More ACPI and power management updates for 3.17-rc1

- Fix for an ACPI-based device hotplug regression introduced in 3.14
    that causes a kernel panic to trigger when memory hot-remove is
    attempted with CONFIG_ACPI_HOTPLUG_MEMORY unset from Tang Chen.
 
  - Fix for a cpufreq regression introduced in 3.16 that triggers a
    "sleeping function called from invalid context" bug in
    dev_pm_opp_init_cpufreq_table() from Stephen Boyd.
 
  - ACPI battery driver fix for a warning message added in 3.16 that
    prints silly stuff sometimes from Mariusz Ceier.
 
  - Hibernation fix for safer handling of mismatches in the 820 memory
    map between the configurations during image creation and during
    the subsequent restore from Chun-Yi Lee.
 
  - ACPI processor driver fix to handle CPU hotplug notifications
    correctly during system suspend/resume from Lan Tianyu.
 
  - Series of four cpuidle menu governor cleanups that also should
    speed it up a bit from Mel Gorman.
 
  - Fixes for the speedstep-smi, integrator, cpu0 and arm_big_little
    cpufreq drivers from Hans Wennborg, Himangi Saraogi, Markus Pargmann
    and Uwe Kleine-König.
 
  - Version 3.0 of the analyze_suspend.py suspend profiling tool
    from Todd E Brandt.
 
 /
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABCAAGBQJT7UnNAAoJEILEb/54YlRxcxIP/ROFeak3+5tt3hkvZCevxpUh
 AMPccgUoqsF2dognO3pcR4AgGP+meM6Qw0zBjPDNx6oo87hw7P1HlngfaRPHnWPh
 iAkY2p1QhGAZW29vqxqBIdLVP9M+Nje0tvOX8/6QEsQgo2y6YCbJU0zITmvb8Tsk
 183cXiz6xXDezt4sPeIVg2QVfngVFtOeNVgHDIhldQSF6zUQJP/3+BVutvaj3olt
 2O3qpNfwJjFh9p6LWQ+CAalq3hJyNZ6ettLNCvudeq4kqRo49WAdjHaRW+qju/NR
 dWybO29MfviczABVQ1ReqSnz0MJOqhZNxkEi5KqnYBb3fx8e2XffsBFzFzTp6BJi
 bp4ALcFIu9r5ctWVxQhmgEC6uhYMIXZ681sH99HyIdzk2cNRgMxRj6u2aVe/Cczu
 Bb489CRHmOrZyXrkmENg+LkOYBNoXcT+RepH9Ex8R+TNBlKLEBKMMgPrfbFeVKWB
 Vm621tHNATJG8nJcs3zJulM2FQ0q8c2irw6WwhUxzbSOxmqSvO5zN3OgYt+c+gWk
 MmA8IhUpQBLkqBx1FMi0lOOdIW3qKZJFrU39VQEjoP4P1nXgf373NPlfgzMvEvqM
 qQ8srMKFUjYxH3g0ftWk5a2MwEjyHQpvZe0djsMCN7ZkFLwUe1ri/R9Ja2LLQcIZ
 SyVkFbbO+moXTRMA1yA9
 =kpiw
 -----END PGP SIGNATURE-----

Merge tag 'pm+acpi-3.17-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more ACPI and power management updates from Rafael Wysocki:
 "These are a couple of regression fixes, cpuidle menu governor
  optimizations, fixes for ACPI proccessor and battery drivers,
  hibernation fix to avoid problems related to the e820 memory map,
  fixes for a few cpufreq drivers and a new version of the suspend
  profiling tool analyze_suspend.py.

  Specifics:

   - Fix for an ACPI-based device hotplug regression introduced in 3.14
     that causes a kernel panic to trigger when memory hot-remove is
     attempted with CONFIG_ACPI_HOTPLUG_MEMORY unset from Tang Chen

   - Fix for a cpufreq regression introduced in 3.16 that triggers a
     "sleeping function called from invalid context" bug in
     dev_pm_opp_init_cpufreq_table() from Stephen Boyd

   - ACPI battery driver fix for a warning message added in 3.16 that
     prints silly stuff sometimes from Mariusz Ceier

   - Hibernation fix for safer handling of mismatches in the 820 memory
     map between the configurations during image creation and during the
     subsequent restore from Chun-Yi Lee

   - ACPI processor driver fix to handle CPU hotplug notifications
     correctly during system suspend/resume from Lan Tianyu

