Merge tag 'pm-6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These add Intel TPMI (Topology Aware Register and PM Capsule
  Interface) support to the power capping subsystem, extend the
  intel_idle driver to work in VM guests where MWAIT is not available,
  extend the system-wide power management diagnostics, fix bugs and
  clean up code.

  Specifics:

   - Introduce power capping core support for Intel TPMI (Topology Aware
     Register and PM Capsule Interface) and a TPMI interface driver for
     Intel RAPL (Zhang Rui, Dan Carpenter)

   - Fix CONFIG_IOSF_MBI dependency in the Intel RAPL power capping
     driver (Zhang Rui)

   - Fix invalid initialization for pl4_supported field in the Intel
     RAPL power capping driver (Sumeet Pawnikar)

   - Clean up the intel_idle driver, make it work with VM guests that
     cannot use the MWAIT instruction and address the case in which the
     host may enter a deep idle state when the guest is idle (Arjan van
     de Ven)

   - Prevent cpufreq drivers that provide the ->adjust_perf() callback
     without a ->fast_switch() one which is used as a fallback from the
     former in some cases (Wyes Karny)

   - Fix some issues related to the AMD P-state cpufreq driver (Mario
     Limonciello, Wyes Karny)

   - Fix the energy_performance_preference attribute handling in the
     intel_pstate driver in passive mode (Tero Kristo)

   - Fix the handling of pm_suspend_target_state when CONFIG_PM is unset
     (Kai-Heng Feng)

   - Correct spelling mistake in a comment in the hibernation code (Wang
     Honghui)

   - Add arch_resume_nosmt() prototype to avoid a "missing prototypes"
     build warning (Arnd Bergmann)

   - Restrict pm_pr_dbg() to system-wide power transitions and use it in
     a few additional places (Mario Limonciello)

   - Drop verification of in-params from genpd_add_device() and ensure
     that all of its callers will do it (Ulf Hansson)

   - Prevent possible integer overflows from occurring in
     genpd_parse_state() (Nikita Zhandarovich)

   - Reorder fieldls in 'struct devfreq_dev_status' to reduce its size
     somewhat (Christophe JAILLET)

   - Ensure that the Exynos PPMU driver is already loaded before the
     Exynos Bus driver starts probing so as to avoid a possible freeze
     loading of the kernel modules (Marek Szyprowski)

   - Fix variable deferencing before NULL check in the mtk-cci devfreq
     driver (Sukrut Bellary)"

* tag 'pm-6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (42 commits)
  intel_idle: Add a "Long HLT" C1 state for the VM guest mode
  cpufreq: intel_pstate: Fix energy_performance_preference for passive
  cpufreq: amd-pstate: Add a kernel config option to set default mode
  cpufreq: amd-pstate: Set a fallback policy based on preferred_profile
  ACPI: CPPC: Add definition for undefined FADT preferred PM profile value
  cpufreq: amd-pstate: Set default governor to schedutil
  PM: domains: Move the verification of in-params from genpd_add_device()
  cpufreq: amd-pstate: Make amd-pstate EPP driver name hyphenated
  cpufreq: amd-pstate: Write CPPC enable bit per-socket
  intel_idle: Add support for using intel_idle in a VM guest using just hlt
  cpufreq: Fail driver register if it has adjust_perf without fast_switch
  intel_idle: clean up the (new) state_update_enter_method function
  intel_idle: refactor state->enter manipulation into its own function
  platform/x86/amd: pmc: Use pm_pr_dbg() for suspend related messages
  pinctrl: amd: Use pm_pr_dbg to show debugging messages
  ACPI: x86: Add pm_debug_messages for LPS0 _DSM state tracking
  include/linux/suspend.h: Only show pm_pr_dbg messages at suspend/resume
  powercap: RAPL: Fix a NULL vs IS_ERR() bug
  powercap: RAPL: Fix CONFIG_IOSF_MBI dependency
  powercap: RAPL: fix invalid initialization for pl4_supported field
  ...

Author: torvalds

drivers/acpi/x86/s2idle.c

@@ -59,6 +59,7 @@ static int lps0_dsm_func_mask;
 
 static guid_t lps0_dsm_guid_microsoft;
 static int lps0_dsm_func_mask_microsoft;
+static int lps0_dsm_state;
 
 /* Device constraint entry structure */
 struct lpi_device_info {
@@ -320,6 +321,44 @@ static void lpi_check_constraints(void)
 	}
 }
 
