOLD            (100)
 
 /* 
  * The polling frequency of this governor depends on the capability of 
@@ -53,10 +48,14 @@
  * All times here are in uS.
  */
 static unsigned int                             def_sampling_rate;
-#define MIN_SAMPLING_RATE                       (def_sampling_rate / 2)
+#define MIN_SAMPLING_RATE_RATIO                 (2)
+/* for correct statistics, we need at least 10 ticks between each measure */
+#define MIN_STAT_SAMPLING_RATE                  (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10))
+#define MIN_SAMPLING_RATE                       (def_sampling_rate / MIN_SAMPLING_RATE_RATIO)
 #define MAX_SAMPLING_RATE                       (500 * def_sampling_rate)
-#define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER    (100000)
-#define DEF_SAMPLING_DOWN_FACTOR                (5)
+#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)
 
 static void do_dbs_timer(void *data);
@@ -66,6 +65,8 @@ struct cpu_dbs_info_s {
         unsigned int            prev_cpu_idle_up;
         unsigned int            prev_cpu_idle_down;
         unsigned int            enable;
+        unsigned int            down_skip;
+        unsigned int            requested_freq;
 };
 static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);
 
@@ -87,6 +88,8 @@ static struct dbs_tuners dbs_tuners_ins = {
         .up_threshold           = DEF_FREQUENCY_UP_THRESHOLD,
         .down_threshold         = DEF_FREQUENCY_DOWN_THRESHOLD,
         .sampling_down_factor   = DEF_SAMPLING_DOWN_FACTOR,
+        .ignore_nice            = 0,
+        .freq_step              = 5,
 };
 
 static inline unsigned int get_cpu_idle_time(unsigned int cpu)
@@ -136,7 +139,7 @@ static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused,
         unsigned int input;
         int ret;
         ret = sscanf (buf, "%u", &input);
-        if (ret != 1 )
+        if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
                 return -EINVAL;
 
         mutex_lock(&dbs_mutex);
@@ -173,8 +176,7 @@ static ssize_t store_up_threshold(struct cpufreq_policy *unused,
         ret = sscanf (buf, "%u", &input);
 
         mutex_lock(&dbs_mutex);
-        if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD || 
-                        input < MIN_FREQUENCY_UP_THRESHOLD ||
+        if (ret != 1 || input > 100 || input < 0 ||
                         input <= dbs_tuners_ins.down_threshold) {
                 mutex_unlock(&dbs_mutex);
                 return -EINVAL;
@@ -194,8 +196,7 @@ static ssize_t store_down_threshold(struct cpufreq_policy *unused,
         ret = sscanf (buf, "%u", &input);
 
         mutex_lock(&dbs_mutex);
-        if (ret != 1 || input > MAX_FREQUENCY_DOWN_THRESHOLD || 
-                        input < MIN_FREQUENCY_DOWN_THRESHOLD ||
+        if (ret != 1 || input > 100 || input < 0 ||
                         input >= dbs_tuners_ins.up_threshold) {
                 mutex_unlock(&dbs_mutex);
                 return -EINVAL;
@@ -297,31 +298,17 @@ static struct attribute_group dbs_attr_group = {
 static void dbs_check_cpu(int cpu)
 {
         unsigned int idle_ticks, up_idle_ticks, down_idle_ticks;
+        unsigned int tmp_idle_ticks, total_idle_ticks;
         unsigned int freq_step;
         unsigned int freq_down_sampling_rate;
-        static int down_skip[NR_CPUS];
-        static int requested_freq[NR_CPUS];
-        static unsigned short init_flag = 0;
-        struct cpu_dbs_info_s *this_dbs_info;
-        struct cpu_dbs_info_s *dbs_info;
-
+        struct cpu_dbs_info_s *this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
         struct cpufreq_policy *policy;
-        unsigned int j;
 
-        this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
         if (!this_dbs_info->enable)
                 return;
 
         policy = this_dbs_info->cur_policy;
 
-        if ( init_flag == 0 ) {
-                for_each_online_cpu(j) {
-                        dbs_info = &per_cpu(cpu_dbs_info, j);
-                        requested_freq[j] = dbs_info->cur_policy->cur;
-                }
-                init_flag = 1;
-        }
-        
         /* 
          * The default safe range is 20% to 80% 
          * Every sampling_rate, we check
@@ -337,39 +324,29 @@ static void dbs_check_cpu(int cpu)
          */
 
