Merge tag 'pm-5.2-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These fix a recent regression causing kernels built with CONFIG_PM
  unset to crash on systems that support the Performance and Energy Bias
  Hint (EPB), clean up the cpufreq core and some users of transition
  notifiers and introduce a new power domain flag into the generic power
  domains framework (genpd).

  Specifics:

   - Fix recent regression causing kernels built with CONFIG_PM unset to
     crash on systems that support the Performance and Energy Bias Hint
     (EPB) by avoiding to compile the EPB-related code depending on
     CONFIG_PM when it is unset (Rafael Wysocki).

   - Clean up the transition notifier invocation code in the cpufreq
     core and change some users of cpufreq transition notifiers
     accordingly (Viresh Kumar).

   - Change MAINTAINERS to cover the schedutil governor as part of
     cpufreq (Viresh Kumar).

   - Simplify cpufreq_init_policy() to avoid redundant computations (Yue
     Hu).

   - Add explanatory comment to the cpufreq core (Rafael Wysocki).

   - Introduce a new flag, GENPD_FLAG_RPM_ALWAYS_ON, to the generic
     power domains (genpd) framework along with the first user of it
     (Leonard Crestez)"

* tag 'pm-5.2-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  soc: imx: gpc: Use GENPD_FLAG_RPM_ALWAYS_ON for ERR009619
  PM / Domains: Add GENPD_FLAG_RPM_ALWAYS_ON flag
  cpufreq: Update MAINTAINERS to include schedutil governor
  cpufreq: Don't find governor for setpolicy drivers in cpufreq_init_policy()
  cpufreq: Explain the kobject_put() in cpufreq_policy_alloc()
  cpufreq: Call transition notifier only once for each policy
  x86: intel_epb: Take CONFIG_PM into account

Author: torvalds

MAINTAINERS

@@ -4133,7 +4133,9 @@ F:	Documentation/admin-guide/pm/intel_pstate.rst
 F:	Documentation/cpu-freq/
 F:	Documentation/devicetree/bindings/cpufreq/
 F:	drivers/cpufreq/
+F:	kernel/sched/cpufreq*.c
 F:	include/linux/cpufreq.h
+F:	include/linux/sched/cpufreq.h
 F:	tools/testing/selftests/cpufreq/
 
 CPU FREQUENCY DRIVERS - ARM BIG LITTLE

arch/arm/kernel/smp.c

@@ -758,15 +758,20 @@ static int cpufreq_callback(struct notifier_block *nb,
 					unsigned long val, void *data)
 {
 	struct cpufreq_freqs *freq = data;
-	int cpu = freq->cpu;
+	struct cpumask *cpus = freq->policy->cpus;
+	int cpu, first = cpumask_first(cpus);
+	unsigned int lpj;
 
 	if (freq->flags & CPUFREQ_CONST_LOOPS)
 		return NOTIFY_OK;
 
-	if (!per_cpu(l_p_j_ref, cpu)) {
-		per_cpu(l_p_j_ref, cpu) =
-			per_cpu(cpu_data, cpu).loops_per_jiffy;
-		per_cpu(l_p_j_ref_freq, cpu) = freq->old;
+	if (!per_cpu(l_p_j_ref, first)) {
+		for_each_cpu(cpu, cpus) {
+			per_cpu(l_p_j_ref, cpu) =
+				per_cpu(cpu_data, cpu).loops_per_jiffy;
+			per_cpu(l_p_j_ref_freq, cpu) = freq->old;
+		}
+
 		if (!global_l_p_j_ref) {
 			global_l_p_j_ref = loops_per_jiffy;
 			global_l_p_j_ref_freq = freq->old;
@@ -778,10 +783,11 @@ static int cpufreq_callback(struct notifier_block *nb,
 		loops_per_jiffy = cpufreq_scale(global_l_p_j_ref,
 						global_l_p_j_ref_freq,
 						freq->new);
-		per_cpu(cpu_data, cpu).loops_per_jiffy =
-			cpufreq_scale(per_cpu(l_p_j_ref, cpu),
-					per_cpu(l_p_j_ref_freq, cpu),
-					freq->new);
+
+		lpj = cpufreq_scale(per_cpu(l_p_j_ref, first),
+				    per_cpu(l_p_j_ref_freq, first), freq->new);
+		for_each_cpu(cpu, cpus)
+			per_cpu(cpu_data, cpu).loops_per_jiffy = lpj;
 	}
 	return NOTIFY_OK;
 }

arch/sparc/kernel/time_64.c

@@ -653,19 +653,23 @@ static int sparc64_cpufreq_notifier(struct notifier_block *nb, unsigned long val
 				    void *data)
 {
 	struct cpufreq_freqs *freq = data;
-	unsigned int cpu = freq->cpu;
-	struct freq_table *ft = &per_cpu(sparc64_freq_table, cpu);
+	unsigned int cpu;
+	struct freq_table *ft;
 
