Merge tag 'pm-4.17-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These include one big-ticket item which is the rework of the idle loop
  in order to prevent CPUs from spending too much time in shallow idle
  states. It reduces idle power on some systems by 10% or more and may
  improve performance of workloads in which the idle loop overhead
  matters. This has been in the works for several weeks and it has been
  tested and reviewed quite thoroughly.

  Also included are changes that finalize the cpufreq cleanup moving
  frequency table validation from drivers to the core, a few fixes and
  cleanups of cpufreq drivers, a cpuidle documentation update and a PM
  QoS core update to mark the expected switch fall-throughs in it.

  Specifics:

   - Rework the idle loop in order to prevent CPUs from spending too
     much time in shallow idle states by making it stop the scheduler
     tick before putting the CPU into an idle state only if the idle
     duration predicted by the idle governor is long enough.

     That required the code to be reordered to invoke the idle governor
     before stopping the tick, among other things (Rafael Wysocki,
     Frederic Weisbecker, Arnd Bergmann).

   - Add the missing description of the residency sysfs attribute to the
     cpuidle documentation (Prashanth Prakash).

   - Finalize the cpufreq cleanup moving frequency table validation from
     drivers to the core (Viresh Kumar).

   - Fix a clock leak regression in the armada-37xx cpufreq driver
     (Gregory Clement).

   - Fix the initialization of the CPU performance data structures for
     shared policies in the CPPC cpufreq driver (Shunyong Yang).

   - Clean up the ti-cpufreq, intel_pstate and CPPC cpufreq drivers a
     bit (Viresh Kumar, Rafael Wysocki).

   - Mark the expected switch fall-throughs in the PM QoS core (Gustavo
     Silva)"

* tag 'pm-4.17-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (23 commits)
  tick-sched: avoid a maybe-uninitialized warning
  cpufreq: Drop cpufreq_table_validate_and_show()
  cpufreq: SCMI: Don't validate the frequency table twice
  cpufreq: CPPC: Initialize shared perf capabilities of CPUs
  cpufreq: armada-37xx: Fix clock leak
  cpufreq: CPPC: Don't set transition_latency
  cpufreq: ti-cpufreq: Use builtin_platform_driver()
  cpufreq: intel_pstate: Do not include debugfs.h
  PM / QoS: mark expected switch fall-throughs
  cpuidle: Add definition of residency to sysfs documentation
  time: hrtimer: Use timerqueue_iterate_next() to get to the next timer
  nohz: Avoid duplication of code related to got_idle_tick
  nohz: Gather tick_sched booleans under a common flag field
  cpuidle: menu: Avoid selecting shallow states with stopped tick
  cpuidle: menu: Refine idle state selection for running tick
  sched: idle: Select idle state before stopping the tick
  time: hrtimer: Introduce hrtimer_next_event_without()
  time: tick-sched: Split tick_nohz_stop_sched_tick()
  cpuidle: Return nohz hint from cpuidle_select()
  jiffies: Introduce USER_TICK_USEC and redefine TICK_USEC
  ...

Documentation/cpu-freq/core.txt

@@ -97,12 +97,10 @@ flags	- flags of the cpufreq driver
 ==================================================================
 For details about OPP, see Documentation/power/opp.txt
 
-dev_pm_opp_init_cpufreq_table - cpufreq framework typically is initialized with
-	cpufreq_table_validate_and_show() which is provided with the list of
-	frequencies that are available for operation. This function provides
-	a ready to use conversion routine to translate the OPP layer's internal
-	information about the available frequencies into a format readily
-	providable to cpufreq.
+dev_pm_opp_init_cpufreq_table -
+	This function provides a ready to use conversion routine to translate
+	the OPP layer's internal information about the available frequencies
+	into a format readily providable to cpufreq.
 
 	WARNING: Do not use this function in interrupt context.
 
