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
  ...

1 files changed, 56 insertions, 9 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2986119dd31f..34b54df41aaa 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -179,6 +179,7 @@ struct vid_data {
  *			based on the MSR_IA32_MISC_ENABLE value and whether or
  *			not the maximum reported turbo P-state is different from
  *			the maximum reported non-turbo one.
+ * @turbo_disabled_mf:	The @turbo_disabled value reflected by cpuinfo.max_freq.
  * @min_perf_pct:	Minimum capacity limit in percent of the maximum turbo
  *			P-state capacity.
  * @max_perf_pct:	Maximum capacity limit in percent of the maximum turbo
@@ -187,6 +188,7 @@ struct vid_data {
 struct global_params {
 	bool no_turbo;
 	bool turbo_disabled;
+	bool turbo_disabled_mf;
 	int max_perf_pct;
 	int min_perf_pct;
 };
@@ -525,7 +527,7 @@ static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
 	u64 epb;
 	int ret;
 
-	if (!static_cpu_has(X86_FEATURE_EPB))
+	if (!boot_cpu_has(X86_FEATURE_EPB))
 		return -ENXIO;
 
 	ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
@@ -539,7 +541,7 @@ static s16 intel_pstate_get_epp(struct cpudata *cpu_data, u64 hwp_req_data)
 {
 	s16 epp;
 
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		/*
 		 * When hwp_req_data is 0, means that caller didn't read
 		 * MSR_HWP_REQUEST, so need to read and get EPP.
@@ -564,7 +566,7 @@ static int intel_pstate_set_epb(int cpu, s16 pref)
 	u64 epb;
 	int ret;
 
-	if (!static_cpu_has(X86_FEATURE_EPB))
+	if (!boot_cpu_has(X86_FEATURE_EPB))
 		return -ENXIO;
 
 	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
@@ -612,7 +614,7 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
 	if (epp < 0)
 		return epp;
 
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		if (epp == HWP_EPP_PERFORMANCE)
 			return 1;
 		if (epp <= HWP_EPP_BALANCE_PERFORMANCE)
@@ -621,7 +623,7 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
 			return 3;
 		else
 			return 4;
-	} else if (static_cpu_has(X86_FEATURE_EPB)) {
+	} else if (boot_cpu_has(X86_FEATURE_EPB)) {
 		/*
 		 * Range:
 		 *	0x00-0x03	:	Performance
@@ -649,7 +651,7 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
 
 	mutex_lock(&intel_pstate_limits_lock);
 
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		u64 value;
 
 		ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, &value);
@@ -824,7 +826,7 @@ static void intel_pstate_hwp_set(unsigned int cpu)
 		epp = cpu_data->epp_powersave;
 	}
 update_epp:
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		value &= ~GENMASK_ULL(31, 24);
 		value |= (u64)epp << 24;
 	} else {
@@ -849,7 +851,7 @@ static void intel_pstate_hwp_force_min_perf(int cpu)
 	value |= HWP_MIN_PERF(min_perf);
 
 	/* Set EPP/EPB to min */
-	if (static_cpu_has(X86_FEATURE_HWP_EPP))
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP))
 		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);
 	else
 		intel_pstate_set_epb(cpu, HWP_EPP_BALANCE_POWERSAVE);
@@ -897,6 +899,48 @@ static void intel_pstate_update_policies(void)
 		cpufreq_update_policy(cpu);
 }
 
+static void intel_pstate_update_max_freq(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);
+	struct cpufreq_policy new_policy;
+	struct cpudata *cpudata;
+
+	if (!policy)
+		return;
+
+	cpudata = all_cpu_data[cpu];
+	policy->cpuinfo.max_freq = global.turbo_disabled_mf ?
+			cpudata->pstate.max_freq : cpudata->pstate.turbo_freq;
+
+	memcpy(&new_policy, policy, sizeof(*policy));
+	new_policy.max = min(policy->user_policy.max, policy->cpuinfo.max_freq);
+	new_policy.min = min(policy->user_policy.min, new_policy.max);
+
+	cpufreq_set_policy(policy, &new_policy);
+
+	cpufreq_cpu_release(policy);
+}
+
+static void intel_pstate_update_limits(unsigned int cpu)
+{
+	mutex_lock(&intel_pstate_driver_lock);
+
+	update_turbo_state();
+	/*
+	 * If turbo has been turned on or off globally, policy limits for
+	 * all CPUs need to be updated to reflect that.
+	 */
+	if (global.turbo_disabled_mf != global.turbo_disabled) {
+		global.turbo_disabled_mf = global.turbo_disabled;
+		for_each_possible_cpu(cpu)
+			intel_pstate_update_max_freq(cpu);
+	} else {
+		cpufreq_update_policy(cpu);
+	}
+
+	mutex_unlock(&intel_pstate_driver_lock);
+}
+
 /************************** sysfs begin ************************/
 #define show_one(file_name, object)					\
 	static ssize_t show_##file_name					\
@@ -1197,7 +1241,7 @@ static void __init intel_pstate_sysfs_expose_params(void)
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
 	/* First disable HWP notification interrupt as we don't process them */
-	if (static_cpu_has(X86_FEATURE_HWP_NOTIFY))
+	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
 		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
@@ -2138,6 +2182,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	/* cpuinfo and default policy values */
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	update_turbo_state();
+	global.turbo_disabled_mf = global.turbo_disabled;
 	policy->cpuinfo.max_freq = global.turbo_disabled ?
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
@@ -2182,6 +2227,7 @@ static struct cpufreq_driver intel_pstate = {
 	.init		= intel_pstate_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
+	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_pstate",
 };
 
@@ -2316,6 +2362,7 @@ static struct cpufreq_driver intel_cpufreq = {
 	.init		= intel_cpufreq_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_cpufreq_stop_cpu,
+	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_cpufreq",
 };