   - Series of four cpuidle menu governor cleanups that also should
     speed it up a bit from Mel Gorman

   - Fixes for the speedstep-smi, integrator, cpu0 and arm_big_little
     cpufreq drivers from Hans Wennborg, Himangi Saraogi, Markus
     Pargmann and Uwe Kleine-König

   - Version 3.0 of the analyze_suspend.py suspend profiling tool from
     Todd E Brandt"

* tag 'pm+acpi-3.17-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  ACPI / battery: Fix warning message in acpi_battery_get_state()
  PM / tools: analyze_suspend.py: update to v3.0
  cpufreq: arm_big_little: fix module license spec
  cpufreq: speedstep-smi: fix decimal printf specifiers
  ACPI / hotplug: Check scan handlers in acpi_scan_hot_remove()
  cpufreq: OPP: Avoid sleeping while atomic
  cpufreq: cpu0: Do not print error message when deferring
  cpufreq: integrator: Use set_cpus_allowed_ptr
  PM / hibernate: avoid unsafe pages in e820 reserved regions
  ACPI / processor: Make acpi_cpu_soft_notify() process CPU FROZEN events
  cpuidle: menu: Lookup CPU runqueues less
  cpuidle: menu: Call nr_iowait_cpu less times
  cpuidle: menu: Use ktime_to_us instead of reinventing the wheel
  cpuidle: menu: Use shifts when calculating averages where possible

drivers/acpi/battery.c

@@ -540,12 +540,12 @@ static int acpi_battery_get_state(struct acpi_battery *battery)
 	 */
 	if (battery->capacity_now > battery->full_charge_capacity
 	    && battery->full_charge_capacity != ACPI_BATTERY_VALUE_UNKNOWN) {
-		battery->capacity_now = battery->full_charge_capacity;
 		if (battery->capacity_now != battery->design_capacity)
 			printk_once(KERN_WARNING FW_BUG
 				"battery: reported current charge level (%d) "
 				"is higher than reported maximum charge level (%d).\n",
 				battery->capacity_now, battery->full_charge_capacity);
+		battery->capacity_now = battery->full_charge_capacity;
 	}
 
 	if (test_bit(ACPI_BATTERY_QUIRK_PERCENTAGE_CAPACITY, &battery->flags)

drivers/acpi/processor_driver.c

@@ -120,6 +120,7 @@ static int acpi_cpu_soft_notify(struct notifier_block *nfb,
 	unsigned int cpu = (unsigned long)hcpu;
 	struct acpi_processor *pr = per_cpu(processors, cpu);
 	struct acpi_device *device;
+	action &= ~CPU_TASKS_FROZEN;
 
 	/*
 	 * CPU_STARTING and CPU_DYING must not sleep. Return here since

drivers/acpi/scan.c

@@ -353,7 +353,8 @@ static int acpi_scan_hot_remove(struct acpi_device *device)
 	unsigned long long sta;
 	acpi_status status;
 
-	if (device->handler->hotplug.demand_offline && !acpi_force_hot_remove) {
+	if (device->handler && device->handler->hotplug.demand_offline
+	    && !acpi_force_hot_remove) {
 		if (!acpi_scan_is_offline(device, true))
 			return -EBUSY;
 	} else {

drivers/cpufreq/arm_big_little.c

@@ -24,6 +24,7 @@
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/export.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of_platform.h>
 #include <linux/pm_opp.h>
@@ -593,3 +594,7 @@ void bL_cpufreq_unregister(struct cpufreq_arm_bL_ops *ops)
 	arm_bL_ops = NULL;
 }
 EXPORT_SYMBOL_GPL(bL_cpufreq_unregister);
+
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
+MODULE_DESCRIPTION("Generic ARM big LITTLE cpufreq driver");
+MODULE_LICENSE("GPL v2");

drivers/cpufreq/arm_big_little_dt.c

@@ -114,4 +114,4 @@ module_platform_driver(generic_bL_platdrv);
 
 MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
 MODULE_DESCRIPTION("Generic ARM big LITTLE cpufreq driver via DT");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");

drivers/cpufreq/cpufreq-cpu0.c

@@ -137,7 +137,7 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 		 * not yet registered, we should try defering probe.
 		 */
 		if (PTR_ERR(cpu_reg) == -EPROBE_DEFER) {
-			dev_err(cpu_dev, "cpu0 regulator not ready, retry\n");
+			dev_dbg(cpu_dev, "cpu0 regulator not ready, retry\n");
 			ret = -EPROBE_DEFER;
 			goto out_put_node;
 		}

drivers/cpufreq/cpufreq_opp.c

@@ -60,7 +60,7 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 		goto out;
 	}
 
