Merge tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These are PM-runtime framework changes to use ktime instead of jiffies
  for accounting, new PM core flag to mark devices that don't need any
  form of power management, cpuidle updates including driver API
  documentation and a new governor, cpufreq updates including a new
  driver for Armada 8K, thermal cleanups and more, some energy-aware
  scheduling (EAS) enabling changes, new chips support in the intel_idle
  and RAPL drivers and assorted cleanups in some other places.

  Specifics:

   - Update the PM-runtime framework to use ktime instead of jiffies for
     accounting (Thara Gopinath, Vincent Guittot)

   - Optimize the autosuspend code in the PM-runtime framework somewhat
     (Ladislav Michl)

   - Add a PM core flag to mark devices that don't need any form of
     power management (Sudeep Holla)

   - Introduce driver API documentation for cpuidle and add a new
     cpuidle governor for tickless systems (Rafael Wysocki)

   - Add Jacobsville support to the intel_idle driver (Zhang Rui)

   - Clean up a cpuidle core header file and the cpuidle-dt and ACPI
     processor-idle drivers (Yangtao Li, Joseph Lo, Yazen Ghannam)

   - Add new cpufreq driver for Armada 8K (Gregory Clement)

   - Fix and clean up cpufreq core (Rafael Wysocki, Viresh Kumar, Amit
     Kucheria)

   - Add support for light-weight tear-down and bring-up of CPUs to the
     cpufreq core and use it in the cpufreq-dt driver (Viresh Kumar)

   - Fix cpu_cooling Kconfig dependencies, add support for CPU cooling
     auto-registration to the cpufreq core and use it in multiple
     cpufreq drivers (Amit Kucheria)

   - Fix some minor issues and do some cleanups in the davinci,
     e_powersaver, ap806, s5pv210, qcom and kryo cpufreq drivers
     (Bartosz Golaszewski, Gustavo Silva, Julia Lawall, Paweł Chmiel,
     Taniya Das, Viresh Kumar)

   - Add a Hisilicon CPPC quirk to the cppc_cpufreq driver (Xiongfeng
     Wang)

   - Clean up the intel_pstate and acpi-cpufreq drivers (Erwan Velu,
     Rafael Wysocki)

   - Clean up multiple cpufreq drivers (Yangtao Li)

   - Update cpufreq-related MAINTAINERS entries (Baruch Siach, Lukas
     Bulwahn)

   - Add support for exposing the Energy Model via debugfs and make
     multiple cpufreq drivers register an Energy Model to support
     energy-aware scheduling (Quentin Perret, Dietmar Eggemann, Matthias
     Kaehlcke)

   - Add Ice Lake mobile and Jacobsville support to the Intel RAPL
     power-capping driver (Gayatri Kammela, Zhang Rui)

   - Add a power estimation helper to the operating performance points
     (OPP) framework and clean up a core function in it (Quentin Perret,
     Viresh Kumar)

   - Make minor improvements in the generic power domains (genpd), OPP
     and system suspend frameworks and in the PM core (Aditya Pakki,
     Douglas Anderson, Greg Kroah-Hartman, Rafael Wysocki, Yangtao Li)"

* tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (80 commits)
  cpufreq: kryo: Release OPP tables on module removal
  cpufreq: ap806: add missing of_node_put after of_device_is_available
  cpufreq: acpi-cpufreq: Report if CPU doesn't support boost technologies
  cpufreq: Pass updated policy to driver ->setpolicy() callback
  cpufreq: Fix two debug messages in cpufreq_set_policy()
  cpufreq: Reorder and simplify cpufreq_update_policy()
  cpufreq: Add kerneldoc comments for two core functions
  PM / core: Add support to skip power management in device/driver model
  cpufreq: intel_pstate: Rework iowait boosting to be less aggressive
  cpufreq: intel_pstate: Eliminate intel_pstate_get_base_pstate()
  cpufreq: intel_pstate: Avoid redundant initialization of local vars
  powercap/intel_rapl: add Ice Lake mobile
  ACPI / processor: Set P_LVL{2,3} idle state descriptions
  cpufreq / cppc: Work around for Hisilicon CPPC cpufreq
  ACPI / CPPC: Add a helper to get desired performance
  cpufreq: davinci: move configuration to include/linux/platform_data
  cpufreq: speedstep: convert BUG() to BUG_ON()
  cpufreq: powernv: fix missing check of return value in init_powernv_pstates()
  cpufreq: longhaul: remove unneeded semicolon
  cpufreq: pcc-cpufreq: remove unneeded semicolon
  ..