@@ -112,7 +110,7 @@ dev_pm_opp_init_cpufreq_table - cpufreq framework typically is initialized with
 		/* Do things */
 		r = dev_pm_opp_init_cpufreq_table(dev, &freq_table);
 		if (!r)
-			cpufreq_table_validate_and_show(policy, freq_table);
+			policy->freq_table = freq_table;
 		/* Do other things */
 	 }
 

Documentation/cpu-freq/cpu-drivers.txt

@@ -259,10 +259,8 @@ CPUFREQ_ENTRY_INVALID. The entries don't need to be in sorted in any
 particular order, but if they are cpufreq core will do DVFS a bit
 quickly for them as search for best match is faster.
 
-By calling cpufreq_table_validate_and_show(), the cpuinfo.min_freq and
-cpuinfo.max_freq values are detected, and policy->min and policy->max
-are set to the same values. This is helpful for the per-CPU
-initialization stage.
+The cpufreq table is verified automatically by the core if the policy contains a
+valid pointer in its policy->freq_table field.
 
 cpufreq_frequency_table_verify() assures that at least one valid
 frequency is within policy->min and policy->max, and all other criteria

Documentation/cpuidle/sysfs.txt

@@ -40,6 +40,7 @@ total 0
 -r--r--r-- 1 root root 4096 Feb  8 10:42 latency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 name
 -r--r--r-- 1 root root 4096 Feb  8 10:42 power
+-r--r--r-- 1 root root 4096 Feb  8 10:42 residency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 time
 -r--r--r-- 1 root root 4096 Feb  8 10:42 usage
 
@@ -50,6 +51,7 @@ total 0
 -r--r--r-- 1 root root 4096 Feb  8 10:42 latency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 name
 -r--r--r-- 1 root root 4096 Feb  8 10:42 power
+-r--r--r-- 1 root root 4096 Feb  8 10:42 residency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 time
 -r--r--r-- 1 root root 4096 Feb  8 10:42 usage
 
@@ -60,6 +62,7 @@ total 0
 -r--r--r-- 1 root root 4096 Feb  8 10:42 latency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 name
 -r--r--r-- 1 root root 4096 Feb  8 10:42 power
+-r--r--r-- 1 root root 4096 Feb  8 10:42 residency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 time
 -r--r--r-- 1 root root 4096 Feb  8 10:42 usage
 
@@ -70,6 +73,7 @@ total 0
 -r--r--r-- 1 root root 4096 Feb  8 10:42 latency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 name
 -r--r--r-- 1 root root 4096 Feb  8 10:42 power
+-r--r--r-- 1 root root 4096 Feb  8 10:42 residency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 time
 -r--r--r-- 1 root root 4096 Feb  8 10:42 usage
 --------------------------------------------------------------------------------
@@ -78,6 +82,8 @@ total 0
 * desc : Small description about the idle state (string)
 * disable : Option to disable this idle state (bool) -> see note below
 * latency : Latency to exit out of this idle state (in microseconds)
+* residency : Time after which a state becomes more effecient than any
+  shallower state (in microseconds)
 * name : Name of the idle state (string)
 * power : Power consumed while in this idle state (in milliwatts)
 * time : Total time spent in this idle state (in microseconds)

arch/x86/xen/smp_pv.c

@@ -425,6 +425,7 @@ static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */
 	 * data back is to call:
 	 */
 	tick_nohz_idle_enter();
+	tick_nohz_idle_stop_tick_protected();
 
 	cpuhp_online_idle(CPUHP_AP_ONLINE_IDLE);
 }

drivers/cpufreq/armada-37xx-cpufreq.c

@@ -202,6 +202,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	cur_frequency = clk_get_rate(clk);
 	if (!cur_frequency) {
 		dev_err(cpu_dev, "Failed to get clock rate for CPU\n");
+		clk_put(clk);
 		return -EINVAL;
 	}
 
@@ -210,6 +211,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 		return -EINVAL;
 
