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
  ...

6 files changed, 49 insertions, 20 deletions

diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index e5dfb6f4de52..451f6276da49 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -307,7 +307,8 @@ enum acpi_preferred_pm_profiles {
 	PM_SOHO_SERVER = 5,
 	PM_APPLIANCE_PC = 6,
 	PM_PERFORMANCE_SERVER = 7,
-	PM_TABLET = 8
+	PM_TABLET = 8,
+	NR_PM_PROFILES = 9
 };
 
 /* Values for sleep_status and sleep_control registers (V5+ FADT) */
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index c10ebf8c42e6..446394f84606 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -94,7 +94,8 @@ struct amd_cpudata {
  * enum amd_pstate_mode - driver working mode of amd pstate
  */
 enum amd_pstate_mode {
-	AMD_PSTATE_DISABLE = 0,
+	AMD_PSTATE_UNDEFINED = 0,
+	AMD_PSTATE_DISABLE,
 	AMD_PSTATE_PASSIVE,
 	AMD_PSTATE_ACTIVE,
 	AMD_PSTATE_GUIDED,
@@ -102,6 +103,7 @@ enum amd_pstate_mode {
 };
 
 static const char * const amd_pstate_mode_string[] = {
+	[AMD_PSTATE_UNDEFINED]   = "undefined",
 	[AMD_PSTATE_DISABLE]     = "disable",
 	[AMD_PSTATE_PASSIVE]     = "passive",
 	[AMD_PSTATE_ACTIVE]      = "active",
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 26e2eb399484..172ff51c1b2a 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -340,7 +340,10 @@ struct cpufreq_driver {
 	/*
 	 * ->fast_switch() replacement for drivers that use an internal
 	 * representation of performance levels and can pass hints other than
-	 * the target performance level to the hardware.
+	 * the target performance level to the hardware. This can only be set
+	 * if ->fast_switch is set too, because in those cases (under specific
+	 * conditions) scale invariance can be disabled, which causes the
+	 * schedutil governor to fall back to the latter.
 	 */
 	void		(*adjust_perf)(unsigned int cpu,
 				       unsigned long min_perf,
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 7fd704bb8f3d..d312ffbac4dd 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -108,7 +108,6 @@ struct devfreq_dev_profile {
 	unsigned long initial_freq;
 	unsigned int polling_ms;
 	enum devfreq_timer timer;
-	bool is_cooling_device;
 
 	int (*target)(struct device *dev, unsigned long *freq, u32 flags);
 	int (*get_dev_status)(struct device *dev,
@@ -118,6 +117,8 @@ struct devfreq_dev_profile {
 
 	unsigned long *freq_table;
 	unsigned int max_state;
+
+	bool is_cooling_device;
 };
 
 /**
diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h
index 9f4b6f5b822f..e6936cb25047 100644
--- a/include/linux/intel_rapl.h
+++ b/include/linux/intel_rapl.h
@@ -14,6 +14,12 @@
 #include <linux/powercap.h>
 #include <linux/cpuhotplug.h>
 
+enum rapl_if_type {
+	RAPL_IF_MSR,	/* RAPL I/F using MSR registers */
+	RAPL_IF_MMIO,	/* RAPL I/F using MMIO registers */
+	RAPL_IF_TPMI,	/* RAPL I/F using TPMI registers */
+};
+
 enum rapl_domain_type {
 	RAPL_DOMAIN_PACKAGE,	/* entire package/socket */
 	RAPL_DOMAIN_PP0,	/* core power plane */
@@ -30,17 +36,23 @@ enum rapl_domain_reg_id {
 	RAPL_DOMAIN_REG_POLICY,
 	RAPL_DOMAIN_REG_INFO,
 	RAPL_DOMAIN_REG_PL4,
+	RAPL_DOMAIN_REG_UNIT,
+	RAPL_DOMAIN_REG_PL2,
 	RAPL_DOMAIN_REG_MAX,
 };
 
 struct rapl_domain;
 
 enum rapl_primitives {
-	ENERGY_COUNTER,
 	POWER_LIMIT1,
 	POWER_LIMIT2,
 	POWER_LIMIT4,
+	ENERGY_COUNTER,
 	FW_LOCK,
+	FW_HIGH_LOCK,
+	PL1_LOCK,
+	PL2_LOCK,
+	PL4_LOCK,
 
 	PL1_ENABLE,		/* power limit 1, aka long term */
 	PL1_CLAMP,		/* allow frequency to go below OS request */
@@ -74,12 +86,13 @@ struct rapl_domain_data {
 	unsigned long timestamp;
 };
 
-#define NR_POWER_LIMITS (3)
+#define NR_POWER_LIMITS	(POWER_LIMIT4 + 1)
+
 struct rapl_power_limit {
 	struct powercap_zone_constraint *constraint;
-	int prim_id;		/* primitive ID used to enable */
 	struct rapl_domain *domain;
 	const char *name;
+	bool locked;
 	u64 last_power_limit;
 };
 
