Merge tag 'pm-4.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These are mostly fixes, including some fixes for changes made during
  the recent merge window and some "stable" material, plus some minor
  extensions of the turbostat utility.

  Specifics:

   - Fix the PM core to avoid introducing a runtime PM usage counter
     imbalance when adding device links during driver probe (Rafael
     Wysocki).

   - Fix the operating performance points (OPP) framework to ensure that
     the regulator voltage is always updated as appropriate when
     updating clock rates (Waldemar Rymarkiewicz).

   - Fix the intel_pstate driver to use correct max/min limits for cores
     with differing maximum frequences (Srinivas Pandruvada).

   - Fix a typo in the intel_pstate driver documentation (Rafael
     Wysocki).

   - Fix two issues with the recently added Kryo cpufreq driver (Ilia
     Lin).

   - Fix two recent regressions and some other minor issues in the
     turbostat utility and extend it to provide some more diagnostic
     information (Len Brown, Nathan Ciobanu)"

* tag 'pm-4.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  Documentation: intel_pstate: Fix typo
  tools/power turbostat: version 18.06.20
  tools/power turbostat: add the missing command line switches
  tools/power turbostat: add single character tokens to help
  tools/power turbostat: alphabetize the help output
  tools/power turbostat: fix segfault on 'no node' machines
  tools/power turbostat: add optional APIC X2APIC columns
  tools/power turbostat: decode cpuid.1.HT
  tools/power turbostat: fix show/hide issues resulting from mis-merge
  PM / OPP: Update voltage in case freq == old_freq
  cpufreq: intel_pstate: Fix scaling max/min limits with Turbo 3.0
  cpufreq: kryo: Add module remove and exit
  cpufreq: kryo: Fix possible error code dereference
  PM / core: Fix supplier device runtime PM usage counter imbalance

Documentation/admin-guide/pm/intel_pstate.rst

@@ -410,7 +410,7 @@ argument is passed to the kernel in the command line.
 	That only is supported in some configurations, though (for example, if
 	the `HWP feature is enabled in the processor <Active Mode With HWP_>`_,
 	the operation mode of the driver cannot be changed), and if it is not
-	supported in the current configuration, writes to this attribute with
+	supported in the current configuration, writes to this attribute will
 	fail with an appropriate error.
 
 Interpretation of Policy Attributes

drivers/base/core.c

@@ -236,6 +236,13 @@ struct device_link *device_link_add(struct device *consumer,
 			link->rpm_active = true;
 		}
 		pm_runtime_new_link(consumer);
+		/*
+		 * If the link is being added by the consumer driver at probe
+		 * time, balance the decrementation of the supplier's runtime PM
+		 * usage counter after consumer probe in driver_probe_device().
+		 */
+		if (consumer->links.status == DL_DEV_PROBING)
+			pm_runtime_get_noresume(supplier);
 	}
 	get_device(supplier);
 	link->supplier = supplier;
@@ -255,12 +262,12 @@ struct device_link *device_link_add(struct device *consumer,
 			switch (consumer->links.status) {
 			case DL_DEV_PROBING:
 				/*
-				 * Balance the decrementation of the supplier's
-				 * runtime PM usage counter after consumer probe
-				 * in driver_probe_device().
+				 * Some callers expect the link creation during
+				 * consumer driver probe to resume the supplier
+				 * even without DL_FLAG_RPM_ACTIVE.
 				 */
 				if (flags & DL_FLAG_PM_RUNTIME)
-					pm_runtime_get_sync(supplier);
+					pm_runtime_resume(supplier);
 
 				link->status = DL_STATE_CONSUMER_PROBE;
 				break;

drivers/cpufreq/intel_pstate.c

@@ -294,6 +294,7 @@ struct pstate_funcs {
 static struct pstate_funcs pstate_funcs __read_mostly;
 
 static int hwp_active __read_mostly;
+static int hwp_mode_bdw __read_mostly;
 static bool per_cpu_limits __read_mostly;
 static bool hwp_boost __read_mostly;
 
@@ -1413,7 +1414,15 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
 	cpu->pstate.scaling = pstate_funcs.get_scaling();
 	cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
+
+	if (hwp_active && !hwp_mode_bdw) {
+		unsigned int phy_max, current_max;
+
+		intel_pstate_get_hwp_max(cpu->cpu, &phy_max, &current_max);
+		cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling;
+	} else {
 		cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+	}
 
 	if (pstate_funcs.get_aperf_mperf_shift)
 		cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();
@@ -2467,28 +2476,36 @@ static inline bool intel_pstate_has_acpi_ppc(void) { return false; }
 static inline void intel_pstate_request_control_from_smm(void) {}
 #endif /* CONFIG_ACPI */
 