 	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
+	clk_put(clk);
 
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
 	     load_lvl++) {

drivers/cpufreq/cppc_cpufreq.c

@@ -162,14 +162,23 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		cpu->perf_caps.highest_perf;
 	policy->cpuinfo.max_freq = cppc_dmi_max_khz;
 
-	policy->cpuinfo.transition_latency = cppc_get_transition_latency(cpu_num);
 	policy->transition_delay_us = cppc_get_transition_latency(cpu_num) /
 		NSEC_PER_USEC;
 	policy->shared_type = cpu->shared_type;
 
-	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
+	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
+		int i;
+
 		cpumask_copy(policy->cpus, cpu->shared_cpu_map);
-	else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) {
+
+		for_each_cpu(i, policy->cpus) {
+			if (unlikely(i == policy->cpu))
+				continue;
+
+			memcpy(&all_cpu_data[i]->perf_caps, &cpu->perf_caps,
+			       sizeof(cpu->perf_caps));
+		}
+	} else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) {
 		/* Support only SW_ANY for now. */
 		pr_debug("Unsupported CPU co-ord type\n");
 		return -EFAULT;

drivers/cpufreq/freq_table.c

@@ -352,20 +352,6 @@ static int set_freq_table_sorted(struct cpufreq_policy *policy)
 	return 0;
 }
 
-int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
-				      struct cpufreq_frequency_table *table)
-{
-	int ret;
-
-	ret = cpufreq_frequency_table_cpuinfo(policy, table);
-	if (ret)
-		return ret;
-
-	policy->freq_table = table;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
-
 int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy)
 {
 	int ret;

drivers/cpufreq/intel_pstate.c

@@ -26,7 +26,6 @@
 #include <linux/sysfs.h>
 #include <linux/types.h>
 #include <linux/fs.h>
-#include <linux/debugfs.h>
 #include <linux/acpi.h>
 #include <linux/vmalloc.h>
 #include <trace/events/power.h>

drivers/cpufreq/scmi-cpufreq.c

@@ -159,13 +159,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	priv->domain_id = handle->perf_ops->device_domain_id(cpu_dev);
 
 	policy->driver_data = priv;
-
-	ret = cpufreq_table_validate_and_show(policy, freq_table);
-	if (ret) {
-		dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__,
-			ret);
-		goto out_free_cpufreq_table;
-	}
+	policy->freq_table = freq_table;
 
 	/* SCMI allows DVFS request for any domain from any CPU */
 	policy->dvfs_possible_from_any_cpu = true;
@@ -179,8 +173,6 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	policy->fast_switch_possible = true;
 	return 0;
 
-out_free_cpufreq_table:
-	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 out_free_priv:
 	kfree(priv);
 out_free_opp:

drivers/cpufreq/ti-cpufreq.c

@@ -304,7 +304,7 @@ static struct platform_driver ti_cpufreq_driver = {
 		.name = "ti-cpufreq",
 	},
 };
-module_platform_driver(ti_cpufreq_driver);
+builtin_platform_driver(ti_cpufreq_driver);
 
 MODULE_DESCRIPTION("TI CPUFreq/OPP hw-supported driver");
 MODULE_AUTHOR("Dave Gerlach <d-gerlach@ti.com>");

drivers/cpuidle/cpuidle.c

@@ -272,12 +272,18 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
  *
  * @drv: the cpuidle driver
  * @dev: the cpuidle device
+ * @stop_tick: indication on whether or not to stop the tick
  *
  * Returns the index of the idle state.  The return value must not be negative.
+ *
+ * The memory location pointed to by @stop_tick is expected to be written the
+ * 'false' boolean value if the scheduler tick should not be stopped before
+ * entering the returned state.
  */
-int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
+		   bool *stop_tick)
 {
-	return cpuidle_curr_governor->select(drv, dev);
+	return cpuidle_curr_governor->select(drv, dev, stop_tick);
 }
 