         /* Check for frequency increase */
-
         idle_ticks = UINT_MAX;
-        for_each_cpu_mask(j, policy->cpus) {
-                unsigned int tmp_idle_ticks, total_idle_ticks;
-                struct cpu_dbs_info_s *j_dbs_info;
 
-                j_dbs_info = &per_cpu(cpu_dbs_info, j);
-                /* Check for frequency increase */
-                total_idle_ticks = get_cpu_idle_time(j);
-                tmp_idle_ticks = total_idle_ticks -
-                        j_dbs_info->prev_cpu_idle_up;
-                j_dbs_info->prev_cpu_idle_up = total_idle_ticks;
-
-                if (tmp_idle_ticks < idle_ticks)
-                        idle_ticks = tmp_idle_ticks;
-        }
+        /* Check for frequency increase */
+        total_idle_ticks = get_cpu_idle_time(cpu);
+        tmp_idle_ticks = total_idle_ticks -
+                this_dbs_info->prev_cpu_idle_up;
+        this_dbs_info->prev_cpu_idle_up = total_idle_ticks;
+
+        if (tmp_idle_ticks < idle_ticks)
+                idle_ticks = tmp_idle_ticks;
 
         /* Scale idle ticks by 100 and compare with up and down ticks */
         idle_ticks *= 100;
         up_idle_ticks = (100 - dbs_tuners_ins.up_threshold) *
-                usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
+                        usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
 
         if (idle_ticks < up_idle_ticks) {
-                down_skip[cpu] = 0;
-                for_each_cpu_mask(j, policy->cpus) {
-                        struct cpu_dbs_info_s *j_dbs_info;
+                this_dbs_info->down_skip = 0;
+                this_dbs_info->prev_cpu_idle_down =
+                        this_dbs_info->prev_cpu_idle_up;
 
-                        j_dbs_info = &per_cpu(cpu_dbs_info, j);
-                        j_dbs_info->prev_cpu_idle_down = 
-                                        j_dbs_info->prev_cpu_idle_up;
-                }
                 /* if we are already at full speed then break out early */
-                if (requested_freq[cpu] == policy->max)
+                if (this_dbs_info->requested_freq == policy->max)
                         return;
                 
                 freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100;
@@ -378,49 +355,45 @@ static void dbs_check_cpu(int cpu)
                 if (unlikely(freq_step == 0))
                         freq_step = 5;
                 
-                requested_freq[cpu] += freq_step;
-                if (requested_freq[cpu] > policy->max)
-                        requested_freq[cpu] = policy->max;
+                this_dbs_info->requested_freq += freq_step;
+                if (this_dbs_info->requested_freq > policy->max)
+                        this_dbs_info->requested_freq = policy->max;
 
-                __cpufreq_driver_target(policy, requested_freq[cpu], 
+                __cpufreq_driver_target(policy, this_dbs_info->requested_freq,
                         CPUFREQ_RELATION_H);
                 return;
         }
 
         /* Check for frequency decrease */
-        down_skip[cpu]++;
-        if (down_skip[cpu] < dbs_tuners_ins.sampling_down_factor)
+        this_dbs_info->down_skip++;
+        if (this_dbs_info->down_skip < dbs_tuners_ins.sampling_down_factor)
                 return;
 
-        idle_ticks = UINT_MAX;
-        for_each_cpu_mask(j, policy->cpus) {
-                unsigned int tmp_idle_ticks, total_idle_ticks;
-                struct cpu_dbs_info_s *j_dbs_info;
+        /* Check for frequency decrease */
+        total_idle_ticks = this_dbs_info->prev_cpu_idle_up;
+        tmp_idle_ticks = total_idle_ticks -
+                this_dbs_info->prev_cpu_idle_down;
+        this_dbs_info->prev_cpu_idle_down = total_idle_ticks;
 
-                j_dbs_info = &per_cpu(cpu_dbs_info, j);
-                total_idle_ticks = j_dbs_info->prev_cpu_idle_up;
-                tmp_idle_ticks = total_idle_ticks -
-                        j_dbs_info->prev_cpu_idle_down;
-                j_dbs_info->prev_cpu_idle_down = total_idle_ticks;
-
-                if (tmp_idle_ticks < idle_ticks)
-                        idle_ticks = tmp_idle_ticks;
-        }
+        if (tmp_idle_ticks < idle_ticks)
+                idle_ticks = tmp_idle_ticks;
 
