Merge branches 'pm-core', 'pm-sleep', 'pm-opp' and 'pm-tools'

Merge PM core changes, updates related to system sleep support,
operating performance points (OPP) changes and power management
utilities changes for 6.4-rc1:

 - Drop unnecessary (void *) conversions from the PM core (Li zeming).

 - Add sysfs files to represent time spent in a platform sleep state
   during suspend-to-idle and make AMD and Intel PMC drivers use them
   (Mario Limonciello).

 - Use of_property_present() for testing DT property presence (Rob
   Herring).

 - Add set_required_opps() callback to the 'struct opp_table', to make
   the code paths cleaner (Viresh Kumar).

 - Update the pm-graph siute of utilities to v5.11 with the following
   changes:
   * New script which allows users to install the latest pm-graph
     from the upstream github repo.
   * Update all the dmesg suspend/resume PM print formats to be able to
     process recent timelines using dmesg only.
   * Add ethtool output to the log for the system's ethernet device if
     ethtool exists.
   * Make the tool more robustly handle events where mangled dmesg or
     ftrace outputs do not include all the requisite data.

 - Make the sleepgraph utility recognize "CPU killed" messages (Xueqin
   Luo).

* pm-core:
  PM: core: Remove unnecessary (void *) conversions

* pm-sleep:
  platform/x86/intel/pmc: core: Report duration of time in HW sleep state
  platform/x86/intel/pmc: core: Always capture counters on suspend
  platform/x86/amd: pmc: Report duration of time in hw sleep state
  PM: Add sysfs files to represent time spent in hardware sleep state

* pm-opp:
  OPP: Move required opps configuration to specialized callback
  OPP: Handle all genpd cases together in _set_required_opps()
  opp: Use of_property_present() for testing DT property presence

* pm-tools:
  PM: tools: sleepgraph: Recognize "CPU killed" messages
  pm-graph: Update to v5.11

Documentation/ABI/testing/sysfs-power

@@ -413,6 +413,35 @@ Description:
 		The /sys/power/suspend_stats/last_failed_step file contains
 		the last failed step in the suspend/resume path.
 
+What:		/sys/power/suspend_stats/last_hw_sleep
+Date:		June 2023
+Contact:	Mario Limonciello <mario.limonciello@amd.com>
+Description:
+		The /sys/power/suspend_stats/last_hw_sleep file
+		contains the duration of time spent in a hardware sleep
+		state in the most recent system suspend-resume cycle.
+		This number is measured in microseconds.
+
+What:		/sys/power/suspend_stats/total_hw_sleep
+Date:		June 2023
+Contact:	Mario Limonciello <mario.limonciello@amd.com>
+Description:
+		The /sys/power/suspend_stats/total_hw_sleep file
+		contains the aggregate of time spent in a hardware sleep
+		state since the kernel was booted. This number
+		is measured in microseconds.
+
+What:		/sys/power/suspend_stats/max_hw_sleep
+Date:		June 2023
+Contact:	Mario Limonciello <mario.limonciello@amd.com>
+Description:
+		The /sys/power/suspend_stats/max_hw_sleep file
+		contains the maximum amount of time that the hardware can
+		report for time spent in a hardware sleep state. When sleep
+		cycles are longer than this time, the values for
+		'total_hw_sleep' and 'last_hw_sleep' may not be accurate.
+		This number is measured in microseconds.
+
 What:		/sys/power/sync_on_suspend
 Date:		October 2019
 Contact:	Jonas Meurer <jonas@freesources.org>

drivers/base/power/main.c

@@ -679,7 +679,7 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 
 static void async_resume_noirq(void *data, async_cookie_t cookie)
 {
-	struct device *dev = (struct device *)data;
+	struct device *dev = data;
 	int error;
 
 	error = device_resume_noirq(dev, pm_transition, true);
@@ -816,7 +816,7 @@ static int device_resume_early(struct device *dev, pm_message_t state, bool asyn
 
 static void async_resume_early(void *data, async_cookie_t cookie)
 {
-	struct device *dev = (struct device *)data;
+	struct device *dev = data;
 	int error;
 
 	error = device_resume_early(dev, pm_transition, true);
@@ -980,7 +980,7 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 
 static void async_resume(void *data, async_cookie_t cookie)
 {
-	struct device *dev = (struct device *)data;
+	struct device *dev = data;
 	int error;
 
 	error = device_resume(dev, pm_transition, true);
@@ -1269,7 +1269,7 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a
 
 static void async_suspend_noirq(void *data, async_cookie_t cookie)
 {
-	struct device *dev = (struct device *)data;
+	struct device *dev = data;
 	int error;
 
