Merge tag 'pm+acpi-3.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull ACPI and power management updates from Rafael Wysocki:

 - Rework of the ACPI namespace scanning code from Rafael J.  Wysocki
   with contributions from Bjorn Helgaas, Jiang Liu, Mika Westerberg,
   Toshi Kani, and Yinghai Lu.

 - ACPI power resources handling and ACPI device PM update from Rafael
   J Wysocki.

 - ACPICA update to version 20130117 from Bob Moore and Lv Zheng with
   contributions from Aaron Lu, Chao Guan, Jesper Juhl, and Tim Gardner.

 - Support for Intel Lynxpoint LPSS from Mika Westerberg.

 - cpuidle update from Len Brown including Intel Haswell support, C1
   state for intel_idle, removal of global pm_idle.

 - cpuidle fixes and cleanups from Daniel Lezcano.

 - cpufreq fixes and cleanups from Viresh Kumar and Fabio Baltieri with
   contributions from Stratos Karafotis and Rickard Andersson.

 - Intel P-states driver for Sandy Bridge processors from Dirk
   Brandewie.

 - cpufreq driver for Marvell Kirkwood SoCs from Andrew Lunn.

 - cpufreq fixes related to ordering issues between acpi-cpufreq and
   powernow-k8 from Borislav Petkov and Matthew Garrett.

 - cpufreq support for Calxeda Highbank processors from Mark Langsdorf
   and Rob Herring.

 - cpufreq driver for the Freescale i.MX6Q SoC and cpufreq-cpu0 update
   from Shawn Guo.

 - cpufreq Exynos fixes and cleanups from Jonghwan Choi, Sachin Kamat,
   and Inderpal Singh.

 - Support for "lightweight suspend" from Zhang Rui.

 - Removal of the deprecated power trace API from Paul Gortmaker.

 - Assorted updates from Andreas Fleig, Colin Ian King, Davidlohr Bueso,
   Joseph Salisbury, Kees Cook, Li Fei, Nishanth Menon, ShuoX Liu,
   Srinivas Pandruvada, Tejun Heo, Thomas Renninger, and Yasuaki
   Ishimatsu.

* tag 'pm+acpi-3.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (267 commits)
  PM idle: remove global declaration of pm_idle
  unicore32 idle: delete stray pm_idle comment
  openrisc idle: delete pm_idle
  mn10300 idle: delete pm_idle
  microblaze idle: delete pm_idle
  m32r idle: delete pm_idle, and other dead idle code
  ia64 idle: delete pm_idle
  cris idle: delete idle and pm_idle
  ARM64 idle: delete pm_idle
  ARM idle: delete pm_idle
  blackfin idle: delete pm_idle
  sparc idle: rename pm_idle to sparc_idle
  sh idle: rename global pm_idle to static sh_idle
  x86 idle: rename global pm_idle to static x86_idle
  APM idle: register apm_cpu_idle via cpuidle
  cpufreq / intel_pstate: Add kernel command line option disable intel_pstate.
  cpufreq / intel_pstate: Change to disallow module build
  tools/power turbostat: display SMI count by default
  intel_idle: export both C1 and C1E
  ACPI / hotplug: Fix concurrency issues and memory leaks
  ...

1 files changed, 41 insertions, 29 deletions

diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 7731f7c7e79..f3eb26cd848 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -26,7 +26,7 @@
 
 #include "cpufreq_governor.h"
 
-/* On-demand governor macors */
+/* On-demand governor macros */
 #define DEF_FREQUENCY_DOWN_DIFFERENTIAL		(10)
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
@@ -47,7 +47,8 @@ static struct cpufreq_governor cpufreq_gov_ondemand;
 static struct od_dbs_tuners od_tuners = {
 	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
 	.sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
-	.down_differential = DEF_FREQUENCY_DOWN_DIFFERENTIAL,
+	.adj_up_threshold = DEF_FREQUENCY_UP_THRESHOLD -
+			    DEF_FREQUENCY_DOWN_DIFFERENTIAL,
 	.ignore_nice = 0,
 	.powersave_bias = 0,
 };
@@ -65,7 +66,7 @@ static void ondemand_powersave_bias_init_cpu(int cpu)
  * 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.
+ * Mike Chan (android.com) claims 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.
  */
@@ -73,7 +74,7 @@ static int should_io_be_busy(void)
 {
 #if defined(CONFIG_X86)
 	/*
-	 * For Intel, Core 2 (model 15) andl later have an efficient idle.
+	 * For Intel, Core 2 (model 15) and later have an efficient idle.
 	 */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
 			boot_cpu_data.x86 == 6 &&
@@ -158,8 +159,8 @@ static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
 
 /*
  * Every sampling_rate, we check, if current idle time is less than 20%
- * (default), then we try to increase frequency Every sampling_rate, we look for
- * a the lowest frequency which can sustain the load while keeping idle time
+ * (default), then we try to increase frequency. Every sampling_rate, we look
+ * for the lowest frequency which can sustain the load while keeping idle time
  * over 30%. If such a frequency exist, we try to decrease to this frequency.
  *
  * Any frequency increase takes it to the maximum frequency. Frequency reduction
@@ -192,11 +193,9 @@ static void od_check_cpu(int cpu, unsigned int load_freq)
 	 * support the current CPU usage without triggering the up policy. To be
 	 * safe, we focus 10 points under the threshold.
 	 */
-	if (load_freq < (od_tuners.up_threshold - od_tuners.down_differential) *
-			policy->cur) {
+	if (load_freq < od_tuners.adj_up_threshold * policy->cur) {
 		unsigned int freq_next;
-		freq_next = load_freq / (od_tuners.up_threshold -
-				od_tuners.down_differential);
+		freq_next = load_freq / od_tuners.adj_up_threshold;
 
