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
  ...

5 files changed, 33 insertions, 10 deletions

diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1fe49724da9e..87f48dd932eb 100644
--- a/include/linux/cpufreq.h
+++ b/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);
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index a806e94c482f..1eefabf1621f 100644
--- a/include/linux/cpuidle.h
+++ b/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);
 };
 
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 78f456fcd242..a2656c3ebe81 100644
--- a/include/linux/hrtimer.h
+++ b/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);
 
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 9385aa57497b..a27cf6652327 100644
--- a/include/linux/jiffies.h
+++ b/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
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 7f8c9a127f5a..55388ab45fd4 100644
--- a/include/linux/tick.h
+++ b/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