-	freq_table = kzalloc(sizeof(*freq_table) * (max_opps + 1), GFP_KERNEL);
+	freq_table = kcalloc(sizeof(*freq_table), (max_opps + 1), GFP_ATOMIC);
 	if (!freq_table) {
 		ret = -ENOMEM;
 		goto out;

drivers/cpufreq/integrator-cpufreq.c

@@ -92,7 +92,7 @@ static int integrator_set_target(struct cpufreq_policy *policy,
 	 * Bind to the specified CPU.  When this call returns,
 	 * we should be running on the right CPU.
 	 */
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 	BUG_ON(cpu != smp_processor_id());
 
 	/* get current setting */
@@ -118,7 +118,7 @@ static int integrator_set_target(struct cpufreq_policy *policy,
 	freqs.new = icst_hz(&cclk_params, vco) / 1000;
 
 	if (freqs.old == freqs.new) {
-		set_cpus_allowed(current, cpus_allowed);
+		set_cpus_allowed_ptr(current, &cpus_allowed);
 		return 0;
 	}
 
@@ -141,7 +141,7 @@ static int integrator_set_target(struct cpufreq_policy *policy,
 	/*
 	 * Restore the CPUs allowed mask.
 	 */
-	set_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, &cpus_allowed);
 
 	cpufreq_freq_transition_end(policy, &freqs, 0);
 
@@ -157,7 +157,7 @@ static unsigned int integrator_get(unsigned int cpu)
 
 	cpus_allowed = current->cpus_allowed;
 
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 	BUG_ON(cpu != smp_processor_id());
 
 	/* detect memory etc. */
@@ -173,7 +173,7 @@ static unsigned int integrator_get(unsigned int cpu)
 
 	current_freq = icst_hz(&cclk_params, vco) / 1000; /* current freq */
 
-	set_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, &cpus_allowed);
 
 	return current_freq;
 }

drivers/cpufreq/speedstep-smi.c

@@ -324,8 +324,8 @@ static int __init speedstep_init(void)
 		return -ENODEV;
 	}
 
-	pr_debug("signature:0x%.8ulx, command:0x%.8ulx, "
-		"event:0x%.8ulx, perf_level:0x%.8ulx.\n",
+	pr_debug("signature:0x%.8x, command:0x%.8x, "
+		"event:0x%.8x, perf_level:0x%.8x.\n",
 		ist_info.signature, ist_info.command,
 		ist_info.event, ist_info.perf_level);
 

drivers/cpuidle/governors/menu.c

@@ -31,7 +31,8 @@
  * The default values do not overflow.
  */
 #define BUCKETS 12
-#define INTERVALS 8
+#define INTERVAL_SHIFT 3
+#define INTERVALS (1UL << INTERVAL_SHIFT)
 #define RESOLUTION 1024
 #define DECAY 8
 #define MAX_INTERESTING 50000
@@ -133,15 +134,12 @@ struct menu_device {
 #define LOAD_INT(x) ((x) >> FSHIFT)
 #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
 
-static int get_loadavg(void)
+static inline int get_loadavg(unsigned long load)
 {
-	unsigned long this = this_cpu_load();
-
-
-	return LOAD_INT(this) * 10 + LOAD_FRAC(this) / 10;
+	return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10;
 }
 
-static inline int which_bucket(unsigned int duration)
+static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters)
 {
 	int bucket = 0;
 
@@ -151,7 +149,7 @@ static inline int which_bucket(unsigned int duration)
 	 * This allows us to calculate
 	 * E(duration)|iowait
 	 */
-	if (nr_iowait_cpu(smp_processor_id()))
+	if (nr_iowaiters)
 		bucket = BUCKETS/2;
 
 	if (duration < 10)
@@ -174,16 +172,16 @@ static inline int which_bucket(unsigned int duration)
  * to be, the higher this multiplier, and thus the higher
  * the barrier to go to an expensive C state.
  */
-static inline int performance_multiplier(void)
+static inline int performance_multiplier(unsigned long nr_iowaiters, unsigned long load)
 {
 	int mult = 1;
 
 	/* for higher loadavg, we are more reluctant */
 
-	mult += 2 * get_loadavg();
+	mult += 2 * get_loadavg(load);
 
