3 files changed, 135 insertions, 95 deletions

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 2d5d575e889d..063b2184caf5 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -662,32 +662,20 @@ static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
         return sprintf(buf, "%u\n", policy->cpuinfo.max_freq);
 }
 
-#define define_one_ro(_name) \
-static struct freq_attr _name = \
-__ATTR(_name, 0444, show_##_name, NULL)
-
-#define define_one_ro0400(_name) \
-static struct freq_attr _name = \
-__ATTR(_name, 0400, show_##_name, NULL)
-
-#define define_one_rw(_name) \
-static struct freq_attr _name = \
-__ATTR(_name, 0644, show_##_name, store_##_name)
-
-define_one_ro0400(cpuinfo_cur_freq);
-define_one_ro(cpuinfo_min_freq);
-define_one_ro(cpuinfo_max_freq);
-define_one_ro(cpuinfo_transition_latency);
-define_one_ro(scaling_available_governors);
-define_one_ro(scaling_driver);
-define_one_ro(scaling_cur_freq);
-define_one_ro(bios_limit);
-define_one_ro(related_cpus);
-define_one_ro(affected_cpus);
-define_one_rw(scaling_min_freq);
-define_one_rw(scaling_max_freq);
-define_one_rw(scaling_governor);
-define_one_rw(scaling_setspeed);
+cpufreq_freq_attr_ro_perm(cpuinfo_cur_freq, 0400);
+cpufreq_freq_attr_ro(cpuinfo_min_freq);
+cpufreq_freq_attr_ro(cpuinfo_max_freq);
+cpufreq_freq_attr_ro(cpuinfo_transition_latency);
+cpufreq_freq_attr_ro(scaling_available_governors);
+cpufreq_freq_attr_ro(scaling_driver);
+cpufreq_freq_attr_ro(scaling_cur_freq);
+cpufreq_freq_attr_ro(bios_limit);
+cpufreq_freq_attr_ro(related_cpus);
+cpufreq_freq_attr_ro(affected_cpus);
+cpufreq_freq_attr_rw(scaling_min_freq);
+cpufreq_freq_attr_rw(scaling_max_freq);
+cpufreq_freq_attr_rw(scaling_governor);
+cpufreq_freq_attr_rw(scaling_setspeed);
 
 static struct attribute *default_attrs[] = {
         &cpuinfo_min_freq.attr,
@@ -1113,6 +1101,8 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev)
         unsigned int cpu = sys_dev->id;
         unsigned long flags;
         struct cpufreq_policy *data;
+        struct kobject *kobj;
+        struct completion *cmp;
 #ifdef CONFIG_SMP
         struct sys_device *cpu_sys_dev;
         unsigned int j;
@@ -1141,10 +1131,11 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev)
                 dprintk("removing link\n");
                 cpumask_clear_cpu(cpu, data->cpus);
                 spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
-                sysfs_remove_link(&sys_dev->kobj, "cpufreq");
+                kobj = &sys_dev->kobj;
                 cpufreq_cpu_put(data);
                 cpufreq_debug_enable_ratelimit();
                 unlock_policy_rwsem_write(cpu);
+                sysfs_remove_link(kobj, "cpufreq");
                 return 0;
         }
 #endif
@@ -1181,7 +1172,10 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev)
                                 data->governor->name, CPUFREQ_NAME_LEN);
 #endif
                         cpu_sys_dev = get_cpu_sysdev(j);
-                        sysfs_remove_link(&cpu_sys_dev->kobj, "cpufreq");
+                        kobj = &cpu_sys_dev->kobj;
+                        unlock_policy_rwsem_write(cpu);
+                        sysfs_remove_link(kobj, "cpufreq");
+                        lock_policy_rwsem_write(cpu);
                         cpufreq_cpu_put(data);
                 }
         }
@@ -1192,19 +1186,22 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev)
         if (cpufreq_driver->target)
                 __cpufreq_governor(data, CPUFREQ_GOV_STOP);
 
-        kobject_put(&data->kobj);
+        kobj = &data->kobj;
+        cmp = &data->kobj_unregister;
+        unlock_policy_rwsem_write(cpu);
+        kobject_put(kobj);
 
         /* we need to make sure that the underlying kobj is actually
          * not referenced anymore by anybody before we proceed with
          * unloading.
          */
         dprintk("waiting for dropping of refcount\n");
-        wait_for_completion(&data->kobj_unregister);
+        wait_for_completion(cmp);
         dprintk("wait complete\n");
 