+#define INTEL_PSTATE_HWP_BROADWELL	0x01
+
+#define ICPU_HWP(model, hwp_mode) \
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_HWP, hwp_mode }
+
 static const struct x86_cpu_id hwp_support_ids[] __initconst = {
-	{ X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP },
+	ICPU_HWP(INTEL_FAM6_BROADWELL_X, INTEL_PSTATE_HWP_BROADWELL),
+	ICPU_HWP(INTEL_FAM6_BROADWELL_XEON_D, INTEL_PSTATE_HWP_BROADWELL),
+	ICPU_HWP(X86_MODEL_ANY, 0),
 	{}
 };
 
 static int __init intel_pstate_init(void)
 {
+	const struct x86_cpu_id *id;
 	int rc;
 
 	if (no_load)
 		return -ENODEV;
 
-	if (x86_match_cpu(hwp_support_ids)) {
+	id = x86_match_cpu(hwp_support_ids);
+	if (id) {
 		copy_cpu_funcs(&core_funcs);
 		if (!no_hwp) {
 			hwp_active++;
+			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
 			goto hwp_cpu_matched;
 		}
 	} else {
-		const struct x86_cpu_id *id;
-
 		id = x86_match_cpu(intel_pstate_cpu_ids);
 		if (!id)
 			return -ENODEV;

drivers/cpufreq/qcom-cpufreq-kryo.c

@@ -42,6 +42,8 @@ enum _msm8996_version {
 	NUM_OF_MSM8996_VERSIONS,
 };
 
+struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
+
 static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
 {
 	size_t len;
@@ -74,7 +76,6 @@ static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
 static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 {
 	struct opp_table *opp_tables[NR_CPUS] = {0};
-	struct platform_device *cpufreq_dt_pdev;
 	enum _msm8996_version msm8996_version;
 	struct nvmem_cell *speedbin_nvmem;
 	struct device_node *np;
@@ -115,6 +116,8 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 
 	speedbin = nvmem_cell_read(speedbin_nvmem, &len);
 	nvmem_cell_put(speedbin_nvmem);
+	if (IS_ERR(speedbin))
+		return PTR_ERR(speedbin);
 
 	switch (msm8996_version) {
 	case MSM8996_V3:
@@ -127,6 +130,7 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 		BUG();
 		break;
 	}
+	kfree(speedbin);
 
 	for_each_possible_cpu(cpu) {
 		cpu_dev = get_cpu_device(cpu);
@@ -162,8 +166,15 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 	return ret;
 }
 
+static int qcom_cpufreq_kryo_remove(struct platform_device *pdev)
+{
+	platform_device_unregister(cpufreq_dt_pdev);
+	return 0;
+}
+
 static struct platform_driver qcom_cpufreq_kryo_driver = {
 	.probe = qcom_cpufreq_kryo_probe,
+	.remove = qcom_cpufreq_kryo_remove,
 	.driver = {
 		.name = "qcom-cpufreq-kryo",
 	},
@@ -198,8 +209,9 @@ static int __init qcom_cpufreq_kryo_init(void)
 	if (unlikely(ret < 0))
 		return ret;
 
-	ret = PTR_ERR_OR_ZERO(platform_device_register_simple(
-		"qcom-cpufreq-kryo", -1, NULL, 0));
+	kryo_cpufreq_pdev = platform_device_register_simple(
+		"qcom-cpufreq-kryo", -1, NULL, 0);
+	ret = PTR_ERR_OR_ZERO(kryo_cpufreq_pdev);
 	if (0 == ret)
 		return 0;
 
@@ -208,5 +220,12 @@ static int __init qcom_cpufreq_kryo_init(void)
 }
 module_init(qcom_cpufreq_kryo_init);
 
+static void __init qcom_cpufreq_kryo_exit(void)
+{
+	platform_device_unregister(kryo_cpufreq_pdev);
+	platform_driver_unregister(&qcom_cpufreq_kryo_driver);
+}
+module_exit(qcom_cpufreq_kryo_exit);
+
 MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver");
 MODULE_LICENSE("GPL v2");

drivers/opp/core.c

@@ -598,7 +598,7 @@ static int _generic_set_opp_regulator(const struct opp_table *opp_table,
 	}
 
 	/* Scaling up? Scale voltage before frequency */
-	if (freq > old_freq) {
+	if (freq >= old_freq) {
 		ret = _set_opp_voltage(dev, reg, new_supply);
 		if (ret)
 			goto restore_voltage;

tools/power/x86/turbostat/turbostat.8

@@ -56,7 +56,7 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--hide column\fP do not show the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
 .PP
-\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default.  Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds".
+\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default.  Currently the only built-in counters disabled by default are "usec", "Time_Of_Day_Seconds", "APIC" and "X2APIC".
 The column name "all" can be used to enable all disabled-by-default built-in counters.
 .PP
 \fB--show column\fP show only the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.