 /**

drivers/cpuidle/governors/ladder.c

@@ -63,9 +63,10 @@ static inline void ladder_do_selection(struct ladder_device *ldev,
  * ladder_select_state - selects the next state to enter
  * @drv: cpuidle driver
  * @dev: the CPU
+ * @dummy: not used
  */
 static int ladder_select_state(struct cpuidle_driver *drv,
-				struct cpuidle_device *dev)
+			       struct cpuidle_device *dev, bool *dummy)
 {
 	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	struct device *device = get_cpu_device(dev->cpu);

drivers/cpuidle/governors/menu.c

@@ -123,6 +123,7 @@
 struct menu_device {
 	int		last_state_idx;
 	int             needs_update;
+	int             tick_wakeup;
 
 	unsigned int	next_timer_us;
 	unsigned int	predicted_us;
@@ -279,8 +280,10 @@ static unsigned int get_typical_interval(struct menu_device *data)
  * menu_select - selects the next idle state to enter
  * @drv: cpuidle driver containing state data
  * @dev: the CPU
+ * @stop_tick: indication on whether or not to stop the tick
  */
-static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
+		       bool *stop_tick)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	struct device *device = get_cpu_device(dev->cpu);
@@ -292,6 +295,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	unsigned int expected_interval;
 	unsigned long nr_iowaiters, cpu_load;
 	int resume_latency = dev_pm_qos_raw_read_value(device);
+	ktime_t delta_next;
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
@@ -303,11 +307,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		latency_req = resume_latency;
 
 	/* Special case when user has set very strict latency requirement */
-	if (unlikely(latency_req == 0))
+	if (unlikely(latency_req == 0)) {
+		*stop_tick = false;
 		return 0;
+	}
 
 	/* determine the expected residency time, round up */
-	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length());
+	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next));
 
 	get_iowait_load(&nr_iowaiters, &cpu_load);
 	data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
@@ -346,6 +352,20 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 */
 	data->predicted_us = min(data->predicted_us, expected_interval);
 
+	if (tick_nohz_tick_stopped()) {
+		/*
+		 * If the tick is already stopped, the cost of possible short
+		 * idle duration misprediction is much higher, because the CPU
+		 * may be stuck in a shallow idle state for a long time as a
+		 * result of it.  In that case say we might mispredict and try
+		 * to force the CPU into a state for which we would have stopped
+		 * the tick, unless a timer is going to expire really soon
+		 * anyway.
+		 */
+		if (data->predicted_us < TICK_USEC)
+			data->predicted_us = min_t(unsigned int, TICK_USEC,
+						   ktime_to_us(delta_next));
+	} else {
 		/*
 		 * Use the performance multiplier and the user-configurable
 		 * latency_req to determine the maximum exit latency.
@@ -353,7 +373,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load);
 		if (latency_req > interactivity_req)
 			latency_req = interactivity_req;
+	}
 
+	expected_interval = data->predicted_us;
 	/*
 	 * Find the idle state with the lowest power while satisfying
 	 * our constraints.
@@ -369,15 +391,52 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 			idx = i; /* first enabled state */
 		if (s->target_residency > data->predicted_us)
 			break;
-		if (s->exit_latency > latency_req)
+		if (s->exit_latency > latency_req) {
+			/*
+			 * If we break out of the loop for latency reasons, use
+			 * the target residency of the selected state as the
+			 * expected idle duration so that the tick is retained
+			 * as long as that target residency is low enough.
+			 */
+			expected_interval = drv->states[idx].target_residency;
 			break;
-
+		}
 		idx = i;
 	}
 
