#include <linux/types.h>
#include <linux/fs.h>
#include <linux/sysfs.h>
+#include <linux/cpu.h>
#include <linux/sched.h>
#include <linux/kmod.h>
#include <linux/workqueue.h>
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);
static unsigned int dbs_enable; /* number of CPUs using this policy */
+/*
+ * DEADLOCK ALERT! There is a ordering requirement between cpu_hotplug
+ * lock and dbs_mutex. cpu_hotplug lock should always be held before
+ * dbs_mutex. If any function that can potentially take cpu_hotplug lock
+ * (like __cpufreq_driver_target()) is being called with dbs_mutex taken, then
+ * cpu_hotplug lock should be taken before that. Note that cpu_hotplug lock
+ * is recursive for the same process. -Venki
+ */
static DEFINE_MUTEX (dbs_mutex);
static DECLARE_WORK (dbs_work, do_dbs_timer, NULL);
.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)
ret = sscanf (buf, "%u", &input);
mutex_lock(&dbs_mutex);
- if (ret != 1 || input > 100 || input < 0 ||
- input <= dbs_tuners_ins.down_threshold) {
+ if (ret != 1 || input > 100 || input <= dbs_tuners_ins.down_threshold) {
mutex_unlock(&dbs_mutex);
return -EINVAL;
}
ret = sscanf (buf, "%u", &input);
mutex_lock(&dbs_mutex);
- if (ret != 1 || input > 100 || input < 0 ||
- input >= dbs_tuners_ins.up_threshold) {
+ if (ret != 1 || input > 100 || input >= dbs_tuners_ins.up_threshold) {
mutex_unlock(&dbs_mutex);
return -EINVAL;
}
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
/* 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;
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;
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);
- /* Check for frequency decrease */
- 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;
* or if we 'cannot' reduce the speed as the user might want
* freq_step to be zero
*/
- if (requested_freq[cpu] == policy->min
+ if (this_dbs_info->requested_freq == policy->min
|| dbs_tuners_ins.freq_step == 0)
return;
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_driver_target(policy, this_dbs_info->requested_freq,
CPUFREQ_RELATION_H);
return;
}
static void do_dbs_timer(void *data)
{
int i;
+ lock_cpu_hotplug();
mutex_lock(&dbs_mutex);
for_each_online_cpu(i)
dbs_check_cpu(i);
schedule_delayed_work(&dbs_work,
usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
mutex_unlock(&dbs_mutex);
+ unlock_cpu_hotplug();
}
static inline void dbs_timer_init(void)
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++;
/*
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();
}
break;
case CPUFREQ_GOV_LIMITS:
+ lock_cpu_hotplug();
mutex_lock(&dbs_mutex);
if (policy->max < this_dbs_info->cur_policy->cur)
__cpufreq_driver_target(
this_dbs_info->cur_policy,
policy->min, CPUFREQ_RELATION_L);
mutex_unlock(&dbs_mutex);
+ unlock_cpu_hotplug();
break;
}
return 0;