+static bool acpi_s2idle_vendor_amd(void)
+{
+	return boot_cpu_data.x86_vendor == X86_VENDOR_AMD;
+}
+
+static const char *acpi_sleep_dsm_state_to_str(unsigned int state)
+{
+	if (lps0_dsm_func_mask_microsoft || !acpi_s2idle_vendor_amd()) {
+		switch (state) {
+		case ACPI_LPS0_SCREEN_OFF:
+			return "screen off";
+		case ACPI_LPS0_SCREEN_ON:
+			return "screen on";
+		case ACPI_LPS0_ENTRY:
+			return "lps0 entry";
+		case ACPI_LPS0_EXIT:
+			return "lps0 exit";
+		case ACPI_LPS0_MS_ENTRY:
+			return "lps0 ms entry";
+		case ACPI_LPS0_MS_EXIT:
+			return "lps0 ms exit";
+		}
+	} else {
+		switch (state) {
+		case ACPI_LPS0_SCREEN_ON_AMD:
+			return "screen on";
+		case ACPI_LPS0_SCREEN_OFF_AMD:
+			return "screen off";
+		case ACPI_LPS0_ENTRY_AMD:
+			return "lps0 entry";
+		case ACPI_LPS0_EXIT_AMD:
+			return "lps0 exit";
+		}
+	}
+
+	return "unknown";
+}
+
 static void acpi_sleep_run_lps0_dsm(unsigned int func, unsigned int func_mask, guid_t dsm_guid)
 {
 	union acpi_object *out_obj;
@@ -331,14 +370,15 @@ static void acpi_sleep_run_lps0_dsm(unsigned int func, unsigned int func_mask, g
 					rev_id, func, NULL);
 	ACPI_FREE(out_obj);
 
-	acpi_handle_debug(lps0_device_handle, "_DSM function %u evaluation %s\n",
-			  func, out_obj ? "successful" : "failed");
+	lps0_dsm_state = func;
+	if (pm_debug_messages_on) {
+		acpi_handle_info(lps0_device_handle,
+				"%s transitioned to state %s\n",
+				 out_obj ? "Successfully" : "Failed to",
+				 acpi_sleep_dsm_state_to_str(lps0_dsm_state));
+	}
 }
 
-static bool acpi_s2idle_vendor_amd(void)
-{
-	return boot_cpu_data.x86_vendor == X86_VENDOR_AMD;
-}
 
 static int validate_dsm(acpi_handle handle, const char *uuid, int rev, guid_t *dsm_guid)
 {

drivers/base/power/domain.c

@@ -1632,9 +1632,6 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 
 	dev_dbg(dev, "%s()\n", __func__);
 
-	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
-		return -EINVAL;
-
 	gpd_data = genpd_alloc_dev_data(dev, gd);
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
@@ -1676,6 +1673,9 @@ int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev)
 {
 	int ret;
 
+	if (!genpd || !dev)
+		return -EINVAL;
+
 	mutex_lock(&gpd_list_lock);
 	ret = genpd_add_device(genpd, dev, dev);
 	mutex_unlock(&gpd_list_lock);
@@ -2523,6 +2523,9 @@ int of_genpd_add_device(struct of_phandle_args *genpdspec, struct device *dev)
 	struct generic_pm_domain *genpd;
 	int ret;
 
+	if (!dev)
+		return -EINVAL;
+
 	mutex_lock(&gpd_list_lock);
 
 	genpd = genpd_get_from_provider(genpdspec);
@@ -2939,10 +2942,10 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state,
 
 	err = of_property_read_u32(state_node, "min-residency-us", &residency);
 	if (!err)
-		genpd_state->residency_ns = 1000 * residency;
+		genpd_state->residency_ns = 1000LL * residency;
 
-	genpd_state->power_on_latency_ns = 1000 * exit_latency;
-	genpd_state->power_off_latency_ns = 1000 * entry_latency;
+	genpd_state->power_on_latency_ns = 1000LL * exit_latency;
+	genpd_state->power_off_latency_ns = 1000LL * entry_latency;
 	genpd_state->fwnode = &state_node->fwnode;
 
 	return 0;

drivers/base/power/wakeup.c

@@ -19,11 +19,6 @@
 
 #include "power.h"
 
-#ifndef CONFIG_SUSPEND
-suspend_state_t pm_suspend_target_state;
-#define pm_suspend_target_state	(PM_SUSPEND_ON)
-#endif
-
 #define list_for_each_entry_rcu_locked(pos, head, member) \
 	list_for_each_entry_rcu(pos, head, member, \
 		srcu_read_lock_held(&wakeup_srcu))

drivers/cpufreq/Kconfig

@@ -38,7 +38,7 @@ choice
 	prompt "Default CPUFreq governor"
 	default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1110_CPUFREQ
 	default CPU_FREQ_DEFAULT_GOV_SCHEDUTIL if ARM64 || ARM
-	default CPU_FREQ_DEFAULT_GOV_SCHEDUTIL if X86_INTEL_PSTATE && SMP
+	default CPU_FREQ_DEFAULT_GOV_SCHEDUTIL if (X86_INTEL_PSTATE || X86_AMD_PSTATE) && SMP
 	default CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 	help
 	  This option sets which CPUFreq governor shall be loaded at

drivers/cpufreq/Kconfig.x86

@@ -51,6 +51,23 @@ config X86_AMD_PSTATE
 
 	  If in doubt, say N.
 