 	if (idx == -1)
 		idx = 0; /* No states enabled. Must use 0. */
 
+	/*
+	 * Don't stop the tick if the selected state is a polling one or if the
+	 * expected idle duration is shorter than the tick period length.
+	 */
+	if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) ||
+	    expected_interval < TICK_USEC) {
+		unsigned int delta_next_us = ktime_to_us(delta_next);
+
+		*stop_tick = false;
+
+		if (!tick_nohz_tick_stopped() && idx > 0 &&
+		    drv->states[idx].target_residency > delta_next_us) {
+			/*
+			 * The tick is not going to be stopped and the target
+			 * residency of the state to be returned is not within
+			 * the time until the next timer event including the
+			 * tick, so try to correct that.
+			 */
+			for (i = idx - 1; i >= 0; i--) {
+			    if (drv->states[i].disabled ||
+			        dev->states_usage[i].disable)
+					continue;
+
+				idx = i;
+				if (drv->states[i].target_residency <= delta_next_us)
+					break;
+			}
+		}
+	}
+
 	data->last_state_idx = idx;
 
 	return data->last_state_idx;
@@ -397,6 +456,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index)
 
 	data->last_state_idx = index;
 	data->needs_update = 1;
+	data->tick_wakeup = tick_nohz_idle_got_tick();
 }
 
 /**
@@ -427,6 +487,18 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * assume the state was never reached and the exit latency is 0.
 	 */
 
+	if (data->tick_wakeup && data->next_timer_us > TICK_USEC) {
+		/*
+		 * The nohz code said that there wouldn't be any events within
+		 * the tick boundary (if the tick was stopped), but the idle
+		 * duration predictor had a differing opinion.  Since the CPU
+		 * was woken up by a tick (that wasn't stopped after all), the
+		 * predictor was not quite right, so assume that the CPU could
+		 * have been idle long (but not forever) to help the idle
+		 * duration predictor do a better job next time.
+		 */
+		measured_us = 9 * MAX_INTERESTING / 10;
+	} else {
 		/* measured value */
 		measured_us = cpuidle_get_last_residency(dev);
 
@@ -435,6 +507,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 			measured_us -= target->exit_latency;
 		else
 			measured_us /= 2;
+	}
 
 	/* Make sure our coefficients do not exceed unity */
 	if (measured_us > data->next_timer_us)

drivers/net/ethernet/sfc/mcdi.c

@@ -375,7 +375,7 @@ static int efx_mcdi_poll(struct efx_nic *efx)
 	 * because generally mcdi responses are fast. After that, back off
 	 * and poll once a jiffy (approximately)
 	 */
-	spins = TICK_USEC;
+	spins = USER_TICK_USEC;
 	finish = jiffies + MCDI_RPC_TIMEOUT;
 
 	while (1) {

include/linux/cpufreq.h

@@ -960,8 +960,6 @@ extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;
 extern struct freq_attr *cpufreq_generic_attr[];
-int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
-				      struct cpufreq_frequency_table *table);
 int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy);
 
 unsigned int cpufreq_generic_get(unsigned int cpu);

include/linux/cpuidle.h

@@ -135,7 +135,8 @@ extern bool cpuidle_not_available(struct cpuidle_driver *drv,
 				  struct cpuidle_device *dev);
 
 extern int cpuidle_select(struct cpuidle_driver *drv,
-			  struct cpuidle_device *dev);
+			  struct cpuidle_device *dev,
+			  bool *stop_tick);
 extern int cpuidle_enter(struct cpuidle_driver *drv,
 			 struct cpuidle_device *dev, int index);
 extern void cpuidle_reflect(struct cpuidle_device *dev, int index);
@@ -167,7 +168,7 @@ static inline bool cpuidle_not_available(struct cpuidle_driver *drv,
 					 struct cpuidle_device *dev)
 {return true; }
 static inline int cpuidle_select(struct cpuidle_driver *drv,
-				 struct cpuidle_device *dev)
+				 struct cpuidle_device *dev, bool *stop_tick)
 {return -ENODEV; }
 static inline int cpuidle_enter(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
@@ -250,7 +251,8 @@ struct cpuidle_governor {
 					struct cpuidle_device *dev);
 