1 files changed, 56 insertions, 49 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index dd66decf2087..002f5169d4eb 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -50,6 +50,8 @@
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
 
+#define ONE_EIGHTH_FP ((int64_t)1 << (FRAC_BITS - 3))
+
 #define EXT_BITS 6
 #define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS)
 #define fp_ext_toint(X) ((X) >> EXT_FRAC_BITS)
@@ -895,7 +897,7 @@ static void intel_pstate_update_policies(void)
 /************************** sysfs begin ************************/
 #define show_one(file_name, object)					\
 	static ssize_t show_##file_name					\
-	(struct kobject *kobj, struct attribute *attr, char *buf)	\
+	(struct kobject *kobj, struct kobj_attribute *attr, char *buf)	\
 	{								\
 		return sprintf(buf, "%u\n", global.object);		\
 	}
@@ -904,7 +906,7 @@ static ssize_t intel_pstate_show_status(char *buf);
 static int intel_pstate_update_status(const char *buf, size_t size);
 
 static ssize_t show_status(struct kobject *kobj,
-			   struct attribute *attr, char *buf)
+			   struct kobj_attribute *attr, char *buf)
 {
 	ssize_t ret;
 
@@ -915,7 +917,7 @@ static ssize_t show_status(struct kobject *kobj,
 	return ret;
 }
 
-static ssize_t store_status(struct kobject *a, struct attribute *b,
+static ssize_t store_status(struct kobject *a, struct kobj_attribute *b,
 			    const char *buf, size_t count)
 {
 	char *p = memchr(buf, '\n', count);
@@ -929,7 +931,7 @@ static ssize_t store_status(struct kobject *a, struct attribute *b,
 }
 
 static ssize_t show_turbo_pct(struct kobject *kobj,
-				struct attribute *attr, char *buf)
+				struct kobj_attribute *attr, char *buf)
 {
 	struct cpudata *cpu;
 	int total, no_turbo, turbo_pct;
@@ -955,7 +957,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj,
 }
 
 static ssize_t show_num_pstates(struct kobject *kobj,
-				struct attribute *attr, char *buf)
+				struct kobj_attribute *attr, char *buf)
 {
 	struct cpudata *cpu;
 	int total;
@@ -976,7 +978,7 @@ static ssize_t show_num_pstates(struct kobject *kobj,
 }
 
 static ssize_t show_no_turbo(struct kobject *kobj,
-			     struct attribute *attr, char *buf)
+			     struct kobj_attribute *attr, char *buf)
 {
 	ssize_t ret;
 
@@ -998,7 +1000,7 @@ static ssize_t show_no_turbo(struct kobject *kobj,
 	return ret;
 }
 
-static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
+static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 			      const char *buf, size_t count)
 {
 	unsigned int input;
@@ -1045,7 +1047,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	return count;
 }
 
-static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
+static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b,
 				  const char *buf, size_t count)
 {
 	unsigned int input;
@@ -1075,7 +1077,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 	return count;
 }
 
-static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
+static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b,
 				  const char *buf, size_t count)
 {
 	unsigned int input;
@@ -1107,12 +1109,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 }
 
 static ssize_t show_hwp_dynamic_boost(struct kobject *kobj,
-				struct attribute *attr, char *buf)
+				struct kobj_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%u\n", hwp_boost);
 }
 
-static ssize_t store_hwp_dynamic_boost(struct kobject *a, struct attribute *b,
+static ssize_t store_hwp_dynamic_boost(struct kobject *a,
+				       struct kobj_attribute *b,
 				       const char *buf, size_t count)
 {
 	unsigned int input;
@@ -1444,12 +1447,6 @@ static int knl_get_turbo_pstate(void)
 	return ret;
 }
 
-static int intel_pstate_get_base_pstate(struct cpudata *cpu)
-{
-	return global.no_turbo || global.turbo_disabled ?
-			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
-}
-
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
@@ -1470,11 +1467,9 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu)
 
 static void intel_pstate_max_within_limits(struct cpudata *cpu)
 {
-	int pstate;
+	int pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio);
 
 	update_turbo_state();
-	pstate = intel_pstate_get_base_pstate(cpu);
-	pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio);
 	intel_pstate_set_pstate(cpu, pstate);
 }
 
@@ -1678,17 +1673,14 @@ static inline int32_t get_avg_pstate(struct cpudata *cpu)
 static inline int32_t get_target_pstate(struct cpudata *cpu)
 {
 	struct sample *sample = &cpu->sample;
-	int32_t busy_frac, boost;
+	int32_t busy_frac;
 	int target, avg_pstate;
 
 	busy_frac = div_fp(sample->mperf << cpu->aperf_mperf_shift,
 			   sample->tsc);
 
-	boost = cpu->iowait_boost;
-	cpu->iowait_boost >>= 1;
-
-	if (busy_frac < boost)
-		busy_frac = boost;
+	if (busy_frac < cpu->iowait_boost)
+		busy_frac = cpu->iowait_boost;
 
 	sample->busy_scaled = busy_frac * 100;
 
@@ -1715,11 +1707,9 @@ static inline int32_t get_target_pstate(struct cpudata *cpu)
 
 static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
 {
-	int max_pstate = intel_pstate_get_base_pstate(cpu);
-	int min_pstate;
+	int min_pstate = max(cpu->pstate.min_pstate, cpu->min_perf_ratio);
+	int max_pstate = max(min_pstate, cpu->max_perf_ratio);
 