-	if (!ft->ref_freq) {
-		ft->ref_freq = freq->old;
-		ft->clock_tick_ref = cpu_data(cpu).clock_tick;
-	}
-	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
-	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
-		cpu_data(cpu).clock_tick =
-			cpufreq_scale(ft->clock_tick_ref,
-				      ft->ref_freq,
-				      freq->new);
+	for_each_cpu(cpu, freq->policy->cpus) {
+		ft = &per_cpu(sparc64_freq_table, cpu);
+
+		if (!ft->ref_freq) {
+			ft->ref_freq = freq->old;
+			ft->clock_tick_ref = cpu_data(cpu).clock_tick;
+		}
+
+		if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
+		    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
+			cpu_data(cpu).clock_tick =
+				cpufreq_scale(ft->clock_tick_ref, ft->ref_freq,
+					      freq->new);
+		}
 	}
 
 	return 0;

arch/x86/kernel/cpu/intel_epb.c

@@ -97,6 +97,7 @@ static void intel_epb_restore(void)
 	wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
 }
 
+#ifdef CONFIG_PM
 static struct syscore_ops intel_epb_syscore_ops = {
 	.suspend = intel_epb_save,
 	.resume = intel_epb_restore,
@@ -193,6 +194,25 @@ static int intel_epb_offline(unsigned int cpu)
 	return 0;
 }
 
+static inline void register_intel_ebp_syscore_ops(void)
+{
+	register_syscore_ops(&intel_epb_syscore_ops);
+}
+#else /* !CONFIG_PM */
+static int intel_epb_online(unsigned int cpu)
+{
+	intel_epb_restore();
+	return 0;
+}
+
+static int intel_epb_offline(unsigned int cpu)
+{
+	return intel_epb_save();
+}
+
+static inline void register_intel_ebp_syscore_ops(void) {}
+#endif
+
 static __init int intel_epb_init(void)
 {
 	int ret;
@@ -206,7 +226,7 @@ static __init int intel_epb_init(void)
 	if (ret < 0)
 		goto err_out_online;
 
-	register_syscore_ops(&intel_epb_syscore_ops);
+	register_intel_ebp_syscore_ops();
 	return 0;
 
 err_out_online:

arch/x86/kernel/tsc.c

@@ -979,7 +979,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
 			mark_tsc_unstable("cpufreq changes");
 
-		set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc());
+		set_cyc2ns_scale(tsc_khz, freq->policy->cpu, rdtsc());
 	}
 
 	return 0;

arch/x86/kvm/x86.c

@@ -6698,10 +6698,8 @@ static void kvm_hyperv_tsc_notifier(void)
 }
 #endif
 
-static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-				     void *data)
+static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu)
 {
-	struct cpufreq_freqs *freq = data;
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
 	int i, send_ipi = 0;
@@ -6745,17 +6743,12 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 	 *
 	 */
 
-	if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
-		return 0;
-	if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
-		return 0;
-
-	smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
+	smp_call_function_single(cpu, tsc_khz_changed, freq, 1);
 
 	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
-			if (vcpu->cpu != freq->cpu)
+			if (vcpu->cpu != cpu)
 				continue;
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 			if (vcpu->cpu != smp_processor_id())
@@ -6777,8 +6770,24 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 		 * guest context is entered kvmclock will be updated,
 		 * so the guest will not see stale values.
 		 */
-		smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
+		smp_call_function_single(cpu, tsc_khz_changed, freq, 1);
 	}
+}
+
+static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+				     void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	int cpu;
+
+	if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
+		return 0;
+	if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
+		return 0;
+
+	for_each_cpu(cpu, freq->policy->cpus)
+		__kvmclock_cpufreq_notifier(freq, cpu);
+
 	return 0;
 }
 

drivers/base/power/domain.c

@@ -128,6 +128,7 @@ static const struct genpd_lock_ops genpd_spin_ops = {
 #define genpd_is_always_on(genpd)	(genpd->flags & GENPD_FLAG_ALWAYS_ON)
 #define genpd_is_active_wakeup(genpd)	(genpd->flags & GENPD_FLAG_ACTIVE_WAKEUP)
 #define genpd_is_cpu_domain(genpd)	(genpd->flags & GENPD_FLAG_CPU_DOMAIN)
+#define genpd_is_rpm_always_on(genpd)	(genpd->flags & GENPD_FLAG_RPM_ALWAYS_ON)
 
 static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
 		const struct generic_pm_domain *genpd)
@@ -515,7 +516,9 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 	 * (1) The domain is configured as always on.
 	 * (2) When the domain has a subdomain being powered on.
 	 */
-	if (genpd_is_always_on(genpd) || atomic_read(&genpd->sd_count) > 0)
+	if (genpd_is_always_on(genpd) ||
+			genpd_is_rpm_always_on(genpd) ||
+			atomic_read(&genpd->sd_count) > 0)
 		return -EBUSY;
 
 	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
@@ -1812,7 +1815,8 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	}
 
 	/* Always-on domains must be powered on at initialization. */
-	if (genpd_is_always_on(genpd) && !genpd_status_on(genpd))
+	if ((genpd_is_always_on(genpd) || genpd_is_rpm_always_on(genpd)) &&
+			!genpd_status_on(genpd))
 		return -EINVAL;
 
 	if (genpd_is_cpu_domain(genpd) &&