         /* Scale idle ticks by 100 and compare with up and down ticks */
         idle_ticks *= 100;
-        down_skip[cpu] = 0;
+        this_dbs_info->down_skip = 0;
 
         freq_down_sampling_rate = dbs_tuners_ins.sampling_rate *
                 dbs_tuners_ins.sampling_down_factor;
         down_idle_ticks = (100 - dbs_tuners_ins.down_threshold) *
-                        usecs_to_jiffies(freq_down_sampling_rate);
+                usecs_to_jiffies(freq_down_sampling_rate);
 
         if (idle_ticks > down_idle_ticks) {
-                /* if we are already at the lowest speed then break out early
+                /*
+                 * if we are already at the lowest speed then break out early
                  * or if we 'cannot' reduce the speed as the user might want
-                 * freq_step to be zero */
-                if (requested_freq[cpu] == policy->min
+                 * freq_step to be zero
+                 */
+                if (this_dbs_info->requested_freq == policy->min
                                 || dbs_tuners_ins.freq_step == 0)
                         return;
 
@@ -430,13 +403,12 @@ static void dbs_check_cpu(int cpu)
                 if (unlikely(freq_step == 0))
                         freq_step = 5;
 
-                requested_freq[cpu] -= freq_step;
-                if (requested_freq[cpu] < policy->min)
-                        requested_freq[cpu] = policy->min;
+                this_dbs_info->requested_freq -= freq_step;
+                if (this_dbs_info->requested_freq < policy->min)
+                        this_dbs_info->requested_freq = policy->min;
 
-                __cpufreq_driver_target(policy,
-                        requested_freq[cpu],
-                        CPUFREQ_RELATION_H);
+                __cpufreq_driver_target(policy, this_dbs_info->requested_freq,
+                                CPUFREQ_RELATION_H);
                 return;
         }
 }
@@ -493,11 +465,13 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
                         j_dbs_info = &per_cpu(cpu_dbs_info, j);
                         j_dbs_info->cur_policy = policy;
                 
-                        j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
+                        j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(cpu);
                         j_dbs_info->prev_cpu_idle_down
                                 = j_dbs_info->prev_cpu_idle_up;
                 }
                 this_dbs_info->enable = 1;
+                this_dbs_info->down_skip = 0;
+                this_dbs_info->requested_freq = policy->cur;
                 sysfs_create_group(&policy->kobj, &dbs_attr_group);
                 dbs_enable++;
                 /*
@@ -507,16 +481,17 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
                 if (dbs_enable == 1) {
                         unsigned int latency;
                         /* policy latency is in nS. Convert it to uS first */
+                        latency = policy->cpuinfo.transition_latency / 1000;
+                        if (latency == 0)
+                                latency = 1;
 
-                        latency = policy->cpuinfo.transition_latency;
-                        if (latency < 1000)
-                                latency = 1000;
-
-                        def_sampling_rate = (latency / 1000) *
+                        def_sampling_rate = 10 * latency *
                                         DEF_SAMPLING_RATE_LATENCY_MULTIPLIER;
+
+                        if (def_sampling_rate < MIN_STAT_SAMPLING_RATE)
+                                def_sampling_rate = MIN_STAT_SAMPLING_RATE;
+
                         dbs_tuners_ins.sampling_rate = def_sampling_rate;
-                        dbs_tuners_ins.ignore_nice = 0;
-                        dbs_tuners_ins.freq_step = 5;
 
                         dbs_timer_init();
                 }
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 69aa1db8336c..956d121cb161 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -84,6 +84,7 @@ struct dbs_tuners {
 static struct dbs_tuners dbs_tuners_ins = {
         .up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
         .sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
+        .ignore_nice = 0,
 };
 
 static inline unsigned int get_cpu_idle_time(unsigned int cpu)
@@ -350,6 +351,9 @@ static void dbs_check_cpu(int cpu)
         freq_next = (freq_next * policy->cur) /
                         (dbs_tuners_ins.up_threshold - 10);
 
+        if (freq_next < policy->min)
+                freq_next = policy->min;
+
         if (freq_next <= ((policy->cur * 95) / 100))
                 __cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_L);
 }
@@ -395,8 +399,11 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
                         return -EINVAL;
 
                 if (policy->cpuinfo.transition_latency >
-                                (TRANSITION_LATENCY_LIMIT * 1000))
+                                (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;
 
@@ -431,8 +438,6 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
                                 def_sampling_rate = MIN_STAT_SAMPLING_RATE;
 
                         dbs_tuners_ins.sampling_rate = def_sampling_rate;
-                        dbs_tuners_ins.ignore_nice = 0;
-
                         dbs_timer_init();
                 }