 	error = __device_suspend_noirq(dev, pm_transition, true);
@@ -1450,7 +1450,7 @@ static int __device_suspend_late(struct device *dev, pm_message_t state, bool as
 
 static void async_suspend_late(void *data, async_cookie_t cookie)
 {
-	struct device *dev = (struct device *)data;
+	struct device *dev = data;
 	int error;
 
 	error = __device_suspend_late(dev, pm_transition, true);
@@ -1727,7 +1727,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 
 static void async_suspend(void *data, async_cookie_t cookie)
 {
-	struct device *dev = (struct device *)data;
+	struct device *dev = data;
 	int error;
 
 	error = __device_suspend(dev, pm_transition, true);

drivers/opp/core.c

@@ -935,8 +935,8 @@ static int _set_opp_bw(const struct opp_table *opp_table,
 	return 0;
 }
 
-static int _set_required_opp(struct device *dev, struct device *pd_dev,
-			     struct dev_pm_opp *opp, int i)
+static int _set_performance_state(struct device *dev, struct device *pd_dev,
+				  struct dev_pm_opp *opp, int i)
 {
 	unsigned int pstate = likely(opp) ? opp->required_opps[i]->pstate : 0;
 	int ret;
@@ -953,37 +953,19 @@ static int _set_required_opp(struct device *dev, struct device *pd_dev,
 	return ret;
 }
 
-/* This is only called for PM domain for now */
-static int _set_required_opps(struct device *dev,
-			      struct opp_table *opp_table,
-			      struct dev_pm_opp *opp, bool up)
+static int _opp_set_required_opps_generic(struct device *dev,
+	struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down)
 {
-	struct opp_table **required_opp_tables = opp_table->required_opp_tables;
-	struct device **genpd_virt_devs = opp_table->genpd_virt_devs;
-	int i, ret = 0;
-
-	if (!required_opp_tables)
-		return 0;
-
-	/* required-opps not fully initialized yet */
-	if (lazy_linking_pending(opp_table))
-		return -EBUSY;
-
-	/*
-	 * We only support genpd's OPPs in the "required-opps" for now, as we
-	 * don't know much about other use cases. Error out if the required OPP
-	 * doesn't belong to a genpd.
-	 */
-	if (unlikely(!required_opp_tables[0]->is_genpd)) {
-		dev_err(dev, "required-opps don't belong to a genpd\n");
-		return -ENOENT;
-	}
-
-	/* Single genpd case */
-	if (!genpd_virt_devs)
-		return _set_required_opp(dev, dev, opp, 0);
+	dev_err(dev, "setting required-opps isn't supported for non-genpd devices\n");
+	return -ENOENT;
+}
 
-	/* Multiple genpd case */
+static int _opp_set_required_opps_genpd(struct device *dev,
+	struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down)
+{
+	struct device **genpd_virt_devs =
+		opp_table->genpd_virt_devs ? opp_table->genpd_virt_devs : &dev;
+	int i, ret = 0;
 
 	/*
 	 * Acquire genpd_virt_dev_lock to make sure we don't use a genpd_dev
@@ -992,15 +974,15 @@ static int _set_required_opps(struct device *dev,
 	mutex_lock(&opp_table->genpd_virt_dev_lock);
 
 	/* Scaling up? Set required OPPs in normal order, else reverse */
-	if (up) {
+	if (!scaling_down) {
 		for (i = 0; i < opp_table->required_opp_count; i++) {
-			ret = _set_required_opp(dev, genpd_virt_devs[i], opp, i);
+			ret = _set_performance_state(dev, genpd_virt_devs[i], opp, i);
 			if (ret)
 				break;
 		}
 	} else {
 		for (i = opp_table->required_opp_count - 1; i >= 0; i--) {
-			ret = _set_required_opp(dev, genpd_virt_devs[i], opp, i);
+			ret = _set_performance_state(dev, genpd_virt_devs[i], opp, i);
 			if (ret)
 				break;
 		}
@@ -1011,6 +993,34 @@ static int _set_required_opps(struct device *dev,
 	return ret;
 }
 