@@ -96,7 +109,9 @@ struct rapl_domain {
 	struct rapl_power_limit rpl[NR_POWER_LIMITS];
 	u64 attr_map;		/* track capabilities */
 	unsigned int state;
-	unsigned int domain_energy_unit;
+	unsigned int power_unit;
+	unsigned int energy_unit;
+	unsigned int time_unit;
 	struct rapl_package *rp;
 };
 
@@ -121,16 +136,20 @@ struct reg_action {
  *				registers.
  * @write_raw:			Callback for writing RAPL interface specific
  *				registers.
+ * @defaults:			internal pointer to interface default settings
+ * @rpi:			internal pointer to interface primitive info
  */
 struct rapl_if_priv {
+	enum rapl_if_type type;
 	struct powercap_control_type *control_type;
-	struct rapl_domain *platform_rapl_domain;
 	enum cpuhp_state pcap_rapl_online;
 	u64 reg_unit;
 	u64 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX];
 	int limits[RAPL_DOMAIN_MAX];
-	int (*read_raw)(int cpu, struct reg_action *ra);
-	int (*write_raw)(int cpu, struct reg_action *ra);
+	int (*read_raw)(int id, struct reg_action *ra);
+	int (*write_raw)(int id, struct reg_action *ra);
+	void *defaults;
+	void *rpi;
 };
 
 /* maximum rapl package domain name: package-%d-die-%d */
@@ -140,9 +159,6 @@ struct rapl_package {
 	unsigned int id;	/* logical die id, equals physical 1-die systems */
 	unsigned int nr_domains;
 	unsigned long domain_map;	/* bit map of active domains */
-	unsigned int power_unit;
-	unsigned int energy_unit;
-	unsigned int time_unit;
 	struct rapl_domain *domains;	/* array of domains, sized at runtime */
 	struct powercap_zone *power_zone;	/* keep track of parent zone */
 	unsigned long power_limit_irq;	/* keep track of package power limit
@@ -156,8 +172,8 @@ struct rapl_package {
 	struct rapl_if_priv *priv;
 };
 
-struct rapl_package *rapl_find_package_domain(int cpu, struct rapl_if_priv *priv);
-struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv);
+struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, bool id_is_cpu);
+struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu);
 void rapl_remove_package(struct rapl_package *rp);
 
 #endif /* __INTEL_RAPL_H__ */
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index f16653f7be32..4d0095e8989e 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -202,6 +202,7 @@ struct platform_s2idle_ops {
 };
 
 #ifdef CONFIG_SUSPEND
+extern suspend_state_t pm_suspend_target_state;
 extern suspend_state_t mem_sleep_current;
 extern suspend_state_t mem_sleep_default;
 
@@ -337,6 +338,8 @@ extern bool sync_on_suspend_enabled;
 #else /* !CONFIG_SUSPEND */
 #define suspend_valid_only_mem	NULL
 
+#define pm_suspend_target_state	(PM_SUSPEND_ON)
+
 static inline void pm_suspend_clear_flags(void) {}
 static inline void pm_set_suspend_via_firmware(void) {}
 static inline void pm_set_resume_via_firmware(void) {}
@@ -472,6 +475,8 @@ static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) {
 }
 #endif /* CONFIG_HIBERNATION */
 
+int arch_resume_nosmt(void);
+
 #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV
 int is_hibernate_resume_dev(dev_t dev);
 #else
@@ -507,7 +512,6 @@ extern void pm_report_max_hw_sleep(u64 t);
 
 /* drivers/base/power/wakeup.c */
 extern bool events_check_enabled;
-extern suspend_state_t pm_suspend_target_state;
 
 extern bool pm_wakeup_pending(void);
 extern void pm_system_wakeup(void);
@@ -555,6 +559,7 @@ static inline void unlock_system_sleep(unsigned int flags) {}
 #ifdef CONFIG_PM_SLEEP_DEBUG
 extern bool pm_print_times_enabled;
 extern bool pm_debug_messages_on;
+extern bool pm_debug_messages_should_print(void);
 static inline int pm_dyn_debug_messages_on(void)
 {
 #ifdef CONFIG_DYNAMIC_DEBUG
@@ -568,14 +573,14 @@ static inline int pm_dyn_debug_messages_on(void)
 #endif
 #define __pm_pr_dbg(fmt, ...)					\
 	do {							\
-		if (pm_debug_messages_on)			\
+		if (pm_debug_messages_should_print())		\
 			printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__);	\
 		else if (pm_dyn_debug_messages_on())		\
 			pr_debug(fmt, ##__VA_ARGS__);	\
 	} while (0)
 #define __pm_deferred_pr_dbg(fmt, ...)				\
 	do {							\
-		if (pm_debug_messages_on)			\
+		if (pm_debug_messages_should_print())		\
 			printk_deferred(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__);	\
 	} while (0)
 #else
@@ -593,7 +598,8 @@ static inline int pm_dyn_debug_messages_on(void)
 /**
  * pm_pr_dbg - print pm sleep debug messages
  *
- * If pm_debug_messages_on is enabled, print message.
+ * If pm_debug_messages_on is enabled and the system is entering/leaving
+ *      suspend, print message.
  * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is enabled,
  *	print message only from instances explicitly enabled on dynamic debug's
  *	control.