 	int  (*select)		(struct cpuidle_driver *drv,
-					struct cpuidle_device *dev);
+					struct cpuidle_device *dev,
+					bool *stop_tick);
 	void (*reflect)		(struct cpuidle_device *dev, int index);
 };
 

include/linux/hrtimer.h

@@ -424,6 +424,7 @@ static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 }
 
 extern u64 hrtimer_get_next_event(void);
+extern u64 hrtimer_next_event_without(const struct hrtimer *exclude);
 
 extern bool hrtimer_active(const struct hrtimer *timer);
 

include/linux/jiffies.h

@@ -62,8 +62,11 @@ extern int register_refined_jiffies(long clock_tick_rate);
 /* TICK_NSEC is the time between ticks in nsec assuming SHIFTED_HZ */
 #define TICK_NSEC ((NSEC_PER_SEC+HZ/2)/HZ)
 
-/* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */
-#define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ)
+/* TICK_USEC is the time between ticks in usec assuming SHIFTED_HZ */
+#define TICK_USEC ((USEC_PER_SEC + HZ/2) / HZ)
+
+/* USER_TICK_USEC is the time between ticks in usec assuming fake USER_HZ */
+#define USER_TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ)
 
 #ifndef __jiffy_arch_data
 #define __jiffy_arch_data

include/linux/tick.h

@@ -115,27 +115,46 @@ enum tick_dep_bits {
 extern bool tick_nohz_enabled;
 extern bool tick_nohz_tick_stopped(void);
 extern bool tick_nohz_tick_stopped_cpu(int cpu);
+extern void tick_nohz_idle_stop_tick(void);
+extern void tick_nohz_idle_retain_tick(void);
+extern void tick_nohz_idle_restart_tick(void);
 extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
-extern ktime_t tick_nohz_get_sleep_length(void);
+extern bool tick_nohz_idle_got_tick(void);
+extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next);
 extern unsigned long tick_nohz_get_idle_calls(void);
 extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
+
+static inline void tick_nohz_idle_stop_tick_protected(void)
+{
+	local_irq_disable();
+	tick_nohz_idle_stop_tick();
+	local_irq_enable();
+}
+
 #else /* !CONFIG_NO_HZ_COMMON */
 #define tick_nohz_enabled (0)
 static inline int tick_nohz_tick_stopped(void) { return 0; }
 static inline int tick_nohz_tick_stopped_cpu(int cpu) { return 0; }
+static inline void tick_nohz_idle_stop_tick(void) { }
+static inline void tick_nohz_idle_retain_tick(void) { }
+static inline void tick_nohz_idle_restart_tick(void) { }
 static inline void tick_nohz_idle_enter(void) { }
 static inline void tick_nohz_idle_exit(void) { }
+static inline bool tick_nohz_idle_got_tick(void) { return false; }
 
-static inline ktime_t tick_nohz_get_sleep_length(void)
+static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 {
-	return NSEC_PER_SEC / HZ;
+	*delta_next = TICK_NSEC;
+	return *delta_next;
 }
 static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
+
+static inline void tick_nohz_idle_stop_tick_protected(void) { }
 #endif /* !CONFIG_NO_HZ_COMMON */
 
 #ifdef CONFIG_NO_HZ_FULL

kernel/power/qos.c

@@ -295,6 +295,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 		 * changed
 		 */
 		plist_del(node, &c->list);
+		/* fall through */
 	case PM_QOS_ADD_REQ:
 		plist_node_init(node, new_value);
 		plist_add(node, &c->list);
@@ -367,6 +368,7 @@ bool pm_qos_update_flags(struct pm_qos_flags *pqf,
 		break;
 	case PM_QOS_UPDATE_REQ:
 		pm_qos_flags_remove_req(pqf, req);
+		/* fall through */
 	case PM_QOS_ADD_REQ:
 		req->flags = val;
 		INIT_LIST_HEAD(&req->node);

