ACPI and power management fixes for 3.11-rc4

- Revert two cpuidle commits added during the 3.8 development cycle that
   turn out to have introduced a significant performance regression as
   requested by Jeremy Eder.
 
 - The recent patches that made the freezer less heavy-weight introduced
   a regression causing user-space-driven hibernation using the ioctl()
   interface to block indefinitely when the hibernate process executes
   try_to_freeze().  Fix from Colin Cross addresses this by adding a
   process flag to mark the hibernate/suspend process to inform the
   freezer that that process should be ignored.
 
 - One of the recent cpufreq reverts uncovered a problem in the core
   causing the cpufreq driver module refcount to become negative after
   a system suspend-resume cycle.  Fix from Rafael J Wysocki.
 
 - The evaluation of the ACPI battery _BIX method has never worked
   correctly, because the commit that added support for it forgot to
   take the "Revision" field in the return package into account.  As
   a result, the reading of battery info doesn't work at all on some
   systems, which is addressed by a fix from Lan Tianyu.
 
 /
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.19 (GNU/Linux)
 
 iQIcBAABAgAGBQJR+6ptAAoJEKhOf7ml8uNsRpIP/0P2HbCFM52/4Rv/Iltnt4fI
 9Vo2dyuL7JKP2U8jtHxfhFGg3oMdYQoUIdnpjtKr4O3obhzl4vHwE9vtrRlhHpRZ
 SnHGe0W5v0eQOdCbVzdwS1NrJwckkTy1JuybV+PH66T84Usu0QoxE4iNveK2LX23
 eJvOgWGBoyEEWJb+1/KJNIcKk77A0Cnc2CCLMN5bmhwH1QGDRZdzSnrjK5fGniF0
 akCGq8jJhBaI1xJF/42LgNBiPpAYk42SPuiSOqniKzweUK1P6YzHjArh0qaTBoUj
 27HRkZlY6Y8WLFxqQio7zvbbLSdRuwosESofw2kCFkAAEnCc71kw2nbebNr3sCap
 MqrmEMcxqT803PiB2RGyS53WNE7mM3NFCPRLOPL+cWeNQhoYzbZ+UiNx4Dw667cr
 Ow+egCY+jyAZm5TFqY6Y75lG61UM6oCs6M6iIwiv/BOmJqCmkTjvNBxHWrVcWxin
 YhiLJGyt7iAcIaxhy+fCs2j2a7B0Ai62kZ6YLqaEtNBzjuDbm6sr61A6Nu8bpOTU
 C7e76AocyfuDpdU99uawDvuazCGWEg+f8eH8C/ij19jF1/Mrlr0x+4x9MmMm9Iz5
 ux0uroTteEuswz9aHmY270qdDLIuSGUsmqD05RoaO61U8dVigWw+ZKqUCImrAM7x
 4bK1+2eOig794g9vSsen
 =7x7r
 -----END PGP SIGNATURE-----

Merge tag 'pm+acpi-3.11-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull ACPI and power management fixes from Rafael Wysocki:

 - Revert two cpuidle commits added during the 3.8 development cycle
   that turn out to have introduced a significant performance regression
   as requested by Jeremy Eder.

 - The recent patches that made the freezer less heavy-weight introduced
   a regression causing user-space-driven hibernation using the ioctl()
   interface to block indefinitely when the hibernate process executes
   try_to_freeze().  Fix from Colin Cross addresses this by adding a
   process flag to mark the hibernate/suspend process to inform the
   freezer that that process should be ignored.

 - One of the recent cpufreq reverts uncovered a problem in the core
   causing the cpufreq driver module refcount to become negative after a
   system suspend-resume cycle.  Fix from Rafael J Wysocki.

 - The evaluation of the ACPI battery _BIX method has never worked
   correctly, because the commit that added support for it forgot to
   take the "Revision" field in the return package into account.  As a
   result, the reading of battery info doesn't work at all on some
   systems, which is addressed by a fix from Lan Tianyu.