+config X86_AMD_PSTATE_DEFAULT_MODE
+	int "AMD Processor P-State default mode"
+	depends on X86_AMD_PSTATE
+	default 3 if X86_AMD_PSTATE
+	range 1 4
+	help
+	  Select the default mode the amd-pstate driver will use on
+	  supported hardware.
+	  The value set has the following meanings:
+		1 -> Disabled
+		2 -> Passive
+		3 -> Active (EPP)
+		4 -> Guided
+
+	  For details, take a look at:
+	  <file:Documentation/admin-guide/pm/amd-pstate.rst>.
+
 config X86_AMD_PSTATE_UT
 	tristate "selftest for AMD Processor P-State driver"
 	depends on X86 && ACPI_PROCESSOR

drivers/cpufreq/amd-pstate.c

@@ -62,7 +62,8 @@
 static struct cpufreq_driver *current_pstate_driver;
 static struct cpufreq_driver amd_pstate_driver;
 static struct cpufreq_driver amd_pstate_epp_driver;
-static int cppc_state = AMD_PSTATE_DISABLE;
+static int cppc_state = AMD_PSTATE_UNDEFINED;
+static bool cppc_enabled;
 
 /*
  * AMD Energy Preference Performance (EPP)
@@ -228,14 +229,38 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata,
 
 static inline int pstate_enable(bool enable)
 {
-	return wrmsrl_safe(MSR_AMD_CPPC_ENABLE, enable);
+	int ret, cpu;
+	unsigned long logical_proc_id_mask = 0;
+
+	if (enable == cppc_enabled)
+		return 0;
+
+	for_each_present_cpu(cpu) {
+		unsigned long logical_id = topology_logical_die_id(cpu);
+
+		if (test_bit(logical_id, &logical_proc_id_mask))
+			continue;
+
+		set_bit(logical_id, &logical_proc_id_mask);
+
+		ret = wrmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_ENABLE,
+				enable);
+		if (ret)
+			return ret;
+	}
+
+	cppc_enabled = enable;
+	return 0;
 }
 
 static int cppc_enable(bool enable)
 {
 	int cpu, ret = 0;
 	struct cppc_perf_ctrls perf_ctrls;
 
+	if (enable == cppc_enabled)
+		return 0;
+
 	for_each_present_cpu(cpu) {
 		ret = cppc_set_enable(cpu, enable);
 		if (ret)
@@ -251,6 +276,7 @@ static int cppc_enable(bool enable)
 		}
 	}
 
+	cppc_enabled = enable;
 	return ret;
 }
 
@@ -1045,6 +1071,26 @@ static const struct attribute_group amd_pstate_global_attr_group = {
 	.attrs = pstate_global_attributes,
 };
 
+static bool amd_pstate_acpi_pm_profile_server(void)
+{
+	switch (acpi_gbl_FADT.preferred_profile) {
+	case PM_ENTERPRISE_SERVER:
+	case PM_SOHO_SERVER:
+	case PM_PERFORMANCE_SERVER:
+		return true;
+	}
+	return false;
+}
+
+static bool amd_pstate_acpi_pm_profile_undefined(void)
+{
+	if (acpi_gbl_FADT.preferred_profile == PM_UNSPECIFIED)
+		return true;
+	if (acpi_gbl_FADT.preferred_profile >= NR_PM_PROFILES)
+		return true;
+	return false;
+}
+
 static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 {
 	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
@@ -1102,10 +1148,14 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	policy->max = policy->cpuinfo.max_freq;
 
 	/*
-	 * Set the policy to powersave to provide a valid fallback value in case
+	 * Set the policy to provide a valid fallback value in case
 	 * the default cpufreq governor is neither powersave nor performance.
 	 */
-	policy->policy = CPUFREQ_POLICY_POWERSAVE;
+	if (amd_pstate_acpi_pm_profile_server() ||
+	    amd_pstate_acpi_pm_profile_undefined())
+		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
+	else
+		policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
 	if (boot_cpu_has(X86_FEATURE_CPPC)) {
 		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value);
@@ -1356,26 +1406,36 @@ static struct cpufreq_driver amd_pstate_epp_driver = {
 	.online		= amd_pstate_epp_cpu_online,
 	.suspend	= amd_pstate_epp_suspend,
 	.resume		= amd_pstate_epp_resume,
-	.name		= "amd_pstate_epp",
+	.name		= "amd-pstate-epp",
 	.attr		= amd_pstate_epp_attr,
 };
 