 	/* for IO wait tasks (per cpu!) we add 5x each */
-	mult += 10 * nr_iowait_cpu(smp_processor_id());
+	mult += 10 * nr_iowaiters;
 
 	return mult;
 }
@@ -227,7 +225,10 @@ static void get_typical_interval(struct menu_device *data)
 				max = value;
 		}
 	}
-	do_div(avg, divisor);
+	if (divisor == INTERVALS)
+		avg >>= INTERVAL_SHIFT;
+	else
+		do_div(avg, divisor);
 
 	/* Then try to determine standard deviation */
 	stddev = 0;
@@ -238,7 +239,11 @@ static void get_typical_interval(struct menu_device *data)
 			stddev += diff * diff;
 		}
 	}
-	do_div(stddev, divisor);
+	if (divisor == INTERVALS)
+		stddev >>= INTERVAL_SHIFT;
+	else
+		do_div(stddev, divisor);
+
 	/*
 	 * The typical interval is obtained when standard deviation is small
 	 * or standard deviation is small compared to the average interval.
@@ -288,7 +293,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	int i;
 	unsigned int interactivity_req;
-	struct timespec t;
+	unsigned long nr_iowaiters, cpu_load;
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
@@ -302,12 +307,10 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		return 0;
 
 	/* determine the expected residency time, round up */
-	t = ktime_to_timespec(tick_nohz_get_sleep_length());
-	data->next_timer_us =
-		t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC;
+	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length());
 
-
-	data->bucket = which_bucket(data->next_timer_us);
+	get_iowait_load(&nr_iowaiters, &cpu_load);
+	data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
 
 	/*
 	 * Force the result of multiplication to be 64 bits even if both
@@ -325,7 +328,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * duration / latency ratio. Adjust the latency limit if
 	 * necessary.
 	 */
-	interactivity_req = data->predicted_us / performance_multiplier();
+	interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load);
 	if (latency_req > interactivity_req)
 		latency_req = interactivity_req;
 

include/linux/sched.h

@@ -169,8 +169,7 @@ extern int nr_processes(void);
 extern unsigned long nr_running(void);
 extern unsigned long nr_iowait(void);
 extern unsigned long nr_iowait_cpu(int cpu);
-extern unsigned long this_cpu_load(void);
-
+extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 
 extern void calc_global_load(unsigned long ticks);
 extern void update_cpu_load_nohz(void);

kernel/power/snapshot.c

@@ -954,6 +954,25 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 	}
 }
 
+static bool is_nosave_page(unsigned long pfn)
+{
+	struct nosave_region *region;
+
+	list_for_each_entry(region, &nosave_regions, list) {
+		if (pfn >= region->start_pfn && pfn < region->end_pfn) {
+			pr_err("PM: %#010llx in e820 nosave region: "
+			       "[mem %#010llx-%#010llx]\n",
+			       (unsigned long long) pfn << PAGE_SHIFT,
+			       (unsigned long long) region->start_pfn << PAGE_SHIFT,
+			       ((unsigned long long) region->end_pfn << PAGE_SHIFT)
+					- 1);
+			return true;
+		}
+	}
+
+	return false;
+}
+
 /**
  *	create_basic_memory_bitmaps - create bitmaps needed for marking page
  *	frames that should not be saved and free page frames.  The pointers
@@ -2015,7 +2034,7 @@ static int mark_unsafe_pages(struct memory_bitmap *bm)
 	do {
 		pfn = memory_bm_next_pfn(bm);
 		if (likely(pfn != BM_END_OF_MAP)) {
-			if (likely(pfn_valid(pfn)))
+			if (likely(pfn_valid(pfn)) && !is_nosave_page(pfn))
 				swsusp_set_page_free(pfn_to_page(pfn));
 			else
 				return -EFAULT;

kernel/sched/core.c

@@ -2393,6 +2393,13 @@ unsigned long nr_iowait_cpu(int cpu)
 	return atomic_read(&this->nr_iowait);
 }
 
+void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
+{
+	struct rq *this = this_rq();
+	*nr_waiters = atomic_read(&this->nr_iowait);
+	*load = this->cpu_load[0];
+}
+
 #ifdef CONFIG_SMP
 
 /*

kernel/sched/proc.c

@@ -8,13 +8,6 @@
 
 #include "sched.h"
 
-unsigned long this_cpu_load(void)
-{
-	struct rq *this = this_rq();
-	return this->cpu_load[0];
-}
-
-
 /*
  * Global load-average calculations
  *