+        lock_policy_rwsem_write(cpu);
         if (cpufreq_driver->exit)
                 cpufreq_driver->exit(data);
-
         unlock_policy_rwsem_write(cpu);
 
         free_cpumask_var(data->related_cpus);
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 599a40b25cb0..526bfbf69611 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -178,12 +178,8 @@ static ssize_t show_sampling_rate_min(struct kobject *kobj,
         return sprintf(buf, "%u\n", min_sampling_rate);
 }
 
-#define define_one_ro(_name)            \
-static struct global_attr _name =       \
-__ATTR(_name, 0444, show_##_name, NULL)
-
-define_one_ro(sampling_rate_max);
-define_one_ro(sampling_rate_min);
+define_one_global_ro(sampling_rate_max);
+define_one_global_ro(sampling_rate_min);
 
 /* cpufreq_conservative Governor Tunables */
 #define show_one(file_name, object)                                     \
@@ -221,12 +217,8 @@ show_one_old(freq_step);
 show_one_old(sampling_rate_min);
 show_one_old(sampling_rate_max);
 
-#define define_one_ro_old(object, _name)        \
-static struct freq_attr object =                \
-__ATTR(_name, 0444, show_##_name##_old, NULL)
-
-define_one_ro_old(sampling_rate_min_old, sampling_rate_min);
-define_one_ro_old(sampling_rate_max_old, sampling_rate_max);
+cpufreq_freq_attr_ro_old(sampling_rate_min);
+cpufreq_freq_attr_ro_old(sampling_rate_max);
 
 /*** delete after deprecation time ***/
 
@@ -364,16 +356,12 @@ static ssize_t store_freq_step(struct kobject *a, struct attribute *b,
         return count;
 }
 
-#define define_one_rw(_name) \
-static struct global_attr _name = \
-__ATTR(_name, 0644, show_##_name, store_##_name)
-
-define_one_rw(sampling_rate);
-define_one_rw(sampling_down_factor);
-define_one_rw(up_threshold);
-define_one_rw(down_threshold);
-define_one_rw(ignore_nice_load);
-define_one_rw(freq_step);
+define_one_global_rw(sampling_rate);
+define_one_global_rw(sampling_down_factor);
+define_one_global_rw(up_threshold);
+define_one_global_rw(down_threshold);
+define_one_global_rw(ignore_nice_load);
+define_one_global_rw(freq_step);
 
 static struct attribute *dbs_attributes[] = {
         &sampling_rate_max.attr,
@@ -409,16 +397,12 @@ write_one_old(down_threshold);
 write_one_old(ignore_nice_load);
 write_one_old(freq_step);
 
-#define define_one_rw_old(object, _name)        \
-static struct freq_attr object =                \
-__ATTR(_name, 0644, show_##_name##_old, store_##_name##_old)
-
-define_one_rw_old(sampling_rate_old, sampling_rate);
-define_one_rw_old(sampling_down_factor_old, sampling_down_factor);
-define_one_rw_old(up_threshold_old, up_threshold);
-define_one_rw_old(down_threshold_old, down_threshold);
-define_one_rw_old(ignore_nice_load_old, ignore_nice_load);
-define_one_rw_old(freq_step_old, freq_step);
+cpufreq_freq_attr_rw_old(sampling_rate);
+cpufreq_freq_attr_rw_old(sampling_down_factor);
+cpufreq_freq_attr_rw_old(up_threshold);
+cpufreq_freq_attr_rw_old(down_threshold);
+cpufreq_freq_attr_rw_old(ignore_nice_load);
+cpufreq_freq_attr_rw_old(freq_step);
 
 static struct attribute *dbs_attributes_old[] = {
         &sampling_rate_max_old.attr,
@@ -444,6 +428,7 @@ static struct attribute_group dbs_attr_group_old = {
 static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 {
         unsigned int load = 0;
+        unsigned int max_load = 0;
         unsigned int freq_target;
 
         struct cpufreq_policy *policy;
@@ -501,6 +486,9 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
                         continue;
 
                 load = 100 * (wall_time - idle_time) / wall_time;
+
+                if (load > max_load)
+                        max_load = load;
         }
 
         /*
@@ -511,7 +499,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
                 return;
 
         /* Check for frequency increase */
-        if (load > dbs_tuners_ins.up_threshold) {
+        if (max_load > dbs_tuners_ins.up_threshold) {
                 this_dbs_info->down_skip = 0;
 