+static int __init amd_pstate_set_driver(int mode_idx)
+{
+	if (mode_idx >= AMD_PSTATE_DISABLE && mode_idx < AMD_PSTATE_MAX) {
+		cppc_state = mode_idx;
+		if (cppc_state == AMD_PSTATE_DISABLE)
+			pr_info("driver is explicitly disabled\n");
+
+		if (cppc_state == AMD_PSTATE_ACTIVE)
+			current_pstate_driver = &amd_pstate_epp_driver;
+
+		if (cppc_state == AMD_PSTATE_PASSIVE || cppc_state == AMD_PSTATE_GUIDED)
+			current_pstate_driver = &amd_pstate_driver;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 static int __init amd_pstate_init(void)
 {
 	struct device *dev_root;
 	int ret;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		return -ENODEV;
-	/*
-	 * by default the pstate driver is disabled to load
-	 * enable the amd_pstate passive mode driver explicitly
-	 * with amd_pstate=passive or other modes in kernel command line
-	 */
-	if (cppc_state == AMD_PSTATE_DISABLE) {
-		pr_info("driver load is disabled, boot with specific mode to enable this\n");
-		return -ENODEV;
-	}
 
 	if (!acpi_cpc_valid()) {
 		pr_warn_once("the _CPC object is not present in SBIOS or ACPI disabled\n");
@@ -1386,6 +1446,33 @@ static int __init amd_pstate_init(void)
 	if (cpufreq_get_current_driver())
 		return -EEXIST;
 
+	switch (cppc_state) {
+	case AMD_PSTATE_UNDEFINED:
+		/* Disable on the following configs by default:
+		 * 1. Undefined platforms
+		 * 2. Server platforms
+		 * 3. Shared memory designs
+		 */
+		if (amd_pstate_acpi_pm_profile_undefined() ||
+		    amd_pstate_acpi_pm_profile_server() ||
+		    !boot_cpu_has(X86_FEATURE_CPPC)) {
+			pr_info("driver load is disabled, boot with specific mode to enable this\n");
+			return -ENODEV;
+		}
+		ret = amd_pstate_set_driver(CONFIG_X86_AMD_PSTATE_DEFAULT_MODE);
+		if (ret)
+			return ret;
+		break;
+	case AMD_PSTATE_DISABLE:
+		return -ENODEV;
+	case AMD_PSTATE_PASSIVE:
+	case AMD_PSTATE_ACTIVE:
+	case AMD_PSTATE_GUIDED:
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	/* capability check */
 	if (boot_cpu_has(X86_FEATURE_CPPC)) {
 		pr_debug("AMD CPPC MSR based functionality is supported\n");
@@ -1438,21 +1525,7 @@ static int __init amd_pstate_param(char *str)
 	size = strlen(str);
 	mode_idx = get_mode_idx_from_str(str, size);
 
-	if (mode_idx >= AMD_PSTATE_DISABLE && mode_idx < AMD_PSTATE_MAX) {
-		cppc_state = mode_idx;
-		if (cppc_state == AMD_PSTATE_DISABLE)
-			pr_info("driver is explicitly disabled\n");
-
-		if (cppc_state == AMD_PSTATE_ACTIVE)
-			current_pstate_driver = &amd_pstate_epp_driver;
-
-		if (cppc_state == AMD_PSTATE_PASSIVE || cppc_state == AMD_PSTATE_GUIDED)
-			current_pstate_driver = &amd_pstate_driver;
-
-		return 0;
-	}
-
-	return -EINVAL;
+	return amd_pstate_set_driver(mode_idx);
 }
 early_param("amd_pstate", amd_pstate_param);
 

drivers/cpufreq/cpufreq.c

@@ -2828,7 +2828,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	     (driver_data->setpolicy && (driver_data->target_index ||
 		    driver_data->target)) ||
 	     (!driver_data->get_intermediate != !driver_data->target_intermediate) ||
-	     (!driver_data->online != !driver_data->offline))
+	     (!driver_data->online != !driver_data->offline) ||
+		 (driver_data->adjust_perf && !driver_data->fast_switch))
 		return -EINVAL;
 
 	pr_debug("trying to register driver %s\n", driver_data->name);

drivers/cpufreq/intel_pstate.c

@@ -824,6 +824,8 @@ static ssize_t store_energy_performance_preference(
 			err = cpufreq_start_governor(policy);
 			if (!ret)
 				ret = err;
+		} else {
+			ret = 0;
 		}
 	}
 

drivers/devfreq/exynos-bus.c

@@ -518,6 +518,7 @@ static struct platform_driver exynos_bus_platdrv = {
 };
 module_platform_driver(exynos_bus_platdrv);
 
+MODULE_SOFTDEP("pre: exynos_ppmu");
 MODULE_DESCRIPTION("Generic Exynos Bus frequency driver");
 MODULE_AUTHOR("Chanwoo Choi <[email protected]>");
 MODULE_LICENSE("GPL v2");