kernel/sched/idle.c

@@ -141,13 +141,15 @@ static void cpuidle_idle_call(void)
 	}
 
 	/*
-	 * Tell the RCU framework we are entering an idle section,
-	 * so no more rcu read side critical sections and one more
+	 * The RCU framework needs to be told that we are entering an idle
+	 * section, so no more rcu read side critical sections and one more
 	 * step to the grace period
 	 */
-	rcu_idle_enter();
 
 	if (cpuidle_not_available(drv, dev)) {
+		tick_nohz_idle_stop_tick();
+		rcu_idle_enter();
+
 		default_idle_call();
 		goto exit_idle;
 	}
@@ -164,20 +166,37 @@ static void cpuidle_idle_call(void)
 
 	if (idle_should_enter_s2idle() || dev->use_deepest_state) {
 		if (idle_should_enter_s2idle()) {
+			rcu_idle_enter();
+
 			entered_state = cpuidle_enter_s2idle(drv, dev);
 			if (entered_state > 0) {
 				local_irq_enable();
 				goto exit_idle;
 			}
+
+			rcu_idle_exit();
 		}
 
+		tick_nohz_idle_stop_tick();
+		rcu_idle_enter();
+
 		next_state = cpuidle_find_deepest_state(drv, dev);
 		call_cpuidle(drv, dev, next_state);
 	} else {
+		bool stop_tick = true;
+
 		/*
 		 * Ask the cpuidle framework to choose a convenient idle state.
 		 */
-		next_state = cpuidle_select(drv, dev);
+		next_state = cpuidle_select(drv, dev, &stop_tick);
+
+		if (stop_tick)
+			tick_nohz_idle_stop_tick();
+		else
+			tick_nohz_idle_retain_tick();
+
+		rcu_idle_enter();
+
 		entered_state = call_cpuidle(drv, dev, next_state);
 		/*
 		 * Give the governor an opportunity to reflect on the outcome
@@ -222,6 +241,7 @@ static void do_idle(void)
 		rmb();
 
 		if (cpu_is_offline(cpu)) {
+			tick_nohz_idle_stop_tick_protected();
 			cpuhp_report_idle_dead();
 			arch_cpu_idle_dead();
 		}
@@ -235,10 +255,12 @@ static void do_idle(void)
 		 * broadcast device expired for us, we don't want to go deep
 		 * idle as we know that the IPI is going to arrive right away.
 		 */
-		if (cpu_idle_force_poll || tick_check_broadcast_expired())
+		if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
+			tick_nohz_idle_restart_tick();
 			cpu_idle_poll();
-		else
+		} else {
 			cpuidle_idle_call();
+		}
 		arch_cpu_idle_exit();
 	}
 

kernel/time/hrtimer.c

@@ -480,6 +480,7 @@ __next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active)
 	while ((base = __next_base((cpu_base), &(active))))
 
 static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base,
+					 const struct hrtimer *exclude,
 					 unsigned int active,
 					 ktime_t expires_next)
 {
@@ -492,9 +493,22 @@ static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base,
 
 		next = timerqueue_getnext(&base->active);
 		timer = container_of(next, struct hrtimer, node);
+		if (timer == exclude) {
+			/* Get to the next timer in the queue. */
+			next = timerqueue_iterate_next(next);
+			if (!next)
+				continue;
+
+			timer = container_of(next, struct hrtimer, node);
+		}
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
 		if (expires < expires_next) {
 			expires_next = expires;
+
+			/* Skip cpu_base update if a timer is being excluded. */
+			if (exclude)
+				continue;
+
 			if (timer->is_soft)
 				cpu_base->softirq_next_timer = timer;
 			else
@@ -538,7 +552,8 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_
 	if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) {
 		active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT;
 		cpu_base->softirq_next_timer = NULL;
-		expires_next = __hrtimer_next_event_base(cpu_base, active, KTIME_MAX);
+		expires_next = __hrtimer_next_event_base(cpu_base, NULL,
+							 active, KTIME_MAX);
 
