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
  ...

6 files changed, 43 insertions, 27 deletions

diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index cfc7a57049e4..c8c272df7154 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -14,7 +14,6 @@
 
 #include <linux/export.h>
 #include <linux/suspend.h>
-#include <linux/syscalls.h>
 #include <linux/reboot.h>
 #include <linux/string.h>
 #include <linux/device.h>
@@ -709,9 +708,7 @@ int hibernate(void)
 		goto Exit;
 	}
 
-	pr_info("Syncing filesystems ... \n");
-	ksys_sync();
-	pr_info("done.\n");
+	ksys_sync_helper();
 
 	error = freeze_processes();
 	if (error)
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 98e76cad128b..4f43e724f6eb 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -16,6 +16,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/suspend.h>
+#include <linux/syscalls.h>
 
 #include "power.h"
 
@@ -51,6 +52,19 @@ void unlock_system_sleep(void)
 }
 EXPORT_SYMBOL_GPL(unlock_system_sleep);
 
+void ksys_sync_helper(void)
+{
+	ktime_t start;
+	long elapsed_msecs;
+
+	start = ktime_get();
+	ksys_sync();
+	elapsed_msecs = ktime_to_ms(ktime_sub(ktime_get(), start));
+	pr_info("Filesystems sync: %ld.%03ld seconds\n",
+		elapsed_msecs / MSEC_PER_SEC, elapsed_msecs % MSEC_PER_SEC);
+}
+EXPORT_SYMBOL_GPL(ksys_sync_helper);
+
 /* Routines for PM-transition notifications */
 
 static BLOCKING_NOTIFIER_HEAD(pm_chain_head);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 59b6def23046..ef908c134b34 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -17,7 +17,6 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/cpuidle.h>
-#include <linux/syscalls.h>
 #include <linux/gfp.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
@@ -568,13 +567,11 @@ static int enter_state(suspend_state_t state)
 	if (state == PM_SUSPEND_TO_IDLE)
 		s2idle_begin();
 
-#ifndef CONFIG_SUSPEND_SKIP_SYNC
-	trace_suspend_resume(TPS("sync_filesystems"), 0, true);
-	pr_info("Syncing filesystems ... ");
-	ksys_sync();
-	pr_cont("done.\n");
-	trace_suspend_resume(TPS("sync_filesystems"), 0, false);
-#endif
+	if (!IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC)) {
+		trace_suspend_resume(TPS("sync_filesystems"), 0, true);
+		ksys_sync_helper();
+		trace_suspend_resume(TPS("sync_filesystems"), 0, false);
+	}
 
 	pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]);
 	pm_suspend_clear_flags();
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 2d8b60a3c86b..cb24e840a3e6 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/suspend.h>
-#include <linux/syscalls.h>
 #include <linux/reboot.h>
 #include <linux/string.h>
 #include <linux/device.h>
@@ -228,9 +227,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		if (data->frozen)
 			break;
 
-		printk("Syncing filesystems ... ");
-		ksys_sync();
-		printk("done.\n");
+		ksys_sync_helper();
 
 		error = freeze_processes();
 		if (error)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3638d2377e3c..5403479073b0 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -13,6 +13,8 @@
 #include <linux/sched/cpufreq.h>
 #include <trace/events/power.h>
 
+#define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)
+
 struct sugov_tunables {
 	struct gov_attr_set	attr_set;
 	unsigned int		rate_limit_us;
@@ -51,7 +53,6 @@ struct sugov_cpu {
 	u64			last_update;
 
 	unsigned long		bw_dl;
-	unsigned long		min;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -291,8 +292,8 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
  *
  * The IO wait boost of a task is disabled after a tick since the last update
  * of a CPU. If a new IO wait boost is requested after more then a tick, then
- * we enable the boost starting from the minimum frequency, which improves
- * energy efficiency by ignoring sporadic wakeups from IO.
+ * we enable the boost starting from IOWAIT_BOOST_MIN, which improves energy
+ * efficiency by ignoring sporadic wakeups from IO.
  */
 static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
 			       bool set_iowait_boost)
@@ -303,7 +304,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
 	if (delta_ns <= TICK_NSEC)
 		return false;
 
-	sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0;
+	sg_cpu->iowait_boost = set_iowait_boost ? IOWAIT_BOOST_MIN : 0;
 	sg_cpu->iowait_boost_pending = set_iowait_boost;
 
 	return true;
@@ -317,8 +318,9 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
  *
  * Each time a task wakes up after an IO operation, the CPU utilization can be
  * boosted to a certain utilization which doubles at each "frequent and
- * successive" wakeup from IO, ranging from the utilization of the minimum
- * OPP to the utilization of the maximum OPP.
+ * successive" wakeup from IO, ranging from IOWAIT_BOOST_MIN to the utilization
+ * of the maximum OPP.
+ *
  * To keep doubling, an IO boost has to be requested at least once per tick,
  * otherwise we restart from the utilization of the minimum OPP.
  */
@@ -349,7 +351,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
 	}
 
 	/* First wakeup after IO: start with minimum boost */
-	sg_cpu->iowait_boost = sg_cpu->min;
+	sg_cpu->iowait_boost = IOWAIT_BOOST_MIN;
 }
 
 /**
@@ -389,7 +391,7 @@ static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 		 * No boost pending; reduce the boost value.
 		 */
 		sg_cpu->iowait_boost >>= 1;
-		if (sg_cpu->iowait_boost < sg_cpu->min) {
+		if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
 			sg_cpu->iowait_boost = 0;
 			return util;
 		}
@@ -827,9 +829,6 @@ static int sugov_start(struct cpufreq_policy *policy)
 		memset(sg_cpu, 0, sizeof(*sg_cpu));
 		sg_cpu->cpu			= cpu;
 		sg_cpu->sg_policy		= sg_policy;
-		sg_cpu->min			=
-			(SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) /
-			policy->cpuinfo.max_freq;
 	}
 
 	for_each_cpu(cpu, policy->cpus) {
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index bdf00c763ee3..f4ee1a3428ae 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1038,6 +1038,18 @@ bool tick_nohz_idle_got_tick(void)
 }
 
 /**
+ * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer
+ * or the tick, whatever that expires first. Note that, if the tick has been
+ * stopped, it returns the next hrtimer.
+ *
+ * Called from power state control code with interrupts disabled
+ */
+ktime_t tick_nohz_get_next_hrtimer(void)
+{
+	return __this_cpu_read(tick_cpu_device.evtdev)->next_event;
+}
+
+/**
  * tick_nohz_get_sleep_length - return the expected length of the current sleep
  * @delta_next: duration until the next event if the tick cannot be stopped
  *