Merge tag 'pm-5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These fix the (Intel-specific) Performance and Energy Bias Hint (EPB)
  handling and expose it to user space via sysfs, fix and clean up
  several cpufreq drivers, add support for two new chips to the qoriq
  cpufreq driver, fix, simplify and clean up the cpufreq core and the
  schedutil governor, add support for "CPU" domains to the generic power
  domains (genpd) framework and provide low-level PSCI firmware support
  for that feature, fix the exynos cpuidle driver and fix a couple of
  issues in the devfreq subsystem and clean it up.

  Specifics:

   - Fix the handling of Performance and Energy Bias Hint (EPB) on Intel
     processors and expose it to user space via sysfs to avoid having to
     access it through the generic MSR I/F (Rafael Wysocki).

   - Improve the handling of global turbo changes made by the platform
     firmware in the intel_pstate driver (Rafael Wysocki).

   - Convert some slow-path static_cpu_has() callers to boot_cpu_has()
     in cpufreq (Borislav Petkov).

   - Fix the frequency calculation loop in the armada-37xx cpufreq
     driver (Gregory CLEMENT).

   - Fix possible object reference leaks in multuple cpufreq drivers
     (Wen Yang).

   - Fix kerneldoc comment in the centrino cpufreq driver (dongjian).

   - Clean up the ACPI and maple cpufreq drivers (Viresh Kumar, Mohan
     Kumar).

   - Add support for lx2160a and ls1028a to the qoriq cpufreq driver
     (Vabhav Sharma, Yuantian Tang).

   - Fix kobject memory leak in the cpufreq core (Viresh Kumar).

   - Simplify the IOwait boosting in the schedutil cpufreq governor and
     rework the TSC cpufreq notifier on x86 (Rafael Wysocki).

   - Clean up the cpufreq core and statistics code (Yue Hu, Kyle Lin).

   - Improve the cpufreq documentation, add SPDX license tags to some PM
     documentation files and unify copyright notices in them (Rafael
     Wysocki).

   - Add support for "CPU" domains to the generic power domains (genpd)
     framework and provide low-level PSCI firmware support for that
     feature (Ulf Hansson).

   - Rearrange the PSCI firmware support code and add support for
     SYSTEM_RESET2 to it (Ulf Hansson, Sudeep Holla).

   - Improve genpd support for devices in multiple power domains (Ulf
     Hansson).

   - Unify target residency for the AFTR and coupled AFTR states in the
     exynos cpuidle driver (Marek Szyprowski).

   - Introduce new helper routine in the operating performance points
     (OPP) framework (Andrew-sh.Cheng).

   - Add support for passing on-die termination (ODT) and auto power
     down parameters from the kernel to Trusted Firmware-A (TF-A) to the
     rk3399_dmc devfreq driver (Enric Balletbo i Serra).

   - Add tracing to devfreq (Lukasz Luba).

   - Make the exynos-bus devfreq driver suspend all devices on system
     shutdown (Marek Szyprowski).

   - Fix a few minor issues in the devfreq subsystem and clean it up
     somewhat (Enric Balletbo i Serra, MyungJoo Ham, Rob Herring,
     Saravana Kannan, Yangtao Li).

   - Improve system wakeup diagnostics (Stephen Boyd).

   - Rework filesystem sync messages emitted during system suspend and
     hibernation (Harry Pan)"