 		next_timer = cpu_base->softirq_next_timer;
 	}
@@ -546,7 +561,8 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_
 	if (active_mask & HRTIMER_ACTIVE_HARD) {
 		active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD;
 		cpu_base->next_timer = next_timer;
-		expires_next = __hrtimer_next_event_base(cpu_base, active, expires_next);
+		expires_next = __hrtimer_next_event_base(cpu_base, NULL, active,
+							 expires_next);
 	}
 
 	return expires_next;
@@ -1190,6 +1206,39 @@ u64 hrtimer_get_next_event(void)
 
 	return expires;
 }
+
+/**
+ * hrtimer_next_event_without - time until next expiry event w/o one timer
+ * @exclude:	timer to exclude
+ *
+ * Returns the next expiry time over all timers except for the @exclude one or
+ * KTIME_MAX if none of them is pending.
+ */
+u64 hrtimer_next_event_without(const struct hrtimer *exclude)
+{
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	u64 expires = KTIME_MAX;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&cpu_base->lock, flags);
+
+	if (__hrtimer_hres_active(cpu_base)) {
+		unsigned int active;
+
+		if (!cpu_base->softirq_activated) {
+			active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT;
+			expires = __hrtimer_next_event_base(cpu_base, exclude,
+							    active, KTIME_MAX);
+		}
+		active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD;
+		expires = __hrtimer_next_event_base(cpu_base, exclude, active,
+						    expires);
+	}
+
+	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+
+	return expires;
+}
 #endif
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)

kernel/time/ntp.c

@@ -31,7 +31,7 @@
 
 
 /* USER_HZ period (usecs): */
-unsigned long			tick_usec = TICK_USEC;
+unsigned long			tick_usec = USER_TICK_USEC;
 
 /* SHIFTED_HZ period (nsecs): */
 unsigned long			tick_nsec;

kernel/time/tick-sched.h

@@ -38,31 +38,37 @@ enum tick_nohz_mode {
  * @idle_exittime:	Time when the idle state was left
  * @idle_sleeptime:	Sum of the time slept in idle with sched tick stopped
  * @iowait_sleeptime:	Sum of the time slept in idle with sched tick stopped, with IO outstanding
- * @sleep_length:	Duration of the current idle sleep
+ * @timer_expires:	Anticipated timer expiration time (in case sched tick is stopped)
+ * @timer_expires_base:	Base time clock monotonic for @timer_expires
  * @do_timer_lst:	CPU was the last one doing do_timer before going idle
+ * @got_idle_tick:	Tick timer function has run with @inidle set
  */
 struct tick_sched {
 	struct hrtimer			sched_timer;
 	unsigned long			check_clocks;
 	enum tick_nohz_mode		nohz_mode;
+
+	unsigned int			inidle		: 1;
+	unsigned int			tick_stopped	: 1;
+	unsigned int			idle_active	: 1;
+	unsigned int			do_timer_last	: 1;
+	unsigned int			got_idle_tick	: 1;
+
 	ktime_t				last_tick;
 	ktime_t				next_tick;
-	int				inidle;
-	int				tick_stopped;
 	unsigned long			idle_jiffies;
 	unsigned long			idle_calls;
 	unsigned long			idle_sleeps;
-	int				idle_active;
 	ktime_t				idle_entrytime;
 	ktime_t				idle_waketime;
 	ktime_t				idle_exittime;
 	ktime_t				idle_sleeptime;
 	ktime_t				iowait_sleeptime;
-	ktime_t				sleep_length;
 	unsigned long			last_jiffies;
+	u64				timer_expires;
+	u64				timer_expires_base;
 	u64				next_timer;
 	ktime_t				idle_expires;
-	int				do_timer_last;
 	atomic_t			tick_dep_mask;
 };