Merge branch 'sched/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip into trace/tip/tracing/core-4

3 files changed, 93 insertions, 9 deletions

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 2d5d575e889d..75d293eeb3ee 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1113,6 +1113,8 @@ 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 +1143,11 @@ 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 +1184,10 @@ 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 +1198,22 @@ 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..3a147874a465 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -444,6 +444,7 @@ 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 +502,9 @@ 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 +515,7 @@ 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 +542,7 @@ 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..8e9dbdc6c700 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,
@@ -249,6 +261,7 @@ 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);
@@ -299,6 +312,23 @@ 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)
 {
@@ -381,6 +411,7 @@ static struct global_attr _name = \
 __ATTR(_name, 0644, show_##_name, store_##_name)
 
 define_one_rw(sampling_rate);
+define_one_rw(io_is_busy);
 define_one_rw(up_threshold);
 define_one_rw(ignore_nice_load);
 define_one_rw(powersave_bias);
@@ -392,6 +423,7 @@ static struct attribute *dbs_attributes[] = {
 	&up_threshold.attr,
 	&ignore_nice_load.attr,
 	&powersave_bias.attr,
+	&io_is_busy.attr,
 	NULL
 };
 
@@ -470,14 +502,15 @@ 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 +520,10 @@ 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 +541,16 @@ 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 +664,29 @@ 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 +749,7 @@ 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);