* tag 'pm-5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (72 commits)
  cpufreq: Fix kobject memleak
  cpufreq: armada-37xx: fix frequency calculation for opp
  cpufreq: centrino: Fix centrino_setpolicy() kerneldoc comment
  cpufreq: qoriq: add support for lx2160a
  x86: tsc: Rework time_cpufreq_notifier()
  PM / Domains: Allow to attach a CPU via genpd_dev_pm_attach_by_id|name()
  PM / Domains: Search for the CPU device outside the genpd lock
  PM / Domains: Drop unused in-parameter to some genpd functions
  PM / Domains: Use the base device for driver_deferred_probe_check_state()
  cpufreq: qoriq: Add ls1028a chip support
  PM / Domains: Enable genpd_dev_pm_attach_by_id|name() for single PM domain
  PM / Domains: Allow OF lookup for multi PM domain case from ->attach_dev()
  PM / Domains: Don't kfree() the virtual device in the error path
  cpufreq: Move ->get callback check outside of __cpufreq_get()
  PM / Domains: remove unnecessary unlikely()
  cpufreq: Remove needless bios_limit check in show_bios_limit()
  drivers/cpufreq/acpi-cpufreq.c: This fixes the following checkpatch warning
  firmware/psci: add support for SYSTEM_RESET2
  PM / devfreq: add tracing for scheduling work
  trace: events: add devfreq trace event file
  ...

7 files changed, 54 insertions, 2 deletions

diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index b160e98076e3..684caf067003 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -178,6 +178,11 @@ static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 static inline void cpufreq_cpu_put(struct cpufreq_policy *policy) { }
 #endif
 
+static inline bool policy_is_inactive(struct cpufreq_policy *policy)
+{
+	return cpumask_empty(policy->cpus);
+}
+
 static inline bool policy_is_shared(struct cpufreq_policy *policy)
 {
 	return cpumask_weight(policy->cpus) > 1;
@@ -193,8 +198,14 @@ unsigned int cpufreq_quick_get_max(unsigned int cpu);
 void disable_cpufreq(void);
 
 u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
+
+struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu);
+void cpufreq_cpu_release(struct cpufreq_policy *policy);
 int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
+int cpufreq_set_policy(struct cpufreq_policy *policy,
+		       struct cpufreq_policy *new_policy);
 void cpufreq_update_policy(unsigned int cpu);
+void cpufreq_update_limits(unsigned int cpu);
 bool have_governor_per_policy(void);
 struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
 void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
@@ -322,6 +333,9 @@ struct cpufreq_driver {
 	/* should be defined, if possible */
 	unsigned int	(*get)(unsigned int cpu);
 
+	/* Called to update policy limits on firmware notifications. */
+	void		(*update_limits)(unsigned int cpu);
+
 	/* optional */
 	int		(*bios_limit)(int cpu, unsigned int *limit);
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index e78281d07b70..dbfdd0fadbef 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -147,6 +147,7 @@ enum cpuhp_state {
 	CPUHP_AP_X86_VDSO_VMA_ONLINE,
 	CPUHP_AP_IRQ_AFFINITY_ONLINE,
 	CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS,
+	CPUHP_AP_X86_INTEL_EPB_ONLINE,
 	CPUHP_AP_PERF_ONLINE,
 	CPUHP_AP_PERF_X86_ONLINE,
 	CPUHP_AP_PERF_X86_UNCORE_ONLINE,
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3b39472324a3..bb9a0db89f1a 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -83,6 +83,7 @@ struct cpuidle_device {
 	unsigned int		use_deepest_state:1;
 	unsigned int		poll_time_limit:1;
 	unsigned int		cpu;
+	ktime_t			next_hrtimer;
 
 	int			last_residency;
 	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 1ed5874bcee0..0e8e356bed6a 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
+#include <linux/cpumask.h>
 
 /*
  * Flags to control the behaviour of a genpd.
@@ -42,11 +43,22 @@
  * GENPD_FLAG_ACTIVE_WAKEUP:	Instructs genpd to keep the PM domain powered
  *				on, in case any of its attached devices is used
  *				in the wakeup path to serve system wakeups.
+ *
+ * GENPD_FLAG_CPU_DOMAIN:	Instructs genpd that it should expect to get
+ *				devices attached, which may belong to CPUs or
+ *				possibly have subdomains with CPUs attached.
+ *				This flag enables the genpd backend driver to
+ *				deploy idle power management support for CPUs
+ *				and groups of CPUs. Note that, the backend
+ *				driver must then comply with the so called,
+ *				last-man-standing algorithm, for the CPUs in the
+ *				PM domain.
  */
 #define GENPD_FLAG_PM_CLK	 (1U << 0)
 #define GENPD_FLAG_IRQ_SAFE	 (1U << 1)
 #define GENPD_FLAG_ALWAYS_ON	 (1U << 2)
 #define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3)
+#define GENPD_FLAG_CPU_DOMAIN	 (1U << 4)
 