                 /* if we are already at full speed then break out early */
@@ -538,7 +526,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
          * can support the current CPU usage without triggering the up
          * policy. To be safe, we focus 10 points under the threshold.
          */
-        if (load < (dbs_tuners_ins.down_threshold - 10)) {
+        if (max_load < (dbs_tuners_ins.down_threshold - 10)) {
                 freq_target = (dbs_tuners_ins.freq_step * policy->max) / 100;
 
                 this_dbs_info->requested_freq -= freq_target;
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index bd444dc93cf2..e1314212d8d4 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -73,6 +73,7 @@ enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE};
 
 struct cpu_dbs_info_s {
         cputime64_t prev_cpu_idle;
+        cputime64_t prev_cpu_iowait;
         cputime64_t prev_cpu_wall;
         cputime64_t prev_cpu_nice;
         struct cpufreq_policy *cur_policy;
@@ -108,6 +109,7 @@ static struct dbs_tuners {
         unsigned int down_differential;
         unsigned int ignore_nice;
         unsigned int powersave_bias;
+        unsigned int io_is_busy;
 } dbs_tuners_ins = {
         .up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
         .down_differential = DEF_FREQUENCY_DOWN_DIFFERENTIAL,
@@ -148,6 +150,16 @@ static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
         return idle_time;
 }
 
+static inline cputime64_t get_cpu_iowait_time(unsigned int cpu, cputime64_t *wall)
+{
+        u64 iowait_time = get_cpu_iowait_time_us(cpu, wall);
+
+        if (iowait_time == -1ULL)
+                return 0;
+
+        return iowait_time;
+}
+
 /*
  * Find right freq to be set now with powersave_bias on.
  * Returns the freq_hi to be used right now and will set freq_hi_jiffies,
@@ -234,12 +246,8 @@ static ssize_t show_sampling_rate_min(struct kobject *kobj,
         return sprintf(buf, "%u\n", min_sampling_rate);
 }
 
-#define define_one_ro(_name)            \
-static struct global_attr _name =       \
-__ATTR(_name, 0444, show_##_name, NULL)
-
-define_one_ro(sampling_rate_max);
-define_one_ro(sampling_rate_min);
+define_one_global_ro(sampling_rate_max);
+define_one_global_ro(sampling_rate_min);
 
 /* cpufreq_ondemand Governor Tunables */
 #define show_one(file_name, object)                                     \
@@ -249,6 +257,7 @@ static ssize_t show_##file_name						\
         return sprintf(buf, "%u\n", dbs_tuners_ins.object);             \
 }
 show_one(sampling_rate, sampling_rate);
+show_one(io_is_busy, io_is_busy);
 show_one(up_threshold, up_threshold);
 show_one(ignore_nice_load, ignore_nice);
 show_one(powersave_bias, powersave_bias);
@@ -274,12 +283,8 @@ show_one_old(powersave_bias);
 show_one_old(sampling_rate_min);
 show_one_old(sampling_rate_max);
 
-#define define_one_ro_old(object, _name)       \
-static struct freq_attr object =               \
-__ATTR(_name, 0444, show_##_name##_old, NULL)
-
-define_one_ro_old(sampling_rate_min_old, sampling_rate_min);
-define_one_ro_old(sampling_rate_max_old, sampling_rate_max);
+cpufreq_freq_attr_ro_old(sampling_rate_min);
+cpufreq_freq_attr_ro_old(sampling_rate_max);
 
 /*** delete after deprecation time ***/
 
@@ -299,6 +304,23 @@ static ssize_t store_sampling_rate(struct kobject *a, struct attribute *b,
         return count;
 }
 
+static ssize_t store_io_is_busy(struct kobject *a, struct attribute *b,
+                                   const char *buf, size_t count)
+{
+        unsigned int input;
+        int ret;
+
+        ret = sscanf(buf, "%u", &input);
+        if (ret != 1)
+                return -EINVAL;
+
+        mutex_lock(&dbs_mutex);
+        dbs_tuners_ins.io_is_busy = !!input;
+        mutex_unlock(&dbs_mutex);
+
+        return count;
+}
+
 static ssize_t store_up_threshold(struct kobject *a, struct attribute *b,
                                   const char *buf, size_t count)
 {
@@ -376,14 +398,11 @@ static ssize_t store_powersave_bias(struct kobject *a, struct attribute *b,
         return count;
 }
 
-#define define_one_rw(_name) \
-static struct global_attr _name = \
-__ATTR(_name, 0644, show_##_name, store_##_name)
-
-define_one_rw(sampling_rate);
-define_one_rw(up_threshold);
-define_one_rw(ignore_nice_load);
-define_one_rw(powersave_bias);
+define_one_global_rw(sampling_rate);
+define_one_global_rw(io_is_busy);
+define_one_global_rw(up_threshold);
+define_one_global_rw(ignore_nice_load);
+define_one_global_rw(powersave_bias);
 
 static struct attribute *dbs_attributes[] = {
         &sampling_rate_max.attr,
@@ -392,6 +411,7 @@ static struct attribute *dbs_attributes[] = {
         &up_threshold.attr,
         &ignore_nice_load.attr,
         &powersave_bias.attr,
+        &io_is_busy.attr,
         NULL
 };
 