+/* This is only called for PM domain for now */
+static int _set_required_opps(struct device *dev, struct opp_table *opp_table,
+			      struct dev_pm_opp *opp, bool up)
+{
+	/* required-opps not fully initialized yet */
+	if (lazy_linking_pending(opp_table))
+		return -EBUSY;
+
+	if (opp_table->set_required_opps)
+		return opp_table->set_required_opps(dev, opp_table, opp, up);
+
+	return 0;
+}
+
+/* Update set_required_opps handler */
+void _update_set_required_opps(struct opp_table *opp_table)
+{
+	/* Already set */
+	if (opp_table->set_required_opps)
+		return;
+
+	/* All required OPPs will belong to genpd or none */
+	if (opp_table->required_opp_tables[0]->is_genpd)
+		opp_table->set_required_opps = _opp_set_required_opps_genpd;
+	else
+		opp_table->set_required_opps = _opp_set_required_opps_generic;
+}
+
 static void _find_current_opp(struct device *dev, struct opp_table *opp_table)
 {
 	struct dev_pm_opp *opp = ERR_PTR(-ENODEV);

drivers/opp/of.c

@@ -196,6 +196,8 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 	/* Let's do the linking later on */
 	if (lazy)
 		list_add(&opp_table->lazy, &lazy_opp_tables);
+	else
+		_update_set_required_opps(opp_table);
 
 	goto put_np;
 
@@ -224,7 +226,7 @@ void _of_init_opp_table(struct opp_table *opp_table, struct device *dev,
 	of_property_read_u32(np, "voltage-tolerance",
 			     &opp_table->voltage_tolerance_v1);
 
-	if (of_find_property(np, "#power-domain-cells", NULL))
+	if (of_property_present(np, "#power-domain-cells"))
 		opp_table->is_genpd = true;
 
 	/* Get OPP table node */
@@ -411,6 +413,7 @@ static void lazy_link_required_opp_table(struct opp_table *new_table)
 
 		/* All required opp-tables found, remove from lazy list */
 		if (!lazy) {
+			_update_set_required_opps(opp_table);
 			list_del_init(&opp_table->lazy);
 
 			list_for_each_entry(opp, &opp_table->opp_list, node)
@@ -536,7 +539,7 @@ static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
 		 * an OPP then the OPP should not be enabled as there is
 		 * no way to see if the hardware supports it.
 		 */
-		if (of_find_property(np, "opp-supported-hw", NULL))
+		if (of_property_present(np, "opp-supported-hw"))
 			return false;
 		else
 			return true;

drivers/opp/opp.h

@@ -184,6 +184,7 @@ enum opp_table_access {
  * @enabled: Set to true if the device's resources are enabled/configured.
  * @genpd_performance_state: Device's power domain support performance state.
  * @is_genpd: Marks if the OPP table belongs to a genpd.
+ * @set_required_opps: Helper responsible to set required OPPs.
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
@@ -234,6 +235,8 @@ struct opp_table {
 	bool enabled;
 	bool genpd_performance_state;
 	bool is_genpd;
+	int (*set_required_opps)(struct device *dev,
+		struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down);
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
@@ -257,6 +260,7 @@ void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, int last_cp
 struct opp_table *_add_opp_table_indexed(struct device *dev, int index, bool getclk);
 void _put_opp_list_kref(struct opp_table *opp_table);
 void _required_opps_available(struct dev_pm_opp *opp, int count);
+void _update_set_required_opps(struct opp_table *opp_table);
 
 static inline bool lazy_linking_pending(struct opp_table *opp_table)
 {

drivers/platform/x86/amd/pmc.c

@@ -393,9 +393,8 @@ static void amd_pmc_validate_deepest(struct amd_pmc_dev *pdev)
 
 	if (!table.s0i3_last_entry_status)
 		dev_warn(pdev->dev, "Last suspend didn't reach deepest state\n");
-	else
-		dev_dbg(pdev->dev, "Last suspend in deepest state for %lluus\n",
-			 table.timein_s0i3_lastcapture);
+	pm_report_hw_sleep_time(table.s0i3_last_entry_status ?
+				table.timein_s0i3_lastcapture : 0);
 }
 
 static int amd_pmc_get_smu_version(struct amd_pmc_dev *dev)
@@ -1015,6 +1014,7 @@ static int amd_pmc_probe(struct platform_device *pdev)
 	}
 
 	amd_pmc_dbgfs_register(dev);
+	pm_report_max_hw_sleep(U64_MAX);
 	return 0;
 
 err_pci_dev_put:

drivers/platform/x86/intel/pmc/core.c

@@ -1153,6 +1153,8 @@ static int pmc_core_probe(struct platform_device *pdev)
 	pmc_core_do_dmi_quirks(pmcdev);
 
 	pmc_core_dbgfs_register(pmcdev);
+	pm_report_max_hw_sleep(FIELD_MAX(SLP_S0_RES_COUNTER_MASK) *
+			       pmc_core_adjust_slp_s0_step(pmcdev, 1));
 
 	device_initialized = true;
 	dev_info(&pdev->dev, " initialized\n");
@@ -1179,12 +1181,6 @@ static __maybe_unused int pmc_core_suspend(struct device *dev)
 {
 	struct pmc_dev *pmcdev = dev_get_drvdata(dev);
 