* tag 'pm+acpi-3.11-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  freezer: set PF_SUSPEND_TASK flag on tasks that call freeze_processes
  ACPI / battery: Fix parsing _BIX return value
  cpufreq: Fix cpufreq driver module refcount balance after suspend/resume
  Revert "cpuidle: Quickly notice prediction failure for repeat mode"
  Revert "cpuidle: Quickly notice prediction failure in general case"

drivers/acpi/battery.c

@@ -117,6 +117,7 @@ struct acpi_battery {
 	struct acpi_device *device;
 	struct notifier_block pm_nb;
 	unsigned long update_time;
+	int revision;
 	int rate_now;
 	int capacity_now;
 	int voltage_now;
@@ -359,6 +360,7 @@ static struct acpi_offsets info_offsets[] = {
 };
 
 static struct acpi_offsets extended_info_offsets[] = {
+	{offsetof(struct acpi_battery, revision), 0},
 	{offsetof(struct acpi_battery, power_unit), 0},
 	{offsetof(struct acpi_battery, design_capacity), 0},
 	{offsetof(struct acpi_battery, full_charge_capacity), 0},

drivers/cpufreq/cpufreq.c

@@ -1177,14 +1177,11 @@ static int __cpufreq_remove_dev(struct device *dev,
 				__func__, cpu_dev->id, cpu);
 	}
 
-	if ((cpus == 1) && (cpufreq_driver->target))
-		__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
-
-	pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
-	cpufreq_cpu_put(data);
-
 	/* If cpu is last user of policy, free policy */
 	if (cpus == 1) {
+		if (cpufreq_driver->target)
+			__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
+
 		lock_policy_rwsem_read(cpu);
 		kobj = &data->kobj;
 		cmp = &data->kobj_unregister;
@@ -1205,10 +1202,14 @@ static int __cpufreq_remove_dev(struct device *dev,
 		free_cpumask_var(data->related_cpus);
 		free_cpumask_var(data->cpus);
 		kfree(data);
-	} else if (cpufreq_driver->target) {
+	} else {
+		pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
+		cpufreq_cpu_put(data);
+		if (cpufreq_driver->target) {
 			__cpufreq_governor(data, CPUFREQ_GOV_START);
 			__cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
 		}
+	}
 
 	per_cpu(cpufreq_policy_cpu, cpu) = -1;
 	return 0;

drivers/cpuidle/governors/menu.c

@@ -28,13 +28,6 @@
 #define MAX_INTERESTING 50000
 #define STDDEV_THRESH 400
 
-/* 60 * 60 > STDDEV_THRESH * INTERVALS = 400 * 8 */
-#define MAX_DEVIATION 60
-
-static DEFINE_PER_CPU(struct hrtimer, menu_hrtimer);
-static DEFINE_PER_CPU(int, hrtimer_status);
-/* menu hrtimer mode */
-enum {MENU_HRTIMER_STOP, MENU_HRTIMER_REPEAT, MENU_HRTIMER_GENERAL};
 
 /*
  * Concepts and ideas behind the menu governor
@@ -116,13 +109,6 @@ enum {MENU_HRTIMER_STOP, MENU_HRTIMER_REPEAT, MENU_HRTIMER_GENERAL};
  *
  */
 
-/*
- * The C-state residency is so long that is is worthwhile to exit
- * from the shallow C-state and re-enter into a deeper C-state.
- */
-static unsigned int perfect_cstate_ms __read_mostly = 30;
-module_param(perfect_cstate_ms, uint, 0000);
-
 struct menu_device {
 	int		last_state_idx;
 	int             needs_update;
@@ -205,52 +191,17 @@ static u64 div_round64(u64 dividend, u32 divisor)
 	return div_u64(dividend + (divisor / 2), divisor);
 }
 