@@ -415,14 +435,10 @@ write_one_old(up_threshold);
 write_one_old(ignore_nice_load);
 write_one_old(powersave_bias);
 
-#define define_one_rw_old(object, _name)       \
-static struct freq_attr object =               \
-__ATTR(_name, 0644, show_##_name##_old, store_##_name##_old)
-
-define_one_rw_old(sampling_rate_old, sampling_rate);
-define_one_rw_old(up_threshold_old, up_threshold);
-define_one_rw_old(ignore_nice_load_old, ignore_nice_load);
-define_one_rw_old(powersave_bias_old, powersave_bias);
+cpufreq_freq_attr_rw_old(sampling_rate);
+cpufreq_freq_attr_rw_old(up_threshold);
+cpufreq_freq_attr_rw_old(ignore_nice_load);
+cpufreq_freq_attr_rw_old(powersave_bias);
 
 static struct attribute *dbs_attributes_old[] = {
        &sampling_rate_max_old.attr,
@@ -470,14 +486,15 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 
         for_each_cpu(j, policy->cpus) {
                 struct cpu_dbs_info_s *j_dbs_info;
-                cputime64_t cur_wall_time, cur_idle_time;
-                unsigned int idle_time, wall_time;
+                cputime64_t cur_wall_time, cur_idle_time, cur_iowait_time;
+                unsigned int idle_time, wall_time, iowait_time;
                 unsigned int load, load_freq;
                 int freq_avg;
 
                 j_dbs_info = &per_cpu(od_cpu_dbs_info, j);
 
                 cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
+                cur_iowait_time = get_cpu_iowait_time(j, &cur_wall_time);
 
                 wall_time = (unsigned int) cputime64_sub(cur_wall_time,
                                 j_dbs_info->prev_cpu_wall);
@@ -487,6 +504,10 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
                                 j_dbs_info->prev_cpu_idle);
                 j_dbs_info->prev_cpu_idle = cur_idle_time;
 
+                iowait_time = (unsigned int) cputime64_sub(cur_iowait_time,
+                                j_dbs_info->prev_cpu_iowait);
+                j_dbs_info->prev_cpu_iowait = cur_iowait_time;
+
                 if (dbs_tuners_ins.ignore_nice) {
                         cputime64_t cur_nice;
                         unsigned long cur_nice_jiffies;
@@ -504,6 +525,16 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
                         idle_time += jiffies_to_usecs(cur_nice_jiffies);
                 }
 
+                /*
+                 * For the purpose of ondemand, waiting for disk IO is an
+                 * indication that you're performance critical, and not that
+                 * the system is actually idle. So subtract the iowait time
+                 * from the cpu idle time.
+                 */
+
+                if (dbs_tuners_ins.io_is_busy && idle_time >= iowait_time)
+                        idle_time -= iowait_time;
+
                 if (unlikely(!wall_time || wall_time < idle_time))
                         continue;
 
@@ -617,6 +648,29 @@ static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
         cancel_delayed_work_sync(&dbs_info->work);
 }
 
+/*
+ * Not all CPUs want IO time to be accounted as busy; this dependson how
+ * efficient idling at a higher frequency/voltage is.
+ * Pavel Machek says this is not so for various generations of AMD and old
+ * Intel systems.
+ * Mike Chan (androidlcom) calis this is also not true for ARM.
+ * Because of this, whitelist specific known (series) of CPUs by default, and
+ * leave all others up to the user.
+ */
+static int should_io_be_busy(void)
+{
+#if defined(CONFIG_X86)
+        /*
+         * For Intel, Core 2 (model 15) andl later have an efficient idle.
+         */
+        if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+            boot_cpu_data.x86 == 6 &&
+            boot_cpu_data.x86_model >= 15)
+                return 1;
+#endif
+        return 0;
+}
+
 static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
                                    unsigned int event)
 {
@@ -679,6 +733,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
                         dbs_tuners_ins.sampling_rate =
                                 max(min_sampling_rate,
                                     latency * LATENCY_MULTIPLIER);
+                        dbs_tuners_ins.io_is_busy = should_io_be_busy();
                 }
                 mutex_unlock(&dbs_mutex);