-	pmcdev->check_counters = false;
-
-	/* No warnings on S0ix failures */
-	if (!warn_on_s0ix_failures)
-		return 0;
-
 	/* Check if the syspend will actually use S0ix */
 	if (pm_suspend_via_firmware())
 		return 0;
@@ -1197,7 +1193,6 @@ static __maybe_unused int pmc_core_suspend(struct device *dev)
 	if (pmc_core_dev_state_get(pmcdev, &pmcdev->s0ix_counter))
 		return -EIO;
 
-	pmcdev->check_counters = true;
 	return 0;
 }
 
@@ -1221,6 +1216,8 @@ static inline bool pmc_core_is_s0ix_failed(struct pmc_dev *pmcdev)
 	if (pmc_core_dev_state_get(pmcdev, &s0ix_counter))
 		return false;
 
+	pm_report_hw_sleep_time((u32)(s0ix_counter - pmcdev->s0ix_counter));
+
 	if (s0ix_counter == pmcdev->s0ix_counter)
 		return true;
 
@@ -1233,12 +1230,16 @@ static __maybe_unused int pmc_core_resume(struct device *dev)
 	const struct pmc_bit_map **maps = pmcdev->map->lpm_sts;
 	int offset = pmcdev->map->lpm_status_offset;
 
-	if (!pmcdev->check_counters)
+	/* Check if the syspend used S0ix */
+	if (pm_suspend_via_firmware())
 		return 0;
 
 	if (!pmc_core_is_s0ix_failed(pmcdev))
 		return 0;
 
+	if (!warn_on_s0ix_failures)
+		return 0;
+
 	if (pmc_core_is_pc10_failed(pmcdev)) {
 		/* S0ix failed because of PC10 entry failure */
 		dev_info(dev, "CPU did not enter PC10!!! (PC10 cnt=0x%llx)\n",

drivers/platform/x86/intel/pmc/core.h

@@ -16,6 +16,8 @@
 #include <linux/bits.h>
 #include <linux/platform_device.h>
 
+#define SLP_S0_RES_COUNTER_MASK			GENMASK(31, 0)
+
 #define PMC_BASE_ADDR_DEFAULT			0xFE000000
 
 /* Sunrise Point Power Management Controller PCI Device ID */
@@ -319,7 +321,6 @@ struct pmc_reg_map {
  * @pmc_xram_read_bit:	flag to indicate whether PMC XRAM shadow registers
  *			used to read MPHY PG and PLL status are available
  * @mutex_lock:		mutex to complete one transcation
- * @check_counters:	On resume, check if counters are getting incremented
  * @pc10_counter:	PC10 residency counter
  * @s0ix_counter:	S0ix residency (step adjusted)
  * @num_lpm_modes:	Count of enabled modes
@@ -338,7 +339,6 @@ struct pmc_dev {
 	int pmc_xram_read_bit;
 	struct mutex lock; /* generic mutex lock for PMC Core */
 
-	bool check_counters; /* Check for counter increments on resume */
 	u64 pc10_counter;
 	u64 s0ix_counter;
 	int num_lpm_modes;

include/linux/suspend.h

@@ -68,6 +68,9 @@ struct suspend_stats {
 	int	last_failed_errno;
 	int	errno[REC_FAILED_NUM];
 	int	last_failed_step;
+	u64	last_hw_sleep;
+	u64	total_hw_sleep;
+	u64	max_hw_sleep;
 	enum suspend_stat_step	failed_steps[REC_FAILED_NUM];
 };
 
@@ -489,6 +492,8 @@ void restore_processor_state(void);
 extern int register_pm_notifier(struct notifier_block *nb);
 extern int unregister_pm_notifier(struct notifier_block *nb);
 extern void ksys_sync_helper(void);
+extern void pm_report_hw_sleep_time(u64 t);
+extern void pm_report_max_hw_sleep(u64 t);
 
 #define pm_notifier(fn, pri) {				\
 	static struct notifier_block fn##_nb =			\
@@ -526,6 +531,9 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 	return 0;
 }
 
+static inline void pm_report_hw_sleep_time(u64 t) {};
+static inline void pm_report_max_hw_sleep(u64 t) {};
+
 static inline void ksys_sync_helper(void) {}
 
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)