-	min_pstate = max(cpu->pstate.min_pstate, cpu->min_perf_ratio);
-	max_pstate = max(min_pstate, cpu->max_perf_ratio);
 	return clamp_t(int, pstate, min_pstate, max_pstate);
 }
 
@@ -1767,29 +1757,30 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time,
 	if (smp_processor_id() != cpu->cpu)
 		return;
 
+	delta_ns = time - cpu->last_update;
 	if (flags & SCHED_CPUFREQ_IOWAIT) {
-		cpu->iowait_boost = int_tofp(1);
-		cpu->last_update = time;
-		/*
-		 * The last time the busy was 100% so P-state was max anyway
-		 * so avoid overhead of computation.
-		 */
-		if (fp_toint(cpu->sample.busy_scaled) == 100)
-			return;
-
-		goto set_pstate;
+		/* Start over if the CPU may have been idle. */
+		if (delta_ns > TICK_NSEC) {
+			cpu->iowait_boost = ONE_EIGHTH_FP;
+		} else if (cpu->iowait_boost) {
+			cpu->iowait_boost <<= 1;
+			if (cpu->iowait_boost > int_tofp(1))
+				cpu->iowait_boost = int_tofp(1);
+		} else {
+			cpu->iowait_boost = ONE_EIGHTH_FP;
+		}
 	} else if (cpu->iowait_boost) {
 		/* Clear iowait_boost if the CPU may have been idle. */
-		delta_ns = time - cpu->last_update;
 		if (delta_ns > TICK_NSEC)
 			cpu->iowait_boost = 0;
+		else
+			cpu->iowait_boost >>= 1;
 	}
 	cpu->last_update = time;
 	delta_ns = time - cpu->sample.time;
 	if ((s64)delta_ns < INTEL_PSTATE_SAMPLING_INTERVAL)
 		return;
 
-set_pstate:
 	if (intel_pstate_sample(cpu, time))
 		intel_pstate_adjust_pstate(cpu);
 }
@@ -1976,7 +1967,8 @@ static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
 	if (hwp_active) {
 		intel_pstate_get_hwp_max(cpu->cpu, &turbo_max, &max_state);
 	} else {
-		max_state = intel_pstate_get_base_pstate(cpu);
+		max_state = global.no_turbo || global.turbo_disabled ?
+			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 		turbo_max = cpu->pstate.turbo_pstate;
 	}
 
@@ -2475,6 +2467,7 @@ static bool __init intel_pstate_no_acpi_pss(void)
 		kfree(pss);
 	}
 
+	pr_debug("ACPI _PSS not found\n");
 	return true;
 }
 
@@ -2485,9 +2478,14 @@ static bool __init intel_pstate_no_acpi_pcch(void)
 
 	status = acpi_get_handle(NULL, "\\_SB", &handle);
 	if (ACPI_FAILURE(status))
-		return true;
+		goto not_found;
+
+	if (acpi_has_method(handle, "PCCH"))
+		return false;
 
-	return !acpi_has_method(handle, "PCCH");
+not_found:
+	pr_debug("ACPI PCCH not found\n");
+	return true;
 }
 
 static bool __init intel_pstate_has_acpi_ppc(void)
@@ -2502,6 +2500,7 @@ static bool __init intel_pstate_has_acpi_ppc(void)
 		if (acpi_has_method(pr->handle, "_PPC"))
 			return true;
 	}
+	pr_debug("ACPI _PPC not found\n");
 	return false;
 }
 
@@ -2539,8 +2538,10 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
 	id = x86_match_cpu(intel_pstate_cpu_oob_ids);
 	if (id) {
 		rdmsrl(MSR_MISC_PWR_MGMT, misc_pwr);
-		if ( misc_pwr & (1 << 8))
+		if (misc_pwr & (1 << 8)) {
+			pr_debug("Bit 8 in the MISC_PWR_MGMT MSR set\n");
 			return true;
+		}
 	}
 
 	idx = acpi_match_platform_list(plat_info);
@@ -2606,22 +2607,28 @@ static int __init intel_pstate_init(void)
 		}
 	} else {
 		id = x86_match_cpu(intel_pstate_cpu_ids);
-		if (!id)
+		if (!id) {
+			pr_info("CPU ID not supported\n");
 			return -ENODEV;
+		}
 
 		copy_cpu_funcs((struct pstate_funcs *)id->driver_data);
 	}
 
-	if (intel_pstate_msrs_not_valid())
+	if (intel_pstate_msrs_not_valid()) {
+		pr_info("Invalid MSRs\n");
 		return -ENODEV;
+	}
 
 hwp_cpu_matched:
 	/*
 	 * The Intel pstate driver will be ignored if the platform
 	 * firmware has its own power management modes.
 	 */
-	if (intel_pstate_platform_pwr_mgmt_exists())
+	if (intel_pstate_platform_pwr_mgmt_exists()) {
+		pr_info("P-states controlled by the platform\n");
 		return -ENODEV;
+	}
 
 	if (!hwp_active && hwp_only)
 		return -ENOTSUPP;