 		/* No longer fully busy, reset rate_mult */
 		dbs_info->rate_mult = 1;
@@ -218,33 +217,42 @@ static void od_check_cpu(int cpu, unsigned int load_freq)
 
 static void od_dbs_timer(struct work_struct *work)
 {
+	struct delayed_work *dw = to_delayed_work(work);
 	struct od_cpu_dbs_info_s *dbs_info =
 		container_of(work, struct od_cpu_dbs_info_s, cdbs.work.work);
-	unsigned int cpu = dbs_info->cdbs.cpu;
-	int delay, sample_type = dbs_info->sample_type;
+	unsigned int cpu = dbs_info->cdbs.cur_policy->cpu;
+	struct od_cpu_dbs_info_s *core_dbs_info = &per_cpu(od_cpu_dbs_info,
+			cpu);
+	int delay, sample_type = core_dbs_info->sample_type;
+	bool eval_load;
 
-	mutex_lock(&dbs_info->cdbs.timer_mutex);
+	mutex_lock(&core_dbs_info->cdbs.timer_mutex);
+	eval_load = need_load_eval(&core_dbs_info->cdbs,
+			od_tuners.sampling_rate);
 
 	/* Common NORMAL_SAMPLE setup */
-	dbs_info->sample_type = OD_NORMAL_SAMPLE;
+	core_dbs_info->sample_type = OD_NORMAL_SAMPLE;
 	if (sample_type == OD_SUB_SAMPLE) {
-		delay = dbs_info->freq_lo_jiffies;
-		__cpufreq_driver_target(dbs_info->cdbs.cur_policy,
-			dbs_info->freq_lo, CPUFREQ_RELATION_H);
+		delay = core_dbs_info->freq_lo_jiffies;
+		if (eval_load)
+			__cpufreq_driver_target(core_dbs_info->cdbs.cur_policy,
+						core_dbs_info->freq_lo,
+						CPUFREQ_RELATION_H);
 	} else {
-		dbs_check_cpu(&od_dbs_data, cpu);
-		if (dbs_info->freq_lo) {
+		if (eval_load)
+			dbs_check_cpu(&od_dbs_data, cpu);
+		if (core_dbs_info->freq_lo) {
 			/* Setup timer for SUB_SAMPLE */
-			dbs_info->sample_type = OD_SUB_SAMPLE;
-			delay = dbs_info->freq_hi_jiffies;
+			core_dbs_info->sample_type = OD_SUB_SAMPLE;
+			delay = core_dbs_info->freq_hi_jiffies;
 		} else {
 			delay = delay_for_sampling_rate(od_tuners.sampling_rate
-						* dbs_info->rate_mult);
+						* core_dbs_info->rate_mult);
 		}
 	}
 
-	schedule_delayed_work_on(cpu, &dbs_info->cdbs.work, delay);
-	mutex_unlock(&dbs_info->cdbs.timer_mutex);
+	schedule_delayed_work_on(smp_processor_id(), dw, delay);
+	mutex_unlock(&core_dbs_info->cdbs.timer_mutex);
 }
 
 /************************** sysfs interface ************************/
@@ -259,7 +267,7 @@ static ssize_t show_sampling_rate_min(struct kobject *kobj,
  * update_sampling_rate - update sampling rate effective immediately if needed.
  * @new_rate: new sampling rate
  *
- * If new rate is smaller than the old, simply updaing
+ * If new rate is smaller than the old, simply updating
  * dbs_tuners_int.sampling_rate might not be appropriate. For example, if the
  * original sampling_rate was 1 second and the requested new sampling rate is 10
  * ms because the user needs immediate reaction from ondemand governor, but not
@@ -287,7 +295,7 @@ static void update_sampling_rate(unsigned int new_rate)
 			cpufreq_cpu_put(policy);
 			continue;
 		}
-		dbs_info = &per_cpu(od_cpu_dbs_info, policy->cpu);
+		dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 		cpufreq_cpu_put(policy);
 
 		mutex_lock(&dbs_info->cdbs.timer_mutex);
@@ -306,8 +314,7 @@ static void update_sampling_rate(unsigned int new_rate)
 			cancel_delayed_work_sync(&dbs_info->cdbs.work);
 			mutex_lock(&dbs_info->cdbs.timer_mutex);
 
-			schedule_delayed_work_on(dbs_info->cdbs.cpu,
-					&dbs_info->cdbs.work,
+			schedule_delayed_work_on(cpu, &dbs_info->cdbs.work,
 					usecs_to_jiffies(new_rate));
 
 		}
@@ -351,6 +358,10 @@ static ssize_t store_up_threshold(struct kobject *a, struct attribute *b,
 			input < MIN_FREQUENCY_UP_THRESHOLD) {
 		return -EINVAL;
 	}
+	/* Calculate the new adj_up_threshold */
+	od_tuners.adj_up_threshold += input;
+	od_tuners.adj_up_threshold -= od_tuners.up_threshold;
+
 	od_tuners.up_threshold = input;
 	return count;
 }
@@ -507,7 +518,8 @@ static int __init cpufreq_gov_dbs_init(void)
 	if (idle_time != -1ULL) {
 		/* Idle micro accounting is supported. Use finer thresholds */
 		od_tuners.up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
-		od_tuners.down_differential = MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
+		od_tuners.adj_up_threshold = MICRO_FREQUENCY_UP_THRESHOLD -
+					     MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
 		/*
 		 * In nohz/micro accounting case we set the minimum frequency
 		 * not depending on HZ, but fixed (very low). The deferred