Merge tag 'pm-5.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These fix the recently added Tegra194 cpufreq driver and the handling
  of devices using runtime PM during system-wide suspend, improve the
  intel_pstate driver documentation and clean up the cpufreq core.

  Specifics:

   - Make the recently added Tegra194 cpufreq driver use
     read_cpuid_mpir() instead of cpu_logical_map() to avoid exporting
     logical_cpu_map (Sumit Gupta).

   - Drop the automatic system wakeup event reporting for devices with
     pending runtime-resume requests during system-wide suspend to avoid
     spurious aborts of the suspend flow (Rafael Wysocki).

   - Fix build warning in the intel_pstate driver documentation and
     improve the wording in there (Randy Dunlap).

   - Clean up two pieces of code in the cpufreq core (Viresh Kumar)"

* tag 'pm-5.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq: Use WARN_ON_ONCE() for invalid relation
  cpufreq: No need to verify cpufreq_driver in show_scaling_cur_freq()
  PM: sleep: core: Fix the handling of pending runtime resume requests
  Documentation: fix pm/intel_pstate build warning and wording
  cpufreq: replace cpu_logical_map() with read_cpuid_mpir()

5 files changed, 22 insertions, 15 deletions

diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst
index 7adef969ffee..cdd1a9a7f9a2 100644
--- a/Documentation/admin-guide/pm/intel_pstate.rst
+++ b/Documentation/admin-guide/pm/intel_pstate.rst
@@ -564,8 +564,8 @@ Energy-Performance Preference (EPP) knob (if supported) or its
 Energy-Performance Bias (EPB) knob. It is also possible to write a positive
 integer value between 0 to 255, if the EPP feature is present. If the EPP
 feature is not present, writing integer value to this attribute is not
-supported. In this case, user can use
- "/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface.
+supported. In this case, user can use the
+"/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface.
 
 [Note that tasks may by migrated from one CPU to another by the scheduler's
 load-balancing algorithm and if different energy vs performance hints are
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 9dd85bea4026..205a06752ca9 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1606,13 +1606,17 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	}
 
 	/*
-	 * If a device configured to wake up the system from sleep states
-	 * has been suspended at run time and there's a resume request pending
-	 * for it, this is equivalent to the device signaling wakeup, so the
-	 * system suspend operation should be aborted.
+	 * Wait for possible runtime PM transitions of the device in progress
+	 * to complete and if there's a runtime resume request pending for it,
+	 * resume it before proceeding with invoking the system-wide suspend
+	 * callbacks for it.
+	 *
+	 * If the system-wide suspend callbacks below change the configuration
+	 * of the device, they must disable runtime PM for it or otherwise
+	 * ensure that its runtime-resume callbacks will not be confused by that
+	 * change in case they are invoked going forward.
 	 */
-	if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
-		pm_wakeup_event(dev, 0);
+	pm_runtime_barrier(dev);
 
 	if (pm_wakeup_pending()) {
 		dev->power.direct_complete = false;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 02ab56b2a0d8..47aa90f9a7c2 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -703,8 +703,7 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf)
 	freq = arch_freq_get_on_cpu(policy->cpu);
 	if (freq)
 		ret = sprintf(buf, "%u\n", freq);
-	else if (cpufreq_driver && cpufreq_driver->setpolicy &&
-			cpufreq_driver->get)
+	else if (cpufreq_driver->setpolicy && cpufreq_driver->get)
 		ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu));
 	else
 		ret = sprintf(buf, "%u\n", policy->cur);
diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c
index bae527e507e0..e1d931c457a7 100644
--- a/drivers/cpufreq/tegra194-cpufreq.c
+++ b/drivers/cpufreq/tegra194-cpufreq.c
@@ -56,9 +56,11 @@ struct read_counters_work {
 
 static struct workqueue_struct *read_counters_wq;
 
-static enum cluster get_cpu_cluster(u8 cpu)
+static void get_cpu_cluster(void *cluster)
 {
-	return MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
+	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
+
+	*((uint32_t *)cluster) = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 }
 
 /*
@@ -186,8 +188,10 @@ static unsigned int tegra194_get_speed(u32 cpu)
 static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
-	int cl = get_cpu_cluster(policy->cpu);
 	u32 cpu;
+	u32 cl;
+
+	smp_call_function_single(policy->cpu, get_cpu_cluster, &cl, true);
 
 	if (cl >= data->num_clusters)
 		return -EINVAL;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 8f141d4c859c..a911e5d06845 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -956,8 +956,8 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 	case CPUFREQ_RELATION_C:
 		return cpufreq_table_find_index_c(policy, target_freq);
 	default:
-		pr_err("%s: Invalid relation: %d\n", __func__, relation);
-		return -EINVAL;
+		WARN_ON_ONCE(1);
+		return 0;
 	}
 }