-/* Cancel the hrtimer if it is not triggered yet */
-void menu_hrtimer_cancel(void)
-{
-	int cpu = smp_processor_id();
-	struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
-
-	/* The timer is still not time out*/
-	if (per_cpu(hrtimer_status, cpu)) {
-		hrtimer_cancel(hrtmr);
-		per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_STOP;
-	}
-}
-EXPORT_SYMBOL_GPL(menu_hrtimer_cancel);
-
-/* Call back for hrtimer is triggered */
-static enum hrtimer_restart menu_hrtimer_notify(struct hrtimer *hrtimer)
-{
-	int cpu = smp_processor_id();
-	struct menu_device *data = &per_cpu(menu_devices, cpu);
-
-	/* In general case, the expected residency is much larger than
-	 *  deepest C-state target residency, but prediction logic still
-	 *  predicts a small predicted residency, so the prediction
-	 *  history is totally broken if the timer is triggered.
-	 *  So reset the correction factor.
-	 */
-	if (per_cpu(hrtimer_status, cpu) == MENU_HRTIMER_GENERAL)
-		data->correction_factor[data->bucket] = RESOLUTION * DECAY;
-
-	per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_STOP;
-
-	return HRTIMER_NORESTART;
-}
-
 /*
  * Try detecting repeating patterns by keeping track of the last 8
  * intervals, and checking if the standard deviation of that set
  * of points is below a threshold. If it is... then use the
  * average of these 8 points as the estimated value.
  */
-static u32 get_typical_interval(struct menu_device *data)
+static void get_typical_interval(struct menu_device *data)
 {
 	int i = 0, divisor = 0;
 	uint64_t max = 0, avg = 0, stddev = 0;
 	int64_t thresh = LLONG_MAX; /* Discard outliers above this value. */
-	unsigned int ret = 0;
 
 again:
 
@@ -291,16 +242,13 @@ static u32 get_typical_interval(struct menu_device *data)
 	if (((avg > stddev * 6) && (divisor * 4 >= INTERVALS * 3))
 							|| stddev <= 20) {
 		data->predicted_us = avg;
-		ret = 1;
+		return;
-		return ret;
 
 	} else if ((divisor * 4) > INTERVALS * 3) {
 		/* Exclude the max interval */
 		thresh = max - 1;
 		goto again;
 	}
-
-	return ret;
 }
 
 /**
@@ -315,9 +263,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	int i;
 	int multiplier;
 	struct timespec t;
-	int repeat = 0, low_predicted = 0;
-	int cpu = smp_processor_id();
-	struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
@@ -352,7 +297,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket],
 					 RESOLUTION * DECAY);
 
-	repeat = get_typical_interval(data);
+	get_typical_interval(data);
 
 	/*
 	 * We want to default to C1 (hlt), not to busy polling
@@ -373,10 +318,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 		if (s->disabled || su->disable)
 			continue;
-		if (s->target_residency > data->predicted_us) {
+		if (s->target_residency > data->predicted_us)
-			low_predicted = 1;
 			continue;
-		}
 		if (s->exit_latency > latency_req)
 			continue;
 		if (s->exit_latency * multiplier > data->predicted_us)
@@ -386,44 +329,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		data->exit_us = s->exit_latency;
 	}
 
-	/* not deepest C-state chosen for low predicted residency */
-	if (low_predicted) {
-		unsigned int timer_us = 0;
-		unsigned int perfect_us = 0;
-
-		/*
-		 * Set a timer to detect whether this sleep is much
-		 * longer than repeat mode predicted.  If the timer
-		 * triggers, the code will evaluate whether to put
-		 * the CPU into a deeper C-state.
-		 * The timer is cancelled on CPU wakeup.
-		 */
-		timer_us = 2 * (data->predicted_us + MAX_DEVIATION);
-
-		perfect_us = perfect_cstate_ms * 1000;
-
-		if (repeat && (4 * timer_us < data->expected_us)) {
-			RCU_NONIDLE(hrtimer_start(hrtmr,
-				ns_to_ktime(1000 * timer_us),
-				HRTIMER_MODE_REL_PINNED));
-			/* In repeat case, menu hrtimer is started */
-			per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_REPEAT;
-		} else if (perfect_us < data->expected_us) {
-			/*
-			 * The next timer is long. This could be because
-			 * we did not make a useful prediction.
-			 * In that case, it makes sense to re-enter
-			 * into a deeper C-state after some time.
-			 */
-			RCU_NONIDLE(hrtimer_start(hrtmr,
-				ns_to_ktime(1000 * timer_us),
-				HRTIMER_MODE_REL_PINNED));
-			/* In general case, menu hrtimer is started */
-			per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_GENERAL;
-		}
-
-	}
-
 	return data->last_state_idx;
 }
 