 enum gpd_status {
 	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
@@ -69,6 +81,7 @@ struct genpd_power_state {
 	s64 residency_ns;
 	struct fwnode_handle *fwnode;
 	ktime_t idle_time;
+	void *data;
 };
 
 struct genpd_lock_ops;
@@ -93,6 +106,7 @@ struct generic_pm_domain {
 	unsigned int suspended_count;	/* System suspend device counter */
 	unsigned int prepared_count;	/* Suspend counter of prepared devices */
 	unsigned int performance_state;	/* Aggregated max performance state */
+	cpumask_var_t cpus;		/* A cpumask of the attached CPUs */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
 	struct opp_table *opp_table;	/* OPP table of the genpd */
@@ -104,15 +118,17 @@ struct generic_pm_domain {
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
 	bool max_off_time_changed;
 	bool cached_power_down_ok;
+	bool cached_power_down_state_idx;
 	int (*attach_dev)(struct generic_pm_domain *domain,
 			  struct device *dev);
 	void (*detach_dev)(struct generic_pm_domain *domain,
 			   struct device *dev);
 	unsigned int flags;		/* Bit field of configs for genpd */
 	struct genpd_power_state *states;
+	void (*free_states)(struct genpd_power_state *states,
+			    unsigned int state_count);
 	unsigned int state_count; /* number of states */
 	unsigned int state_idx; /* state that genpd will go to when off */
-	void *free; /* Free the state that was allocated for default */
 	ktime_t on_time;
 	ktime_t accounting_time;
 	const struct genpd_lock_ops *lock_ops;
@@ -159,6 +175,7 @@ struct generic_pm_domain_data {
 	struct pm_domain_data base;
 	struct gpd_timing_data td;
 	struct notifier_block nb;
+	int cpu;
 	unsigned int performance_state;
 	void *data;
 };
@@ -187,6 +204,9 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
+#ifdef CONFIG_CPU_IDLE
+extern struct dev_power_governor pm_domain_cpu_gov;
+#endif
 #else
 
 static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 24c757a32a7b..b150fe97ce5a 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -102,6 +102,8 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 
 struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					      unsigned long *freq);
+struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
+						     unsigned long u_volt);
 
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq);
@@ -207,6 +209,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	return ERR_PTR(-ENOTSUPP);
 }
 
+static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
+					unsigned long u_volt)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+
 static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					unsigned long *freq)
 {
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 3f529ad9a9d2..6b3ea9ea6a9e 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -425,6 +425,7 @@ void restore_processor_state(void);
 /* kernel/power/main.c */
 extern int register_pm_notifier(struct notifier_block *nb);
 extern int unregister_pm_notifier(struct notifier_block *nb);
+extern void ksys_sync_helper(void);
 
 #define pm_notifier(fn, pri) {				\
 	static struct notifier_block fn##_nb =			\
@@ -462,6 +463,8 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 	return 0;
 }
 
+static inline void ksys_sync_helper(void) {}
+
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
 
 static inline bool pm_wakeup_pending(void) { return false; }
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 76acb48acdb7..f92a10b5e112 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -128,6 +128,7 @@ extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
 extern bool tick_nohz_idle_got_tick(void);
+extern ktime_t tick_nohz_get_next_hrtimer(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);
@@ -151,7 +152,11 @@ 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_next_hrtimer(void)
+{
+	/* Next wake up is the tick period, assume it starts now */
+	return ktime_add(ktime_get(), TICK_NSEC);
+}
 static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 {
 	*delta_next = TICK_NSEC;