Merge branches 'gemini' and 'misc' into devel

1 files changed, 103 insertions, 45 deletions

diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index bd444dc93cf2..7b5093664e49 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,
@@ -443,6 +459,17 @@ static struct attribute_group dbs_attr_group_old = {
 
 /************************** sysfs end ************************/
 
+static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
+{
+        if (dbs_tuners_ins.powersave_bias)
+                freq = powersave_bias_target(p, freq, CPUFREQ_RELATION_H);
+        else if (p->cur == p->max)
+                return;
+
+        __cpufreq_driver_target(p, freq, dbs_tuners_ins.powersave_bias ?
+                        CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
+}
+
 static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 {
         unsigned int max_load_freq;
@@ -470,14 +497,15 @@ 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 +515,10 @@ 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 +536,16 @@ 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;
 
@@ -520,19 +562,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 
         /* Check for frequency increase */
         if (max_load_freq > dbs_tuners_ins.up_threshold * policy->cur) {
-                /* if we are already at full speed then break out early */
-                if (!dbs_tuners_ins.powersave_bias) {
-                        if (policy->cur == policy->max)
-                                return;
-
-                        __cpufreq_driver_target(policy, policy->max,
-                                CPUFREQ_RELATION_H);
-                } else {
-                        int freq = powersave_bias_target(policy, policy->max,
-                                        CPUFREQ_RELATION_H);
-                        __cpufreq_driver_target(policy, freq,
-                                CPUFREQ_RELATION_L);
-                }
+                dbs_freq_increase(policy, policy->max);
                 return;
         }
 
@@ -579,7 +609,9 @@ static void do_dbs_timer(struct work_struct *work)
         /* We want all CPUs to do sampling nearly on same jiffy */
         int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
 
-        delay -= jiffies % delay;
+        if (num_online_cpus() > 1)
+                delay -= jiffies % delay;
+
         mutex_lock(&dbs_info->timer_mutex);
 
         /* Common NORMAL_SAMPLE setup */
@@ -604,7 +636,9 @@ static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
 {
         /* We want all CPUs to do sampling nearly on same jiffy */
         int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
-        delay -= jiffies % delay;
+
+        if (num_online_cpus() > 1)
+                delay -= jiffies % delay;
 
         dbs_info->sample_type = DBS_NORMAL_SAMPLE;
         INIT_DELAYED_WORK_DEFERRABLE(&dbs_info->work, do_dbs_timer);
@@ -617,6 +651,29 @@ 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 +736,7 @@ 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);