@@ -514,9 +419,6 @@ static int menu_enable_device(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev)
 {
 	struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
-	struct hrtimer *t = &per_cpu(menu_hrtimer, dev->cpu);
-	hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	t->function = menu_hrtimer_notify;
 
 	memset(data, 0, sizeof(struct menu_device));
 

include/linux/sched.h

@@ -1628,6 +1628,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
+#define PF_SUSPEND_TASK 0x80000000      /* this thread called freeze_processes and should not be frozen */
 
 /*
  * Only the _current_ task can read/write to tsk->flags, but other

include/linux/tick.h

@@ -174,10 +174,4 @@ static inline void tick_nohz_task_switch(struct task_struct *tsk) { }
 #endif
 
 
-# ifdef CONFIG_CPU_IDLE_GOV_MENU
-extern void menu_hrtimer_cancel(void);
-# else
-static inline void menu_hrtimer_cancel(void) {}
-# endif /* CONFIG_CPU_IDLE_GOV_MENU */
-
 #endif

kernel/freezer.c

@@ -33,7 +33,7 @@ static DEFINE_SPINLOCK(freezer_lock);
  */
 bool freezing_slow_path(struct task_struct *p)
 {
-	if (p->flags & PF_NOFREEZE)
+	if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK))
 		return false;
 
 	if (pm_nosig_freezing || cgroup_freezing(p))

kernel/power/process.c

@@ -109,6 +109,8 @@ static int try_to_freeze_tasks(bool user_only)
 
 /**
  * freeze_processes - Signal user space processes to enter the refrigerator.
+ * The current thread will not be frozen.  The same process that calls
+ * freeze_processes must later call thaw_processes.
  *
  * On success, returns 0.  On failure, -errno and system is fully thawed.
  */
@@ -120,6 +122,9 @@ int freeze_processes(void)
 	if (error)
 		return error;
 
+	/* Make sure this task doesn't get frozen */
+	current->flags |= PF_SUSPEND_TASK;
+
 	if (!pm_freezing)
 		atomic_inc(&system_freezing_cnt);
 
@@ -168,6 +173,7 @@ int freeze_kernel_threads(void)
 void thaw_processes(void)
 {
 	struct task_struct *g, *p;
+	struct task_struct *curr = current;
 
 	if (pm_freezing)
 		atomic_dec(&system_freezing_cnt);
@@ -182,10 +188,15 @@ void thaw_processes(void)
 
 	read_lock(&tasklist_lock);
 	do_each_thread(g, p) {
+		/* No other threads should have PF_SUSPEND_TASK set */
+		WARN_ON((p != curr) && (p->flags & PF_SUSPEND_TASK));
 		__thaw_task(p);
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
 
+	WARN_ON(!(curr->flags & PF_SUSPEND_TASK));
+	curr->flags &= ~PF_SUSPEND_TASK;
+
 	usermodehelper_enable();
 
 	schedule();

kernel/time/tick-sched.c

@@ -827,14 +827,11 @@ void tick_nohz_irq_exit(void)
 {
 	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 
-	if (ts->inidle) {
+	if (ts->inidle)
-		/* Cancel the timer because CPU already waken up from the C-states*/
-		menu_hrtimer_cancel();
 		__tick_nohz_idle_enter(ts);
-	} else {
+	else
 		tick_nohz_full_stop_tick(ts);
 }
-}
 
 /**
  * tick_nohz_get_sleep_length - return the length of the current sleep
@@ -931,8 +928,6 @@ void tick_nohz_idle_exit(void)
 
 	ts->inidle = 0;
 
-	/* Cancel the timer because CPU already waken up from the C-states*/
-	menu_hrtimer_cancel();
 	if (ts->idle_active || ts->tick_stopped)
 		now = ktime_get();